Intelligent scheduling method and system for cross-regional load migration of virtual power plants

Abstract

The present invention discloses a method and system for intelligent scheduling of cross-regional load migration of a virtual power plant, which relates to the technical field of load scheduling. The method comprises: collecting power generation cost parameter data of power generation nodes, line capacity data, network loss coefficient data, PTDF matrix data, photovoltaic impact factor data, wind power impact factor data, photovoltaic power generation data, wind power generation data, conventional power generation data and node load data; the method and system for intelligent scheduling of cross-regional load migration of a virtual power plant predicts the power generation power and load demand of each power generation node within a set time period in the future, thereby scheduling the load according to the predicted power generation power and load demand to meet the electricity demand, and calculating the change in the predicted load demand of each node to determine whether the load needs to be re-scheduled, thereby reducing the power generation cost under the current load demand.

Description

Technical Field

[0001] The present invention relates to the technical field of load scheduling, and in particular to a method and system for intelligent scheduling of cross-regional load migration in a virtual power plant. Background Art

[0002] Virtual power plants generally use technologies such as the Internet of Things, big data, and artificial intelligence to aggregate fragmented resources such as distributed photovoltaics, wind power, energy storage batteries, electric vehicles, and controllable loads to facilitate unified coordination, participate in power market transactions and power grid scheduling, and achieve flexible regulation and optimized energy allocation. The prior art, published as CN119005647A, discloses a scheduling method and system for power grid loads. Its specific solution is as follows: using a first impact curve of the passenger flow of each electricity consumer on the response delay time of electricity demand and a second impact curve of passenger flow on the migration time of electricity peak, the electricity demand of each electricity consumer in a first future time period is predicted, thereby determining a grid load estimation curve for the first power grid in the first future time period; then, based on the regulation requirements of the first power grid's allowable adjustable load, the grid load estimation curve for the first power grid in the first future time period is optimized to obtain a power load scheduling plan for the first power grid in the first future time period; and in the first future time period, based on the power load scheduling plan for the first power grid in the first future time period, load scheduling is performed on the first power grid.

[0003] The generator sets and loads in the virtual power plant may be distributed at different nodes, resulting in different costs for the generator sets at different nodes to supply power to the loads at different nodes. The existing technology generally only considers the balance between the total power supply power and the load power to schedule the load, and does not consider the situation where the total load does not change significantly, but the loads between different nodes change significantly. This means that power supply according to the original scheduling plan may lead to increased power supply costs. Summary of the Invention

[0004] The purpose of the present invention is to provide a method and system for intelligent scheduling of cross-regional load migration of virtual power plants to address the above-mentioned deficiencies in the prior art.

[0005] In order to achieve the above objectives, the present invention provides the following technical solution: a method for intelligent scheduling of cross-regional load migration of virtual power plants, comprising the following steps:

[0006] S1. Collect power generation cost parameter data, line capacity data, network loss coefficient data, PTDF matrix data, photovoltaic impact factor data, wind power impact factor data, photovoltaic power generation data, wind power generation data, conventional power generation data, and node load data of power generation nodes;

[0007] S2. updating the pre-trained photovoltaic power generation prediction model and the wind power generation prediction model based on the photovoltaic impact factor data, the wind power impact factor data, the photovoltaic power generation data, and the wind power generation data;

[0008] S3. Inputting the photovoltaic impact factor data into a pre-trained photovoltaic power generation prediction model to generate photovoltaic power generation prediction data, and inputting the wind power impact factor data into a pre-trained wind power generation prediction model to generate wind power generation prediction data;

[0009] S4. Inputting the node load data into a pre-trained load forecasting model to generate node load forecast data;

[0010] S5. Calculate and process the variation of the node load prediction data to generate node load variation prediction data;

[0011] S6. Perform minimum power supply cost power generation node power generation analysis based on the power generation node power generation cost parameter data, line capacity data, network loss coefficient data, PTDF matrix data, photovoltaic power generation power prediction data, wind power generation power prediction data, and node load change prediction data to generate minimum power supply cost power generation node power generation analysis data;

[0012] S7. Perform load dispatching of the virtual power plant based on the power generation analysis data of the minimum power supply cost power generation node.

