A method and apparatus for configuring energy sources

Abstract

The application discloses an energy configuration method and device, and the method comprises the following steps: acquiring renewable energy data, load demand data, network frame data and to-be-tested energy data; based on the renewable energy data, the load demand data and the network frame data, a power flow optimization configuration model is established in combination with a preset constraint condition; the renewable energy data is divided into training set data and verification set data; the power flow optimization configuration model is trained and verified based on a multi-objective backbone particle swarm optimization algorithm, the training set data and the verification set data; target power flow optimization configuration model is obtained; the to-be-tested energy data is input into the target power flow optimization configuration model; and optimization configuration result data of energy corresponding to the to-be-tested energy data is obtained. The application is favorable for solving the technical problem that the existing energy optimization configuration method cannot improve energy penetration rate while ensuring the safety and stability of a power grid, and improves the energy configuration efficiency.

Description

Technical Field

[0001] This invention relates to the technical field of energy optimization allocation, and more particularly to an energy allocation method and apparatus. Background Technology

[0002] Optimizing the configuration of renewable energy clusters, making full use of the complementary characteristics of renewable energy, and flexibly integrating and connecting them to the grid are important solutions for achieving orderly and efficient access of renewable energy to the distribution network, fully absorbing renewable energy, and meeting the needs of "source-grid" interactive regulation of renewable energy clusters.

[0003] Existing optimization goals for renewable energy clusters are mostly focused on economic efficiency. However, with the increasing penetration rate of distributed renewable energy and the deepening application scenarios, a single economic objective cannot meet the needs of practical applications. Regarding constraints, previous optimization methods for renewable energy clusters only considered the supply and demand balance of electricity, failing to comprehensively ensure that the increase in renewable energy penetration rate is balanced with the safety and stability of the power grid.

[0004] Therefore, in order to improve the efficiency of energy allocation and solve the technical problem that existing energy optimization allocation methods cannot improve energy penetration while ensuring the safety and stability of the power grid, it is urgent to construct an energy allocation method. Summary of the Invention

[0005] This invention provides an energy allocation method and apparatus, which solves the technical problem that existing energy optimization allocation methods cannot improve energy penetration while ensuring the safety and stability of the power grid.

[0006] In a first aspect, the present invention provides a method for configuring energy, comprising:

[0007] Acquire renewable energy data, load demand data, grid data, and energy data to be measured;

[0008] Based on the renewable energy data, the load demand data, and the grid data, and combined with preset constraints, a power flow optimization configuration model is established.

[0009] The renewable energy data is divided into training set data and validation set data;

[0010] Based on the multi-objective backbone particle swarm optimization algorithm, the training set data, and the validation set data, the power flow optimization configuration model is trained and validated to obtain the target power flow optimization configuration model.

[0011] The energy data to be tested is input into the target power flow optimization configuration model to obtain the optimized configuration result data of the energy corresponding to the energy data to be tested.

[0012] Optionally, the power flow optimization configuration model is trained and validated based on the multi-objective backbone particle swarm optimization algorithm, the training set data, and the validation set data to obtain a target power flow optimization configuration model, including:

[0013] The power flow optimization configuration model is trained using the multi-objective backbone particle swarm optimization algorithm and the training set data to obtain the trained power flow optimization configuration model.

[0014] Based on the validation set data, the trained power flow optimization configuration model is validated to obtain the target power flow optimization configuration model.

[0015] Optionally, the multi-objective backbone particle swarm optimization algorithm, combined with the training set data, is used to train the power flow optimization configuration model, resulting in a trained power flow optimization configuration model, including:

[0016] The training set data is input into the power flow optimization configuration model to obtain the corresponding energy prediction configuration result data;

[0017] The training error is determined based on the data labels corresponding to the training set data and the energy prediction configuration result data;

[0018] Based on the training error, the power flow optimization configuration model is adjusted using the multi-objective backbone particle swarm optimization algorithm to obtain the optimal parameters. The optimal parameters are then used to optimize the power flow optimization configuration model, resulting in the trained power flow optimization configuration model.

[0019] Optionally, based on the training error, the power flow optimization configuration model is adjusted using the multi-objective backbone particle swarm optimization algorithm to obtain optimal parameters, and the optimal parameters are then used to optimize the power flow optimization configuration model to obtain the trained power flow optimization configuration model, including:

[0020] Using the multi-objective backbone particle swarm optimization algorithm, Pareto front data are calculated based on the training error and the power flow optimization configuration model.

