1. A planning method of a park comprehensive energy system based on statistical machine learning is characterized by comprising the following steps:

acquiring historical meteorological data influencing a distributed photovoltaic power supply and a building heating load, and processing the historical meteorological data to obtain a simulation sample set;

calculating the power generation power of the distributed photovoltaic power supply and the building heating load according to the simulation sample set;

calculating the power generation power of a thermodynamic system and the gas supply power of a natural gas system of the park comprehensive energy system according to the building heating load;

performing load flow calculation according to the power generation power of the distributed photovoltaic power supply, the power generation power of the thermodynamic system and the gas supply power of the natural gas system to obtain the running state variable of the park comprehensive energy system;

and establishing an objective function according to the operation state variables of the park comprehensive energy system, forming a planning problem by the objective function and constraint conditions, and performing iterative solution on the planning problem to obtain a site selection and volume determination planning scheme of the distributed photovoltaic power supply.

2. The method of claim 1, wherein the historical weather-meteorological data comprises a raw data set of outdoor ambient temperature and solar illumination intensity of the campus during heating, and the processing of the historical weather-meteorological data to obtain a simulated sample set comprises:

carrying out maximum likelihood estimation on the original data set of the solar illumination intensity by using Beta distribution to obtain shape parameters of the Beta distribution, and obtaining a solar illumination intensity simulation sample set according to the shape parameters of the Beta distribution and a Markov chain model;

and processing the original data set of the outdoor environment temperature by adopting a time series model to obtain an outdoor environment temperature simulation sample set.

3. The method of claim 2, wherein obtaining the simulated sample set of solar irradiance according to the shape parameter of the Beta distribution and the Markov chain model comprises:

acquiring a static edge cumulative probability distribution function of the solar illumination intensity based on the shape parameters and the Beta distribution of the Beta distribution;

performing time sequence reconstruction on the static edge cumulative probability distribution function of the solar illumination intensity by using a Markov chain model to obtain a dynamic edge cumulative probability distribution function;

randomly generating a preset number of edge cumulative probability distribution values according to the dynamic edge cumulative probability distribution function, and substituting the edge cumulative probability distribution values into the corresponding edge cumulative probability distribution function to obtain the sunlight intensity simulation sample set.

4. The method of claim 2, wherein processing the raw data set of outdoor environment temperature using a time series model to obtain an outdoor environment temperature simulation sample set comprises:

setting the amplitude, frequency, phase constant and sequence item of a sine model, and processing the original data set of the outdoor environment temperature according to the sine model to obtain a fitting curve determining component of the outdoor environment temperature;

obtaining an outdoor environment temperature fitting curve random component by utilizing a seasonal autoregressive model and a least square method based on white noise;

estimating time distribution parameters by adopting a maximum likelihood estimation method to obtain a probability distribution function of outdoor environment temperature residual variables;

and creating a time-shifting sequence matrix, and determining a probability distribution function of a component, an outdoor environment temperature fitting curve random component and an outdoor environment temperature residual variable according to the time-shifting sequence matrix and the fitting curve of the outdoor environment temperature to obtain a time sequence simulation sample set of the outdoor environment temperature.

5. The method according to any one of claims 1-4, wherein calculating the generated power of the distributed photovoltaic power source and the building heating load from the simulation sample set comprises:

acquiring the generating power of the distributed photovoltaic power supply based on the simulation sample set and the rated power of the distributed photovoltaic power supply by utilizing a mathematical model of the photovoltaic power generation system;

and calculating the building heating load based on the simulation sample set by utilizing a building heat load mathematical model.

6. The method of any one of claims 1-4, wherein calculating the thermal power system generation power and the natural gas system supply power of the campus energy system based on the building heating load comprises:

acquiring the heat power output by a heat source node of the park comprehensive energy system, and calculating the power generation power of the thermodynamic system by using a mathematical model of a cogeneration system according to the building heating heat load and the heat power output by the heat source node;

and obtaining a power system load flow calculation result of the park comprehensive energy system, and calculating the gas supply power of the natural gas system by using a mathematical model of the cogeneration system according to the heat source node output heat power and the power system load flow calculation result.

7. The method of claim 6, wherein obtaining heat source node output thermal power for the campus complex energy system comprises:

and under the working mode that the cogeneration system works with heat and fixed electricity, the flow of the thermodynamic system is calculated to obtain the heat output power of the heat source node.