[0013] Furthermore, the S1 includes the following steps:

[0014] S11. Collect power generation cost parameter data of power generation nodes and generate power generation cost parameter data set of power generation nodes , , represents the power generation cost parameter data of the w-th power generation node, Represents the maximum number of power generation nodes. Cost parameters for power generation nodes are obtained from government and authoritative reports, academic research, industry reports, and enterprise data. Cost parameters can be composed of capital costs (CAPEX): including power plant construction, equipment procurement, and land costs; operating and maintenance costs (OPEX): including daily operations, labor, and insurance; fuel costs: including the prices of fuels such as coal, natural gas, and uranium; financing costs: including loan interest rates and depreciation cycles; and environmental costs: including carbon emissions taxes and pollution treatment costs.

[0015] S12. Collect line capacity data and generate line capacity data set , , represents the capacity data of the qth line, Indicates the maximum number of lines; line capacity data can be obtained through industry standards. Line capacity data is used to constrain line flow when performing minimum power supply cost analysis to ensure that line flow does not exceed capacity;

[0016] S13. Collect network loss coefficient data and generate a network loss coefficient data set ,in represents the network loss coefficient between nodes w and j, , reflecting the influence of line parameters on network loss, It represents the single-machine network loss coefficient of node w, which represents the loss caused by the output of this unit alone. is a constant loss term that is independent of the unit output (such as fixed network loss);

[0017] S14. Collect Power Transfer Distribution Factors (PTDF) and generate PTDF matrix data C. The PTDF matrix data can be calculated based on network topology (i.e., the connection between nodes and lines); line parameters (i.e., resistance RR, reactance XX, and susceptance BB (used to construct an admittance matrix); and reference nodes (Slack Bus): typically, a balancing node is selected as a power reference point.

[0018] S15. Collect photovoltaic impact factor data , Wind power impact factor data , Photovoltaic power generation data , wind power generation data , conventional power generation data ;

[0019] S16. Collect node load data and generate node load data set , , represents the load data of the u-th node, Indicates the maximum number of nodes.

[0020] Furthermore, the S2 includes the following steps:

[0021] S21, judging the collected photovoltaic impact factor data and photovoltaic power generation data Whether the set quantity is reached, if so, based on the photovoltaic impact factor data and photovoltaic power generation data Update the pre-trained photovoltaic power generation prediction model and collect the photovoltaic impact factor data and photovoltaic power generation data Conduct a recount;

[0022] 22. Determine the collected wind power impact factor data , and wind power generation data Whether the set number is reached, if so, based on the wind power impact factor data , and wind power generation data Update the pre-trained wind power generation prediction model and collect the wind power influencing factor data , and wind power generation data Re-counting is performed. For example, the photovoltaic impact factor data and photovoltaic power generation data are collected as update sample data 1, and the wind power impact factor data and wind power generation data are collected as update sample data 2. When the update sample data 1 / update sample data 2 reaches the corresponding set sample data quantity, the pre-trained photovoltaic power generation prediction model / wind power generation prediction model is updated using the update sample data 1 / update sample data 2. Photovoltaic impact factor data during training update and wind power impact factor data As input to each model, photovoltaic power generation data and wind power generation data The output of each model. Pre-trained PV and wind power prediction models can use deep learning models, such as LSTM (Long Short-Term Memory) models. These models are used to output the average PV and wind power generation over a set forecast period based on the input PV and wind power influencing factors.

[0023] Furthermore, the S3 includes the following steps:

[0024] S31, the photovoltaic impact factor data Input the pre-trained photovoltaic power generation prediction model to obtain the predicted photovoltaic power generation prediction data ;

[0025] S32, the wind power impact factor data Input the pre-trained wind power generation prediction model to generate wind power generation prediction data .