[0021] Based on the Pareto frontier data, the optimal weight evaluation values ​​for different energy sources are calculated.

[0022] Based on the optimal weight evaluation value, the power flow optimization configuration model is adjusted to obtain the optimal parameters, and the optimal parameters are used to optimize the power flow optimization configuration model to obtain the trained power flow optimization configuration model.

[0023] Optionally, before inputting the training set data into the power flow optimization configuration model to obtain the corresponding energy prediction configuration result data, the method further includes:

[0024] The renewable energy data is set as the objective function, and the parameters of the power flow optimization configuration model are initialized.

[0025] Secondly, the present invention provides an energy configuration device, comprising:

[0026] The acquisition module is used to acquire renewable energy data, load demand data, grid data, and energy data to be measured.

[0027] A module is established to build a power flow optimization configuration model based on the renewable energy data, the load demand data, and the grid data, combined with preset constraints.

[0028] A partitioning module is used to partition the renewable energy data into training set data and validation set data;

[0029] The training module is used to train and validate the power flow optimization configuration model based on the multi-objective backbone particle swarm algorithm, the training set data, and the validation set data, so as to obtain the target power flow optimization configuration model.

[0030] The configuration module is used to input the energy data to be tested into the target power flow optimization configuration model to obtain the optimized configuration result data of the energy corresponding to the energy data to be tested.

[0031] Optionally, the training module includes:

[0032] The training submodule is used to train the power flow optimization configuration model by applying the multi-objective backbone particle swarm optimization algorithm and combining the training set data, so as to obtain the trained power flow optimization configuration model.

[0033] The verification submodule is used to verify the trained power flow optimization configuration model based on the verification set data, and obtain the target power flow optimization configuration model.

[0034] Optionally, the training submodule includes:

[0035] The prediction unit is used to input the training set data into the power flow optimization configuration model to obtain the corresponding energy prediction configuration result data.

[0036] An error unit is used to determine the training error based on the data labels corresponding to the training set data and the energy prediction configuration result data.

[0037] An optimization unit is used to adjust the power flow optimization configuration model based on the training error using the multi-objective backbone particle swarm optimization algorithm to obtain optimal parameters, and then use the optimal parameters to optimize the power flow optimization configuration model to obtain the trained power flow optimization configuration model.

[0038] Optionally, the optimization unit includes:

[0039] The computational subunit is used to calculate the Pareto front data based on the training error and the power flow optimization configuration model using the multi-objective backbone particle swarm algorithm.

[0040] The weighting subunit is used to calculate the optimal weight evaluation value for different energy sources based on the Pareto front data.

[0041] An optimization subunit is used to adjust the power flow optimization configuration model based on the optimal weight evaluation value to obtain the optimal parameters, and then use the optimal parameters to optimize the power flow optimization configuration model to obtain the trained power flow optimization configuration model.

[0042] Optionally, the training submodule further includes:

[0043] The parameter unit is used to set the renewable energy data as the objective function and initialize the parameters of the power flow optimization configuration model.

[0044] As can be seen from the above technical solutions, the present invention has the following advantages: The present invention provides an energy allocation method, which acquires renewable energy data, load demand data, grid data, and energy data to be tested. Based on the renewable energy data, load demand data, and grid data, and combined with preset constraints, a power flow optimization allocation model is established. The renewable energy data is divided into training set data and validation set data. Based on the multi-objective backbone particle swarm optimization algorithm, the training set data, and the validation set data, the power flow optimization allocation model is trained and validated to obtain a target power flow optimization allocation model. The energy data to be tested is input into the target power flow optimization allocation model to obtain the energy optimization allocation result data corresponding to the energy data to be tested. Through this energy allocation method, the technical problem that existing energy optimization allocation methods cannot improve energy penetration rate while ensuring the safety and stability of the power grid is solved, thereby improving the efficiency of energy allocation. Attached Figure Description

[0045] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0046] Figure 1 This is a flowchart illustrating the steps of an embodiment of an energy configuration method according to the present invention;

[0047] Figure 2 This is a flowchart illustrating the steps of a second embodiment of an energy configuration method according to the present invention.