8. The method of claim 7, wherein obtaining power system load flow calculations for the campus renewable energy system comprises:

and carrying out power flow calculation on the power system based on the generated power of the distributed photovoltaic power supply, the generated power of the thermodynamic system and the obtained power load to obtain the output electric power of the power source node.

9. The method of claim 8, wherein obtaining the operating state variables of the park integrated energy system by performing a power flow calculation based on the generated power of the distributed photovoltaic power source, the generated power of the thermodynamic system, and the supplied gas power of the natural gas system comprises:

and calculating the flow of the natural gas system based on the generated power of the distributed photovoltaic power supply, the output electric power of the power supply node, the generated power of the thermodynamic system and the gas supply power of the natural gas system to obtain the running state variable of the park comprehensive energy system, wherein the running state variable comprises the node voltage of the electric power system, the line tide, the network loss, the heat supply temperature of the thermodynamic system, the heat return temperature, the network loss and the gas supply quantity of the natural gas system pipeline.

10. A computer-readable storage medium, on which a statistical machine learning-based park integrated energy system planning program is stored, which, when executed by a processor, implements the statistical machine learning-based park integrated energy system planning method according to any one of claims 1 to 9.

Background

With the widespread access of renewable energy, the campus integrated energy system has more and more uncertainties and complexities, which brings difficulties and challenges to the safe operation of the integrated energy system. In order to solve the problem of uncertainty of the park comprehensive energy system, accurate modeling of uncertainty of output of new energy is needed. In addition, the randomness of renewable energy sources can also cause the randomness of the injection load or power of the garden integrated energy system nodes, and the probability distribution characteristics of each state variable of the system can be counted through probability load flow calculation to solve the problem, so that the method has an important role in analyzing the safe and economic operation of the multi-energy system. The modeling of renewable energy uncertainty using a probabilistic model in the related art has the following problems: the model capacity is small, the digital characteristics can only capture local data characteristics, the complicated high-dimensional big data characteristics of the renewable energy output cannot be fully described, and the calculation requirement of the probability energy flow of the park comprehensive energy system containing various uncertain related variables cannot be met. Furthermore, the probabilistic model used in the related art models the uncertainty of renewable energy, which results in low accuracy of final energy system planning decision, accuracy of safety situation and low energy utilization efficiency.

Disclosure of Invention

The present invention is directed to solving, at least to some extent, one of the technical problems in the related art.

Therefore, the first purpose of the invention is to provide a planning method of a park comprehensive energy system based on statistical machine learning, which combines the natural gas and combined heat and power technology with photovoltaic power generation, considers the influence of the distributed photovoltaic power supply and the multi-energy flow coupling characteristics of the power load, the building heating heat load and the natural gas load fluctuation on the safe operation of the park comprehensive energy system, and calculates the probability energy flow of the park comprehensive energy system by constructing a refined scene, thereby greatly improving the comprehensive utilization efficiency of energy. And moreover, a weather scene is simulated through seasonal time sequence characteristics of the temperature, a photovoltaic output scene is generated, and the simulation accuracy of a complex operation scene is improved. Compared with the traditional probability model, the method avoids the fitting probability distribution of the explicit appointed random model, greatly improves the efficiency of random production simulation, and provides decision suggestions for safe and economic operation of the garden comprehensive energy system.

A second object of the invention is to propose a computer-readable storage medium.

In order to achieve the above object, an embodiment of a first aspect of the present invention provides a method for planning a campus integrated energy system based on statistical machine learning, including: acquiring historical meteorological data influencing a distributed photovoltaic power supply and a building heating load, and processing the historical meteorological data to obtain a simulation sample set; calculating the power generation power of the distributed photovoltaic power supply and the building heating load according to the simulation sample set; calculating the power generation power of a thermodynamic system and the gas supply power of a natural gas system of the park comprehensive energy system according to the building heating load; performing load flow calculation according to the power generation power of the distributed photovoltaic power supply, the power generation power of the thermodynamic system and the gas supply power of the natural gas system to obtain the running state variable of the park comprehensive energy system; and establishing an objective function according to the operation state variables of the park comprehensive energy system, forming a planning problem by the objective function and constraint conditions, and performing iterative solution on the planning problem to obtain a site selection and volume determination planning scheme of the distributed photovoltaic power supply.

