Electric energy distribution optimization method and system based on user demands

Abstract

The invention discloses a demand response-based electric energy distribution optimization method and a demand response-based electric energy distribution optimization system, and relates to the technical field of electric power management. According to the method, based on line loss, converter loss and transformer loss, the out-of-limit behavior of the node is considered, the corresponding objective function is formulated, the power loss condition in the power system is more comprehensively described, the electric energy distribution instruction is assisted to be optimized, the expected effect is achieved, and electric energy is accurately controlled to be distributed to the corresponding user side; a GRU gating unit and an SVR support vector regression model are combined to construct an electric quantity prediction model, the GRU gating unit is utilized to extract deep time features and improve data quality, and the SVR support vector regression model is adopted to perform electric quantity prediction, so that the accuracy of electric quantity prediction can be improved; and the electric energy distribution index is optimized based on the electric quantity predicted value and the objective function, so that the electricity demand of each user side can be met, the electric energy loss is reduced, and the resource waste is prevented.

Description

Technical Field

[0001] The present invention relates to the technical field of power management, and in particular to an optimization method and system for power distribution based on demand response. Background Art

[0002] In traditional power systems, the management of electric energy mainly relies on manual methods, which has many problems. For example, unreasonable distribution of electric energy in the power system may lead to energy waste, affect the user's power experience, and even cause instability in the power system. Therefore, it is an important and urgent task to optimize the distribution of electric energy in the power system to improve energy utilization, reduce energy consumption, and improve the user's power experience.

[0003] Nowadays, researchers use deep neural networks or intelligent algorithms to assist in power management. In the use of deep neural networks, for example, using LSTM long short-term memory networks or SVR support vector regression models to assist in power command optimization can better capture the user's time series, but the required data quality is high. When the data quality is poor, the corresponding accuracy will drop significantly, and a large amount of training data is required. Some studies use machine learning algorithms to solve the problem of power distribution in power systems, but ignore the losses of transformers and converters, cannot dynamically adjust the objective function according to actual conditions, and cannot accurately predict user needs. Summary of the invention

[0004] The object of the present invention is to provide an optimization method and system for electric energy distribution based on demand response, so as to improve the above technical problems.

[0005] In order to achieve the above-mentioned object of the invention, the embodiment of the present invention provides the following technical solutions:

[0006] A method for optimizing electric energy distribution based on user demand, comprising:

[0007] S1. Obtaining the initial power distribution instruction of the power system;

[0008] S2. constructing a corresponding objective function based on the constraints of the power system;

[0009] S3, constructing a power prediction model; obtaining user power data, and inputting it into the power prediction model, and outputting the power consumption of each user end in the next time period, that is, the user demand;

[0010] S4, based on the power consumption of each user terminal in the next time period and the objective function, updating the initial power allocation instruction, and obtaining an updated power allocation instruction;

[0011] S5. Based on the objective function, optimizing the once updated electric energy distribution instruction to obtain an optimized electric energy distribution instruction;

[0012] S6. Operating the power system based on the optimized power distribution instruction to complete the optimization of power distribution.

[0013] Furthermore, the power system includes power generation equipment, a main power grid, a distribution network and power consumption ends; the initial power distribution instructions include power generation scheduling instructions, output control instructions and power distribution instructions.

[0014] Furthermore, the constraints include power balance constraints, power flow safety constraints, reactive power allocation constraints and flow constraints of transmission lines.

