1. An energy utilization control strategy generation method is applied to a distribution and distribution system, and the distribution and distribution system comprises the following steps: the system comprises an energy consumption system, an energy storage system and a renewable energy system, wherein the energy consumption system is coupled with the energy storage system and the renewable energy system to obtain energy supply, at least one of the energy storage system and the energy consumption system is coupled with a main energy generation system to obtain energy supply according to unit energy supply parameters, and the unit energy supply parameters change along with time; the method comprises the following steps:

predicting the predicted renewable energy supply of each time slot in the future period according to the input historical renewable energy supply data of the renewable energy system through a first predictor;

according to the predicted renewable energy supply of each time slot in the future time period and the actual energy demand of the energy consumption system, each time decomposition slice and the corresponding slice energy demand in the future time period are obtained;

predicting a prediction unit energy supply parameter of each time slot in the future period according to the input historical unit energy supply parameter data by a second predictor, and determining a strategy threshold value of each time decomposition slice in the current time slot according to the minimum value of the prediction unit energy supply parameter of each time slot in each time decomposition slice; the comparison result of the actual unit energy supply parameter of each current time slot and the strategy threshold value of the at least one time decomposition slice to which the actual unit energy supply parameter belongs in the current time slot is used for determining whether the current time slot needs to obtain energy supply from the main energy generation system, and the determined energy supply for obtaining the energy supply is determined by the energy demand of the slice of the corresponding time decomposition slice;

acquiring energy utilization control strategies constructed according to the strategy threshold values; wherein the energy usage control strategy is used to control at least one of the energy storage system and the energy usage system to perform energy harvesting from the primary energy generation system.

2. The method of claim 1, wherein determining whether the current time slot requires power from a master-slave power generation system according to the comparison comprises:

obtaining a comparison result between the strategy threshold value of each time decomposition slice in the current time slot and the actual unit energy supply parameter of the current time slot;

when the comparison result is that the strategy threshold is smaller than the actual unit energy supply parameter, determining that energy supply needs to be obtained from a main energy generation system at the current time slot; or when the comparison result is that the strategy threshold is larger than the actual unit energy supply parameter, determining that energy supply does not need to be obtained from the main energy generation system at the current time slot.

3. The method of claim 1, wherein the energy supply is determined by slice energy requirements of corresponding time resolved slices, comprising:

the slice energy requirements of the individual time resolved slices determining the need to obtain energy from the primary energy generation system at the current time slot are superimposed to obtain the energy supply.

4. The energy usage control strategy generation method according to claim 1, wherein the first predictor and/or the second predictor comprises: at least one recurrent neural network.

5. The energy usage control strategy generation method according to claim 1, wherein the first predictor and/or the second predictor comprises: at least one long-short term memory artificial neural network.

6. The energy use control strategy generation method according to claim 4 or 5, wherein the first predictor and/or the second predictor is/are configured to iteratively perform the following operations until a prediction unit energy supply parameter of each time slot in a future period is obtained:

predicting renewable energy supply/prediction unit energy supply parameters of a future time slot according to the historical renewable energy supply/historical unit energy supply parameters of the previous k historical time slots;

and the predicted renewable energy supply/predicted historical unit energy supply parameter of the future time slot is combined with the historical renewable energy supply/historical unit energy supply parameters of k-1 previous historical time slots for executing the next operation to predict the predicted renewable energy supply/predicted unit energy supply parameter of the next future time slot of the future time slot.

7. The energy usage control strategy generation method of claim 6, wherein the first predictor and/or the second predictor are implemented by a long-short term memory artificial neural network comprising: one or more layers of cells; each unit in the first layer respectively obtains historical data input of a corresponding time slot and outputs hidden state information, and the hidden state information and the unit state information of each unit are also output to the next unit in the same layer; under the condition of multiple layers, the unit in each layer obtains the input of hidden state information output by the unit corresponding to the time slot in the previous layer; the output of the unit in the last layer corresponding to the future time slot is taken as the prediction result.

8. The energy consumption control strategy generation method according to claim 4 or 5, wherein the first predictor and/or the second predictor is/are configured to encode a corresponding context vector according to a plurality of historical renewable energy supply/historical unit energy supply parameters, and decode a sequence formed by the predicted renewable energy supply/predicted unit energy supply parameters of each future time slot in the future time period according to the context vector.

9. The energy usage control strategy generation method according to claim 8, wherein the first predictor and/or the second predictor comprises: an encoder and a decoder, wherein the encoder is used for encoding to obtain the context vector, and the decoder is used for decoding to obtain the sequence; wherein, the encoder and the decoder are respectively realized by one or more layers of recurrent neural networks or long-short term memory artificial neural networks.

10. The energy consumption control strategy generation method according to claim 1, comprising: and outputting the energy utilization control strategy.

11. An energy use control strategy generation system, which is applied to a distribution and distribution system, the distribution and distribution system comprising: the system comprises an energy consumption system, an energy storage system and a renewable energy system, wherein the energy consumption system is coupled with the energy storage system and the renewable energy system to obtain energy supply, at least one of the energy storage system and the energy consumption system is coupled with a main energy generation system to obtain energy supply according to unit energy supply parameters, and the unit energy supply parameters change along with time; the method comprises the following steps:

the first predictor is used for predicting the predicted renewable energy supply of each time slot in the future period according to the input historical renewable energy supply data of the renewable energy system;

the decomposer is used for decomposing slices and corresponding slice energy requirements at each time in the future period according to the predicted renewable energy supply of each time slot in the future period and the actual energy requirements of the energy utilization system;

the second predictor is used for predicting the prediction unit energy supply parameter of each time slot in the future period according to the input historical unit energy supply parameter data;

the strategy generation module is used for determining a strategy threshold value of each time decomposition slice in the current time slot according to the minimum value of the prediction unit energy supply parameter of each time slot in each time decomposition slice; the comparison result of the actual unit energy supply parameter of each current time slot and the strategy threshold value of the at least one time decomposition slice to which the actual unit energy supply parameter belongs in the current time slot is used for determining whether the current time slot needs to obtain energy supply from the main energy generation system, and the determined energy supply for obtaining the energy supply is determined by the energy demand of the slice of the corresponding time decomposition slice;

the strategy generation module is also used for acquiring an energy utilization control strategy constructed according to each strategy threshold; wherein the energy usage control strategy is used to control at least one of the energy storage system and the energy usage system to perform energy harvesting from the primary energy generation system.

12. The system of claim 11, wherein determining whether the current time slot requires power from a master-slave power generation system based on the comparison comprises:

obtaining a comparison result between the strategy threshold value of each time decomposition slice in the current time slot and the actual unit energy supply parameter of the current time slot;

when the comparison result is that the strategy threshold is smaller than the actual unit energy supply parameter, determining that energy supply needs to be obtained from a main energy generation system at the current time slot; or when the comparison result is that the strategy threshold is larger than the actual unit energy supply parameter, determining that energy supply does not need to be obtained from the main energy generation system at the current time slot.

13. The energy usage control strategy generation system of claim 11, wherein the energy supply is determined by a slice energy demand of the corresponding time resolved slice, comprising:

the slice energy requirements of the individual time resolved slices determining the need to obtain energy from the primary energy generation system at the current time slot are superimposed to obtain the energy supply.

14. The energy usage control strategy generation system of claim 11, wherein the first predictor and/or the second predictor comprises: at least one recurrent neural network.

15. The energy usage control strategy generation system of claim 11, wherein the first predictor and/or the second predictor comprises: at least one long-short term memory artificial neural network.

16. The energy use control strategy generation system according to claim 14 or 15, wherein the first predictor and/or the second predictor is/are configured to iteratively perform the following operations until a predicted unit energy supply parameter of each time slot in a future period is obtained:

predicting renewable energy supply/prediction unit energy supply parameters of a future time slot according to the historical renewable energy supply/historical unit energy supply parameters of the previous k historical time slots;

and the predicted renewable energy supply/predicted historical unit energy supply parameter of the future time slot is combined with the historical renewable energy supply/historical unit energy supply parameters of k-1 previous historical time slots for executing the next operation to predict the predicted renewable energy supply/predicted unit energy supply parameter of the next future time slot of the future time slot.

17. The energy usage control strategy generation system of claim 16, wherein the first predictor and/or the second predictor is implemented by a long-short term memory artificial neural network comprising: one or more layers of cells; each unit in the first layer respectively obtains historical data input of a corresponding time slot and outputs hidden state information, and the hidden state information and the unit state information of each unit are also output to the next unit in the same layer; under the condition of multiple layers, the unit in each layer obtains the input of hidden state information output by the unit corresponding to the time slot in the previous layer; the output of the unit in the last layer corresponding to the future time slot is taken as the prediction result.

18. The system according to claim 14 or 15, wherein the first predictor and/or the second predictor is configured to encode a corresponding context vector according to a plurality of historical renewable energy supply/historical unit energy supply parameters, and decode a sequence of the predicted renewable energy supply/predicted unit energy supply parameters of each future time slot in the future time period according to the context vector.

19. The energy usage control strategy generation system of claim 18, wherein the first predictor and/or the second predictor comprises: an encoder and a decoder, wherein the encoder is used for encoding to obtain the context vector, and the decoder is used for decoding to obtain the sequence; wherein, the encoder and the decoder are respectively realized by one or more layers of recurrent neural networks or long-short term memory artificial neural networks.