According to the planning method of the park integrated energy system based on statistical machine learning provided by the embodiment of the invention, historical meteorological data influencing distributed photovoltaic power supplies and building heating loads are obtained, the historical meteorological data are processed to obtain a simulation sample set, then the power generation power of the distributed photovoltaic power supplies and the building heating loads are calculated according to the simulation sample set, the building heating loads are further calculated to obtain the thermodynamic system power generation power and the natural gas system gas supply power of the park integrated energy system, then the power generation power of the distributed photovoltaic power supplies, the thermodynamic system power generation power and the natural gas system gas supply power are subjected to tidal current calculation to obtain the operation state variables of the park integrated energy system, finally, a target function is established according to the operation state variables of the park integrated energy system, and the planning problem composed of the target function and the constraint condition is subjected to iterative solution, and obtaining a site selection and volume fixing planning scheme of the distributed photovoltaic power supply.

Therefore, according to the planning method of the park comprehensive energy system based on statistical machine learning, disclosed by the embodiment of the invention, the natural gas and heat and power cogeneration technology is combined with photovoltaic power generation, the influence of the distributed photovoltaic power supply and the multi-energy flow coupling characteristics of the power load, the building heating heat load and the natural gas load fluctuation on the safe operation of the park comprehensive energy system is considered, the probability energy flow of the park comprehensive energy system is calculated by constructing a refined scene, and the comprehensive utilization efficiency of energy can be greatly improved. And moreover, a weather scene is simulated through seasonal time sequence characteristics of the temperature to generate a photovoltaic output scene, the simulation accuracy of a complex operation scene is improved, the random production simulation efficiency is greatly improved, and a decision suggestion is provided for safe and economic operation of a park comprehensive energy system.

In addition, the planning method of the campus comprehensive energy system based on the statistical machine learning according to the above embodiment of the present invention may further have the following additional technical features:

optionally, according to an embodiment of the present invention, obtaining a solar illumination intensity simulation sample set according to a shape parameter of a Beta distribution and a markov chain model, includes: acquiring a static edge cumulative probability distribution function of the solar illumination intensity based on the shape parameters and the Beta distribution of the Beta distribution; performing time sequence reconstruction on the static edge cumulative probability distribution function of the solar illumination intensity by using a Markov chain model to obtain a dynamic edge cumulative probability distribution function; randomly generating a preset number of edge cumulative probability distribution values according to the dynamic edge cumulative probability distribution function, and substituting the edge cumulative probability distribution values into the corresponding edge cumulative probability distribution function to obtain the sunlight intensity simulation sample set.

Optionally, according to an embodiment of the present invention, processing the original data set of the outdoor environment temperature by using a time series model to obtain an outdoor environment temperature simulation sample set includes: setting the amplitude, frequency, phase constant and sequence item of a sine model, and processing the original data set of the outdoor environment temperature according to the sine model to obtain a fitting curve determining component of the outdoor environment temperature; obtaining an outdoor environment temperature fitting curve random component by utilizing a seasonal autoregressive model and a least square method based on white noise; estimating time distribution parameters by adopting a maximum likelihood estimation method to obtain a probability distribution function of outdoor environment temperature residual variables; and creating a time-shifting sequence matrix, and determining a probability distribution function of a component, an outdoor environment temperature fitting curve random component and an outdoor environment temperature residual variable according to the time-shifting sequence matrix and the fitting curve of the outdoor environment temperature to obtain a time sequence simulation sample set of the outdoor environment temperature.

Optionally, according to an embodiment of the present invention, calculating the generated power of the distributed photovoltaic power source and the building heating load according to the simulation sample set includes: acquiring the generating power of the distributed photovoltaic power supply based on the simulation sample set and the rated power of the distributed photovoltaic power supply by utilizing a mathematical model of the photovoltaic power generation system; and calculating the building heating load based on the simulation sample set by utilizing a building heat load mathematical model.

Optionally, according to an embodiment of the present invention, calculating the thermal power system generated power and the natural gas system supplied power of the campus integrated energy system according to the building heating load includes: acquiring the heat power output by a heat source node of the park comprehensive energy system, and calculating the power generation power of the thermodynamic system by using a mathematical model of a cogeneration system according to the building heating heat load and the heat power output by the heat source node; and obtaining a power system load flow calculation result of the park comprehensive energy system, and calculating the gas supply power of the natural gas system by using a mathematical model of the cogeneration system according to the heat source node output heat power and the power system load flow calculation result.

Optionally, according to an embodiment of the present invention, acquiring heat source node output thermal power of the campus integrated energy system includes: and under the working mode that the cogeneration system works with heat and fixed electricity, the flow of the thermodynamic system is calculated to obtain the heat output power of the heat source node.