[0015] Furthermore, the formula of the objective function is:

[0016] ;

[0017] ;

[0018] ;

[0019] ;

[0020] ;

[0021] in, represents the objective function, , They represent the minimum function and the maximum function respectively. , , They represent the voltage transformation loss, current transformation loss and line loss respectively. represents the penalty function, represents the summation function, , They represent the number of units of power generation equipment and the number of current conversion times of the distribution network. Indicates the power generation equipment Converter loss of each unit, The distribution network The loss corresponding to the secondary conversion is: Indicates the total number of nodes of the power grid corresponding to the power system, Indicates the first Nodes and The conductance between nodes, , They represent the first Nodes and The voltage value of each node, represents the cosine function, Indicates the first Nodes and The voltage phase difference of each node is , Respectively represent the voltage over-limit coefficient and power over-limit coefficient, , They represent the first The maximum and minimum voltages allowed for each node are: Indicates the power generation equipment The output power of each unit, , Respectively represent the first The maximum and minimum output power allowed for each unit, , They represent the transformer loss of power generation equipment and the transformer loss of distribution network respectively. , They represent the no-load loss of the transformer of the power generation equipment and the no-load loss of the transformer of the distribution network respectively. , They represent the transformer load loss of the power generation equipment and the transformer load loss of the distribution network respectively.

[0022] Furthermore, the power prediction model includes a data screening layer, a feature extraction layer and a power prediction layer connected in series; the feature extraction layer adopts a GRU gated recurrent unit; and the power prediction layer adopts an SVR support vector regression model.

[0023] Furthermore, the training process of the power prediction model includes:

[0024] S3-1, obtaining the power data of the training user;

[0025] The training user power data includes historical meteorological data, historical user data and historical time data; the historical meteorological data includes temperature, humidity, wind speed and rainfall; the historical user data includes user power usage time, user power usage behavior, user working time and user rest time; the historical time factors include months and holidays;

[0026] S3-2, input the training user power data into the data screening layer, calculate the corresponding Pearson correlation coefficient, and sort the Pearson correlation coefficients in descending order, and output the training user power data corresponding to the top 15% of the Pearson correlation coefficients;

[0027] S3-3, inputting the training power consumption data outputted by S3-2 into the GRU gated recurrent unit for feature extraction, and outputting corresponding training time features;

[0028] S3-4. Input the training time feature into the SVR support vector regression model, and use the simulated annealing algorithm to adjust the parameters of the SVR support vector regression model to complete the training of the power prediction model.

[0029] Further, the updating of the initial power allocation instruction based on the power consumption in the next time period and the objective function to obtain an updated power allocation instruction includes:

[0030] Determine the remaining amount of electric energy of the energy storage device of the power generation equipment, and summarize the total power consumption corresponding to the power consumption of each user terminal in the next time period;

[0031] Based on the remaining electric energy, the total power consumption and the objective function, the particle swarm optimization algorithm is used to adjust the output and reactive power distribution of each unit of the power generation equipment, that is, to update the power generation scheduling instruction to obtain an updated electric energy distribution instruction.

[0032] Furthermore, the optimizing the once updated electric energy distribution instruction based on the objective function to obtain the optimized electric energy distribution instruction includes:

[0033] S5-1, based on the objective function and the updated generation dispatching instruction, adjusting the tap position of the transformer of the power system, controlling the switch state of the transmission line, adjusting the voltage and frequency of the power grid, the operation mode of the distribution transformer, and controlling the switch state of the distribution line, that is, updating the output control instruction and the distribution instruction, and obtaining the corresponding updated output control instruction and updated distribution instruction;

[0034] S5-2, based on the updated power generation dispatching instructions, the updated output control instructions, and the updated power distribution instructions, using simulation software to simulate the operation process of the power system to obtain corresponding power quality indicators and power generation;

[0035] S5-3. Determine whether the power quality index complies with the provisions of the power industry standards and whether the difference between the power generation and the total power consumption falls within a preset reference range; if so, use the updated power generation scheduling instructions, updated output control instructions, and updated power distribution instructions as optimized power distribution instructions; otherwise, return to S3.