[0026] Furthermore, the S4 includes the following steps:

[0027] S41, the node load data Input the pre-trained load forecasting model to obtain node load forecast data , generate node load forecast data set , in which the collected node load data can be Count and use these node load data when the count reaches the set number The pre-trained load forecasting model is trained and updated. The LSTM model can be used for training and updating. The pre-trained load forecasting model predicts the average node load data within the set prediction period in the future.

[0028] Furthermore, the S5 includes the following steps:

[0029] S51, the node load prediction data set Node load forecast data for all nodes in Perform change calculation to obtain node load change prediction data , generate node load change prediction data set .

[0030] Furthermore, the S6 includes the following steps:

[0031] S61. Construct a formula for calculating the power generation of each power generation node at the minimum cost while meeting the power demand:

[0032] (1);

[0033] in, 、 、 are the power generation cost parameter data of the power generation node w, namely =( , , ), When the corresponding node is a photovoltaic power generation node Adopt corresponding , The corresponding node is the node of wind power generation Adopt corresponding , When the corresponding node is a conventional power generation node Use the corresponding (It is assumed that the power generated by conventional power generation will not fluctuate significantly);

[0034] S62. Construct the constraint condition. The formula is as follows:

[0035] ;

[0036] ;

[0037] ;

[0038] in, is the grid loss power prediction data, 、 is the minimum and maximum power generation of the wth power generation node. If the power generation node is a photovoltaic power generation node or a wind power generation node, equal , is the maximum capacity of the qth line;

[0039] Based on photovoltaic power generation power forecast data , wind power generation power forecast data , conventional power generation data , node load forecast data set And the network loss coefficient data set B, the network loss power is calculated to obtain the network loss power prediction data , the calculation formula is as follows:

[0040] ;

[0041] S63. Solve formula (1) to obtain the power generation of each power generation node w, and generate the power generation analysis data of the power generation node with the minimum power supply cost , including the following steps:

[0042] S631. Initialize the population and randomly generate M node power generation search cuckoos. Each cuckoo represents a potential minimum power supply cost power generation node power generation analysis data. ;

[0043] S632. Based on formula (1) and the constraints, a fitness function is constructed to calculate the fitness of the cuckoo search for each node's power generation:

[0044] ;

[0045] in, 、 is the penalty coefficient;

[0046] S633. Each cuckoo reaches its new position through Lévy flight. The cuckoo position update formula is as follows:

[0047] ;

[0048] in, represents the cuckoo search for the power generated by the i-th node, t represents the current number of iterations, represents the step length, Levy random number ;

[0049] S634, based on the probability of discovery Discard the node power generation search cuckoo with non-optimal fitness and generate a new node power generation search cuckoo instead. The formula is as follows:

[0050] ;

[0051] in, Represents the node power generation search cuckoo of non-optimal fitness, The node power generation power search cuckoo that represents the best fitness;

[0052] S635, resetting the node power generation power search cuckoo that exceeds the boundary to the nearest boundary;

[0053] S636: Determine whether the maximum number of iterations has been reached. If so, output the power generation power of the node with the best fitness and search for the power generation power analysis data of the minimum power supply cost power generation node corresponding to the cuckoo. , if not, return to S632.

[0054] Furthermore, the step S7 includes the following steps:

[0055] S71: Determine the node load change prediction data set Is there any node load change prediction data in the The absolute value of is greater than the set node load change threshold;

[0056] S72, if not, then analyze the power generation data based on the minimum power supply cost power generation node Perform scheduling operations on each power generation node;

[0057] S73. If yes, return to S4.

[0058] The intelligent dispatching system for cross-regional load migration of virtual power plants includes a data acquisition module, an interface, a storage device, a processor, and a control module.