Optionally, according to an embodiment of the present invention, the obtaining a power flow calculation result of the park integrated energy system includes: and carrying out power flow calculation on the power system based on the generated power of the distributed photovoltaic power supply, the generated power of the thermodynamic system and the obtained power load to obtain the output electric power of the power source node.

Optionally, according to an embodiment of the present invention, performing a power flow calculation according to the generated power of the distributed photovoltaic power supply, the generated power of the thermodynamic system, and the gas supply power of the natural gas system, to obtain the operation state variable of the campus comprehensive energy system, includes: and calculating the flow of the natural gas system based on the generated power of the distributed photovoltaic power supply, the output electric power of the power supply node, the generated power of the thermodynamic system and the gas supply power of the natural gas system to obtain the running state variable of the park comprehensive energy system, wherein the running state variable comprises the node voltage of the electric power system, the line tide, the network loss, the heat supply temperature of the thermodynamic system, the heat return temperature, the network loss and the gas supply quantity of the natural gas system pipeline.

In order to achieve the above object, a second aspect of the present invention provides a computer-readable storage medium, on which a statistical machine learning-based planning program of a campus integrated energy system is stored, which, when executed by a processor, implements the statistical machine learning-based planning method of the campus integrated energy system of the above embodiment.

According to the computer-readable storage medium provided by the embodiment of the invention, when the stored planning program of the park comprehensive energy system based on statistical machine learning is executed, the natural gas and combined heat and power technology is combined with photovoltaic power generation, the influence of the distributed photovoltaic power supply and the multi-energy flow coupling characteristics of power load, building heating heat load and natural gas load fluctuation on the safe operation of the park comprehensive energy system is considered, and the probability energy flow of the park comprehensive energy system is calculated by constructing a refined scene, so that the comprehensive utilization efficiency of energy can be greatly improved. And moreover, a weather scene is simulated through seasonal time sequence characteristics of the temperature to generate a photovoltaic output scene, the simulation accuracy of a complex operation scene is improved, the random production simulation efficiency is greatly improved, and a decision suggestion is provided for safe and economic operation of a park comprehensive energy system.

Drawings

FIG. 1 is a flow chart of a method for planning a campus integrated energy system based on statistical machine learning according to an embodiment of the present invention;

FIG. 2 is a flow chart of a method for planning a campus integrated energy system based on statistical machine learning according to an embodiment of the present invention;

FIG. 3 is a flowchart of processing historical meteorological data to obtain a simulated sample set, according to an embodiment of the present invention;

FIG. 4 is a flowchart of obtaining a simulation sample set of outdoor environment temperature through a time series model according to an embodiment of the present invention;

FIG. 5 is a flow chart of the thermodynamic system power generation calculation for a campus integrated energy system based on building heating thermal load according to an embodiment of the present invention;

FIG. 6 is a flow chart for calculating the supply gas power of a natural gas system using a mathematical model of a cogeneration system, according to an embodiment of the invention.

Detailed Description

Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the drawings are illustrative and intended to be illustrative of the invention and are not to be construed as limiting the invention.

In order to better understand the technical solution, the technical solution will be described in detail with reference to the drawings and the specific embodiments.

Fig. 1 is a flowchart of a method for planning a campus integrated energy system based on statistical machine learning according to an embodiment of the present invention. As shown in fig. 1, the method for planning the campus comprehensive energy system based on the statistical machine learning includes the following steps:

and S01, acquiring historical meteorological data influencing the distributed photovoltaic power supply and the building heating load, and processing the historical meteorological data to obtain a simulation sample set.

The historical meteorological data influencing the distributed photovoltaic power supply and the building heating load comprise outdoor environment temperature and solar illumination intensity. Specifically, a raw data set of outdoor ambient temperature and solar illumination intensity at 96 points per day during heating may be obtained from the central office. The simulation sample set comprises a solar illumination intensity simulation sample set and an outdoor environment temperature simulation sample set.

Optionally, in an embodiment of the present invention, a Beta distribution is used to perform maximum likelihood estimation on an original data set of solar illumination intensity to obtain a shape parameter of the Beta distribution, and a solar illumination intensity simulation sample set is obtained according to the shape parameter of the Beta distribution and a markov chain model; and processing the original data set of the outdoor environment temperature by adopting a time series model to obtain an outdoor environment temperature simulation sample set. Based on the embodiment of the invention, the weather scene is simulated through the time series model, the simulation accuracy of the complex operation scene is improved, the simulation efficiency of random production is greatly improved, and a decision suggestion is provided for the safe and economic operation of the park comprehensive energy system.