[0036] Provided is an optimization system for electric energy distribution based on user demand, which includes a data acquisition module, an objective function design module, an electric energy consumption prediction module, and an instruction optimization module; the electric energy consumption prediction module includes a data screening submodule, a feature extraction submodule, and an electric energy consumption prediction submodule; wherein:

[0037] A data acquisition module, used to obtain the initial power distribution instructions of the power system and user power data;

[0038] An objective function design module, used for constructing the objective function based on the constraints of the power system;

[0039] A data screening submodule is used to calculate the Pearson correlation coefficient of the user power data, sort the Pearson correlation coefficients in descending order, and output the user power data corresponding to the top 15% of the Pearson correlation coefficients;

[0040] A feature extraction submodule, used for inputting the user power data output by the data screening submodule into the GRU gated recurrent unit, and outputting a time feature;

[0041] The power prediction submodule is used to input the time feature into the SVR support vector regression model to obtain the user demand;

[0042] The instruction optimization module is used to optimize the initial power distribution instruction based on the objective function and the power consumption of each user terminal in the next time period.

[0043] The beneficial effects of the present invention are:

[0044] The present invention is based on line loss, converter loss and transformer loss, takes into account the node's over-limit behavior, formulates a corresponding objective function, more comprehensively describes the power loss situation in the power system, assists in optimizing the distribution of electric energy instructions and achieves the expected effect, and accurately controls the distribution of electric energy to the corresponding user end; combines the GRU gating unit and the SVR support vector regression model to build an electric power prediction model, uses the GRU gating unit to extract deep time features, improves data quality, and adopts the SVR support vector regression model for electric power prediction, which can improve the accuracy of electric power prediction; optimizes the electric power distribution index based on the electric power prediction value and the objective function, can meet the electricity demand of each user end, reduce electric energy loss and prevent the waste of resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0046] Figure 1 is a data flow diagram in an embodiment of the present invention;

[0047] Figure 2 4 is a structural diagram of an optimization system in an embodiment of the present invention. DETAILED DESCRIPTION

[0048] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. The components of the embodiments of the present invention generally described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed invention, but merely represents the selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present invention.

[0049] See also Figure 1 , this embodiment provides an optimization method for electric energy distribution based on user demand, which includes:

[0050] S1. Obtaining the initial power distribution instruction of the power system;

[0051] The power system includes power generation equipment, a main power grid, a distribution network and power consumption ends; the initial power distribution instructions include power generation scheduling instructions, output control instructions and power distribution instructions.

[0052] S2. constructing a corresponding objective function based on the constraints of the power system;

[0053] The constraints include power balance constraints, power flow safety constraints, reactive power allocation constraints and flow constraints of transmission lines.

[0054] The formula corresponding to the power balance constraint is:

[0055] ;

[0056] in, , , They represent the number of generating units, the total number of users, and the total number of transmission lines in the power system. , , Respectively represent The active power output of each unit, Active power demand of each user, The active power loss of the transmission line, , , Respectively represent The reactive power output of each unit, The reactive power demand of each user, Reactive power loss of the transmission line, Represents a sum function.

[0057] The formula corresponding to the reactive power allocation constraint is:

[0058]

[0059] in, , Respectively represent the first The minimum and maximum values ​​of reactive power output of each unit, Indicates the power generation equipment The absolute value of the reactive power output of each unit.

[0060] The formula corresponding to the flow constraint of the transmission line is:

[0061] ;

[0062] in, Indicates the first Nodes and The rated capacity of the transmission line consisting of nodes.

[0063] The objective function formula is:

[0064] ;

[0065] ;

[0066] ;

[0067] ;

[0068] ;

[0069] in, represents the objective function, , They represent the minimum function and the maximum function respectively. , , They represent the voltage transformation loss, current transformation loss and line loss respectively. represents the penalty function, represents the summation function, , They represent the number of units of power generation equipment and the number of current conversion times of the distribution network. Indicates the power generation equipment Converter loss of each unit, The distribution network The loss corresponding to the secondary conversion is: Indicates the total number of nodes of the power grid corresponding to the power system, Indicates the first Nodes and The conductance between nodes, , They represent the first Nodes and The voltage value of each node, represents the cosine function, Indicates the first Nodes and The voltage phase difference of each node is , Respectively represent the voltage over-limit coefficient and power over-limit coefficient, , They represent the first The maximum and minimum voltages allowed for each node are: Indicates the power generation equipment The output power of each unit, , Respectively represent the first The maximum and minimum output power allowed for each unit, , They represent the transformer loss of power generation equipment and the transformer loss of distribution network respectively. , They represent the no-load loss of the transformer of the power generation equipment and the no-load loss of the transformer of the distribution network respectively. , They represent the transformer load loss of the power generation equipment and the transformer load loss of the distribution network respectively.

