1. A new energy consumption capability assessment method is characterized by comprising the following steps:

acquiring the operation mode data of the power system on a day to be predicted;

inputting the operation mode data of the power system on the day to be predicted into an established new energy consumption capability evaluation model to obtain a new energy output sequence of the day to be predicted, wherein the new energy consumption capability evaluation model is obtained by training a convolutional neural network model through the operation mode data of the power system on a plurality of selected days before the day to be predicted and the new energy output sequence on the plurality of selected days before the day to be predicted;

and determining new energy consumption capacity index data of the day to be predicted according to the new energy output sequence of the day to be predicted, and evaluating the new energy consumption capacity through the new energy consumption capacity index data of the day to be predicted.

2. The new energy consumption capability assessment method according to claim 1, wherein the establishment of the new energy consumption capability assessment model comprises:

acquiring a training sample set, wherein the training sample set comprises a plurality of training samples;

and training the convolutional neural network model by utilizing each training sample in the plurality of training samples in sequence to obtain the new energy consumption capability evaluation model.

3. The method for evaluating new energy consumption capability according to claim 2, wherein before the obtaining of the training sample set, the method further comprises:

acquiring operation mode data of the power system on a plurality of selected days before a day to be predicted;

determining a new energy output sequence of a plurality of selected days before the day to be predicted according to the power system operation mode data of the plurality of selected days before the day to be predicted and a preset power system maximum new energy consumption capability evaluation model;

combining the power system operation mode data of a plurality of selected days before the day to be predicted and the new energy output sequence of the plurality of selected days before the day to be predicted to determine a plurality of training samples, wherein the power system operation mode data of the plurality of selected days, the new energy output sequence of the plurality of selected days and the plurality of training samples correspond to one another;

and combining the plurality of training samples to obtain the training sample set.

4. The method according to claim 3, wherein the training the convolutional neural network model with each training sample in the training sample set in turn to obtain the new energy absorption capability evaluation model comprises:

acquiring the convolutional neural network model;

and taking the power system operation mode data of the selected day in each training sample as input data of the convolutional neural network model and taking the new energy output sequence of the selected day in each training sample as output data, and training the convolutional neural network model to determine the new energy absorption capacity evaluation model.

5. The new energy consumption capability assessment method according to any one of claims 1 to 4, wherein the determining new energy consumption capability index data of the day to be predicted according to the new energy output sequence of the day to be predicted and assessing the new energy consumption capability through the new energy consumption capability index data of the day to be predicted comprises:

performing integral operation on the new energy output sequence of the day to be predicted to obtain the maximum consumption electric quantity data of the new energy of the day to be predicted;

and taking the maximum consumption electric quantity data of the new energy on the day to be predicted and the new energy output sequence on the day to be predicted as new energy consumption capacity index data on the day to be predicted, and evaluating the new energy consumption capacity through the new energy consumption capacity index data on the day to be predicted.

6. The new energy consumption capability assessment method according to claim 3, wherein the determining the new energy output sequence of the plurality of selected days before the day to be predicted according to the power system operation mode data of the plurality of selected days before the day to be predicted and a preset power system maximum new energy consumption capability assessment model comprises:

establishing a power element model of a power system operation mode;

and solving the preset power system maximum new energy consumption capability evaluation model by using the power element model of the power system operation mode as a constraint condition and using the power system operation mode data of a plurality of selected days before the day to be predicted to obtain a new energy output sequence of the plurality of selected days before the day to be predicted.

7. The new energy consumption capability assessment method according to claim 3, wherein before the obtaining the power system operation mode data of a plurality of selected days before the day to be predicted, the method further comprises:

acquiring power system operation data of a plurality of selected days before a day to be predicted;

and extracting the power system operation mode data in the power system operation data of a plurality of selected days before the day to be predicted to obtain the power system operation mode data of the plurality of selected days before the day to be predicted.

8. A new energy consumption capability evaluation apparatus, comprising:

the data acquisition module is used for acquiring the operation mode data of the power system on the day to be predicted;

the model operation module is used for inputting the operation mode data of the power system on the day to be predicted into the established new energy consumption capability evaluation model to obtain a new energy output sequence of the day to be predicted, wherein the new energy consumption capability evaluation model is obtained by training a convolutional neural network model through the operation mode data of the power system on a plurality of selected days before the day to be predicted and the new energy output sequence on the plurality of selected days before the day to be predicted;

and the consumption capability evaluation module is used for determining the new energy consumption capability index data of the day to be predicted according to the new energy output sequence of the day to be predicted and evaluating the new energy consumption capability according to the new energy consumption capability index data of the day to be predicted.

9. A terminal device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the new energy absorption capability assessment method according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, in which a computer program is stored, which, when being executed by a processor, carries out the steps of the new energy consumption capability assessment method according to any one of claims 1 to 7.