Optionally, in an embodiment of the present invention, a static edge cumulative probability distribution function of the solar illumination intensity is obtained according to the Beta distribution and the shape parameter of the Beta distribution; performing time sequence reconstruction on the static edge cumulative probability distribution function of the solar illumination intensity by using a Markov chain model to obtain a dynamic edge cumulative probability distribution function; randomly generating a preset number of edge cumulative probability distribution values according to the dynamic edge cumulative probability distribution function, and substituting the edge cumulative probability distribution values into the corresponding edge cumulative probability distribution function to obtain a solar illumination intensity simulation sample set.

Optionally, in an embodiment of the present invention, the component is determined by setting the amplitude, frequency, phase constant and sequence term of the sinusoidal model, and processing the raw data set of the outdoor environment temperature according to the sinusoidal model to obtain a fitted curve of the outdoor environment temperature; obtaining an outdoor environment temperature fitting curve random component by utilizing a seasonal autoregressive model and a least square method based on white noise; estimating time distribution parameters by adopting a maximum likelihood estimation method to obtain a probability distribution function of outdoor environment temperature residual variables; and creating a time-shifting sequence matrix, and determining a probability distribution function of a component, an outdoor environment temperature fitting curve random component and an outdoor environment temperature residual variable according to the time-shifting sequence matrix and the fitting curve of the outdoor environment temperature to obtain a time-sequence simulation sample set of the outdoor environment temperature. Based on the time series model simulation weather scene in the embodiment of the invention, the accuracy of the simulation of the complex operation scene is improved, the efficiency of the random production simulation is greatly improved, and a decision suggestion is provided for the safe and economic operation of the park comprehensive energy system.

And S02, calculating the power generation power of the distributed photovoltaic power supply and the building heating load according to the simulation sample set.

Specifically, in one embodiment of the present invention, a mathematical model of a photovoltaic power generation system is used to obtain the generated power of a distributed photovoltaic power source based on a simulation sample set and the rated power of the distributed photovoltaic power source, wherein the rated power of the distributed photovoltaic power source can be obtained from a photovoltaic power station. And calculating the heating load of the building based on the simulation sample set by utilizing the mathematical model of the heat load of the building.

And S03, calculating the power generation power of the thermodynamic system and the gas supply power of the natural gas system of the park comprehensive energy system according to the heating load of the building.

Optionally, in an embodiment of the present invention, the thermal system power generation power is calculated by obtaining the heat source node output thermal power of the park comprehensive energy system, and according to the building heating thermal load and the heat source node output thermal power, using a mathematical model of the cogeneration system; and calculating the gas supply power of the natural gas system by using a mathematical model of the cogeneration system by obtaining the power system load flow calculation result of the park comprehensive energy system and outputting the thermal power and the power system load flow calculation result according to the heat source node.

Optionally, in an embodiment of the present invention, in a cogeneration system operating in a fixed-heat mode, the thermodynamic system flow calculation is performed to obtain the heat output power of the heat source node.

Optionally, in an embodiment of the present invention, a power system load flow calculation is performed based on the generated power of the distributed photovoltaic power supply, the generated power of the thermodynamic system, and the obtained power load, so as to obtain the output electric power of the power node. Wherein, the power load can count the power load data during heating through the smart meters in the local industrial park.

Optionally, in an embodiment of the present invention, the natural gas system flow calculation is performed based on the generated power of the distributed photovoltaic power source, the power source node output electric power, the generated power of the thermodynamic system, and the gas supply power of the natural gas system, so as to obtain the operation state variables of the park comprehensive energy system, where the operation state variables include the node voltage of the electric power system, the line load flow, the network loss, the heating temperature of the thermodynamic system, the regenerative temperature, the network loss, and the gas supply amount of the natural gas system pipeline. According to the planning method of the park comprehensive energy system based on statistical machine learning, the natural gas and heat and power combined supply technology and photovoltaic power generation are combined, the influence of the distributed photovoltaic power supply and the power load, the building heating heat load and the multi-energy flow coupling characteristic of natural gas load fluctuation on the safe operation of the park comprehensive energy system is considered, the probability energy flow of the park comprehensive energy system is calculated by constructing a refined scene, and the comprehensive utilization efficiency of energy can be greatly improved.

And S04, performing load flow calculation according to the generated power of the distributed photovoltaic power supply, the generated power of the thermodynamic system and the gas supply power of the natural gas system to obtain the operation state variable of the park comprehensive energy system.