[0070] The objective function is formulated taking into account various losses, and assists in optimizing the power distribution instructions in the direction of minimizing losses, so as to meet the user needs of each user end with the minimum output of the power generation equipment, reduce the operating burden of the power generation equipment, extend the service life of the generator set, and achieve power generation at the lowest cost.

[0071] S3. Build a power forecasting model; obtain user power data and input it into the power forecasting model, and output the power consumption of each user end in the next time period, that is, the user demand; the length of the next time period is uncertain, and the length of the time period can be determined based on actual needs, which can be one week, one month, one quarter or one year.

[0072] The power prediction model comprises a data screening layer, a feature extraction layer and a power prediction layer connected in series; the feature extraction layer adopts a GRU gated recurrent unit; and the power prediction layer adopts an SVR support vector regression model.

[0073] The training process of the power prediction model includes:

[0074] S3-1, obtaining the power data of the training user;

[0075] The training user power data includes historical meteorological data, historical user data and historical time data; the historical meteorological data includes temperature, humidity, wind speed and rainfall; the historical user data includes user power usage time, user power usage behavior, user working time and user rest time; the historical time factors include months and holidays;

[0076] S3-2, input the training user power data into the data screening layer, calculate the corresponding Pearson correlation coefficient, and sort the Pearson correlation coefficients in descending order, and output the training user power data corresponding to the top 15% of the Pearson correlation coefficients;

[0077] S3-3, inputting the training power consumption data outputted by S3-2 into the GRU gated recurrent unit for feature extraction, and outputting corresponding training time features;

[0078] S3-4, input the training time feature into the SVR support vector regression model, and use the simulated annealing algorithm to adjust the parameters of the SVR support vector regression model to complete the training of the power prediction model. The parameters of the SVR support vector regression model include kernel function, penalty parameter, kernel function coefficient and value.

[0079] The simulated annealing algorithm is a heuristic global optimization method based on simulating the process of natural substances transforming from low-level to high-level at different temperatures. The main idea of ​​the simulated annealing algorithm is to set an initial solution and an objective function, calculate the fitness value of the current solution, and then gradually increase the fitness value of the solution through a certain strategy until the optimal solution is reached or the termination condition is met. The simulated annealing algorithm can handle complex large-scale optimization problems, and can automatically adjust the step size of the algorithm during the search process to avoid falling into the local optimal solution. In addition, the simulated annealing algorithm has a strong global search capability and can find the global optimal solution.

[0080] The specific process of adjusting the parameters of the SVR support vector regression model using the simulated annealing algorithm is as follows:

[0081] S3-4-1. Set the initial temperature, final temperature and number of iterations, randomly select the parameters of the SVR support vector regression model as the initial solution and calculate the corresponding optimization objective function; the optimization objective function can use the MSE mean square error function, MAE mean absolute error function, RMSE root mean square error function, MAPE absolute mean absolute error function; the current number of iterations is 0;

[0082] S3-4-2. According to the initial temperature, randomly perturb the initial solution to generate a new solution as the current solution;

[0083] S3-4-3, calculating the optimization objective function of the current solution;

[0084] S3-4-4, determine whether the optimization objective function of the initial solution is greater than the optimization objective function of the current solution; if so, accept the current solution and enter S3-4-7; otherwise, enter S3-4-5;

[0085] S3-4-5, according to the formula:

[0086] ;