Background

With the increasing of the proportion of wind, electricity and electricity installation in an electric power system, the influence of uncertainty on the operation of the system is continuously expanded, and the problem of self consumption is increasingly severe while the new energy brings remarkable benefits to the whole society, so that the new energy becomes one of the main factors for restricting the development and utilization of the new energy in the future.

At present, Monte Carlo simulation method and convolution method are generally adopted to evaluate the new energy consumption capability. The Monte Carlo simulation method is used for calculating the consumption capacity of the simulation system in different running states through large-scale sampling, and the new energy consumption capacity of a large-scale power system can be evaluated; when the new energy consumption capability is evaluated by the convolution method, only the influence of the system peak regulation capability on the consumption capability is considered, and the evaluation result only can reflect the overall consumption level of the system and cannot comprehensively evaluate the system consumption level.

The new energy consumption capability evaluation method has the problems of long calculation time and low evaluation precision.

Disclosure of Invention

In view of this, embodiments of the present invention provide a method and an apparatus for evaluating new energy consumption capability, a terminal device, and a storage medium, so as to solve the problems of long computation time and low evaluation accuracy in the prior art.

The first aspect of the embodiments of the present invention provides a new energy consumption capability assessment method, including:

acquiring the operation mode data of the power system on a day to be predicted;

inputting the operation mode data of the power system on the day to be predicted into the established new energy consumption capability evaluation model to obtain a new energy output sequence of the day to be predicted, wherein the new energy consumption capability evaluation model is obtained by training a convolutional neural network model through the operation mode data of the power system on a plurality of selected days before the day to be predicted and the new energy output sequence on a plurality of selected days before the day to be predicted;

and determining new energy consumption capacity index data of the day to be predicted according to the new energy output sequence of the day to be predicted, and evaluating the new energy consumption capacity through the new energy consumption capacity index data of the day to be predicted.

A second aspect of an embodiment of the present invention provides a new energy consumption capability assessment apparatus, including:

the data acquisition module is used for acquiring the operation mode data of the power system on the day to be predicted;

the model operation module is used for inputting the operation mode data of the power system on the day to be predicted into the established new energy consumption capability evaluation model to obtain a new energy output sequence of the day to be predicted, wherein the new energy consumption capability evaluation model is obtained by training a convolutional neural network model through the operation mode data of the power system on a plurality of selected days before the day to be predicted and the new energy output sequence on a plurality of selected days before the day to be predicted;

and the consumption capability evaluation module is used for determining the new energy consumption capability index data of the day to be predicted according to the new energy output sequence of the day to be predicted and evaluating the new energy consumption capability according to the new energy consumption capability index data of the day to be predicted.

A third aspect of embodiments of the present invention provides a terminal device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor implements the steps of the new energy consumption capability assessment method according to any one of the above items when executing the computer program.

A fourth aspect of embodiments of the present invention provides a computer-readable storage medium, which stores a computer program that, when executed by a processor, implements the steps of the new energy consumption capability assessment method according to any one of the above.

Compared with the prior art, the embodiment of the invention has the following beneficial effects:

the method comprises the steps of firstly obtaining operation mode data of the power system on a day to be predicted, inputting the operation mode data of the power system on the day to be predicted into an established new energy consumption capability evaluation model, and obtaining a new energy output sequence of the day to be predicted, wherein the new energy consumption capability evaluation model is obtained by training a convolutional neural network model through the operation mode data of the power system on a plurality of selected days before the day to be predicted and the new energy output sequence on a plurality of selected days before the day to be predicted; and finally, determining new energy consumption capacity index data of the day to be predicted according to the new energy output sequence of the day to be predicted, and evaluating the new energy consumption capacity through the new energy consumption capacity index data of the day to be predicted. The method can quickly complete the prediction of the evaluation result of the new input data by adopting the established new energy consumption capability evaluation model, thereby greatly saving the calculation time when the system scale is large and improving the evaluation precision.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the embodiments or the prior art descriptions will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive exercise.

Fig. 1 is a schematic flow chart illustrating an implementation of a new energy consumption capability assessment method according to an embodiment of the present invention;

FIG. 2 is a schematic structural diagram of a convolutional neural network model in an embodiment of the present invention;

FIG. 3 is a flowchart illustrating an implementation of the refinement step of S102 in the embodiment of the present invention;

FIG. 4 is a schematic diagram of an implementation flow of a step before S301 in the embodiment of the present invention;

FIG. 5 is a flowchart illustrating an implementation of the refinement step of S302 in the embodiment of the present invention;

FIG. 6 is a schematic diagram of a flow chart of implementing the step of refining S103 in the embodiment of the present invention;

FIG. 7 is a schematic diagram of a descending new energy output sequence according to an embodiment of the present invention;

FIG. 8 is a schematic diagram of a one-year new energy output sequence in an embodiment of the present invention;

FIG. 9 is a flowchart illustrating the implementation of the refinement step of S402 in the embodiment of the present invention;

FIG. 10 is a flowchart illustrating an implementation of a step before S401 in an embodiment of the present invention;

fig. 11 is a schematic structural diagram of a new energy consumption capability assessment apparatus according to an embodiment of the present invention;

fig. 12 is a schematic diagram of a terminal device according to an embodiment of the present invention.