[0059] The data acquisition module is used to collect data required by the cross-regional load migration intelligent scheduling method of the virtual power plant provided by the present invention, including power generation cost parameter data of power generation nodes, line capacity data, network loss coefficient data, PTDF matrix data, photovoltaic influence factor data, wind power influence factor data, photovoltaic power generation data, wind power generation data, conventional power generation data, node load data, set sample data quantity, set prediction time, set node load change threshold, etc.;

[0060] The data acquisition module is connected to the storage via an interface and is used to import the collected data into the system;

[0061] The memory is used to store collected data and computer programs;

[0062] The processor is used to execute a computer program to implement the virtual power plant cross-regional load migration intelligent scheduling method provided by the present invention, and generate power generation analysis data of the minimum power supply cost power generation node;

[0063] The control module is used to receive the power generation analysis data of the minimum power supply cost power generation node, and dispatch each power generation node based on the power generation analysis data of the minimum power supply cost power generation node.

[0064] 1. Compared with the existing technology, the intelligent scheduling method and system for cross-regional load migration of virtual power plants provided by the present invention predicts the power generation power and load demand of each power generation node within a set time period in the future, so that the load can be scheduled according to the predicted power generation power and load demand to meet the electricity demand.

[0065] 2. Compared with the existing technology, the intelligent scheduling method and system for cross-regional load migration of virtual power plants provided by the present invention determines whether the load needs to be re-scheduled by calculating the change in the predicted load demand of each node, thereby reducing the power generation cost under the current load demand and avoiding the problem that the total load does not change significantly, but the load between different nodes changes significantly, resulting in an increase in power supply costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments described in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0067] Figure 1 A diagram of method steps provided by an embodiment of the present invention;

[0068] Figure 2 This is a system structure block diagram provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0069] In order to enable those skilled in the art to better understand the technical solution of the present invention, the present invention will be further described in detail below with reference to the accompanying drawings.

[0070] Example embodiments will be described more fully hereinafter with reference to the accompanying drawings, but the example embodiments may be embodied in different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete and will fully convey the scope of this disclosure to those skilled in the art.

[0071] In the absence of conflict, the various embodiments of the present disclosure and the various features therein may be combined with each other.

[0072] As used herein, the term "and / or" includes any and all combinations of one or more of the associated listed items.

[0073] The terms used herein are used only to describe specific embodiments and are not intended to limit the present disclosure. As used herein, the singular forms "a," "an," and "the" are also intended to include the plural forms, unless the context clearly indicates otherwise. It will also be understood that when the terms "comprising" and / or "made of" are used in this specification, the presence of the features, wholes, steps, operations, elements, and / or components is specified, but the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or groups thereof is not excluded.

[0074] The embodiments described herein may be described with reference to plan views and / or cross-sectional views, with the aid of idealized schematic diagrams of the present disclosure. Thus, the example illustrations may be modified based on manufacturing techniques and / or tolerances. Therefore, the embodiments are not limited to the embodiments shown in the accompanying drawings, but include modifications of the configurations formed based on the manufacturing process. Therefore, the regions illustrated in the accompanying drawings are schematic in nature, and the shapes of the regions shown in the drawings illustrate specific shapes of the regions of the elements, but are not intended to be limiting.

[0075] See also Figure 1 ,The intelligent scheduling method for cross-regional load migration of a virtual power plant includes the following steps:

[0076] S1. Collecting power generation cost parameter data, line capacity data, network loss coefficient data, PTDF matrix data, photovoltaic impact factor data, wind power impact factor data, photovoltaic power generation data, wind power generation data, conventional power generation data, and node load data of power generation nodes, including the following steps:

[0077] S11. Collect power generation cost parameter data of power generation nodes and generate power generation cost parameter data set of power generation nodes , , represents the power generation cost parameter data of the w-th power generation node, Represents the maximum number of power generation nodes. Cost parameters for power generation nodes are obtained from government and authoritative reports, academic research, industry reports, and enterprise data. Cost parameters can be composed of capital costs (CAPEX): including power plant construction, equipment procurement, and land costs; operating and maintenance costs (OPEX): including daily operations, labor, and insurance; fuel costs: including the prices of fuels such as coal, natural gas, and uranium; financing costs: including loan interest rates and depreciation cycles; and environmental costs: including carbon emissions taxes and pollution treatment costs.