20. The energy usage control strategy generation system of claim 11, comprising: and the output module is used for outputting the energy utilization control strategy.

21. A computer device, comprising:

communication means for communicating with the outside;

a storage device for storing at least one program;

processing means for executing the at least one program to perform the energy usage control policy generation method according to any one of claims 1 to 10.

22. A distribution and energy distribution system, comprising:

an energy utilization system, an energy storage system, and a renewable energy system; wherein the energy usage system is coupled to the energy storage system and the renewable energy system to obtain energy, at least one of the energy storage system and the energy usage system is coupled to the primary energy generation system to obtain energy per unit energy parameter, the unit energy parameter varying with time;

the computer apparatus of claim 21, in communication with the energy usage system and/or energy storage system.

23. A computer-readable storage medium characterized by storing at least one program which, when being called, executes and implements the energy use control policy generation method according to any one of claims 1 to 10.

Background

Based on the great trend of energy development of energy conservation and emission reduction, the power generation of renewable energy sources needs to occupy a part of proportion in the current power system.

Although there have been many research results for optimizing the power efficiency and cost of the user side in the conventional power system, for example, a power control strategy for controlling to obtain electric energy to the power grid according to the predicted energy supply price, or an energy storage device is adopted to store/discharge electric energy at peak-valley time of the energy supply price, or charge-discharge strategy control of the energy storage device, etc., these optimization measures cannot be directly applied to the power system including renewable energy supply, and the optimization strategy for such a system is lost, so that in an actual scene, the power consumption device can use more electric power of the power grid when using the electric energy, which is not beneficial to energy saving and emission reduction, is not beneficial to saving the cost of the user, and can cause unreasonable power supply allocation and waste of the electric power.

Disclosure of Invention

In view of the above-mentioned shortcomings of the prior art, it is an object of the present application to provide a method, system, apparatus, distribution and energy distribution system and medium for generating an energy control policy, which overcome various deficiencies of the prior art.

To achieve the above and other related objects, a first aspect of the present application provides an energy use control policy generation method applied to a distribution and distribution system, where the distribution and distribution system includes: the system comprises an energy consumption system, an energy storage system and a renewable energy system, wherein the energy consumption system is coupled with the energy storage system and the renewable energy system to obtain energy supply, at least one of the energy storage system and the energy consumption system is coupled with a main energy generation system to obtain energy supply according to unit energy supply parameters, and the unit energy supply parameters change along with time; the method comprises the following steps: predicting the predicted renewable energy supply of each time slot in the future period according to the input historical renewable energy supply data of the renewable energy system through a first predictor; according to the predicted renewable energy supply of each time slot in the future time period and the actual energy demand of the energy consumption system, each time decomposition slice and the corresponding slice energy demand in the future time period are obtained; predicting a prediction unit energy supply parameter of each time slot in the future period according to the input historical unit energy supply parameter data by a second predictor, and determining a strategy threshold value of each time decomposition slice in the current time slot according to the minimum value of the prediction unit energy supply parameter of each time slot in each time decomposition slice; the comparison result of the actual unit energy supply parameter of each current time slot and the strategy threshold value of the at least one time decomposition slice to which the actual unit energy supply parameter belongs in the current time slot is used for determining whether the current time slot needs to obtain energy supply from the main energy generation system, and the determined energy supply for obtaining the energy supply is determined by the energy demand of the slice of the corresponding time decomposition slice; acquiring energy utilization control strategies constructed according to the strategy threshold values; wherein the energy usage control strategy is used to control at least one of the energy storage system and the energy usage system to perform energy harvesting from the primary energy generation system.

In certain embodiments of the first aspect of the present application, determining whether the current timeslot requires power from a master-slave power generation system based on the comparison result comprises: obtaining a comparison result between the strategy threshold value of each time decomposition slice in the current time slot and the actual unit energy supply parameter of the current time slot; when the comparison result is that the strategy threshold is smaller than the actual unit energy supply parameter, determining that energy supply needs to be obtained from a main energy generation system at the current time slot; or when the comparison result is that the strategy threshold is larger than the actual unit energy supply parameter, determining that energy supply does not need to be obtained from the main energy generation system at the current time slot.

In certain embodiments of the first aspect of the present application, the energy supply is determined by a slice energy demand of the corresponding time resolved slice, comprising: the slice energy requirements of the individual time resolved slices determining the need to obtain energy from the primary energy generation system at the current time slot are superimposed to obtain the energy supply.

In certain embodiments of the first aspect of the present application, the first predictor and/or the second predictor comprises: at least one recurrent neural network.

In certain embodiments of the first aspect of the present application, the first predictor and/or the second predictor comprises: at least one long-short term memory artificial neural network.

In certain embodiments of the first aspect of the present application, the first predictor and/or the second predictor is configured to iteratively perform the following operations until a predicted unit energization parameter for each time slot in a future period is obtained: predicting renewable energy supply/prediction unit energy supply parameters of a future time slot according to the historical renewable energy supply/historical unit energy supply parameters of the previous k historical time slots; and the predicted renewable energy supply/predicted historical unit energy supply parameter of the future time slot is combined with the historical renewable energy supply/historical unit energy supply parameters of k-1 previous historical time slots for executing the next operation to predict the predicted renewable energy supply/predicted unit energy supply parameter of the next future time slot of the future time slot.

In certain embodiments of the first aspect of the present application, the first predictor and/or the second predictor is/are implemented by a long-short term memory artificial neural network comprising: one or more layers of cells; each unit in the first layer respectively obtains historical data input of a corresponding time slot and outputs hidden state information, and the hidden state information and the unit state information of each unit are also output to the next unit in the same layer; under the condition of multiple layers, the unit in each layer obtains the input of hidden state information output by the unit corresponding to the time slot in the previous layer; the output of the unit in the last layer corresponding to the future time slot is taken as the prediction result.

In certain embodiments of the first aspect of the present application, the first predictor and/or the second predictor is configured to encode a corresponding context vector according to a plurality of historical renewable energy supply/historical unit energy supply parameters, and decode a sequence formed by the predicted renewable energy supply/predicted unit energy supply parameters of each future time slot in the future time period according to the context vector.

In certain embodiments of the first aspect of the present application, the first predictor and/or the second predictor comprises: an encoder and a decoder, wherein the encoder is used for encoding to obtain the context vector, and the decoder is used for decoding to obtain the sequence; wherein, the encoder and the decoder are respectively realized by one or more layers of recurrent neural networks or long-short term memory artificial neural networks.

In certain embodiments of the first aspect of the present application, the energy use control policy generation method includes: and outputting the energy utilization control strategy.

To achieve the above and other related objects, a second aspect of the present application provides an energy use control policy generation system applied to a distribution and distribution system, the distribution and distribution system including: the system comprises an energy consumption system, an energy storage system and a renewable energy system, wherein the energy consumption system is coupled with the energy storage system and the renewable energy system to obtain energy supply, at least one of the energy storage system and the energy consumption system is coupled with a main energy generation system to obtain energy supply according to unit energy supply parameters, and the unit energy supply parameters change along with time; the energy consumption control strategy generation system comprises: the first predictor is used for predicting the predicted renewable energy supply of each time slot in the future period according to the input historical renewable energy supply data of the renewable energy system; the decomposer is used for decomposing slices and corresponding slice energy requirements at each time in the future period according to the predicted renewable energy supply of each time slot in the future period and the actual energy requirements of the energy utilization system; the second predictor is used for predicting the prediction unit energy supply parameter of each time slot in the future period according to the input historical unit energy supply parameter data; the strategy generation module is used for determining a strategy threshold value of each time decomposition slice in the current time slot according to the minimum value of the prediction unit energy supply parameter of each time slot in each time decomposition slice; the comparison result of the actual unit energy supply parameter of each current time slot and the strategy threshold value of the at least one time decomposition slice to which the actual unit energy supply parameter belongs in the current time slot is used for determining whether the current time slot needs to obtain energy supply from the main energy generation system, and the determined energy supply for obtaining the energy supply is determined by the energy demand of the slice of the corresponding time decomposition slice; the strategy generation module is also used for acquiring an energy utilization control strategy constructed according to each strategy threshold; wherein the energy usage control strategy is used to control at least one of the energy storage system and the energy usage system to perform energy harvesting from the primary energy generation system.

In certain embodiments of the second aspect of the present application, determining whether the current time slot requires power from a master-slave power generation system based on the comparison result comprises: obtaining a comparison result between the strategy threshold value of each time decomposition slice in the current time slot and the actual unit energy supply parameter of the current time slot; when the comparison result is that the strategy threshold is smaller than the actual unit energy supply parameter, determining that energy supply needs to be obtained from a main energy generation system at the current time slot; or when the comparison result is that the strategy threshold is larger than the actual unit energy supply parameter, determining that energy supply does not need to be obtained from the main energy generation system at the current time slot.

In certain embodiments of the second aspect of the present application, the energy supply is determined by a slice energy demand of the corresponding time resolved slice, comprising: the slice energy requirements of the individual time resolved slices determining the need to obtain energy from the primary energy generation system at the current time slot are superimposed to obtain the energy supply.