Detailed Description

In the following description, for purposes of explanation and not limitation, specific details are set forth, such as particular system structures, techniques, etc. in order to provide a thorough understanding of the embodiments of the invention. It will be apparent, however, to one skilled in the art that the present invention may be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present invention with unnecessary detail.

With the development of socio-economy, environmental pollution problems and the gradual exhaustion of fossil fuels have become two invariants of the sustainable development of the people who are the brakes. The development of clean renewable new energy is one of effective solutions to the problems of environmental problems and energy restriction, and is also a necessary way for the sustainable development of human society. At present, new energy power generation is paid much attention at home and abroad, and with the technical progress and the support of governments of various countries, the installed capacity of the new energy power generation is rapidly developed in the last decade.

With the increasing of the proportion of wind, electricity and electricity installation in an electric power system, the influence of uncertainty on the operation of the system is continuously expanded, and the problem of self consumption is increasingly severe while the new energy brings remarkable benefits to the whole society, so that the new energy becomes one of the main factors for restricting the development and utilization of the new energy in the future. In the initial stage of the new energy consumption capability assessment research, the new energy consumption capability assessment is mainly used for power system planning and is used for determining the maximum installed capacity of new energy.

The evaluation by using the constraint factor method is simpler, but the influence of a certain constraint factor is only considered, so that the result obtained by the evaluation method is not general, can only reflect the overall consumption capability of the system, cannot quantify the consumption capabilities of regional power grids and nodes, and cannot comprehensively reflect the consumption capability of new energy.

Because the installed scale of the new energy is enlarged day by day, the electricity abandonment condition is serious, researchers hope to evaluate the new energy consumption capability of the system from the aspect of operation scheduling, so that the new energy consumption capability is improved, the electricity abandonment problem is solved, and an optimization evaluation model which aims at the minimum system operation cost or the maximum new energy consumption capability and comprehensively considers various operation constraints of the system is widely applied to new energy evaluation research. Because the installed proportion of the new energy in the power system is continuously expanded, at the moment, the influence caused by uncertainty of the output of the new energy is not ignored.

The digestion capacity evaluation method based on the Monte Carlo simulation method calculates the digestion capacities of the simulation system in different running states through a large amount of samples, the evaluation result precision is high, but the calculation speed is reduced along with the enlargement of the scale of the power system, so that the Monte Carlo simulation method is not high in calculation efficiency for the large-scale power system new energy digestion capacity evaluation. The evaluation of the absorption capacity based on the convolution method is also researched, the method can realize quick evaluation, but the evaluation process only considers the influence of the system peak regulation capacity on the absorption capacity, so that the result accuracy is not high, and the evaluation result only can reflect the overall absorption level of the system and cannot comprehensively evaluate the system absorption level.

When the scale of the power system is continuously enlarged and the new energy access proportion is continuously increased, the problems brought by the traditional new energy consumption capability assessment method in the aspects of calculation time and precision are more obvious. With the development of the modern convolutional neural learning technology, the number of network layers is further deepened, the nonlinear fitting and feature extraction capability is further enhanced, the prediction of the evaluation result of brand new input data can be quickly finished for the trained evaluation network, and particularly, the calculation time is greatly saved when the system scale is large. In addition, the situation that actual data of the existing time sequence Monte Carlo new energy system is insufficient can be dealt with, and a countermeasure network can be generated by utilizing conditions to generate corresponding data so as to meet the training requirement of a subsequent absorption capacity evaluation network. Therefore, the new energy consumption capability evaluation method is provided, and the evaluation model is established by utilizing the network technology to realize rapid and accurate prediction of the evaluation result.

In order to explain the technical means of the present invention, the following description will be given by way of specific examples.

Fig. 1 is a schematic flow chart illustrating an implementation process of a new energy consumption capability assessment method according to an embodiment of the present invention. As shown in fig. 1, a new energy consumption capability assessment method according to this embodiment includes:

step S101: acquiring the operation mode data of the power system on a day to be predicted;

step S102: inputting the operation mode data of the power system on the day to be predicted into the established new energy consumption capability evaluation model to obtain a new energy output sequence of the day to be predicted, wherein the new energy consumption capability evaluation model is obtained by training a convolutional neural network model through the operation mode data of the power system on a plurality of selected days before the day to be predicted and the new energy output sequence on a plurality of selected days before the day to be predicted;

step S103: and determining new energy consumption capacity index data of the day to be predicted according to the new energy output sequence of the day to be predicted, and evaluating the new energy consumption capacity through the new energy consumption capacity index data of the day to be predicted.

In an embodiment, in the operation process of the power system, various monitoring devices are generally used to monitor operation data in the operation process of the power system, and the operation data of the power system in different operation modes, such as power generator startup mode data, power generator generation power data, node load power data, and the like, can be obtained by extracting the operation data of the power system.