And S05, establishing an objective function according to the operation state variables of the park comprehensive energy system, forming a planning problem by the objective function and constraint conditions, and performing iterative solution on the planning problem to obtain a site selection and volume determination planning scheme of the distributed photovoltaic power supply.

To sum up, according to the planning method of the campus comprehensive energy system based on statistical machine learning, disclosed by the embodiment of the invention, the natural gas and heat and power cogeneration technology is combined with photovoltaic power generation, the influence of the distributed photovoltaic power supply and the multi-energy flow coupling characteristics of the power load, the building heating heat load and the natural gas load fluctuation on the safe operation of the campus comprehensive energy system is considered, and the probability energy flow of the campus comprehensive energy system is calculated by constructing a refined scene, so that the comprehensive utilization efficiency of energy can be greatly improved. And moreover, a weather scene is simulated through seasonal time sequence characteristics of the temperature to generate a photovoltaic output scene, the simulation accuracy of a complex operation scene is improved, the random production simulation efficiency is greatly improved, and a decision suggestion is provided for safe and economic operation of a park comprehensive energy system.

As shown in fig. 2, an embodiment of the method for planning the campus integrated energy system based on statistical machine learning according to the present invention includes the following steps:

s10, acquiring 96 outdoor ambient temperature and sun illumination intensity original data sets every day during heating from a local meteorological office, and acquiring the rated power of the distributed photovoltaic power supply from a photovoltaic power station;

for example, the outdoor temperature data of 96 points per day during the whole heating period can be obtained from a meteorological data acquisition system of a local meteorological office, wherein the meteorological data acquisition system comprises a plurality of sensors, a solar radiation measuring instrument, an intelligent meteorological data acquisition instrument and a GPRS DTU communication module. Specifically, the solar radiation measuring instrument can be used for collecting 96-point-per-day solar illumination intensity data in a heating time period, and the photovoltaic power station is used for obtaining rated power data of the distributed photovoltaic power supply.

And S20, processing the historical meteorological data to obtain a simulation sample set.

As shown in fig. 3, the specific implementation steps include:

and S201, carrying out maximum likelihood estimation on the solar illumination intensity data acquired in the S10 by using the Beta distribution to obtain the shape parameters of the Beta distribution.

S202, acquiring a static edge cumulative probability distribution function of the solar illumination intensity G according to the shape parameters and the Beta distribution of the Beta distribution.

The specific formula is as follows:

in the formula: alpha and Beta are shape parameters of Beta distribution, Gamma is Gamma function, G_maxThe maximum illumination intensity.

And S203, performing time sequence reconstruction on the static edge cumulative probability distribution function of the solar illumination intensity G acquired in the S202 by using a Markov transition probability matrix to acquire a dynamic edge cumulative probability distribution function of the solar illumination intensity G.

The specific formula of the Markov transition probability matrix is as follows:

P_ij＝P(X_n+1＝s_i|X_n＝s_j),s_i,s_j∈s

in the formula: p_ijRepresenting the state transition probability, X, of the ith row and jth column in a Markov transition probability matrix P_nRepresenting the current state of the variable, X_n+1Representing the next state of the variable, s being a sequence of states of the variable, s_iRepresenting the ith variable state, s_jRepresenting the j variable state, wherein the variables include the sun illumination intensity and the outdoor ambient temperature.

Calculating by using a Chapman-Kolmogorov equation

Representing the transition probability of the ith row and the jth column of the state transition matrix of the n + h step,representing the transition probability of the ith row and the kth column of the n-step state transition matrix,the transition probability of the kth row and the jth column of the h-step state transition matrix is represented.

And S204, randomly generating a preset number of edge cumulative probability distribution values according to the dynamic edge cumulative probability distribution function of the solar illumination intensity G obtained in the S203, and substituting the edge cumulative probability distribution values into the corresponding edge cumulative probability distribution function to obtain a solar illumination intensity simulation sample set.

And S30, obtaining an outdoor environment temperature simulation sample set through a time series model based on the outdoor environment temperature data of the set time.

As shown in fig. 4, the specific implementation steps include:

s301, setting the amplitude, frequency, phase constant and sequence item of the sine model, and obtaining a fitting curve determining component of the outdoor environment temperature according to the outdoor environment temperature data obtained in S10.

The specific formula is as follows:

model＝fit(x,T_fit)

in the formula, T_fitTemperature fit curve representing a given time for a given year, x represents a vector of dates per hour that the system needs to convert to sequential date numbers, A_iDenotes the ith amplitude, ω_iDenotes the ith frequency, c_iThe phase constant of the ith sine wave term is shown, n is a sequence term, and when n is 2, the equation parameters are calculated by using a nonlinear least square method. It should be noted that the fitted curve of the outdoor ambient temperature includes a fitted curve of the temperature at a given time for n given years.