In certain embodiments of the second aspect of the present application, the first predictor and/or the second predictor comprises: at least one recurrent neural network.

In certain embodiments of the second aspect of the present application, the first predictor and/or the second predictor comprises: at least one long-short term memory artificial neural network.

In certain embodiments of the second aspect of the present application, the first predictor and/or the second predictor is configured to iteratively perform the following operations until a predicted unit energization parameter for each time slot in a future period is obtained: predicting renewable energy supply/prediction unit energy supply parameters of a future time slot according to the historical renewable energy supply/historical unit energy supply parameters of the previous k historical time slots; and the predicted renewable energy supply/predicted historical unit energy supply parameter of the future time slot is combined with the historical renewable energy supply/historical unit energy supply parameters of k-1 previous historical time slots for executing the next operation to predict the predicted renewable energy supply/predicted unit energy supply parameter of the next future time slot of the future time slot.

In certain embodiments of the second aspect of the present application, the first predictor and/or the second predictor is/are implemented by a long-short term memory artificial neural network comprising: one or more layers of cells; each unit in the first layer respectively obtains historical data input of a corresponding time slot and outputs hidden state information, and the hidden state information and the unit state information of each unit are also output to the next unit in the same layer; under the condition of multiple layers, the unit in each layer obtains the input of hidden state information output by the unit corresponding to the time slot in the previous layer; the output of the unit in the last layer corresponding to the future time slot is taken as the prediction result.

In some embodiments of the second aspect of the present application, the first predictor and/or the second predictor is configured to encode a corresponding context vector according to a plurality of historical renewable energy supply/historical unit energy supply parameters, and decode a sequence formed by the predicted renewable energy supply/predicted unit energy supply parameters of each future time slot in the future time period according to the context vector.

In certain embodiments of the second aspect of the present application, the first predictor and/or the second predictor comprises: an encoder and a decoder, wherein the encoder is used for encoding to obtain the context vector, and the decoder is used for decoding to obtain the sequence; wherein, the encoder and the decoder are respectively realized by one or more layers of recurrent neural networks or long-short term memory artificial neural networks.

In certain embodiments of the second aspect of the present application, the energy use control policy generation system comprises: and the output module is used for outputting the energy utilization control strategy.

To achieve the above and other related objects, a third aspect of the present application provides a computer apparatus comprising: communication means for communicating with the outside; a storage device for storing at least one program; processing means for executing the at least one program to perform the energy use control policy generation method according to any one of the first aspect.

To achieve the above and other related objects, a fourth aspect of the present application provides a distribution power distribution system comprising: an energy utilization system, an energy storage system, and a renewable energy system; wherein the energy usage system is coupled to the energy storage system and the renewable energy system to obtain energy, at least one of the energy storage system and the energy usage system is coupled to the primary energy generation system to obtain energy per unit energy parameter, the unit energy parameter varying with time; the computer apparatus of the third aspect, in communication with the energy usage system and/or the energy storage system.

To achieve the above and other related objects, a fifth aspect of the present application provides a computer-readable storage medium storing at least one program which, when invoked, executes and implements the energy use control policy generation method according to the first aspect.

As described above, the energy consumption control strategy generation method, system, device, distribution and distribution system and medium of the present application are applied to a distribution and distribution system, and predict the predicted renewable energy supply of each time slot in the future period according to the historical data of the renewable energy system by the first predictor; obtaining each time decomposition slice and corresponding slice energy demand in the future time period according to the predicted renewable energy supply and the actual energy demand of the energy consumption system; predicting unit energy supply parameters through a second predictor, and determining a strategy threshold value of the time decomposition slice at the current time slot; the comparison result of the actual unit energy supply parameter of each current time slot and the strategy threshold value of the at least one time decomposition slice to which the actual unit energy supply parameter belongs in the current time slot is used for determining whether the current time slot needs to obtain energy supply from the main energy generation system, and the determined energy supply for obtaining the energy supply is determined by the energy demand of the slice of the corresponding time decomposition slice; the energy utilization control strategy constructed by each strategy threshold value is used for controlling energy utilization; the renewable energy supply and cost prediction method and the system have the advantages that the renewable energy supply and cost prediction parameters are predicted through the predictor to construct an online control strategy for obtaining the energy supply, the prediction is accurate, the energy utilization efficiency and the energy utilization cost can be effectively optimized, and the problems in the prior art are solved.

Drawings

Fig. 1 is a schematic diagram of an application scenario in an embodiment of the present application.

Fig. 2 is a schematic diagram illustrating the principle of performing time-resolved slicing in an embodiment of the present application.

Fig. 3A shows a logical structure of a unit of the recurrent neural network in the embodiment of the present application.

Fig. 3B shows the logical structure of the cell of the LSTM in the embodiment of the present application.

Fig. 4 is a flowchart illustrating a point prediction method according to an embodiment of the present application.

FIG. 5 shows the logical structure of a predictor based on LSTM implementation for point prediction mode in the embodiment of the present application.

Fig. 6 is a flowchart illustrating a sequence-to-sequence prediction method in an embodiment of the present application.

FIG. 7 shows the logical structure of a predictor based on LSTM implementation for sequence-to-sequence prediction mode in the embodiment of the present application.

Fig. 8 is a flowchart illustrating a method for generating an energy use control policy according to an embodiment of the present application.

Fig. 9 is a schematic structural diagram of a computer device according to an embodiment of the present application.

Fig. 10 is a schematic diagram illustrating an application scenario of the computer device according to the embodiment of the present application.

Fig. 11 is a block diagram showing a control strategy generation system according to an embodiment of the present application.

Detailed Description

The following description of the embodiments of the present application is provided for illustrative purposes, and other advantages and capabilities of the present application will become apparent to those skilled in the art from the present disclosure.

In the following description, reference is made to the accompanying drawings that describe several embodiments of the application. It is to be understood that other embodiments may be utilized and that changes in the module or unit composition, electrical, and operation may be made without departing from the spirit and scope of the present disclosure. The following detailed description is not to be taken in a limiting sense, and the scope of embodiments of the present application is defined only by the claims of the issued patent. The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application.

Although the terms first, second, etc. may be used herein to describe various elements, information, or parameters in some instances, these elements or parameters should not be limited by these terms. These terms are only used to distinguish one element or parameter from another element or parameter. For example, a first element could be termed a second element, and, similarly, a second element could be termed a first element, without departing from the scope of the various described embodiments. Both the first and second elements are described as one element, but they are not the same element unless the context clearly dictates otherwise. Depending on context, for example, the word "if" as used herein may be interpreted as "at … …" or "at … …".

Also, as used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context indicates otherwise. It will be further understood that the terms "comprises," "comprising," "includes" and/or "including," when used in this specification, specify the presence of stated features, steps, operations, elements, components, items, species, and/or groups, but do not preclude the presence, or addition of one or more other features, steps, operations, elements, components, species, and/or groups thereof. The terms "or" and/or "as used herein are to be construed as inclusive or meaning any one or any combination. Thus, "A, B or C" or "A, B and/or C" means "any of the following: a; b; c; a and B; a and C; b and C; A. b and C ". An exception to this definition will occur only when a combination of elements, functions, steps or operations are inherently mutually exclusive in some way.

Those of ordinary skill in the art will appreciate that the various illustrative modules and method steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.

In an energy supply and distribution system containing renewable energy, due to the fact that the lack of an energy management strategy can lead to unreasonable energy distribution, energy waste, energy conservation and emission reduction, user cost saving and the like, the technical scheme of the energy management strategy is provided, and therefore the problems are solved.

Please refer to fig. 1, which is a diagram illustrating an application scenario in an embodiment of the present application.

As shown, a main energy system 101, a renewable energy system 102, an energy storage system 103, and an energy utilization system 104 are shown in the application scenario.

The energy usage system 104 is coupled to the energy storage system 103 and the renewable energy system to obtain energy, and at least one of the energy storage system 103 and the energy usage system 104 is coupled to the primary energy generation system to obtain energy per unit energy parameter, which varies with time.

In some embodiments, the types of energy transferred between main energy system 101, renewable energy system 102, energy storage system 103, and energy usage system 104 include, but are not limited to, electrical energy or thermal energy, among others; alternatively, the type of energy may be electrical energy, and the application scenario may be an application scenario of an electrical power system, as there is already a mature market for electrical power.

In some embodiments, the main energy system 101 may be a power grid, and the power grid supplies electric energy to the energy consumption system 104 and the energy storage system 103 through a power transmission line; the unit energy supply parameters may include, for example, an energy supply price, and the like, that is, the energy storage system 103 and the energy consumption system 104 may purchase electric energy according to the energy supply price.

In some embodiments, the energy use system 104 can include one or more devices requiring energy use, such as industrial devices, e.g., manufacturing/processing devices, in-line devices, etc.; and for example, household appliances such as televisions, refrigerators, air conditioners, and the like, and lamps such as lighting systems and the like. In some embodiments, the energy consumption system 104 may be a generic term of at least one energy consumption device accessing the same metering device, or the energy consumption system 104 may be a generic term of at least one energy consumption device compensated by the same energy storage system 103.

