Multi-virtual power plant scheduling method and device based on cloud edge collaboration, and medium

Abstract

The invention provides a multi-virtual power plant scheduling method based on cloud edge collaboration. The method comprises the following steps: 1) a dispatching master station of a power system cloud accesses a plurality of virtual power plants, and establishes unified management ledger data; (2) each virtual power plant respectively calculates the maximum value, the minimum value and the optimal solution of the adjustable load of the virtual power plant in the time period according to a demand index issued by the master station, and returns a result to the scheduling master station of the cloud; and 3) the scheduling master station performs unified fine adjustment calculation according to the results submitted by the virtual power plants, and issues the adjusted load results to the corresponding virtual power plants, and the virtual power plants perform power generation according to the issued load results and then supply power to the network. According to the application of the method, improvement is carried out for insufficient collaboration of a plurality of virtual power plants in an existing method, the situation that local power supply adequacy of a power distribution network is unbalanced is avoided, and distributed clean energy is preferentially consumed in the virtual power plants.

Description

Technical Field

[0001] The present invention belongs to the field of electric power technology and relates to a multi-virtual power plant scheduling method based on cloud-edge collaboration. Background Art

[0002] In order to achieve the goal of "carbon peak and carbon neutrality", my country has stepped up the development and utilization of clean energy power generation technologies such as hydropower, wind power and photovoltaics, and a large number of distributed power sources have been connected to the power grid. Now, with the rapid increase in the number of power equipment, the gradual increase in adjustable power sources and adjustable loads, and the greatly increased complexity of dispatching requirements, the original power system dispatching platform faces a series of practical problems.

[0003] In order to achieve aggregate management of a huge number of dispersed participants in the new power system, virtual power plant (VPP) technology can aggregate the scattered power generation energy at the information and communication level, realize cross-regional power coordination and complementarity, promote the rational distribution and utilization of resources, form a multi-regional integrated energy virtual power plant (multi-energy virtual power plant, MEVPP), and reduce the total operating cost of the system.

[0004] However, since the distribution of distributed power sources is random due to geographical restrictions, and the power generation is subject to large fluctuations due to weather conditions, the overall scheduling of most virtual power plants currently suffers from uneven local redundancy in the distribution network and insufficient absorption of new energy.

[0005] Therefore, a multi-virtual power plant scheduling method based on cloud-edge collaboration is used to solve the problem of unified collaborative optimization scheduling of multiple virtual power plants. Summary of the invention

[0006] The purpose of the present invention is to provide a multi-virtual power plant scheduling method based on cloud-edge collaboration to solve the problem of unified collaborative optimization scheduling of multiple virtual power plants.

[0007] The technical solution of the present invention is a multi-virtual power plant scheduling method based on cloud-edge collaboration, comprising the following steps:

[0008] 1) The dispatching master station in the power system cloud is connected to multiple virtual power plants and establishes a unified management ledger data;

[0009] 2) Each virtual power plant calculates its own maximum and minimum values ​​of adjustable load in the period, as well as the optimal solution, according to the demand indicators issued by the master station, and returns the results to the cloud dispatching master station;

[0010] 3) The dispatching master station performs unified fine-tuning calculations based on the results reported by each virtual power plant, and sends the adjusted load results to the corresponding virtual power plants. Each virtual power plant generates electricity according to the sent load results and then sends electricity into the grid.

[0011] Preferably, in step 1), the basic archive management data in the process of constructing virtual power plant resource access includes different partitions and different types, and the resource information under different dimensions is integrated. According to the grid access criteria and protection requirements, the virtual power plant resources are connected to the dispatching master station system in accordance with the access method and interaction format specifications.

[0012] Preferably, step 2) is specifically

[0013] 2.1) The master station system sends a load request for a certain period of time to each virtual power plant, and issues the load demand P that needs to be responded to in that period of time de ;

[0014] 2.2) The virtual power plant calculates the maximum load P that can be adjusted during this period based on the distributed resource characteristics of its own operation and management. max , minimum value P min and the optimal value P best , where the optimal solution is the one with the minimum cost;

[0015] Then, (P max -P min ) / n as the step length, the value range of n is 5 to 15, in the interval [P min , P max ] insert n-1 values ​​and calculate the cost value corresponding to each output power. Finally, the data format of the result returned by each virtual power plant to the dispatching master station is:

[0016] [(P0,C0); (P1,C1);.(P best ,C best )..(P n ,C n )];

[0017] 2.3) The dispatching master station constructs an m×n candidate set matrix based on the data reported by each virtual power plant, where m is the number of virtual power plants and n is the length of the above output power-cost vector group.