[0048] Figure 3 This is a load curve prediction diagram according to the present invention;

[0049] Figure 4 This is a data diagram showing the optimized configuration result of the present invention;

[0050] Figure 5 This is a data verification diagram of an optimized configuration result according to the present invention;

[0051] Figure 6 This is a structural block diagram of an embodiment of an energy configuration device according to the present invention. Detailed Implementation

[0052] This invention provides an energy allocation method and apparatus to address the technical problem that existing energy optimization allocation methods cannot improve energy penetration while ensuring the safety and stability of the power grid.

[0053] To make the objectives, features, and advantages of this invention more apparent and understandable, the technical solutions of the embodiments of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the embodiments described below are only some embodiments of this invention, and not all embodiments. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this invention.

[0054] Example 1, please refer to Figure 1 , Figure 1 The flowchart of an embodiment of the energy configuration method of the present invention includes:

[0055] Step S101: Obtain renewable energy data, load demand data, grid data, and energy cluster data to be tested;

[0056] It should be noted that renewable energy data includes maximum energy access data, minimum grid loss data, and minimum resource abandonment rate.

[0057] The load demand data includes the typical 24-hour load curves for each node, the typical daily existing photovoltaic power output curves, and the typical daily existing wind turbine power output curves.

[0058] The network data includes line and node data, including the 10kV network structure, transmission line unit impedance, and length parameters.

[0059] In this embodiment of the invention, renewable energy data, load demand data, grid data, and energy cluster data to be tested are acquired.

[0060] Step S102: Based on the renewable energy data, the load demand data, and the grid data, and in conjunction with preset constraints, establish a power flow optimization configuration model;

[0061] It should be noted that the preset constraints are node voltage constraints, power flow constraints, transmission current constraints, and constraints with no power backfeed.

[0062] Step S103: Divide the renewable energy data into training set data and validation set data;

[0063] Step S104: Based on the multi-objective backbone particle swarm optimization algorithm, the training set data, and the validation set data, the power flow optimization configuration model is trained and validated to obtain the target power flow optimization configuration model.

[0064] In this embodiment of the invention, the multi-objective backbone particle swarm optimization algorithm is used in conjunction with the training set data to train the power flow optimization configuration model, thereby obtaining the trained power flow optimization configuration model. Based on the validation set data, the trained power flow optimization configuration model is validated to obtain the target power flow optimization configuration model.

[0065] Step S105: Input the energy data to be tested into the target power flow optimization configuration model to obtain the energy optimization configuration result data corresponding to the energy data to be tested.

[0066] An energy allocation method provided in this embodiment of the invention acquires renewable energy data, load demand data, grid data, and energy data to be tested. Based on the renewable energy data, load demand data, and grid data, and combined with preset constraints, a power flow optimization allocation model is established. The renewable energy data is divided into training set data and validation set data. Based on a multi-objective backbone particle swarm optimization algorithm, the training set data, and the validation set data, the power flow optimization allocation model is trained and validated to obtain a target power flow optimization allocation model. The energy data to be tested is input into the target power flow optimization allocation model to obtain the energy optimization allocation result data corresponding to the energy data to be tested. This energy allocation method solves the technical problem that existing energy optimization allocation methods cannot improve energy penetration while ensuring the safety and stability of the power grid, thus improving the efficiency of energy allocation.

[0067] Example 2, please refer to Figure 2 , Figure 2 The flowchart of an energy configuration method according to the present invention includes:

[0068] Step S201: Obtain renewable energy data, load demand data, grid data, and energy data to be measured;

[0069] In this embodiment of the invention, renewable energy data, load demand data, grid data, and energy data to be tested are acquired. The renewable energy data includes maximum energy access data, minimum grid loss data, and minimum resource abandonment rate. The load demand data includes the typical daily 24-hour load curve of each node, the typical daily existing photovoltaic power output curve, and the typical daily existing wind turbine power output curve. The grid data includes line and node data, including 10kV grid structure, transmission line unit impedance, and length parameters.

[0070] For a detailed implementation, please refer to Figure 3 , Figure 3 This is a load curve prediction diagram according to the present invention, where the horizontal axis A represents time / hour and the vertical axis B represents power / kilowatt. The obtained grid data is shown in the table below:

[0071] node i Node j Branch impedance Node j load 1 2 0.09222+j0.47 PLOAD 2 3 0.4930+j0.2511 PLOAD 3 4 0.3660+j0.1864 0 4 5 0.3811+j0.1941 PLOAD 5 6 0.8190+j0.7070 0 6 7 0.1872+j0.384 PLOAD 7 8 0.7114+j0.2351 0 8 9 1.0300+j0.74 0 9 10 1.0400+j0.74 PLOAD 10 11 0.1966+j0.0650 0 11 12 0.3744+j0.1238 PLOAD 12 13 1.4680+j1.1550 0 13 14 0.5416+j0.7129 PLOAD 14 15 0.5910+j0.5260 0 15 16 0.7463+j0.5450 0 16 17 1.2890+j1.7210 PLOAD 17 18 0.3720+j0.5740 PLOAD