Further, the new energy consumption capability evaluation model is obtained by training a convolutional neural network by using power system operation data. The convolutional neural network adopted by the application is introduced by combining with the graph 2, the convolutional neural network is good at extracting spatial data characteristics, the input two-channel n multiplied by n square matrix has the characteristic of sparseness, and the application extracts the characteristics by using 2 layers of convolutional networks and 1 layer of convolutional network with the largest pooling layer.

The time domain convolution network has strong extraction capability on the sequence data features, and the frequency domain convolution in the channel axis direction after passing through a plurality of convolution kernels can further enrich the extracted features. The 56 × n single-channel data input by the second channel, although not strictly time-series data, contains parameter sequences that cause timing variation of the system, and here, the 56 × n feature matrix can be passed through a time-frequency domain convolution network to better simulate the influence of numerous random variables in the system on the system absorption capability.

Scalar generator contribution constraint P for input network_Gmax、P_GminRestriction of climbing P_up、P_downAnd line flow constraint P_Lmax、P_LminThe characteristics are single, and only the input is needed to be directly input into the fully-connected network.

The channel nxn conductance matrix G and the susceptance matrix B are used as CNN input, firstly, the CNN input passes through two modules of 2-dimensional convolution-batch standardization-ReLU activation function, wherein the 2-dimensional convolution network is used for extracting system structural features, the BN is batch standardization technology and is used for regularizing the network and avoiding gradient problems, the ReLU activation layer is used for enhancing network expression capacity generation, a group of feature maps are generated through the modules, and then the CNN input passes through the modules of 2-dimensional convolution-batch standardization-ReLU activation function and is subjected to non-overlapping maximum pooling for down-sampling to reduce dimensionality, so that three paths of input data can be integrated, and the feature maps at the moment are straightened and sent into a 1-layer full-connection network to be integrated.

A56 xn system characteristic matrix firstly enters a time domain convolution layer, the height of a convolution kernel is equal to 56, the width of the convolution kernel is selected according to the proportion of 1% -2% of n, a plurality of convolution kernels are adopted, the convolution kernels only move on the transverse dimension, the output of the time domain convolution layer is more comprehensive in describing the variable characteristics and the rules of the nodes of the whole system along with backward movement, the output of the time domain convolution layer is also prevented from gradient dispersion and gradient explosion through a batch standardization layer, and is subjected to ReLU function activation and down-sampling through maximum pooling so as to reduce the dimension. The characteristic graph after the time domain convolution layer needs to be spliced with each channel through dimension transformation through a time-frequency domain transformation module, a frequency domain convolution kernel is also spliced along the channel direction, the spliced characteristic graph enters a frequency domain convolution network, and the frequency domain convolution is equivalent to the transformed time domain convolution through the time-frequency domain transformation module, and the extracted characteristics are output according to a format to be integrated through a batch standardization BN layer, a ReLU activation layer, a maximum pooling layer and a straightening full connection layer.

The concatemate splicing layer outputs the CNN, the output of the time-frequency domain CNN and the output of the one-dimensional scalar input generator are constrained by P_Gmax、P_GminRestriction of climbing P_up、P_downAnd line flow constraint P_Lmax、P_LminAnd (3) directly splicing in a one-dimensional direction, then sending into 3 continuous Dense layers, and decreasing the number of neurons of each Dense layer to finally obtain new energy consumption capability index data.

Specifically, the number of selected days before the day to be predicted in the present application is at least 2 days. Take the example that the day to be predicted is 2021 year 5 month 30 day, and a plurality of selected days are from 2021 year 4 month 1 day to 2021 year 4 month 25 day. The method comprises the steps of firstly obtaining power system operation mode data of 5-month-30-day 2021, then inputting the power system operation mode data of 5-month-30-day 2021 into an established new energy consumption capacity evaluation model to obtain a new energy output sequence of 5-month-30-day 2021, wherein the new energy consumption capacity evaluation model is obtained through power system operation mode data of 4-month-1-2021-4-month-25-day 2021 and a new energy output sequence training convolutional neural network model of 4-month-1-2021-4-month-25-day 2021, and finally determining new energy consumption capacity index data of 5-month-30-2021 according to the new energy output sequence of 5-month-30-day 2021, and evaluating new energy consumption capacity through the new energy consumption capacity index data of 5-month-30-day 2021.

The method comprises the steps of firstly obtaining operation mode data of the power system on a day to be predicted, inputting the operation mode data of the power system on the day to be predicted into an established new energy consumption capability evaluation model, and obtaining a new energy output sequence of the day to be predicted, wherein the new energy consumption capability evaluation model is obtained by training a convolutional neural network model through the operation mode data of the power system on a plurality of selected days before the day to be predicted and the new energy output sequence on a plurality of selected days before the day to be predicted; and finally, determining new energy consumption capacity index data of the day to be predicted according to the new energy output sequence of the day to be predicted, and evaluating the new energy consumption capacity through the new energy consumption capacity index data of the day to be predicted. The method can quickly complete the prediction of the evaluation result of the new input data by adopting the established new energy consumption capability evaluation model, thereby greatly saving the calculation time when the system scale is large and improving the evaluation precision.