In some embodiments, the energy storage system 103 includes, but is not limited to, a battery, an ultracapacitor, and the like. The storage battery can be a lead-acid battery, a nickel-cadmium battery, a nickel-hydrogen battery, a sodium-sulfur battery, a lithium battery or a fuel battery and the like.

In some embodiments, the coupling relationship between the energy consumption system 104, the energy storage system 103, the main energy system 101, and the renewable energy system 102 refers to a connection relationship through a direct or indirect energy transmission medium, as long as energy can be transmitted, and the specific implementation form is not limited thereto.

The energy usage system 104 and the energy storage system 103 may constitute a distribution and distribution system. In some embodiments, the energy usage system 104 may be located on the same side as the energy storage system 103, for example, the energy usage system 104 and the energy storage system 103 are both located on a user side. The energy storage system 103 on the user side may provide the user with its energy stored in the autonomous energy system 101, the renewable energy system 102. In still other cases, the energy usage system 104 is located on a different side than the energy storage system 103. For example, the energy usage system 104 is located at the user side, the energy storage system 103 is located at the energy system side, and the energy storage system 103 at the energy system side can provide the user with the energy stored in the autonomous energy system 101 and the renewable energy system 102.

For example, it is assumed that the energy consumption system 104 includes one or more energy consumption devices belonging to one user, and may also include a plurality of energy consumption devices distributed among a plurality of users. For example, if only energy consuming devices are provided at customer C, then one energy storage system 103 is only coupled and provides energy consuming compensation to customer C; for another example, energy utilization devices are respectively installed at the user C, the user D, and the user E, and one energy storage system 103 is respectively coupled to the energy utilization devices at the user C, the user D, and the user E, so as to provide energy utilization compensation to the user C, the user D, and the user E.

It should be noted that, as can be seen from the above examples, the distribution and energy distribution system is only a general term for the energy utilization system 104 and the energy storage system 103, and does not determine the distribution structure thereof.

In some embodiments, the renewable energy source includes non-fossil energy sources such as wind energy, solar energy, hydro energy, biomass energy, geothermal energy, ocean energy, and the like. In a possible example, the renewable energy system 102 may include one or more renewable energy generation devices for converting renewable energy into electrical energy, such as hydroelectric, wind, biomass, solar, ocean, and geothermal power, which may be commercial or residential, such as solar panels, and the like. In some examples, the renewable energy system 102 may be a decentralized power generation system or a centralized power generation system.

The renewable energy system 102, the energy storage system 103 and the energy utilization system 104 may form a distribution and distribution system. In some practical scenarios, the distribution and energy system may be implemented as, for example, a Micro-Grid system (Micro-Grid). The microgrid system is connected with the main energy system 101 and then can be operated in a grid-connected mode, and energy exchange can be carried out between the microgrid system and the main energy system 101, namely energy purchased from the main energy system 101 for storage by the energy storage system 103 or energy purchased for use by the energy utilization system 104. The renewable energy system 102 of the distribution energy system may provide energy for storage by the energy storage system 103 or for use by the energy usage system 104.

Based on the application scenario of fig. 1, the following relationship can be obtained:

in each t time slot, the energy provided by the main energy system 101 to the energy utilization system 104 is g (t), the energy provided to the energy storage system 103 is b (t), and the energy required by the energy utilization system 104 is d (t); the stored energy of the energy storage system 103 is s (t), and the energy storage capacity of the energy storage system 103 is limited to B; the energy provided by the energy storage system 103 to the energy utilization system 104 is c (t), the energy provided by the renewable energy system 102 to the energy utilization system 104 is r (t), and the energy supply limit of the renewable energy system 102 is R (t); if the unit energy supply parameter (i.e., energy supply price) of the main energy system 101 is p (t), the cost paid by the energy consumption system 104 to the main energy system 101 is g (t) p (t), and the cost paid by the energy storage system 103 to the main energy system 101 is b (t) p (t).

It should be noted that, macroscopically, the time slot may be regarded as a scale, i.e., a time, on a time axis; microscopically, the time slots may also have a length of time in units of nanoseconds, milliseconds, seconds, minutes, or the like

Based on the above relationship, an optimized control strategy is adopted in consideration of optimizing the cost of obtaining energy from the main energy system 101 to solve the problem corresponding to the following equation (1):

in the problem of equation (1), it is for an industrial system to substantially follow a production plan, substantially predicting actual compliance, i.e., d (t) may be the actual energy used from the prediction that actually complies. Wherein r (t), p (t), etc. can be replaced by predicted values, which are respectively expressed as

Further, the problem of formula (1) can be converted to formula (2):

in the idea of the present application, a time-resolved slicing (one-shot) is performed on energy demand in a future period of time to obtain a policy threshold at a corresponding time to construct an online energy utilization control policy.

Fig. 2 is a schematic diagram illustrating the principle of performing time-resolved slicing in an embodiment of the present application.

In the figure, the horizontal axis is a time axis, and the time slot t is defined as the time axis₀、t₁、t₂The vertical axis represents the cumulative energy demand; d (t) represents the cumulative energy demand curve (shown in bold lines) to be met at each time slot, at t₁The time slot is required to satisfy the required energy D (t)₁) At t₂The time slot is required to satisfy D (t)₂) Let the energy storage capacity of the energy storage system be limited to B, assuming D (t) in this example₁)<B，D(t₁)+D(t₂)>B, performing time decomposition slicing to obtain the slice at t₀～t₁Time-resolved slice of arbitrary time slots and corresponding slice energy requirements d₁(t₀，t₁) And d is₁(t₀，t₁) Can be composed ofCalculated and D (t2) is atSuperposition on a foundationAnd because of the existence of the energy storage system B, a curve D exists_shift(shown in dotted lines in the figure) the user may be at t₀、t₁Or t₂Choose buy d₂(t₀，t₂) Is selected at t₁～t₂Buy d₃(t₁，t₂) Thereby reaching the maximum memory capacity; is at t₂Begin to buyTo satisfy D (t)₂) Then it needs to be at t₂Buy d₄(t₂，t₂)。

It can be seen that the time-resolved slice in the above process has t₀～t₁、t₀～t₂、t₁～t₂And t₂The corresponding slice requires energy having a value of d₁(t₀，t₁)，d₂(t₀，t₂)，d₃(t₁，t₂)，d₄(t₂，t₂)。

As can be seen from fig. 3, the problem of equation (2) can be transformed into the problem of energy required for selecting whether to buy the corresponding slice in each timeslot, for example, as shown in equation (3):

wherein the content of the first and second substances,the start and end points of each temporal decomposition slice are separately represented,and u (t) represents the decision to buy or not buy energy at time slot t, where "1" represents buy and "0" represents not buy.

To minimize energy cost, it may be desirable to buy energy for each slice at the time slot with the lowest energy supply parameter (e.g., energy price), e.g., at t₀、t₁Or t₂Time slot t with lowest price of medium energy supply₁Choose buy d₂(t₀，t₂) And the like.

Taking this as an example, if t₁、t₂Belonging to future time slots not yet occurring and under the assumption of t₀At the moment, judging whether to buy energy, the t is passed₀P (t) of a time slot₀) Co-predict t₁、t₂P (t) of a time slot₁)、p(t₂) Comparing and judging p (t)₀) If it is the minimum of the three unit energy supply parameters, if so, at t₀Time slot acquisition d₂(t₀，t₂) (ii) a If not, it is not at t₀Time slot acquisition d₂(t₀，t₂)。

By analogy, the determination of whether to perform u (t) obtaining the slice energy demand from the primary energy system at each time slot may be summarized by decomposing the slice at each time slot t by the actual specific energy supply parameter p (t) at each time slot t and the policy threshold θ (t) at each time slot including the time slot_tAnd the comparison result of (a), and the theta_tPredicted specific energy supply parameters for individual time slots that can be spanned by each time-resolved sliceIs determined by the minimum value in (a), and can be expressed by formula (4):

wherein T is a future time slot after the current time slot T, and T + 1-T form a future time period.

It can be understood that each strategy threshold value of each time decomposition slice containing each current time slot t in the time slot t is obtained through calculation, and an energy utilization control strategy is constructed according to the strategy threshold value, so that the energy utilization cost is optimized while the energy requirement is met, and the problems of unreasonable energy allocation, waste and low efficiency caused by the fact that a user randomly uses energy are avoided.

In the above embodiment, the calculation of the slice decomposition energy requirement depends on the prediction of renewable energy supply for the future time slot, and the calculation of the policy threshold depends on the prediction of the unit energy supply parameter for the future time slot; in some embodiments, in order to obtain a prediction result more accurately, the prediction may be accomplished using a predictor implemented by a deep learning model.

The deep learning model can be realized by an end-to-end neural network model. The end-to-end is compared with the traditional machine learning process. The traditional machine learning process usually consists of a plurality of independent modules, for example, in a typical Natural Language Processing (Natural Language Processing) problem, the process comprises a plurality of independent steps such as word segmentation, part of speech tagging, syntactic analysis, semantic analysis and the like, each step is an independent task, and the quality of the result affects the next step, so that the result of the whole training is affected, and the process is not end-to-end; in the training process of the deep learning model, a prediction result is obtained from an input end (input data) to an output end, an error is obtained by comparing the prediction result with a real result, the error is transmitted (reversely propagated) in each layer of the model, the representation of each layer is adjusted according to the error, the adjustment is not finished until the model converges or reaches the expected effect, and all the operations in the middle are contained in the neural network and are not divided into a plurality of modules for processing. The neural network from the input end to the output end is self-integrated from the original data input to the result output, so the neural network is called end-to-end.