And S302, obtaining the random component of the outdoor environment temperature fitting curve by using a seasonal autoregressive model and a least square method based on white noise.

The specific formula is as follows:

T_res,k＝a₀+a₁T_res,k-1+…+a_pT_res,k-p+ε_k

in the formula, T_res,kRepresenting the random component of the fitted curve of the outdoor ambient temperature, T_res,k-1Represents the random component of the (k-1) th fitted curve of the outdoor ambient temperature, T_res,k-pRepresents the random component of the k-p th fitted curve of the outdoor environment temperature, epsilon_kRepresenting the kth white noise sequence, a₀，a₁，…，a_pCoefficients representing a multiple linear regression are solved using the least squares method.

S303, estimating the distribution parameters of the t distribution by using a maximum likelihood estimation method to obtain a probability distribution function of the outdoor environment temperature residual error variable.

S304, a time-shift sequence matrix is created, positive lag corresponds to delay, negative lag corresponds to lead, and a time-sequence simulation sample set of the outdoor environment temperature is calculated according to the obtained fitted curve determining component of the outdoor environment temperature, the random component of the fitted curve of the outdoor environment temperature and the environment temperature residual variable.

And S40, calculating the generated power of the distributed photovoltaic power supply.

Specifically, by using a mathematical model of the photovoltaic power generation system, the power generation power of the distributed photovoltaic power supply is obtained according to the solar illumination intensity simulation sample set obtained in S204, the outdoor environment temperature simulation sample set obtained in S30, and the rated power of the distributed photovoltaic power supply obtained in S1O.

Calculated by the following formula:

in the formula, Y_PVFor obtaining rated capacity [ kW ] of photovoltaic power supply connected to power distribution network]；f_PVIs the power derating factor of the photovoltaic power system; g_TIs the current solar illumination intensity (kW/square meter)]；G_T，STCSolar illumination intensity under standard test condition [ kW/square meter]；T_CThe temperature of the battery of the photovoltaic power supply is [ DEGC]；T_C，STCBattery temperature of photovoltaic power supply under standard test conditions [ deg.C ]]。

And S50, inputting the solar illumination intensity simulation sample set obtained in the S204 and the outdoor environment temperature simulation sample set obtained in the S30 as input variables into a mathematical model of the building heating heat load to obtain the building heating heat load.

And S60, calculating the generated power of the thermodynamic system of the park comprehensive energy system according to the heating heat load of the building.

As shown in fig. 5, the specific implementation steps include:

s601, under the working mode that the cogeneration system uses heat for electricity, the flow of the thermodynamic system is calculated, and the output thermal power of the heat source node is obtained.

And S602, calculating the power generation power of the thermodynamic system according to the building heating heat load, the output heat power of the heat source node and the mathematical model of the cogeneration system.

And S70, calculating the gas supply power of the natural gas system by using the mathematical model of the cogeneration system according to the heat power output by the heat source node and the power flow calculation result of the power system.

As shown in fig. 6, the specific implementation steps include:

and S701, performing power flow calculation of the power system according to the power generation power of the distributed photovoltaic power supply obtained in the S40, the power generation power of the thermodynamic system obtained in the S602 and the power load during the statistical heating period of the intelligent electric meters in the local industrial park to obtain the output electric power of the power supply node.

It should be noted that the industrial park in this embodiment is only used as the range to be calculated, and the specific calculation range is not limited.

And S702, calculating the gas supply power of the natural gas system by utilizing a mathematical model of the cogeneration system according to the heat power output by the heat source node and the electric power output by the power source node.

And S80, calculating the flow of the natural gas system according to the power generation power of the distributed photovoltaic power supply, the power generation power of the thermodynamic system and the gas supply power of the natural gas system, and acquiring the running state variable result of the park comprehensive energy system, wherein the running state variable result comprises the node voltage of the power system, the line tide, the network loss, the heat supply temperature of the thermodynamic system, the heat return temperature, the network loss and the gas supply quantity of the natural gas system pipeline.

And S90, establishing an objective function according to the operation state variables of the park comprehensive energy system, performing iterative solution, obtaining the minimum value of the objective function as a result, and obtaining the location and volume planning scheme of the distributed photovoltaic power supply.