Fig. 3 is a schematic flow chart of an implementation process of the step S102 in the embodiment of the present invention, and as shown in fig. 3, the building of the new energy consumption capability evaluation model in step S102 includes:

step S301: acquiring a training sample set, wherein the training sample set comprises a plurality of training samples;

step S302: and training the convolutional neural network model by using each training sample in the plurality of training samples in sequence to obtain a new energy consumption capability evaluation model.

In one embodiment, the new energy consumption capability evaluation model is obtained by training the convolutional neural network model through a large number of training samples. The training mode is repeated training, taking 50 training samples as an example, 1-50 training samples are sequentially selected and trained one by one on the convolutional neural network model until an iteration threshold set by the convolutional neural network model indicates that the training is finished, and then the new energy consumption capability evaluation model is obtained. The number of training samples is not particularly limited, and is adjusted according to the specific situation.

Fig. 4 is a schematic flow chart of an implementation procedure of a step before step S301 in the embodiment of the present invention, as shown in fig. 4, step S301 includes:

step S401: acquiring operation mode data of the power system on a plurality of selected days before a day to be predicted;

step S402: determining a new energy output sequence of a plurality of selected days before the day to be predicted according to the operation mode data of the power system of the plurality of selected days before the day to be predicted and a preset power system maximum new energy consumption capability evaluation model;

step S403: combining the power system operation mode data of a plurality of selected days before the day to be predicted and the new energy output sequence of the plurality of selected days before the day to be predicted to determine a plurality of training samples, wherein the power system operation mode data of the plurality of selected days, the new energy output sequence of the plurality of selected days and the plurality of training samples correspond to one another;

step S404: and combining the plurality of training samples to obtain a training sample set.

In an embodiment, the objective function of the preset power system maximum new energy consumption capability evaluation model is the maximum new energy output, and the objective function is as follows:

wherein the content of the first and second substances,n is the actual output of the wind turbine generator in the time period t_wThe total number of the wind turbine generators is,n is the actual output of the photovoltaic unit in the time period t_sThe total number of the photovoltaic units;

the preset power system maximum new energy consumption capability evaluation model is restricted through a universal power element model in each operation mode in the power system, and the specific restriction comprises the following steps:

1. node power balance constraints

Wherein, P_itPower, P, emitted for thermal power generating unit in time period t_L,tIs the value of the load during the time period t; b is the imaginary part of the node admittance matrix; theta is a node voltage phase angle vector; p_R,tIs the power generation power of the new energy unit in the period t,the power is cut off in the t period of the new energy source unit.

The dc power flow equation can be described by:

P_g-P_d＝Bθ (3)

wherein Pg is a system generator output vector; pd is the system load vector.

2. Generator output restraint

P_Gmin,i<P_i,t<P_Gmax,i (4)

The maximum output and the minimum output of the thermal power generating unit are respectively represented by PGmin, i, PGmax and i, and if the constraint is out of range, the new energy consumption is limited by the peak regulation capacity.

At the same time, the output constraints of the new energy bank are as shown above, wherein,andthe available power of the wind turbine generator and the available power of the photovoltaic generator are random variables in nature, and the specific numerical value depends on meteorological conditions and a power curve of the new energy source generator.

3. Generator climbing capability constraint

P_i,t-P_i,t-1>-R_down,iΔt (7)

P_i,t-P_i,t-1<R_up,iΔt (8)

Wherein Rdown, i, Rup, i is the upward climbing rate and the downward climbing rate of the generator i.

4. The form of the line flow constraint is:

P_l,min<P_l<P_l,max (9)

wherein, P_lActive power flowing on the line; p_l,minFor the minimum power allowed to flow on the line, P_l,maxThe maximum power allowed to flow on the line; branch active power flow P_ijThe calculation formula of (the direction of the power flow is positive from the node i to the node j):

wherein x is_ijIs the reactance of branch i-j; i is the head end node of the branch; j is the end node of the branch.

Further, according to the above embodiment, taking a plurality of selected days from 4/month 1/2021 to 4/month 25/2021 as an example, the power system operation mode data of 4/month 1/2021 and the new energy output sequence of 4/month 1/2021 are used as a training sample, the power system operation mode data of 4/month 2/2021 and the new energy output sequence of 4/month 2/2021 are used as a training sample.

Fig. 5 is a schematic flow chart of an implementation of the step of refining step S302 in the embodiment of the present invention, and as shown in fig. 5, step S302 includes:

step S501: acquiring a convolutional neural network model;

step S502: and taking the power system operation mode data of the selected day in each training sample as input data of the convolutional neural network model and taking the new energy output sequence of the selected day in each training sample as output data, and training the convolutional neural network model to determine the new energy absorption capacity evaluation model.