It can be found that the prediction is based on a time-sequential iterative computation, and a predictor suitable for this type of prediction can be, for example, a Recurrent Neural Network (RNN) model; preferably, the LSTM model or the like is also used.

As shown in fig. 3A, a logic structure of a cell (cell) of the recurrent neural network in the embodiment is shown.

As shown, each circle represents a cell, each cell may correspond to a time slot, t represents the tth time slot, x_t-1Representing the input of t-1 time slots, s_t-1Cell state information of a cell representing a t-1 time slot, o_t-1Representing the output of the t-1 time slot, and so on; w is s from the previous cell and is used for calculating the weight of the current s; u is a weight calculated from the input to the cell state information, and V is a weight calculated from the cell state information to the output; the output layer is calculated in the following way: o_t＝g(Vs_t) (ii) a The calculation of the hidden layer is denoted as s_t＝f(Ux_t+W_st-1) A 1 is to_tSubstitution of the formula into o_tIn the formula, can be converted into o_tAnd U, V, W, s_tThe relationship between f and g can be selected from a Tanh function (hyperbolic tangent function) or a ReLU function (linear rectification function), g can be selected from a Softmax function, and the whole model adopts a training algorithm of a BPTT (back-propagation through time), i.e., an output value of each unit is calculated in the previous direction, an error term value of each unit is calculated in the reverse direction, which is a partial derivative of the error function to a weighted input of the unit, the gradient of each weight is calculated, and finally the weight is updated by a stochastic gradient descent algorithm, wherein specific calculation of the BPTT is not exemplified here.

When applied to the scheme of the application, x is the predicted unit energy supply parameter when the future time slot needs to be predicted_tCan select each history time in the energy supply parameter data of the history unitHistorical unit energy supply parameters (such as historical energy supply price) of actual occurrence of gaps, and h output_TCan be a predicted unit energy supply parameter of the Tth time slot in the future. For example, according to x_t-kTo x_tHistorical energy supply price of, forecast x_t+1Predicted energy supply price to each time slot in T; in the same way, if x_tThe actual occurrence of the historical renewable energy supply amount per historical time slot in the historical renewable energy supply data is adopted, and the output is o_TMay be the predicted renewable energy supply amount for the future tth time slot.

As shown in fig. 3B, a logic structure of a cell (cell) of the LSTM in the embodiment of the present application is shown.

The internal logic structure of the cell of the LSTM is different compared to the RNN cell, and reference can be made to fig. 3B.

Specifically, take the cell corresponding to the time slot t as an example, s_t-1Cell state information (s also represents long-term memory information) for a cell corresponding to a t-1 slot, f_tIndicating forgetting gate, i_tDenotes an input gate, o_tIndicates an output gate, < > indicates a Hadamard product, < > indicates a cascade (i.e., vector stitching), s_t-1Represents its cell state information from the cell transmission of the previous slot, σ represents sigmoid calculation, Tanh represents Tanh calculation,represents intermediate state information, h_t-1And h_tThe hidden state information (h also represents short term memory information) respectively representing the previous cell and the current cell output, and h is shown in the figure_t-1And x_tAfter summation, after sigma or Tanh calculation, the sum is output after operation through a forgetting gate, an input gate and an output gate.

Wherein f is_t＝σ(w_f[h_t-1,x_t]+b_f)，w_fIs the weight parameter of the forgetting gate, b_fIs the offset vector of the forgetting gate;

i_t＝σ(w_i[h_t-1,x_t]+b_i)，w_iis the weight parameter of the input gate, b_iIs the offset vector of the input gate；

w_sIs thatWeight parameters used for the calculation, b_iIs thatCalculating a bias vector to be used;

h_t＝σ(w_o[h_t-1,x_t]+b_o)tanh(s_t)，w_ois a weight parameter of the output gate, b_oIs the offset vector of the output gate.

As with the RNN, LSTM may predict the corresponding prediction by inputting historical renewable energy supply data or historical unit supply parameter data.

It is understood that the predictor before being used for actual application may be trained, for example, by dividing the historical data into a training set and a test set, calculating the error between the predicted result and the actual result of the training set (for example, calculating the error between the predicted energy supply price and the actual energy supply price of time slot t +1) through a loss function, adjusting the parameters through the BPTT, and then testing through the test set until the actual prediction application is performed after the model training is completed.

In some embodiments, the prediction of future data from historical data by a predictor may also be subdivided into a variety of ways. Hereinafter, different prediction methods are described by taking LSTM as an example.

In some embodiments, a "point prediction approach" may be employed for prediction; fig. 4 is a flow chart of a point prediction method in an embodiment.

The process comprises the following steps:

step S401: and predicting a predicted value (such as renewable energy supply prediction/unit energy supply prediction parameter) of a future time slot according to the historical values (such as historical renewable energy supply/historical unit energy supply parameters) of the previous k historical time slots.

It is to be understood that k is any natural number.

Step S402: the predicted value is combined with k-1 history values before it into a new k values, and the process returns to step S401 for performing the next operation to predict the predicted value of the next future time slot of the future time slot.

If an upper limit for a future period, e.g., T +1 to T, is set, step S403 may also be included before S402 returns to S401: judging whether a predicted value of the Tth time slot is predicted or not; if not, returning to S401 to continue execution; if yes, no circulation is performed, and a prediction result is output.

For example, based on historical data { x }_t-a，....，x_tGet the predictionThen make up intoReuse for predictionAnd so on until obtaining

For the above calculation process, a predictor, such as the predictor of FIG. 5, which may be constructed from RNN or LSTM, may be employed.

Taking LSTM as an example, as shown in fig. 5, a schematic diagram of a logical architecture of a predictor for point prediction in the embodiment of the present application is shown.

In this embodiment, the predictor may be a multi-layer architecture, each layer having a plurality of cells; in fig. 5, the corresponding layers are indicated by superscripts, and if N layers exist, the superscripts are 1 to N; the layer being indicated by subscriptThe xth cell; each cell in the first layer (i.e., e.g., input layer) obtains a historical data input, e.g., first layer input (x), for the corresponding time slot, respectively₁，...x_t) (ii) a Each cell outputs hidden state information h and cell state information s to the next cell in the same layer, e.g. the first cell in the first layer of the figure will beAndoutputting the data to a second cell of the first layer; in the case of multiple layers, the unit in each layer (i.e. e.g. input layer, hidden layer, output layer) gets an input of hidden state information output by the unit corresponding to the time slot in the previous layer, e.g.; the output of the unit (e.g., T + 1.., T) in the last layer (i.e., e.g., output layer) corresponding to the future time slot is taken as the prediction result; it can be understood that the multi-layer depth model architecture can achieve better learning and prediction effects, but does not limit the single-layer architecture to be applied to the embodiments of the present application.

In some embodiments, a "sequence to sequence" prediction approach may be employed for prediction; fig. 6 shows a flow chart of a sequence-to-sequence prediction method in an embodiment.

The process comprises the following steps:

step S601: and coding according to the historical data to obtain a corresponding context vector.

Step S602: and decoding according to the context vector to obtain a sequence formed by the predicted value of each future time slot in the future time interval.

For example, an encoder implemented with a predictor would { x }_t-k，...，x_tMapping the V into a context vector V, and decoding the V by an encoder realized by a predictor to obtain the VOutput as a prediction result; wherein the predictor may be implemented by RNN or LSTM.

As shown in fig. 7, a schematic diagram of a logical architecture of a predictor for sequence-to-sequence prediction in the embodiment of the present application is shown.

In this embodiment, the predictor includes: an Encoder (Encoder) and a Decoder (Decode), wherein the Encoder is used for encoding the context vector, and the Decoder is used for decoding the sequence; wherein the encoder and decoder may be implemented by a deep learning model, such as one or more layers of a recurrent neural network or a long-short term memory artificial neural network, respectively.

Using LSTM as an example, as shown in the figure, in the multi-layer LSTM architecture of the encoder, the cell input { x ] to the input layer_t-k，...，x_tThe signal transmission manner among the cells in the multiple layers is similar to that in fig. 5, and is not repeated herein; the output context vector V, V of the output layer of the coder is input into the multi-layer LSTM framework of the decoder, and output is obtained at the output layer after the decoding processing of the decoderWhere the structure in the decoder can be seen, each predictorIs the output of a column of cells connected corresponding to the same time slot in a different layer as input to the cell located at the first layer in the next column (as indicated by the gray line in the figure) to predict the predicted value of the next time slot, thereby predicting the predicted value of the next time slot from the previous time slotPredict to

According to the principle, the embodiment of the application provides a method for generating an energy control strategy. Fig. 8 is a schematic flow chart illustrating a method for generating an energy use control policy in the embodiment of the present application. The method comprises the following steps:

step S801: and predicting the predicted renewable energy supply of each time slot in the future period according to the input historical renewable energy supply data of the renewable energy system through the first predictor.