[0087] Get a parameter value ;in, represents a natural constant, represents the initial temperature, , Represent the optimization objective function values ​​of the initial solution and the current solution respectively;

[0088] S3-4-6. Determine parameter value Is it less than ; If yes, accept the current solution; otherwise, reject the current solution; go to S3-4-7; where, Represents a constant randomly generated in the range of 0 to 1;

[0089] S3-4-7, determine whether sufficient search is performed at the initial temperature; if so, increase the current number of iterations by 1 and enter S3-4-8; otherwise, return to S3-4-2;

[0090] S3-4-8, determine whether the current number of iterations reaches the set number of iterations; if so, take the current solution as the optimal solution; otherwise, perform temperature decay on the initial temperature to obtain a new temperature, and return to S3-4-2; in the next round of iterations, the new temperature is used as the initial temperature.

[0091] The data screening layer screens the user's power data and selects data with strong correlation, which can reduce the feature extraction time of the GRU gated recurrent unit, further reduce the size and running time of the power prediction model, and improve data quality; the GRU gated recurrent unit can flexibly capture the long-term dependencies of the data output by the data screening layer, output key feature data, and reduce computational complexity; the support vector regression model has good performance in solving problems such as limited-scale samples and nonlinearity. It is faster than deep learning methods in prediction and has less empirical risk. Using the support vector regression model for power prediction can improve the accuracy of power prediction, and has certain generalization and noise resistance capabilities, further ensuring the quality of power prediction.

[0092] S4, based on the power consumption of each user terminal in the next time period and the objective function, updating the initial power allocation instruction, and obtaining an updated power allocation instruction;

[0093] The updating of the initial electric energy allocation instruction based on the electric energy consumption in the next time period and the objective function to obtain an updated electric energy allocation instruction includes:

[0094] Determine the remaining amount of electric energy of the energy storage device of the power generation equipment, and summarize the total power consumption corresponding to the power consumption of each user terminal in the next time period;

[0095] Based on the remaining electric energy, the total power consumption and the objective function, the particle swarm optimization algorithm is used to adjust the output and reactive power distribution of each unit of the power generation equipment, that is, to update the power generation scheduling instruction to obtain an updated electric energy distribution instruction.

[0096] S5. Based on the objective function, optimizing the once updated electric energy distribution instruction to obtain an optimized electric energy distribution instruction;

[0097] The step of optimizing the once updated electric energy distribution instruction based on the objective function to obtain an optimized electric energy distribution instruction includes:

[0098] S5-1, based on the objective function and the updated generation dispatching instruction, adjusting the tap position of the transformer of the power system, controlling the switch state of the transmission line, adjusting the voltage and frequency of the power grid, the operation mode of the distribution transformer, and controlling the switch state of the distribution line, that is, updating the output control instruction and the distribution instruction, and obtaining the corresponding updated output control instruction and updated distribution instruction;

[0099] S5-2, based on the updated power generation dispatching instructions, the updated output control instructions, and the updated power distribution instructions, use simulation software (DSIM, ETAP) to simulate the operation process of the power system, monitor the state of the power system during operation, and obtain corresponding power quality indicators and power generation;

[0100] S5-3. Determine whether the power quality index complies with the provisions of the power industry standards and whether the difference between the power generation and the total power consumption falls within a preset reference range; if so, use the updated power generation scheduling instructions, updated output control instructions, and updated power distribution instructions as optimized power distribution instructions; otherwise, return to S3.

[0101] S6. Operating the power system based on the optimized power distribution instruction to complete the optimization of power distribution.