In an embodiment, taking an example that the selected day is 2021 year, 4 month and 1 day, the power system operation mode data of 2021 year, 4 month and 1 day is used as input data of the convolutional neural network model, and the new energy maximum consumption electric quantity data of 2021 year, 4 month and 1 day is used as output data, and the convolutional neural network model is trained to determine the new energy consumption capability evaluation model.

Fig. 6 is a schematic flow chart of an implementation of the step of refining step S103 in the embodiment of the present invention, and as shown in fig. 6, step S103 includes:

step S601: performing integral operation on the new energy output sequence of the day to be predicted to obtain the maximum consumption electric quantity data of the new energy of the day to be predicted;

step S602: and taking the maximum consumption electric quantity data of the new energy on the day to be predicted and the output sequence of the new energy on the day to be predicted as new energy consumption capacity index data of the day to be predicted, and evaluating the new energy consumption capacity through the new energy consumption capacity index data of the day to be predicted.

In one embodiment, the relationship between the maximum consumption electric quantity of the new energy and the output of the new energy is as follows:

wherein E is the maximum consumption electric quantity of the new energy, P_rT is the total hours for new energy output. As shown in fig. 7, the new energy output of each hour is reordered from large to small to obtain a new energy output continuous curve, and the new energy output continuous curves are alignedThe integral of the axis, namely the area, is easy to obtain the maximum consumption electric quantity of the new energy. It should be noted that, when the total hours T and the maximum consumption electric quantity E of the new energy are known, the new energy output P can also be solved through the formula (11)_r. And because the optimization model obtains a new energy output continuous curve with the maximum consumption on the day, the integral of the curve is the maximum new energy consumption electric quantity.

As shown in fig. 8, the operation mode data of the power system every 365 days a year are respectively input into the new energy consumption capability evaluation model, 365 groups of output daily new energy output continuous sequences are merged and reordered to obtain a new energy output continuous curve of 8760 hours a year, and the area enclosed by the curve and the coordinate axes is extremely easy to calculate and is the maximum new energy consumption electric quantity all the year round.

Fig. 9 is a schematic flow chart of an implementation of the step of refining step S402 in the embodiment of the present invention, and as shown in fig. 9, step S402 includes:

step S901: establishing a power element model of a power system operation mode;

step S902: and taking the power element model of the power system operation mode as a constraint condition, and solving the preset power system maximum new energy consumption capability evaluation model by using the power system operation mode data of a plurality of selected days before the day to be predicted to obtain a new energy output sequence of the plurality of selected days before the day to be predicted.

In one embodiment, the power element model includes: the method comprises the following steps of (1) loading model, wind power output model and photovoltaic unit output model, specifically comprising the following steps:

1. load model

Annual peak load L of load model_maxFor reference, the load l (t) at time t can be calculated by the following equation, without considering the change in peak load during the simulation:

L(t)＝L_w(t)×L_d(t)×L_h(t)×L_max (12)

wherein L is_w(t) is the percentage of the weekly load peak to the annual load peak at time t; l is_d(t) is the percentage of daily peak load to weekly peak load at time t; l is_hWhen (t) is tPeak hourly load as a percentage of daily peak load.

2. Wind power output model

The distribution of wind speed V can be modeled by a two-parameter weibull distribution with a probability density function as shown in the following equation:

wherein a is a scale parameter of Weibull distribution, and reflects the average wind speed; b is the shape parameter of Weibull distribution, which reflects the skewness of Weibull distribution; v is a given wind speed value/m.s-1.

The relation between the output of the wind turbine generator and the wind speed is not a simple linear relation but a piecewise function. A typical output characteristic curve of a wind turbine may be represented by a quadratic piecewise function, as follows.

According to the obtained wind speed sampling value, the power output model of the wind generation set is utilized, so that the output power sampling value of each fan can be obtained through conversion, and the output power of all the wind generation sets in the wind power plant is summed to obtain the actual output model of the whole wind power plant.

3. Photovoltaic unit output model

The beta distribution can well simulate the probability of the illumination intensity in a short time period (1-several hours), and if the sunshine irradiance at the installation position of the photovoltaic cell component at the time t is known, the output of the photovoltaic cell component can be obtained through conversion.

Wherein P (t) is the output/MW of the photovoltaic cell assembly at the time t; a is the area/m of the unit cell module²(ii) a η is the conversion efficiency of the cell assembly, which is temperature dependent; i (t) solar irradiance/MJ. at time tm^-2。

Fig. 10 is a schematic flow chart of an implementation procedure of a step before step S401 in the embodiment of the present invention, as shown in fig. 10, step S401 includes:

step S1001: acquiring power system operation data of a plurality of selected days before a day to be predicted;

step S1002: and extracting the power system operation mode data in the power system operation data of a plurality of selected days before the day to be predicted to obtain the power system operation mode data of the plurality of selected days before the day to be predicted.