[0078] S12. Collect line capacity data and generate line capacity data set , , represents the capacity data of the qth line, Indicates the maximum number of lines; line capacity data can be obtained through industry standards. Line capacity data is used to constrain line flow when performing minimum power supply cost analysis to ensure that line flow does not exceed capacity;

[0079] S13. Collect network loss coefficient data and generate a network loss coefficient data set ,in represents the network loss coefficient between nodes w and j, , reflecting the influence of line parameters on network loss, It represents the single-machine network loss coefficient of node w, which represents the loss caused by the output of this unit alone. is a constant loss term that is independent of the unit output (such as fixed network loss);

[0080] S14. Collect Power Transfer Distribution Factors (PTDF) and generate PTDF matrix data C. The PTDF matrix data can be calculated based on network topology (i.e., the connection between nodes and lines); line parameters (i.e., resistance RR, reactance XX, and susceptance BB (used to construct an admittance matrix); and reference nodes (Slack Bus): typically, a balancing node is selected as a power reference point.

[0081] S15. Collect photovoltaic impact factor data , Wind power impact factor data , Photovoltaic power generation data , wind power generation data , conventional power generation data ;

[0082] S16. Collect node load data and generate node load data set , , represents the load data of the u-th node, Indicates the maximum number of nodes.

[0083] S2. Updating the pre-trained photovoltaic power generation prediction model and wind power generation prediction model based on the photovoltaic impact factor data, the wind power impact factor data, the photovoltaic power generation data, and the wind power generation data, including the following steps:

[0084] S21. Determine the collected photovoltaic impact factor data and photovoltaic power generation data Whether the set quantity is reached, if so, based on the photovoltaic impact factor data and photovoltaic power generation data Update the pre-trained photovoltaic power generation prediction model and collect the photovoltaic impact factor data and photovoltaic power generation data Conduct a recount;

[0085] 22. Determine the collected wind power impact factor data , and wind power generation data Whether the set quantity is reached, if so, based on the wind power impact factor data , and wind power generation data Update the pre-trained wind power generation prediction model and collect wind power influencing factor data , and wind power generation data Re-count. For example, if photovoltaic impact factor data and photovoltaic power generation data are collected as update sample data 1, wind power impact factor data and wind power generation data are collected as update sample data 2, and each time the update sample data 1 / update sample data 2 reaches the corresponding set sample data quantity, the pre-trained photovoltaic power generation prediction model / wind power generation prediction model is updated using the update sample data 1 / update sample data 2. Photovoltaic impact factor data during training update and wind power impact factor data As input to each model, photovoltaic power generation data and wind power generation data The output of each model. Pre-trained PV and wind power prediction models can use deep learning models, such as LSTM (Long Short-Term Memory) models. These models are used to output the average PV and wind power generation over a set forecast period based on the input PV and wind power influencing factors.

[0086] S3. Inputting the photovoltaic impact factor data into a pre-trained photovoltaic power generation prediction model to generate photovoltaic power generation prediction data, and inputting the wind power impact factor data into a pre-trained wind power generation prediction model to generate wind power generation prediction data, including the following steps:

[0087] S31. Photovoltaic impact factor data Input the pre-trained photovoltaic power generation prediction model to obtain the predicted photovoltaic power generation prediction data ;

[0088] S32. Wind power impact factor data Input the pre-trained wind power generation prediction model to generate wind power generation prediction data .