In some embodiments, the prediction mode adopted by the first predictor may be, for example, the point prediction mode of fig. 4 or the sequence-to-sequence prediction mode of fig. 6, and accordingly, the first predictor may be implemented by a deep learning model as shown in fig. 5 or fig. 7.

In some embodiments, the historical renewable energy supply data may include: historical renewable energy supply of the renewable energy system of each historical time slot; the historical renewable energy supply can be obtained by counting the production capacity and output quantity of the renewable energy system, or by counting the energy received by the energy utilization system.

In some embodiments, if the first predictor predicts by a point prediction manner as illustrated in the embodiment of fig. 4, the first predictor iteratively performs the following operations until a predicted unit energy supply parameter of each time slot in the future period is obtained: predicting the predicted renewable energy supply of a future time slot according to the historical renewable energy supply of the previous k historical time slots; and the predicted renewable energy supply/predicted historical unit energy supply parameter of the future time slot is combined with the historical renewable energy supply of k-1 previous historical time slots to be used for executing the next operation to predict the predicted renewable energy supply of the next future time slot of the future time slot, and the like.

In some embodiments, if the first predictor predicts through a sequence-to-sequence prediction manner as illustrated in the embodiment of fig. 6, the first predictor may encode a corresponding context vector according to a plurality of historical renewable energy supplies, and decode a sequence composed of the predicted renewable energy supplies of each future time slot in the future time period according to the context vector.

In a practical implementation, assuming that the current time slot is T and the future period is T + 1-T, the first predictor may for example be represented as a function φ R, and φ R (R)_t-k，....，r_t) Is calculated to obtainOptionally, the future period may be segmented depending on the output width limitation of the first predictor, e.g. by setting a slot window W according to phir (R)_t-k，....，r_t) Can output Etc. for the calculation of policy thresholds for subsequent time-resolved slices at time slots t +1 to t + W; by analogy, r of the t +1 to t + W slots that actually occur can then be_t+1，...，r_t+wPredicting a next time window as historical dataMay regenerate the energy supply to recalculate the policy threshold for each future time slot for each time resolved slice in the next time window.

Step S802: and according to the predicted renewable energy supply of each time slot in the future time period and the actual energy demand of the energy consumption system, obtaining each time decomposition slice and the corresponding slice energy demand in the future time period.

In some embodiments, assuming that the current time slot is T and the future time period is T + 1T, the renewable energy supply for each time slot of the future time period is expressed asAccording to the predicted or actually planned d (T +1) -d (T) and the known energy storage limiting quantity B of the energy storage system, energy-demand decomposition can be carried out according to the principle of the graph 2 to obtain time decomposition slices in T or W, and if L slices exist, the energy demand of the corresponding slices is expressed asWherein the content of the first and second substances,the superscript of (a) denotes the lth time resolution slice, the subscript s denotes the starting slot of this time resolution slice, and the subscript e denotes the ending slot of this time resolution slice.

If the decomposition step is represented by a decomposer xi, the above decomposition process is represented as: note that, if T is divided by W, T in the formula may be replaced with T + W.

Step S803: and predicting the predicted unit energy supply parameter of each time slot in the future period according to the input historical unit energy supply parameter data by the second predictor, and determining the strategy threshold value of each time decomposition slice at the current time slot according to the minimum value of the predicted unit energy supply parameter of each time slot in each time decomposition slice.

In some embodiments, the prediction mode adopted by the second predictor may be, for example, the point prediction mode of fig. 4 or the sequence-to-sequence prediction mode of fig. 6, and accordingly, the second predictor may be implemented by a deep learning model as shown in fig. 5 or fig. 7.

In some embodiments, the historical unit energy supply parameter data may include: a historical energizing unit parameter (e.g., a historical energizing price) for each historical time slot; if the current time slot is t, the historical energy supply price of t-k-t that has occurred can be expressed as p (t-k) to p (t).

In some embodiments, if the second predictor predicts by a point prediction manner as illustrated in the embodiment of fig. 4, the second predictor is configured to iteratively perform the following operations until a predicted unit energy supply parameter of each time slot in the future period is obtained: predicting a prediction unit energy supply parameter of a future time slot according to the historical unit energy supply parameters of the previous k historical time slots; the predicted historical unit energy supply parameter of the future time slot is combined with the historical unit energy supply parameters of k-1 previous historical time slots for performing the next operation to predict the predicted unit energy supply parameter of the next future time slot of the future time slot, and the like.

In some embodiments, if the second predictor predicts through a sequence-to-sequence prediction manner as shown in the embodiment of fig. 6, the second predictor may encode a corresponding context vector according to a plurality of energy-supplying parameters of historical units, and decode a sequence formed by energy-supplying parameters of prediction units of each future time slot in the future time period according to the context vector.

In a practical implementation, assuming that the current time slot is T and the future period is T + 1-T, the second predictor may for example be represented as a function φ P, and φ P (P)_t-k，....，p_t) Is calculated to obtainOptionally, the future period may be segmented depending on the output width limitation of the first predictor, e.g. by setting a slot window W according to phip (P)_t-k，....，p_t) Can output Etc. for the calculation of policy thresholds for subsequent time-resolved slices at time slots t +1 to t + W; optionally, if each time-resolved slice is analyzed one by one in sequence, the predicted value of each future time slot in each time-resolved slice can also be predicted separately, for example, the slice energy requirement of time-resolved slice l isThen can be based on phi P (P)_t-k，....，p_t) Obtaining a prediction result of each future time slotBy analogy, p for the t +1 to t + W slots that actually occur may then be_t+1，...，p_t+wPredicting a next time window as historical dataMay regenerate the energy supply to recalculate the policy threshold for each future time slot for each time resolved slice in the next time window.

After determining the time slices for the future time period (T or each W) in step S802, a policy threshold θ T for each time slice at the current time slot T may be calculated, which may be based on the predicted unit energy supply parameter for each time slot in the future that the time slice containsIs determined by the minimum value of; moreover, since there may be overlap of time-resolved slices in the same time slot, the policy threshold at t of these time-resolved slices (assuming that there are m, i.e., time-resolved slices 1-m) can be calculated separately

Step S804: and acquiring an energy utilization control strategy constructed according to each strategy threshold.

The comparison result of the actual unit energy supply parameter of each current time slot and the strategy threshold value of the at least one time decomposition slice to which the actual unit energy supply parameter belongs in the current time slot is used for determining whether the current time slot needs to obtain energy supply from the main energy generation system, and the determined energy supply for obtaining the energy supply is determined by the energy demand of the slice of the corresponding time decomposition slice.

The principle as previously demonstrated by the embodiment of FIG. 2 is to illustrate the policy thresholdThe use of (1): the actual unit energy supply parameter p (t) of the time slot t (e.g. energy supply price) and the strategy threshold value of the time division slices 1-m at tCarry out the ratio of eachIf a strategy threshold value is smaller than the actual unit energy supply parameter, determining to obtain energy supply from the main energy generation system in the time slot t, wherein the energy supply can be the slice energy demand of the time-resolved slice corresponding to the strategy threshold value, for exampleThen decide to buySlice energy requirement of corresponding time-resolved slice 1By analogy, inAfter the time division slices are respectively compared with p (t), the energy required by each slice which is determined to be required to obtain energy supply from the main energy system at t is superposed according to each comparison result so as to determine the total energy required to obtain energy supply from the main energy system at the current time slot t. For example, assume a passAfter the comparison, the slices 1, 3 and 5 are decomposed by time when the power is needed to be obtained at t, and the total energy needed to be obtained from the main energy system at the time slot t is

The energy usage control strategy is used for controlling the energy storage system and at least one of the energy usage systems to perform energy supply from the main energy generation system. Thus, in this example, the energy use control strategy involved in the energy capture action (action) at time t may be described as "obtaining energy from the primary energy generating system for purchaseMay also be expressed as a"buyBuy an"and so on. It should be noted that the expression "in this example is only described by the meaning of the energy supply acquisition action corresponding to the energy supply controllable strategy, so as to facilitate the understanding of the reader, and is not the actual implementation; in a practical scenario, the control strategy should be implemented in code that is machine-recognizable, and not limited by the above description.

In a practical implementation, the generator using the energy control strategy can be represented as η, and the generated energy supply acquisition action corresponding to each time-resolved slice at t can be represented as ηl denotes the l-th time resolved slice in the future period,the strategy threshold value of the ith time decomposition slice at the time slot t is represented, and a represents the energy supply acquisition action of the ith time decomposition slice at the time slot t.

It is understood that in the scenario shown in fig. 1, the energy supply obtaining action may be performed by the energy storage system, the energy utilization system, or both the energy storage system and the energy utilization system.

In some embodiments, the method for generating an energy use control policy may further include: and outputting the energy utilization control strategy. The output energy use control strategy can be used for controlling the energy storage system and/or the energy use system in the figure 1 to execute corresponding energy supply obtaining actions.

Fig. 9 is a schematic structural diagram of a computer device provided in the embodiment of the present application.