Specifically, the generated power of the distributed photovoltaic power supply is used as the injection power of a PV node in an electric power system, an objective function is established according to the network loss of the electric power system and the network loss of a thermodynamic system, constraint conditions are established according to the node voltage of the electric power system, the heat supply temperature of the thermodynamic system, the heat return temperature and the gas supply quantity of a natural gas system pipeline, finally the objective function and the constraint conditions are combined into a random planning problem, the random planning problem is iteratively solved, the minimum value of the objective function is obtained as a result, and the site selection and volume fixing planning scheme of the distributed photovoltaic power supply in the garden is obtained.

In summary, the planning method of the campus comprehensive energy system based on statistical machine learning according to the embodiment of the present invention combines the natural gas and cogeneration technology with photovoltaic power generation, considers the influence of the distributed photovoltaic power supply and the multi-energy flow coupling characteristics of the power load, the building heating heat load and the natural gas load fluctuation on the safe operation of the campus comprehensive energy system, and calculates the probability energy flow of the campus comprehensive energy system by constructing a refined scene, thereby greatly improving the comprehensive utilization efficiency of energy. And moreover, a weather scene is simulated through seasonal time sequence characteristics of the temperature to generate a photovoltaic output scene, the simulation accuracy of a complex operation scene is improved, the random production simulation efficiency is greatly improved, and a decision suggestion is provided for safe and economic operation of a park comprehensive energy system.

Further, an embodiment of the present invention further provides a computer-readable storage medium, on which a planning program of the park integrated energy system based on statistical machine learning is stored, where the planning program of the park integrated energy system based on statistical machine learning is executed by a processor to implement the planning method of the park integrated energy system based on statistical machine learning of the above embodiment.

According to the computer-readable storage medium provided by the embodiment of the invention, when the stored planning program of the park comprehensive energy system based on statistical machine learning is executed, the natural gas and combined heat and power technology is combined with photovoltaic power generation, the influence of the distributed photovoltaic power supply and the multi-energy flow coupling characteristics of power load, building heating heat load and natural gas load fluctuation on the safe operation of the park comprehensive energy system is considered, and the probability energy flow of the park comprehensive energy system is calculated by constructing a refined scene, so that the comprehensive utilization efficiency of energy can be greatly improved. And moreover, a weather scene is simulated through seasonal time sequence characteristics of the temperature to generate a photovoltaic output scene, the simulation accuracy of a complex operation scene is improved, the random production simulation efficiency is greatly improved, and a decision suggestion is provided for safe and economic operation of a park comprehensive energy system.

As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

In the description of the present invention, it is to be understood that the terms "central," "longitudinal," "lateral," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," "clockwise," "counterclockwise," "axial," "radial," "circumferential," and the like are used in the orientations and positional relationships indicated in the drawings for convenience in describing the invention and to simplify the description, and are not intended to indicate or imply that the referenced devices or elements must have a particular orientation, be constructed and operated in a particular orientation, and are therefore not to be considered limiting of the invention.

Furthermore, the terms "first", "second", and the like used in the embodiments of the present invention are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated in the embodiments. Thus, a feature of an embodiment of the present invention that is defined by the terms "first," "second," etc. may explicitly or implicitly indicate that at least one of the feature is included in the embodiment. In the description of the present invention, the word "plurality" means at least two or two and more, such as two, three, four, etc., unless specifically limited otherwise in the examples.

In the present invention, unless otherwise explicitly stated or limited by the relevant description or limitation, the terms "mounted," "connected," and "fixed" in the embodiments are to be understood in a broad sense, for example, the connection may be a fixed connection, a detachable connection, or an integrated connection, and it may be understood that the connection may also be a mechanical connection, an electrical connection, etc.; of course, they may be directly connected or indirectly connected through intervening media, or they may be interconnected within one another or in an interactive relationship. Those of ordinary skill in the art will understand the specific meaning of the above terms in the present invention according to their specific implementation.

In the present invention, unless otherwise expressly stated or limited, the first feature "on" or "under" the second feature may be directly contacting the first and second features or indirectly contacting the first and second features through an intermediate. Also, a first feature "on," "over," and "above" a second feature may be directly or diagonally above the second feature, or may simply indicate that the first feature is at a higher level than the second feature. A first feature being "under," "below," and "beneath" a second feature may be directly under or obliquely under the first feature, or may simply mean that the first feature is at a lesser elevation than the second feature.

Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention, and that variations, modifications, substitutions and alterations can be made to the above embodiments by those of ordinary skill in the art within the scope of the present invention.