[0102] like Figure 2 As shown, an optimization system for electric energy distribution based on user demand includes a data acquisition module, an objective function design module, an electric energy consumption prediction module, and an instruction optimization module; the electric energy consumption prediction module includes a data screening submodule, a feature extraction submodule, and an electric energy prediction submodule; wherein:

[0103] A data acquisition module, used to obtain the initial power distribution instructions of the power system and user power data;

[0104] An objective function design module, used for constructing the objective function based on the constraints of the power system;

[0105] A data screening submodule is used to calculate the Pearson correlation coefficient of the user power data, sort the Pearson correlation coefficients in descending order, and output the user power data corresponding to the top 15% of the Pearson correlation coefficients;

[0106] A feature extraction submodule, used for inputting the user power data output by the data screening submodule into the GRU gated recurrent unit, and outputting a time feature;

[0107] The power prediction submodule is used to input the time feature into the SVR support vector regression model to obtain the user demand;

[0108] The instruction optimization module is used to optimize the initial power distribution instruction based on the objective function and the power consumption of each user terminal in the next time period.

[0109] The present invention is based on line loss, converter loss and transformer loss, takes into account the node's over-limit behavior, formulates a corresponding objective function, more comprehensively describes the power loss situation in the power system, assists in optimizing the distribution of electric energy instructions and achieves the expected effect, and accurately controls the distribution of electric energy to the corresponding user end; combines the GRU gating unit and the SVR support vector regression model to build an electric power prediction model, uses the GRU gating unit to extract deep time features, improves data quality, and adopts the SVR support vector regression model for electric power prediction, which can improve the accuracy of electric power prediction; optimizes the electric power distribution index based on the electric power prediction value and the objective function, can meet the electricity demand of each user end, reduce electric energy loss and prevent the waste of resources.

[0110] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A method for optimizing electric energy distribution based on user demand, characterized in that: include: S1. Obtaining the initial power distribution instruction of the power system; S2. constructing a corresponding objective function based on the constraints of the power system; S3, building a power prediction model; Obtaining user power data and inputting it into the power prediction model, and outputting the power consumption of each user terminal in the next time period, that is, user demand; S4, based on the power consumption of each user terminal in the next time period and the objective function, updating the initial power allocation instruction, and obtaining an updated power allocation instruction; S5. Based on the objective function, optimizing the once updated electric energy distribution instruction to obtain an optimized electric energy distribution instruction; S6. Operating the power system based on the optimized power distribution instruction to complete the optimization of power distribution.

2. A method for optimizing electric energy distribution based on user demand according to claim 1, characterized in that: The power system includes power generation equipment, a main power grid, a distribution network and power consumption ends; the initial power distribution instructions include power generation scheduling instructions, output control instructions and power distribution instructions.

3. An optimization method for electric energy distribution based on user demand according to claim 2, characterized in that: The constraints include power balance constraints, power flow safety constraints, reactive power allocation constraints and flow constraints of transmission lines.

4. A method for optimizing electric energy distribution based on user demand according to claim 3, characterized in that: The formula of the objective function is: ； ； ； ； ； in, represents the objective function, , They represent the minimum function and the maximum function respectively. , , They represent the voltage transformation loss, current transformation loss and line loss respectively. represents the penalty function, represents the summation function, , They represent the number of units of power generation equipment and the number of current conversion times of the distribution network. Indicates the power generation equipment Converter loss of each unit, The distribution network The loss corresponding to the secondary conversion is: Indicates the total number of nodes of the power grid corresponding to the power system, Indicates the first Nodes and The conductance between nodes, , They represent the first Nodes and The voltage value of each node, represents the cosine function, Indicates the first Nodes and The voltage phase difference of each node is , Respectively represent the voltage over-limit coefficient and power over-limit coefficient, , They represent the first The maximum and minimum voltages allowed for each node are: Indicates the power generation equipment The output power of each unit, , Respectively represent the first The maximum and minimum output power allowed for each unit, , They represent the transformer loss of power generation equipment and the transformer loss of distribution network respectively. , They represent the no-load loss of the transformer of the power generation equipment and the no-load loss of the transformer of the distribution network respectively. , They represent the transformer load loss of the power generation equipment and the transformer load loss of the distribution network respectively.