[0072] Step S202: Based on the renewable energy data, the load demand data, and the grid data, and in conjunction with preset constraints, establish a power flow optimization configuration model;

[0073] It should be noted that the preset constraints are node voltage constraints, power flow constraints, transmission current constraints, and constraints with no power backfeed.

[0074] In this embodiment of the invention, a power flow optimization configuration model is established based on the renewable energy data, the load demand data, and the grid data, combined with preset constraints.

[0075] In the specific implementation, the preset constraints include power flow constraints, node voltage constraints, and line transmission current constraints. The specific preset constraints are as follows:

[0076]

[0077] Among them, P i,j With Q i,j These represent the active power and reactive power on line (i, j), respectively, and r i,j With x i,j The resistance and reactance of line (i, j) are respectively, P j With Q j These represent the injected active and reactive power at node j, respectively, u j Let i be the square of the voltage at node j. i,j Let be the square of the current transmitted on line (i, j).

[0078] Step S203: Divide the renewable energy data into training set data and validation set data;

[0079] Step S204: Using the multi-objective backbone particle swarm optimization algorithm and the training set data, the power flow optimization configuration model is trained to obtain the trained power flow optimization configuration model.

[0080] In an optional embodiment, before training the power flow optimization configuration model using a multi-objective backbone particle swarm optimization algorithm in conjunction with the training set data, the method further includes:

[0081] The renewable energy data is set as the objective function, and the parameters of the power flow optimization configuration model are initialized.

[0082] In an optional embodiment, the multi-objective backbone particle swarm optimization algorithm is used, combined with the training set data, to train the power flow optimization configuration model, resulting in a trained power flow optimization configuration model, including:

[0083] The training set data is input into the power flow optimization configuration model to obtain the corresponding energy prediction configuration result data;

[0084] The training error is determined based on the data labels corresponding to the training set data and the energy prediction configuration result data;

[0085] Using the multi-objective backbone particle swarm optimization algorithm, Pareto front data are calculated based on the training error and the power flow optimization configuration model.

[0086] Based on the Pareto frontier data, the optimal weight evaluation values ​​for different energy sources are calculated.

[0087] Based on the optimal weight evaluation value, the power flow optimization configuration model is adjusted to obtain the optimal parameters, and the optimal parameters are used to optimize the power flow optimization configuration model to obtain the trained power flow optimization configuration model.

[0088] In this embodiment of the invention, the renewable energy data is set as the objective function, and the parameters of the power flow optimization configuration model are initialized. The training set data is input into the power flow optimization configuration model to obtain the corresponding energy prediction configuration result data. Based on the data labels corresponding to the training set data and the energy prediction configuration result data, the training error is determined. Using the multi-objective backbone particle swarm optimization algorithm, Pareto front data is calculated based on the training error and the power flow optimization configuration model. Based on the Pareto front data, the optimal weight evaluation value for different energy sources is calculated. Based on the optimal weight evaluation value, the power flow optimization configuration model is adjusted to obtain the optimal parameters. The optimal parameters are then used to optimize the power flow optimization configuration model to obtain the trained power flow optimization configuration model.

[0089] In the specific implementation, the renewable energy data is set as the objective function, and the objective function is specifically as follows:

[0090] f = min{-G} der ,P loss ,DEP};

[0091] Among them, G der P represents the total installed capacity of renewable energy. loss DEP represents the resource abandonment rate, indicating network loss.

[0092] The specific network loss is as follows:

[0093]

[0094] Where N is the set of nodes, T is the simulation duration, and r i,j I represents the resistance of line (i, j). i,j This represents the transmission current of line (i, j).

[0095] The specific resource abandonment rate is as follows:

[0096]

[0097] Among them, P dp P represents the amount of renewable energy power generation that has been abandoned. re This indicates the maximum power generation capacity of renewable energy sources.