The computer device 900 comprises:

the storage device 901 stores at least one computer program. In some embodiments, the storage 901 comprises at least one memory for storing at least one computer program; in embodiments, the memory may include high speed random access memory, and may also include non-volatile memory, such as one or more magnetic disk storage devices, flash memory devices, or other non-volatile solid state storage devices. In certain embodiments, the memory may also include memory that is remote from the one or more processors, such as network attached memory that is accessed via RF circuitry or external ports and a communications network, which may be the internet, one or more intranets, local area networks, wide area networks, storage area networks, and the like, or suitable combinations thereof. The memory controller may control access to the memory by other components of the device, such as the CPU and peripheral interfaces.

Processing means 902 for running the computer program to execute and implement the energy use control policy generation method in fig. 8 to obtain the energy use control policy. In some embodiments, the processing device 902 includes at least one processor, which is connected to the at least one memory, and is configured to execute and implement at least one embodiment described in the above visual user classification method, such as the embodiment described in fig. 1, when the at least one computer program is executed. In an embodiment, the processor is operatively coupled with a memory and/or a non-volatile storage device. More specifically, the processor may execute instructions stored in the memory and/or the non-volatile storage device to perform operations in the computing device, such as generating image data and/or transmitting image data to an electronic display. As such, at least one of the processors may comprise one or more general purpose microprocessors, one or more special purpose processors, one or more field programmable logic arrays, or any combination thereof.

And a communication device 903 for communicating with the outside for outputting the energy utilization control strategy to control the energy storage system and/or the energy utilization system to execute the energy supply obtaining action. The communication device 903 may comprise one or more wired or wireless communication circuits, such as an IO interface, a wired ethernet card, a USB interface, etc., and wireless communication circuits, such as a wireless network card (WiFi), a 2G/3G/4G/5G mobile communication module, bluetooth, infrared, etc.

In some embodiments, the computer apparatus may be embodied as an electronic device, such as an electronic device loaded with an APP application computer program or having communication network access capabilities, including components such as memory, memory controllers, one or more processing units (CPUs), peripheral interfaces, RF circuitry, audio circuitry, speakers, microphones, input/output (I/O) subsystems, display screens, other output or control devices, and external ports, which communicate over one or more communication buses or signal lines. The electronic device includes, but is not limited to, personal computers such as desktop computers, notebook computers, tablet computers, smart phones, smart televisions, and the like. The electronic device can also be an electronic device consisting of a host with a plurality of virtual machines and a human-computer interaction device (such as a touch display screen, a keyboard and a mouse) corresponding to each virtual machine.

The electronic device may be the electronic device category of the above example, or may be a service terminal, and communicates with the local electronic device through a network; wherein the network may be the internet, a mobile network, a Local Area Network (LAN), a wide area network (WLAN), a Storage Area Network (SAN), one or more intranets, the like, or a suitable combination thereof; the service terminals can be arranged on one or more entity servers according to various factors such as functions, loads and the like. When distributed in a plurality of entity servers, the service terminal may be composed of a server based on a cloud architecture. For example, the Cloud-based server includes a Public Cloud (Public Cloud) server system and a Private Cloud (Private Cloud) server system, wherein the Public or Private Cloud server system includes Software-as-a-Service (SaaS), Platform-as-a-Service (PaaS), Infrastructure as a Service (IaaS), and the like. The private cloud server system is used for example for a Mei Tuo cloud computing service platform, an Array cloud computing service platform, an Amazon cloud computing service platform, a Baidu cloud computing platform, a Tencent cloud computing platform and the like. The server system may also be constituted by a distributed or centralized cluster of servers. For example, the server cluster is composed of at least one entity server. Each entity server is provided with a plurality of virtual servers, each virtual server runs at least one functional module in the catering merchant information management server system, and the virtual servers are communicated with each other through a network.

Fig. 10 is a schematic diagram illustrating an application scenario applied by a computer device according to an embodiment of the present application.

The application scenario of fig. 10 is based on the embodiment of fig. 1. In fig. 10, in addition to a main energy system 1001, a renewable energy system 1002, an energy storage system 1003, and an energy usage system 1004, a computer device 1005 is shown. The computer device may for example be the computer device in fig. 9.

The computer device 1005 may be communicatively connected to at least one of the energy storage system 1003 (e.g., its controller, or management terminal) and the energy utilization system 1004 (e.g., its controller, or management terminal) to output the obtained energy utilization control policy to the at least one of the energy storage system 1003 and the energy utilization system 1004 to control the energy storage system 1003 and/or the energy utilization system 1004 to perform the corresponding energy supply obtaining action.

In some embodiments, the computer device 1005 may also be communicatively connected to the energy consumption system 1004, the renewable energy system 1002 (e.g., its controller, or a management terminal) to obtain historical renewable energy consumption data in the previous embodiments; in some embodiments, the computer device 1005 may also be communicatively coupled to the energy usage system 1004, the main energy system 1001 (e.g., their controller, or management terminal), or other devices (e.g., web servers, readable storage media, etc.) to obtain the historical unit energy usage parameter data.

Fig. 11 is a schematic block diagram of a system capable of controlling policy generation according to an embodiment of the present application.

The modules (e.g., 1101-1104) included in the control-capable policy generation system 1100 may be implemented in hardware, software, firmware, or any combination thereof. When implemented in software, one or more instructions or codes corresponding to the modules may be stored in or transmitted to a computer-readable storage medium, such as the storage device of the computer apparatus in fig. 9, so as to implement the functions corresponding to the modules when executed by a processing device.

Referring to fig. 1, the energy use control policy generation system 1100 is applicable to a distribution and distribution system including: the system comprises an energy consumption system, an energy storage system and a renewable energy system, wherein the energy consumption system is coupled with the energy storage system and the renewable energy system to obtain energy supply, at least one of the energy storage system and the energy consumption system is coupled with a main energy generation system to obtain energy supply according to unit energy supply parameters, and the unit energy supply parameters change along with time.

The energy use control policy generation system 1100 includes:

a first predictor 1101 for predicting the predicted renewable energy supply for each time slot in the future period based on the input historical renewable energy supply data for the renewable energy system.

In some embodiments, the prediction mode adopted by the first predictor 1101 may be, for example, the point prediction mode of fig. 4 or the sequence-to-sequence prediction mode of fig. 6, and accordingly, the first predictor may be implemented by a deep learning model as shown in fig. 5 or fig. 7.

In some embodiments, the historical renewable energy supply data may include: historical renewable energy supply of the renewable energy system of each historical time slot; the historical renewable energy supply can be obtained by counting the production capacity and output quantity of the renewable energy system, or by counting the energy received by the energy utilization system.

In some embodiments, if the first predictor 1101 predicts by a point prediction as illustrated in the embodiment of fig. 4, the first predictor iteratively performs the following operations until a predicted unit energy supply parameter for each time slot in the future period is obtained: predicting the predicted renewable energy supply of a future time slot according to the historical renewable energy supply of the previous k historical time slots; and the predicted renewable energy supply/predicted historical unit energy supply parameter of the future time slot is combined with the historical renewable energy supply of k-1 previous historical time slots to be used for executing the next operation to predict the predicted renewable energy supply of the next future time slot of the future time slot, and the like.

In some embodiments, if the first predictor 1101 performs prediction through a sequence-to-sequence prediction manner as illustrated in the embodiment of fig. 6, the first predictor may encode a corresponding context vector according to a plurality of historical renewable energy supplies, and decode a sequence composed of predicted renewable energy supplies of each future time slot in the future time period according to the context vector.

In a practical implementation, assuming that the current time slot is T and the future period is T + 1-T, the first predictor may for example be represented as a function φ R, and φ R (R)_t-k，....，r_t) Is calculated to obtainOptionally, the future period may be segmented depending on the output width limitation of the first predictor, e.g. by setting a slot window W according to phir (R)_t-k，....，r_t) Can output Etc. for the calculation of policy thresholds for subsequent time-resolved slices at time slots t +1 to t + W; by analogy, r of the t +1 to t + W slots that actually occur can then be_t+1，...，r_t+wPredicting a next time window as historical dataPrediction of (2)The energy supply may be regenerated to recalculate the policy threshold for each time-resolved slice at each future time slot in the next time window.

A decomposer 1102 for decomposing slices and corresponding slice energy requirements at each time in the future period according to the predicted renewable energy supply of each time slot in the future period and the actual energy requirements of the energy consumption system. In some embodiments, assuming that the current time slot is T and the future time period is T + 1T, the renewable energy supply for each time slot of the future time period is expressed as According to the predicted or actually planned d (T +1) -d (T) and the known energy storage limiting quantity B of the energy storage system, energy-demand decomposition can be carried out according to the principle of the graph 2 to obtain time decomposition slices in T or W, and if L slices exist, the energy demand of the corresponding slices is expressed asWherein the content of the first and second substances,the superscript of (a) denotes the lth time resolution slice, the subscript s denotes the starting slot of this time resolution slice, and the subscript e denotes the ending slot of this time resolution slice.

If the decomposer is represented by ξ, the decomposition process described above is represented as: note that, if T is divided by W, T in the formula may be replaced with T + W.

And a second predictor 1103, configured to predict, according to the input historical unit energization parameter data, a predicted unit energization parameter of each time slot in the future period.

In some embodiments, the prediction mode adopted by the second predictor 1103 may be, for example, the point prediction mode of fig. 4 or the sequence-to-sequence prediction mode of fig. 6, and accordingly, the second predictor may be implemented by a deep learning model as shown in fig. 5 or fig. 7.