In one embodiment, the power grid currently employs a series of operation monitoring systems, such as a data acquisition and monitoring control System (SCADA), an Energy Management System (EMS), a Wide Area Measurement System (WAMS), and the like, to perform real-time panoramic monitoring of the operation of the power grid. These automation systems generate a large amount of data with the grid operation, including power system operating data such as real-time grid operating status, equipment status, fault information, etc.

And extracting data from the power system operation data to form a data vector consisting of a line switch state, a generator starting mode, generator power generation power, node load power and the like, establishing a power grid operation mode data set, correspondingly extracting data of each operation mode, and forming key attribute data items in the power data at corresponding moments.

Step S1003: acquiring operation mode data of the power system on a plurality of selected days before a day to be predicted;

step S1004: determining a new energy output sequence of a plurality of selected days before the day to be predicted according to the operation mode data of the power system of the plurality of selected days before the day to be predicted and a preset power system maximum new energy consumption capability evaluation model;

step S1005: combining the power system operation mode data of a plurality of selected days before the day to be predicted and the new energy output sequence of the plurality of selected days before the day to be predicted to determine a plurality of training samples, wherein the power system operation mode data of the plurality of selected days, the new energy output sequence of the plurality of selected days and the plurality of training samples correspond to one another;

step S1006: and combining the plurality of training samples to obtain a training sample set.

It should be understood that, the sequence numbers of the steps in the foregoing embodiments do not imply an execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.

In one embodiment, as shown in fig. 11, there is provided a new energy consumption capability evaluation apparatus including: a data acquisition module 1101, a model operation module 1102 and a digestion capability evaluation module 1103, wherein:

the data acquisition module 1101 is used for acquiring the operation mode data of the power system on the day to be predicted;

the model operation module 1102 is configured to input the power system operation mode data of the day to be predicted into the established new energy consumption capability evaluation model to obtain a new energy output sequence of the day to be predicted, where the new energy consumption capability evaluation model is obtained by training a convolutional neural network model through the power system operation mode data of a plurality of selected days before the day to be predicted and the new energy output sequence of a plurality of selected days before the day to be predicted;

and the consumption capability evaluation module 1103 is configured to determine new energy consumption capability index data of the day to be predicted according to the new energy output sequence of the day to be predicted, and evaluate the new energy consumption capability according to the new energy consumption capability index data of the day to be predicted.

In one embodiment, the model operation module 1102 includes:

the system comprises a sample acquisition submodule and a training sample acquisition submodule, wherein the sample acquisition submodule is used for acquiring a training sample set, and the training sample set comprises a plurality of training samples; and the sample training submodule is used for training the convolutional neural network model by utilizing each training sample in the plurality of training samples in sequence to obtain a new energy consumption capability evaluation model.

In an embodiment, before the sample acquiring sub-module, the method further includes:

the operation mode data acquisition submodule is used for acquiring the operation mode data of the power system on a plurality of selected days before the day to be predicted; the electric quantity determining submodule is used for determining a new energy output sequence of a plurality of selected days before the day to be predicted according to the electric power system operation mode data of a plurality of selected days before the day to be predicted and a preset electric power system maximum new energy consumption capability evaluation model; the training sample determining submodule is used for combining the power system operation mode data of a plurality of selected days before the day to be predicted and the new energy output sequence of the plurality of selected days before the day to be predicted to determine a plurality of training samples, wherein the power system operation mode data of the plurality of selected days, the new energy output sequence of the plurality of selected days and the plurality of training samples are in one-to-one correspondence;

and the training sample set determining submodule is used for combining the plurality of training samples to obtain a training sample set.

In one embodiment, the sample training submodule includes:

the neural network obtaining unit is used for obtaining a convolutional neural network model; and the evaluation model training unit is used for training the convolutional neural network model to determine a new energy absorption capacity evaluation model by taking the power system operation mode data of the selected day in each training sample as input data of the convolutional neural network model and taking the new energy output sequence of the selected day in each training sample as output data.

In one embodiment, the absorption capability evaluation module 1103 includes:

the integral operation submodule is used for carrying out integral operation on the new energy output sequence of the day to be predicted to obtain the maximum consumption electric quantity data of the new energy of the day to be predicted; and the consumption capacity index determining submodule is used for taking the maximum consumption electric quantity data of the new energy on the day to be predicted and the output sequence of the new energy on the day to be predicted as new energy consumption capacity index data of the day to be predicted and evaluating the new energy consumption capacity through the new energy consumption capacity index data of the day to be predicted.

In one embodiment, the power determination submodule includes:

the component model establishing unit is used for establishing a power component model of the power system operation mode; and the consumption electric quantity determining unit is used for solving the preset electric power system maximum new energy consumption capacity evaluation model by using the electric power system operation mode data of a plurality of selected days before the day to be predicted by taking the electric power element model of the electric power system operation mode as a constraint condition to obtain a new energy output sequence of the plurality of selected days before the day to be predicted.