[0089] S4. Inputting the node load data into the pre-trained load forecasting model to generate node load forecast data includes the following steps:

[0090] S41, node load data Input the pre-trained load forecasting model to obtain node load forecast data , generate node load forecast data set , in which the collected node load data can be Count and use these node load data when the count reaches the set number The pre-trained load forecasting model is trained and updated. The LSTM model can be used for training and updating. The pre-trained load forecasting model predicts the average node load data within the set prediction period in the future.

[0091] S5. Calculating and processing the change amount of the node load prediction data to generate node load change prediction data, including the following steps:

[0092] S51. Node load prediction data collection Node load forecast data for all nodes in Perform change calculation to obtain node load change prediction data , generate node load change prediction data set .

[0093] S6. Based on the power generation cost parameter data of the power generation node, the line capacity data, the network loss coefficient data, the PTDF matrix data, the photovoltaic power generation power prediction data, the wind power generation power prediction data, and the node load change prediction data, the power generation power of the power generation node with the minimum power supply cost is analyzed to generate the power generation power analysis data of the power generation node with the minimum power supply cost, including the following steps:

[0094] S61. Construct a formula for calculating the power generation of each power generation node at the minimum cost while meeting the power demand:

[0095] (1);

[0096] in, 、 、 are the power generation cost parameter data of the power generation node w, namely =( , , ), When the corresponding node is a photovoltaic power generation node Adopt corresponding , The corresponding node is the node of wind power generation Adopt corresponding , When the corresponding node is a conventional power generation node Use the corresponding (It is assumed that the power generated by conventional power generation will not fluctuate significantly);

[0097] S62. Construct the constraint condition. The formula is as follows:

[0098] ;

[0099] ;

[0100] ;

[0101] in, is the grid loss power prediction data, 、 is the minimum and maximum power generation of the wth power generation node. If the power generation node is a photovoltaic power generation node or a wind power generation node, equal , is the maximum capacity of the qth line;

[0102] Based on photovoltaic power generation power forecast data , wind power generation power forecast data , conventional power generation data , node load forecast data set And the network loss coefficient data set B, the network loss power is calculated to obtain the network loss power prediction data , the calculation formula is as follows:

[0103] ;

[0104] S63. Solve formula (1) to obtain the power generation of each power generation node w, and generate the power generation analysis data of the power generation node with the minimum power supply cost , including the following steps:

[0105] S631. Initialize the population and randomly generate M node power generation search cuckoos. Each cuckoo represents a potential minimum power supply cost power generation node power generation analysis data. ;

[0106] S632. Based on formula (1) and the constraints, a fitness function is constructed to calculate the fitness of the cuckoo search for each node's power generation:

[0107] ;

[0108] in, 、 is the penalty coefficient;

[0109] S633. Each cuckoo reaches its new position through Lévy flight. The cuckoo position update formula is as follows:

[0110] ;

[0111] in, represents the cuckoo search for the power generated by the i-th node, t represents the current number of iterations, represents the step length, Levy random number ;

[0112] S634, based on the probability of discovery Discard the node power generation search cuckoo with non-optimal fitness and generate a new node power generation search cuckoo instead. The formula is as follows:

[0113] ;

[0114] in, Represents the node power generation search cuckoo of non-optimal fitness, The node power generation power search cuckoo that represents the best fitness;

[0115] S635, resetting the node power generation power search cuckoo that exceeds the boundary to the nearest boundary;

[0116] S636: Determine whether the maximum number of iterations has been reached. If so, output the power generation power of the node with the best fitness and search for the power generation power analysis data of the minimum power supply cost power generation node corresponding to the cuckoo. , if not, return to S632.

[0117] S7. Performing load dispatching of the virtual power plant based on the power generation analysis data of the power generation node with the minimum power supply cost, including the following steps:

[0118] S71. Determine the node load change prediction data set Is there any node load change prediction data in the The absolute value of is greater than the set node load change threshold;

[0119] S72, if not, then analyze the power generation data based on the minimum power supply cost power generation node Perform scheduling operations on each power generation node;

[0120] S73. If yes, return to S4.