[0098] Please see Figure 4 , Figure 4 This is a data graph showing the optimized configuration results of the present invention, where the horizontal axis C represents nodes and the vertical axis D represents the configured renewable energy capacity / kW. The model is used for solving the problem, and the optimization objective priority is: full renewable energy consumption (no resource abandonment) > maximum renewable energy access > minimum network loss. The resulting optimized configuration is as follows: Figure 4As shown, the renewable energy units configured at this time have no resource abandonment, and the access scale has reached the maximum access scale of the cluster, and network loss has been minimized.

[0099] Step S205: Based on the validation set data, validate the trained power flow optimization configuration model to obtain the target power flow optimization configuration model;

[0100] In this embodiment of the invention, the trained power flow optimization configuration model is verified based on the validation set data to obtain the target power flow optimization configuration model.

[0101] For a detailed implementation, please refer to Figure 5 , Figure 5 This is a data verification diagram of the optimized configuration result of the present invention, where the horizontal axis A represents time / hour and the vertical axis E represents the voltage per unit value. The optimized configuration result is input into the trained power flow optimization configuration model for verification, and the voltage of each node can be observed as follows: Figure 5 As shown, within the allowable fluctuation range, the target power flow optimization configuration model is thus obtained.

[0102] Step S206: Input the energy data to be tested into the target power flow optimization configuration model to obtain the energy optimization configuration result data corresponding to the energy data to be tested;

[0103] In this embodiment of the invention, the energy data to be tested is input into the target power flow optimization configuration model to obtain the optimized configuration result data of the energy corresponding to the energy data to be tested, and the configuration priority of the energy corresponding to the energy data to be tested is determined.

[0104] An energy allocation method provided in this embodiment of the invention acquires renewable energy data, load demand data, grid data, and energy data to be tested. Based on the renewable energy data, load demand data, and grid data, and combined with preset constraints, a power flow optimization allocation model is established. The renewable energy data is divided into training set data and validation set data. Based on a multi-objective backbone particle swarm optimization algorithm, the training set data, and the validation set data, the power flow optimization allocation model is trained and validated to obtain a target power flow optimization allocation model. The energy data to be tested is input into the target power flow optimization allocation model to obtain the energy optimization allocation result data corresponding to the energy data to be tested. This energy allocation method solves the technical problem that existing energy optimization allocation methods cannot improve energy penetration while ensuring the safety and stability of the power grid, thus improving the efficiency of energy allocation.

[0105] Please see Figure 6 , Figure 6 A structural block diagram of an embodiment of an energy configuration device according to the present invention includes:

[0106] The acquisition module 601 is used to acquire renewable energy data, load demand data, grid data, and energy data to be measured.

[0107] Module 602 is used to establish a power flow optimization configuration model based on the renewable energy data, the load demand data, and the grid data, combined with preset constraints.

[0108] The partitioning module 603 is used to partition the renewable energy data into training set data and validation set data;

[0109] Training module 604 is used to train and validate the power flow optimization configuration model based on the multi-objective backbone particle swarm algorithm, the training set data and the validation set data, to obtain the target power flow optimization configuration model.

[0110] The configuration module 605 is used to input the energy data to be tested into the target power flow optimization configuration model to obtain the optimized configuration result data of the energy corresponding to the energy data to be tested.

[0111] In an optional embodiment, the training module 604 includes:

[0112] The training submodule is used to train the power flow optimization configuration model by applying the multi-objective backbone particle swarm optimization algorithm and combining the training set data, so as to obtain the trained power flow optimization configuration model.

[0113] The verification submodule is used to verify the trained power flow optimization configuration model based on the verification set data, and obtain the target power flow optimization configuration model.

[0114] In an optional embodiment, the training submodule includes:

[0115] The prediction unit is used to input the training set data into the power flow optimization configuration model to obtain the corresponding energy prediction configuration result data.

[0116] An error unit is used to determine the training error based on the data labels corresponding to the training set data and the energy prediction configuration result data.

[0117] An optimization unit is used to adjust the power flow optimization configuration model based on the training error using the multi-objective backbone particle swarm optimization algorithm to obtain optimal parameters, and then use the optimal parameters to optimize the power flow optimization configuration model to obtain the trained power flow optimization configuration model.

[0118] In an optional embodiment, the optimization unit includes:

[0119] The computational subunit is used to calculate the Pareto front data based on the training error and the power flow optimization configuration model using the multi-objective backbone particle swarm algorithm.

[0120] The weighting subunit is used to calculate the optimal weight evaluation value for different energy sources based on the Pareto front data.