In some embodiments, the historical unit energy supply parameter data may include: a historical energizing unit parameter (e.g., a historical energizing price) for each historical time slot; if the current time slot is t, the historical energy supply price of t-k-t that has occurred can be expressed as p (t-k) to p (t).

In some embodiments, if the second predictor 1103 predicts by a point prediction manner as illustrated in the embodiment of fig. 4, the second predictor is configured to iteratively perform the following operations until obtaining the predicted unit energy supply parameter of each time slot in the future period: predicting a prediction unit energy supply parameter of a future time slot according to the historical unit energy supply parameters of the previous k historical time slots; the predicted historical unit energy supply parameter of the future time slot is combined with the historical unit energy supply parameters of k-1 previous historical time slots for performing the next operation to predict the predicted unit energy supply parameter of the next future time slot of the future time slot, and the like.

In some embodiments, if the second predictor 1103 performs prediction through a sequence-to-sequence prediction manner as shown in the embodiment of fig. 6, the second predictor may encode a corresponding context vector according to a plurality of energy-supplying parameters of historical units, and decode a sequence formed by energy-supplying parameters of prediction units of each future time slot in the future time period according to the context vector.

In a practical implementation, assuming that the current time slot is T and the future period is T + 1-T, the second predictor may for example be represented as a function φ P, and φ P (P)_t-k，....，p_t) Is calculated to obtainOptionally, the future period may be segmented depending on the output width limit of the first predictor, e.g. a slot window W is set,according to phi P (P)_t-k，....，p_t) Can output Etc. for the calculation of policy thresholds for subsequent time-resolved slices at time slots t +1 to t + W; optionally, if each time-resolved slice is analyzed one by one in sequence, the predicted value of each future time slot in each time-resolved slice can also be predicted separately, for example, the slice energy requirement of time-resolved slice l isThen can be based on phi P (P)_t-k，....，p_t) Obtaining a prediction result of each future time slotBy analogy, p for the t +1 to t + W slots that actually occur may then be_t+1，...，p_t+wPredicting a next time window as historical dataMay regenerate the energy supply to recalculate the policy threshold for each future time slot for each time resolved slice in the next time window.

The strategy generation module 1104 is used for determining a strategy threshold value of each time division slice at the current time slot according to the minimum value of the prediction unit energy supply parameter of each time slot in each time division slice; the comparison result of the actual unit energy supply parameter of each current time slot and the strategy threshold value of the at least one time decomposition slice to which the actual unit energy supply parameter belongs in the current time slot is used for determining whether the current time slot needs to obtain energy supply from the main energy generation system, and the determined energy supply for obtaining the energy supply is determined by the slice energy demand of the corresponding time decomposition slice.

After determining the respective time-resolved slice for the future period (e.g., T or each W), each time-resolved slice may be computedThe strategy threshold value thetat of the time decomposition slice at the current time slot t can be obtained according to the predicted unit energy supply parameter of each time slot of the future contained in the time decomposition sliceIs determined by the minimum value of; moreover, since there may be overlap of time-resolved slices in the same time slot, the policy threshold at t of these time-resolved slices (assuming that there are m, i.e., time-resolved slices 1-m) can be calculated separately

The policy generation module 1104 is further configured to obtain an energy utilization control policy constructed according to each policy threshold; wherein the energy usage control strategy is used to control at least one of the energy storage system and the energy usage system to perform energy harvesting from the primary energy generation system.

The comparison result of the actual unit energy supply parameter of each current time slot and the strategy threshold value of the at least one time decomposition slice to which the actual unit energy supply parameter belongs in the current time slot is used for determining whether the current time slot needs to obtain energy supply from the main energy generation system, and the determined energy supply for obtaining the energy supply is determined by the energy demand of the slice of the corresponding time decomposition slice.

The principle as previously demonstrated by the embodiment of FIG. 2 is to illustrate the policy thresholdThe use of (1): the actual unit energy supply parameter p (t) of the time slot t (e.g. energy supply price) and the strategy threshold value of the time division slices 1-m at tComparing respectively, if a strategy threshold is smaller than the actual unit energy supply parameter, determining to obtain energy supply from the main energy generation system at the time slot t, where the energy supply may be slice energy required by a time decomposition slice corresponding to the strategy threshold, for exampleThen decide to buySlice energy requirement of corresponding time-resolved slice 1By analogy, inAfter the time division slices are respectively compared with p (t), the energy required by each slice which is determined to be required to obtain energy supply from the main energy system at t is superposed according to each comparison result so as to determine the total energy required to obtain energy supply from the main energy system at the current time slot t. For example, assume a passAfter the comparison, the slices 1, 3 and 5 are decomposed by time when the power is needed to be obtained at t, and the total energy needed to be obtained from the main energy system at the time slot t is

The energy usage control strategy is used for controlling the energy storage system and at least one of the energy usage systems to perform energy supply from the main energy generation system. Thus, in this example, the energy use control strategy involved in the energy capture action (action) at time t may be described as "obtaining energy from the primary energy generating system for purchaseMay also be expressed as a"buyBuy an"and so on. It should be noted that the expression "in this example is only described by the meaning of the energy supply acquisition action corresponding to the energy supply controllable strategy, so as to facilitate the understanding of the reader, and is not the actual implementation; in a practical scenario, the control strategy should be implemented in code that is machine-recognizable, and not limited by the above description.

In a practical implementation, the generator using the energy control strategy can be represented as η, and the generated energy supply acquisition action corresponding to each time-resolved slice at t can be represented as ηl denotes the l-th time resolved slice in the future period,the strategy threshold value of the ith time decomposition slice at the time slot t is represented, and a represents the energy supply acquisition action of the ith time decomposition slice at the time slot t.

It is understood that in the scenario shown in fig. 1, the energy supply obtaining action may be performed by the energy storage system, the energy utilization system, or both the energy storage system and the energy utilization system.

In some embodiments, the energy use control policy generation system may further include: an output module 1105 (the dotted box represents optional) for outputting the energy use control strategy. The output energy utilization control strategy can be used for controlling the energy storage system and/or the energy utilization system in fig. 1 and 10 to execute corresponding energy utilization obtaining actions.

A computer-readable storage medium may be provided in an embodiment of the present application, and store at least one computer program, which executes and implements the energy-consumption control policy generation method shown in fig. 8 or the modules of the energy-consumption control policy generation system shown in fig. 10 when being called.

These computer programs, if implemented in the form of software functional units and sold or used as separate products, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application or portions thereof that substantially contribute to the prior art may be embodied in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method of the present application.

In the embodiments provided herein, the computer-readable and writable storage medium may comprise read-only memory, random-access memory, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, flash memory, a USB flash drive, a removable hard disk, or any other medium which can be used to store desired computer program code in the form of instructions or data structures and which can be accessed by a computer. Also, any connection is properly termed a computer-readable medium. For example, if the instructions are transmitted from a website, server, or other remote source using a coaxial cable, fiber optic cable, twisted pair, Digital Subscriber Line (DSL), or wireless technologies such as infrared, radio, and microwave, then the coaxial cable, fiber optic cable, twisted pair, DSL, or wireless technologies such as infrared, radio, and microwave are included in the definition of medium. It should be understood, however, that computer-readable-writable storage media and data storage media do not include connections, carrier waves, signals, or other transitory media, but are intended to be non-transitory, tangible storage media. Disk and disc, as used in this application, includes Compact Disc (CD), laser disc, optical disc, Digital Versatile Disc (DVD), floppy disk and blu-ray disc where disks usually reproduce data magnetically, while discs reproduce data optically with lasers.

The flowcharts and block diagrams in the figures described above of the present application illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, computer program segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

In summary, the energy utilization control strategy generation method, system, device, distribution and distribution system and medium of the present application are applied to a distribution and distribution system, and predict the predicted renewable energy supply of each time slot in the future time period according to the historical data of the renewable energy system by the first predictor; obtaining each time decomposition slice and corresponding slice energy demand in the future time period according to the predicted renewable energy supply and the actual energy demand of the energy consumption system; predicting unit energy supply parameters through a second predictor, and determining a strategy threshold value of the time decomposition slice at the current time slot; the comparison result of the actual unit energy supply parameter of each current time slot and the strategy threshold value of the at least one time decomposition slice to which the actual unit energy supply parameter belongs in the current time slot is used for determining whether the current time slot needs to obtain energy supply from the main energy generation system, and the determined energy supply for obtaining the energy supply is determined by the energy demand of the slice of the corresponding time decomposition slice; the energy utilization control strategy constructed by each strategy threshold value is used for controlling energy utilization; the renewable energy supply and cost prediction method and the system have the advantages that the renewable energy supply and cost prediction parameters are predicted through the predictor to construct an online control strategy for obtaining the energy supply, the prediction is accurate, the energy utilization efficiency and the energy utilization cost can be effectively optimized, and the problems in the prior art are solved.

The above embodiments are merely illustrative of the principles and utilities of the present application and are not intended to limit the application. Any person skilled in the art can modify or change the above-described embodiments without departing from the spirit and scope of the present application. Accordingly, it is intended that all equivalent modifications or changes which can be made by those skilled in the art without departing from the spirit and technical concepts disclosed in the present application shall be covered by the claims of the present application.