[0121] Please see the attached Figure 2, a virtual power plant cross-regional load migration intelligent scheduling system is used to execute the virtual power plant cross-regional load migration intelligent scheduling method provided by the present invention, including a data acquisition module, an interface, a storage, a processor, and a control module.

[0122] The data acquisition module is used to collect data required by the cross-regional load migration intelligent scheduling method of the virtual power plant provided by the present invention, including power generation cost parameter data of power generation nodes, line capacity data, network loss coefficient data, PTDF matrix data, photovoltaic influence factor data, wind power influence factor data, photovoltaic power generation data, wind power generation data, conventional power generation data, node load data, set sample data quantity, set prediction time, set node load change threshold, etc.;

[0123] The data acquisition module is connected to the storage via an interface and is used to import the collected data into the system;

[0124] The memory is used to store collected data and computer programs;

[0125] The processor is used to execute a computer program to implement the virtual power plant cross-regional load migration intelligent scheduling method provided by the present invention, and generate power generation analysis data of the minimum power supply cost power generation node;

[0126] The control module is used to receive the power generation analysis data of the minimum power supply cost power generation node, and dispatch each power generation node based on the power generation analysis data of the minimum power supply cost power generation node.

[0127] The above description is merely illustrative of certain exemplary embodiments of the present invention. It goes without saying that those skilled in the art will be able to modify the described embodiments in various ways without departing from the spirit and scope of the present invention. Therefore, the above drawings and description are illustrative in nature and should not be construed as limiting the scope of protection of the claims.

Claims

1. An intelligent scheduling method for cross-regional load migration in a virtual power plant, characterized by: The following steps are involved: S1. Collect power generation cost parameter data, line capacity data, network loss coefficient data, PTDF matrix data, photovoltaic impact factor data, wind power impact factor data, photovoltaic power generation data, wind power generation data, conventional power generation data, and node load data of power generation nodes; Said S1 comprises the following steps: S11. Collect power generation cost parameter data of power generation nodes and generate power generation cost parameter data set of power generation nodes , , represents the power generation cost parameter data of the w-th power generation node, Indicates the maximum number of power generation nodes; S12. Collect line capacity data and generate line capacity data set , , represents the capacity data of the qth line, Indicates the maximum number of lines; S13. Collect network loss coefficient data and generate a network loss coefficient data set ,in represents the network loss coefficient between nodes w and j, , represents the single-machine network loss coefficient of node w, is a constant loss term that is independent of the unit output; S14, collecting power transmission distribution factors and generating PTDF matrix data C; S15. Collect photovoltaic impact factor data , Wind power impact factor data , Photovoltaic power generation data , wind power generation data , conventional power generation data ; S16. Collect node load data and generate node load data set , , represents the load data of the u-th node, Indicates the maximum number of nodes; S2. updating the pre-trained photovoltaic power generation prediction model and the wind power generation prediction model based on the photovoltaic impact factor data, the wind power impact factor data, the photovoltaic power generation data, and the wind power generation data; S3. Inputting the photovoltaic impact factor data into a pre-trained photovoltaic power generation prediction model to generate photovoltaic power generation prediction data, and inputting the wind power impact factor data into a pre-trained wind power generation prediction model to generate wind power generation prediction data; S4. Inputting the node load data into a pre-trained load forecasting model to generate node load forecast data; S5. Calculate and process the variation of the node load prediction data to generate node load variation prediction data; S6. Perform minimum power supply cost power generation node power generation analysis based on the power generation node power generation cost parameter data, line capacity data, network loss coefficient data, PTDF matrix data, photovoltaic power generation power prediction data, wind power generation power prediction data, and node load change prediction data to generate minimum power supply cost power generation node power generation analysis data; S61. Construct a formula for calculating the power generation of each power generation node at the minimum cost while meeting the power demand: （1）； in, 、 、 are the power generation cost parameter data of the power generation node w, When the corresponding node is a photovoltaic power generation node Adopt corresponding , The corresponding node is the node of wind power generation Adopt corresponding , When the corresponding node is a conventional power generation node Use the corresponding ; S62. Construct the constraint condition. The formula is as follows: ； ； ； in, is the grid loss power prediction data, 、 is the minimum and maximum power generation of the w-th power generation node, is the maximum capacity of the qth line; Based on photovoltaic power generation power forecast data , wind power generation power forecast data , conventional power generation data , node load forecast data set And the network loss coefficient data set B, the network loss power is calculated to obtain the network loss power prediction data ; S63. Solve formula (1) to obtain the power generation of each power generation node w, and generate the power generation analysis data of the power generation node with the minimum power supply cost , including the following steps: S631. Initialize the population and randomly generate M node power generation search cuckoos. Each cuckoo represents a potential minimum power supply cost power generation node power generation analysis data. ; S632. Based on formula (1) and the constraints, a fitness function is constructed to calculate the fitness of the cuckoo search for each node's power generation: ； in, 、 is the penalty coefficient; S633, each cuckoo reaches a new location via Lévy flight; S634, based on the probability of discovery Discard the node power generation search cuckoo with non-optimal fitness and generate a new node power generation search cuckoo instead; S635, resetting the node power generation power search cuckoo that exceeds the boundary to the nearest boundary; S636: Determine whether the maximum number of iterations has been reached. If so, output the power generation power of the node with the best fitness and search for the power generation power analysis data of the minimum power supply cost power generation node corresponding to the cuckoo. If not, return to S632; S7. Perform load dispatching of the virtual power plant based on the power generation analysis data of the power generation node with the minimum power supply cost; S71: Determine the node load change prediction data set Is there any node load change prediction data in the The absolute value of is greater than the set node load change threshold; S72, if not, then analyze the power generation data based on the minimum power supply cost power generation node Perform scheduling operations on each power generation node; S73. If yes, return to S4.