[0121] An optimization subunit is used to adjust the power flow optimization configuration model based on the optimal weight evaluation value to obtain the optimal parameters, and then use the optimal parameters to optimize the power flow optimization configuration model to obtain the trained power flow optimization configuration model.

[0122] In an optional embodiment, the training submodule further includes:

[0123] The parameter unit is used to set the renewable energy data as the objective function and initialize the parameters of the power flow optimization configuration model.

[0124] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0125] In the several embodiments provided in this application, it should be understood that the methods and apparatus disclosed in this invention can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces, or indirect coupling or communication connection between devices or units, and may be electrical, mechanical, or other forms.

[0126] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0127] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0128] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a readable storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned readable storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0129] The above-described embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for configuring energy, characterized in that, include: Acquire renewable energy data, load demand data, grid data, and energy data to be measured; Based on the renewable energy data, the load demand data, and the grid data, and combined with preset constraints, a power flow optimization configuration model is established. The renewable energy data is divided into training set data and validation set data; Based on the multi-objective backbone particle swarm optimization algorithm, the training set data, and the validation set data, the power flow optimization configuration model is trained and validated to obtain the target power flow optimization configuration model, including: The renewable energy data is set as the objective function, and the parameters of the power flow optimization configuration model are initialized; wherein, the objective function is specifically: ； in, This indicates the total installed capacity of renewable energy. Indicates network loss. N is the set of nodes, and T is the simulation duration. This represents the resistance of the line (i, j). The transmission current of line (i, j) is represented by DEP, which represents the resource abandonment rate. , This indicates the amount of renewable energy power generation that has been abandoned. Indicates the maximum power generation capacity of renewable energy sources; The training set data is input into the power flow optimization configuration model to obtain the corresponding energy prediction configuration result data; the training error is determined based on the data labels corresponding to the training set data and the energy prediction configuration result data. Using the multi-objective backbone particle swarm optimization algorithm, Pareto front data are calculated based on the training error and the power flow optimization configuration model. Based on the Pareto frontier data, the optimal weight evaluation values ​​for different energy sources are calculated. Based on the optimal weight evaluation value, the power flow optimization configuration model is adjusted to obtain the optimal parameters, and the optimal parameters are used to optimize the power flow optimization configuration model to obtain the trained power flow optimization configuration model. Based on the validation set data, the trained power flow optimization configuration model is validated to obtain the target power flow optimization configuration model. The energy data to be tested is input into the target power flow optimization configuration model to obtain the optimized configuration result data of the energy corresponding to the energy data to be tested.

2. An energy distribution device, characterized in that, include: The acquisition module is used to acquire renewable energy data, load demand data, grid data, and energy data to be measured. A module is established to build a power flow optimization configuration model based on the renewable energy data, the load demand data, and the grid data, combined with preset constraints. A partitioning module is used to partition the renewable energy data into training set data and validation set data; The training module is used to train and validate the power flow optimization configuration model based on the multi-objective backbone particle swarm optimization algorithm, the training set data, and the validation set data, to obtain the target power flow optimization configuration model, including: The renewable energy data is set as the objective function, and the parameters of the power flow optimization configuration model are initialized; wherein, the objective function is specifically: ； in, This indicates the total installed capacity of renewable energy. Indicates network loss. N is the set of nodes, and T is the simulation duration. This represents the resistance of the line (i, j). The transmission current of line (i, j) is represented by DEP, which represents the resource abandonment rate. , This indicates the amount of renewable energy power generation that has been abandoned. Indicates the maximum power generation capacity of renewable energy sources; The training set data is input into the power flow optimization configuration model to obtain the corresponding energy prediction configuration result data; the training error is determined based on the data labels corresponding to the training set data and the energy prediction configuration result data. Using the multi-objective backbone particle swarm optimization algorithm, Pareto front data are calculated based on the training error and the power flow optimization configuration model. Based on the Pareto frontier data, the optimal weight evaluation values ​​for different energy sources are calculated. Based on the optimal weight evaluation value, the power flow optimization configuration model is adjusted to obtain the optimal parameters, and the optimal parameters are used to optimize the power flow optimization configuration model to obtain the trained power flow optimization configuration model. Based on the validation set data, the trained power flow optimization configuration model is validated to obtain the target power flow optimization configuration model. The configuration module is used to input the energy data to be tested into the target power flow optimization configuration model to obtain the optimized configuration result data of the energy corresponding to the energy data to be tested.

Images