[0018] Preferably, in step 2.2), the unified constraints of the calculation process need to include the priority of distributed new energy consumption.

[0019] Preferably, in step 3), if the total amount of the optimal values ​​returned by each virtual power plant meets the current load demand, then according to the candidate set matrix, a minimum number of virtual power plants are selected to participate in the scheduling and adjustment;

[0020] Calculation method: Substitute (Pbest ,C best ) columns are taken out to form an array of value pairs with a length of m:

[0022] [(P0′,C0′); (P i ′,C i ′)...(P m ′,C m ′)];

[0023] Set the array length to P de The array dp[x], which is rounded up and added with 1, is used to record the minimum cost value that can be achieved when the sum of the loads of the selected value pairs is exactly equal to x.

[0024] Initially, except for dp[0]=0, the cost value is 0, and the other dp[x] are initialized to infinity;

[0025] For each value pair, update all possible states dp[x],

[0026] Let x = P de -P' i , that is, from P' i To the target value P de For all possible sums, the state transition equation is as follows:

[0027] dp[x]=min(dp[x],dp[xP' i ]+C' i )

[0028] In the formula, dp[xP' i ]+C' i Indicates that some value pairs have been selected so that the sum of their loads is xP' i In the case of i ,C' i ) after the new state;

[0029] Traverse all given value pairs, for each value pair, update the array of all possible states from large to small, and obtain the dp[Pde] corresponding to each value pair. At the same time, use the selected[Pde+1] array to record the best selected value pair for each state. dp[Pde] is the final minimum cost result. During the solution process, the value pair recorded by selected[Pde+1] is the selected combination result, that is, the virtual power plant combination with the lowest cost is selected to participate in the dispatch and regulation.

[0030] If the total amount of optimal values ​​returned by each virtual power plant is significantly different from the current load demand, that is, m P bestAdding the values ​​does not satisfy P de , then the master station fine-tunes the baseline based on the optimal value;

[0031] Calculation method: The calculation method under the conditions is extended to a two-dimensional problem, and additional constraints are set: only one value pair can be selected in each row to ensure that each virtual power plant can only have one operating mode in a certain period of time;

[0032] Let dp[i][j] represent the minimum cost value that can be achieved when selecting value pairs from the first i rows of the matrix so that the sum of the loads of the selected value pairs is exactly j;

[0033] Initially, except for dp[0][0]=0, the cost value is 0, and the other dp[i][j] are initialized to infinity;

[0034] For each value pair (P n ,C n ), update all possible states dp[i+1][j], where j is the sum of all possible values ​​from 0 to the target value, and set j = P de , i = m;

[0035] The state transfer equation is as follows:

[0036] dp[i][j]=min(dp[i+1][j],dp[i][jP n ]+C n )

[0037] Where dp[i+1][j] represents the minimum cost value with the sum of loads j after considering the first i+1 rows; dp[i][jP n ]+C n Indicates that some value pairs have been selected so that the sum of their loads is jP n In the case of n ,C n ) after the new state;

[0038] Traverse all rows, and for each value pair (Pn, Cn) in each row, update all possible states dp[i+1][Pde] from large to small. At the same time, use the selected[m+1][Pde+1] array to record the best selected value pair for each state. Finally, the value pair recorded in selected[m+1][Pde+1] is the combination result of the selection, and the result with the minimum cost is dp[m][P de ].

[0039] Preferably, in step 3), after each virtual power plant receives the load result sent by the dispatching master station, it executes according to its own situation and dispatching strategy. During the execution process, the virtual power plant needs to monitor its own operating status in real time to ensure that it is adjusted according to the dispatching strategy.

[0040] If special circumstances occur during the execution process, such as equipment failure or changes in the external environment, the virtual power plant needs to promptly provide feedback to the dispatching master station so that the dispatching master station can make adjustments.

[0041] A computer device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, it is based on the multi-virtual power plant scheduling method based on cloud-edge collaboration as described in any one of the above items.