In an embodiment, before the operation mode data obtaining sub-module, the method further includes:

the operation data acquisition submodule is used for acquiring the operation data of the power system on a plurality of selected days before the day to be predicted; and the data extraction submodule is used for extracting the power system operation mode data in the power system operation data of a plurality of selected days before the day to be predicted to obtain the power system operation mode data of the plurality of selected days before the day to be predicted.

Fig. 12 is a schematic diagram of a terminal device according to an embodiment of the present invention. As shown in fig. 12, the terminal device 12 of this embodiment includes: a processor 1201, a memory 1202, and a computer program 1203 stored in the memory 1202 and executable on the processor 1201. The processor 1201, when executing the computer program 1203, implements the steps in the various scene reduction method embodiments described above, such as the steps 101 to 103 shown in fig. 1. Alternatively, the processor 1201 realizes the functions of the modules/units in the above-described apparatus embodiments, for example, the functions of the modules 1101 to 1103 illustrated in fig. 11, when executing the computer program 1203.

Illustratively, the computer program 1203 may be partitioned into one or more modules/units, which are stored in the memory 1202 and executed by the processor 1201 to implement the present invention. One or more modules/units may be a series of computer program instruction segments capable of performing specific functions, which are used to describe the execution of the computer program 1203 in the terminal device 12. For example, the computer program 1203 may be divided into a data acquisition module, a model operation module, and a digestion capability evaluation module, and each module has the following specific functions:

the data acquisition module is used for acquiring the operation mode data of the power system on the day to be predicted;

the model operation module is used for inputting the operation mode data of the power system on the day to be predicted into the established new energy consumption capability evaluation model to obtain a new energy output sequence of the day to be predicted, wherein the new energy consumption capability evaluation model is obtained by training a convolutional neural network model through the operation mode data of the power system on a plurality of selected days before the day to be predicted and the new energy output sequence on a plurality of selected days before the day to be predicted;

and the consumption capability evaluation module is used for determining the new energy consumption capability index data of the day to be predicted according to the new energy output sequence of the day to be predicted and evaluating the new energy consumption capability according to the new energy consumption capability index data of the day to be predicted.

The terminal device 12 may be a desktop computer, a notebook, a palm computer, a cloud server, or other computing devices. 12 terminal device may include, but is not limited to, a processor 1201, memory 1202. Those skilled in the art will appreciate that fig. 12 is merely an example of a terminal device and is not limiting of terminal devices and may include more or fewer components than shown, or some components may be combined, or different components, e.g., a terminal device may also include input output devices, network access devices, buses, etc.

The Processor 1201 may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.

Memory 1202 may be an internal storage unit of terminal device 12, such as a hard disk or a memory of terminal device 12. The memory 1202 may also be an external storage device of the terminal device 12, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like provided on the terminal device 12. Further, memory 1202 may also include both internal and external memory storage devices of terminal device 12. The memory 1202 is used for storing computer programs and other programs and data required by the terminal device. The memory 1202 may also be used to temporarily store data that has been output or is to be output.

It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-mentioned division of the functional units and modules is illustrated, and in practical applications, the above-mentioned function distribution may be performed by different functional units and modules according to needs, that is, the internal structure of the apparatus is divided into different functional units or modules, so as to perform all or part of the functions described above. Each functional unit and module in the embodiments may be integrated in one processing unit, or each unit may exist alone physically, or two or more units are integrated in one unit, and the integrated unit may be implemented in a form of hardware, or in a form of software functional unit. In addition, specific names of the functional units and modules are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present application. The specific working processes of the units and modules in the system may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.

In the above embodiments, the descriptions of the respective embodiments have respective emphasis, and reference may be made to the related descriptions of other embodiments for parts that are not described or illustrated in a certain embodiment.

Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm 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 invention.

In the embodiments provided in the present invention, it should be understood that the disclosed apparatus/terminal device and method may be implemented in other ways. For example, the above-described embodiments of the apparatus/terminal device are merely illustrative, and for example, a module or a unit may be divided into only one logical function, and may be implemented in other ways, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.

Units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.

The integrated modules/units, 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, all or part of the flow in the method according to the embodiments of the present invention may also be implemented by a computer program to instruct related hardware, where the computer program may be stored in a computer readable storage medium, and when the computer program is executed by a processor, the computer program may implement the steps of the embodiments of the method. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer readable medium may include: any entity or device capable of carrying computer program code, recording medium, U.S. disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution media, and the like. It should be noted that the computer readable medium may contain other components which may be suitably increased or decreased as required by legislation and patent practice in jurisdictions, for example, in some jurisdictions, in accordance with legislation and patent practice, the computer readable medium does not include electrical carrier signals and telecommunications signals.

The above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not substantially depart from the spirit and scope of the embodiments of the present invention, and are intended to be included within the scope of the present invention.