5. A method for optimizing electric energy distribution based on user demand according to claim 1, characterized in that: The power prediction model comprises a data screening layer, a feature extraction layer and a power prediction layer connected in series; the feature extraction layer adopts a GRU gated recurrent unit; and the power prediction layer adopts an SVR support vector regression model.

6. An optimization method for electric energy distribution based on user demand according to claim 2 or 5, characterized in that: The training process of the power prediction model includes: S3-1, obtaining the power data of the training user; The training user power data includes historical meteorological data, historical user data and historical time data; the historical meteorological data includes temperature, humidity, wind speed and rainfall; the historical user data includes user power usage time, user power usage behavior, user working time and user rest time; the historical time factors include months and holidays; S3-2, input the training user power data into the data screening layer, calculate the corresponding Pearson correlation coefficient, and sort the Pearson correlation coefficients in descending order, and output the training user power data corresponding to the top 15% of the Pearson correlation coefficients; S3-3, inputting the training power consumption data outputted by S3-2 into the GRU gated recurrent unit for feature extraction, and outputting corresponding training time features; S3-4. Input the training time feature into the SVR support vector regression model, and use the simulated annealing algorithm to adjust the parameters of the SVR support vector regression model to complete the training of the power prediction model.

7. An optimization method for electric energy distribution based on user demand according to claim 6, characterized in that: The updating of the initial electric energy allocation instruction based on the electric energy consumption in the next time period and the objective function to obtain an updated electric energy allocation instruction includes: Determine the remaining amount of electric energy of the energy storage device of the power generation equipment, and summarize the total power consumption corresponding to the power consumption of each user terminal in the next time period; Based on the remaining electric energy, the total power consumption and the objective function, the particle swarm optimization algorithm is used to adjust the output and reactive power distribution of each unit of the power generation equipment, that is, to update the power generation scheduling instruction to obtain an updated electric energy distribution instruction.

8. A method for optimizing electric energy distribution based on user demand according to claim 7, characterized in that: The step of optimizing the once updated electric energy distribution instruction based on the objective function to obtain an optimized electric energy distribution instruction includes: S5-1, based on the objective function and the updated generation dispatching instruction, adjusting the tap position of the transformer of the power system, controlling the switch state of the transmission line, adjusting the voltage and frequency of the power grid, the operation mode of the distribution transformer, and controlling the switch state of the distribution line, that is, updating the output control instruction and the distribution instruction, and obtaining the corresponding updated output control instruction and updated distribution instruction; S5-2, based on the updated power generation dispatching instructions, the updated output control instructions, and the updated power distribution instructions, using simulation software to simulate the operation process of the power system to obtain corresponding power quality indicators and power generation; S5-3. Determine whether the power quality index complies with the provisions of the power industry standards and whether the difference between the power generation and the total power consumption falls within a preset reference range; if so, use the updated power generation scheduling instructions, updated output control instructions, and updated power distribution instructions as optimized power distribution instructions; otherwise, return to S3.

9. An optimization system for electric energy distribution based on user demand, used to implement an optimization method for electric energy distribution based on user demand as claimed in any one of claims 1 to 8, characterized in that: It includes a data acquisition module, an objective function design module, a power consumption prediction module, and an instruction optimization module; the power consumption prediction module includes a data screening submodule, a feature extraction submodule, and a power consumption prediction submodule; wherein: A data acquisition module, used to obtain the initial power distribution instructions of the power system and user power data; An objective function design module, used for constructing the objective function based on the constraints of the power system; A data screening submodule is used to calculate the Pearson correlation coefficient of the user power data, sort the Pearson correlation coefficients in descending order, and output the user power data corresponding to the top 15% of the Pearson correlation coefficients; A feature extraction submodule, used for inputting the user power data output by the data screening submodule into the GRU gated recurrent unit, and outputting a time feature; The power prediction submodule is used to input the time feature into the SVR support vector regression model to obtain the user demand; The instruction optimization module is used to optimize the initial power distribution instruction based on the objective function and the power consumption of each user terminal in the next time period.

Images