2. The method for intelligent scheduling of cross-regional load migration of a virtual power plant according to claim 1, characterized in that: The S2 comprises the following steps: S21, judging the collected photovoltaic impact factor data and photovoltaic power generation data Whether the set quantity is reached, if so, based on the photovoltaic impact factor data and photovoltaic power generation data Update the pre-trained photovoltaic power generation prediction model and collect the photovoltaic impact factor data and photovoltaic power generation data Conduct a recount; S22. Determine the collected wind power impact factor data , and wind power generation data Whether the set number is reached, if so, based on the wind power impact factor data , and wind power generation data Update the pre-trained wind power generation prediction model and collect the wind power influencing factor data , and wind power generation data Recounting is performed.

3. The method for intelligent scheduling of cross-regional load migration of a virtual power plant according to claim 2, characterized in that: The S3 includes the following steps: S31, the photovoltaic impact factor data Input the pre-trained photovoltaic power generation prediction model to obtain the predicted photovoltaic power generation prediction data ; S32, the wind power impact factor data Input the pre-trained wind power generation prediction model to generate wind power generation prediction data .

4. The method for intelligent scheduling of cross-regional load migration of a virtual power plant according to claim 3 is characterized by: The S4 comprises the following steps: S41, the node load data Input the pre-trained load forecasting model to obtain node load forecast data , generate node load forecast data set .

5. The method for intelligent scheduling of cross-regional load migration of a virtual power plant according to claim 4 is characterized in that: The S5 comprises the following steps: S51, the node load prediction data set Node load forecast data for all nodes in Perform change calculation to obtain node load change prediction data , generate node load change prediction data set .

6. A virtual power plant cross-regional load migration intelligent scheduling system, configured to execute the virtual power plant cross-regional load migration intelligent scheduling method according to any one of claims 1 to 5, characterized in that: It includes data acquisition module, interface, storage, processor and control module.

Images