[0042] A computer-readable storage medium is also provided, on which a computer program is stored. When the computer program is executed by a processor, the multi-virtual power plant scheduling method based on cloud-edge collaboration as described in any one of the above items is implemented.

[0043] The beneficial effects of the present invention are as follows: (1) multiple virtual power plants are fully coordinated for unified dispatching to avoid the situation of uneven local power supply in the distribution network; (2) adjustment costs are introduced to encourage virtual power plants to give priority to the absorption of distributed clean energy, so that distributed new energy can be fully absorbed; (3) the master station calculation is simple and does not require various detailed measurement data of the virtual power plant, reducing storage overhead; (4) there are many dispatching schemes to choose from, and the optimal dispatching scheme can be selected based on real-time weather, future weather changes, equipment operating status, personnel location arrangements, etc., fully considering the actual situation and with high flexibility.

[0044] The application of this method aims to improve the insufficient coordination of multiple virtual power plants in the existing method, avoid the imbalance of local power supply in the distribution network, and give priority to the consumption of distributed clean energy within the virtual power plant. The dispatching master station system serves as a unified cloud computing center, and each virtual power plant serves as an edge computing unit to achieve cloud-edge coordination between the master station and the virtual power plant. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 This is the overall framework diagram of the unified dispatch optimization method for multiple virtual power plants based on cloud-edge collaboration;

[0046] Figure 2 This is the overall architecture diagram of the unified dispatching system for multiple virtual power plants in cloud-edge collaboration; DETAILED DESCRIPTION

[0047] The technical solution of the present invention will be described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0048] See also Figure 1 , a multi-virtual power plant scheduling method based on cloud-edge collaboration, comprising the following steps:

[0049] 1) The dispatching master station in the power system cloud is connected to multiple virtual power plants and establishes a unified management ledger data;

[0050] 2) Each virtual power plant calculates its own maximum and minimum values ​​of adjustable load in the period, as well as the optimal solution, according to the demand indicators issued by the master station, and returns the results to the cloud dispatching master station;

[0051] 3) The dispatching master station performs unified fine-tuning calculations based on the results reported by each virtual power plant, and sends the adjusted load results to the corresponding virtual power plants. Each virtual power plant generates electricity according to the sent load results and then sends electricity into the grid.

[0052] In step 1) of this embodiment, the basic archive management data in the process of constructing virtual power plant resource access includes different partitions and different types, and the resource information under different dimensions is integrated. According to the grid access criteria and protection requirements, the virtual power plant resources are connected to the dispatching master station system in accordance with the access method and interactive format specifications. The connection between the dispatching master station and the virtual power plant in the power system cloud is a conventional technology in the field, and the details of the specific implementation are not repeated.

[0053] Step 2) of this embodiment is specifically as follows:

[0054] 2.1) The master station system sends a load request for a certain period of time to each virtual power plant, and issues the load demand P that needs to be responded to in that period of time de ;

[0055] 2.2) Virtual power plant, based on the distributed resource characteristics of its own operation and management, calculates the maximum adjustable load P during this period max , minimum value P min and the optimal value P best , where the optimal solution is the one with the minimum cost;

[0056] Then, (P max -P min ) / n as the step size in the interval [P min , P max] Insert n-1 values, where n ranges from 5 to 15, and is generally 10, and calculate the cost value corresponding to each output power. Finally, the data format of the result returned by each virtual power plant to the dispatching master station is:

[0057] [(P0,C0); (P1,C1);.(P best ,C best )..(P n ,C n )];

[0058] 2.3) The dispatching master station constructs an m×n candidate set matrix based on the data reported by each virtual power plant, where m is the number of virtual power plants and n is the length of the above output power-cost vector group.

[0059] In step 2.2), the unified constraint condition must include the priority of distributed new energy consumption. The calculation process is that the virtual power plant is calculated according to the internal distributed power characteristics. The calculation can be performed by target optimization algorithms such as particle swarm and genetic algorithm. Such algorithms can use conventional target optimization algorithms to solve the internal output of the virtual power plant. This is a conventional technology in this field, and the specific calculation process will not be repeated.

[0060] In step 3), if the total amount of optimal values ​​returned by each virtual power plant meets the current load demand, the minimum number of virtual power plants is selected to participate in the dispatching and adjustment according to the candidate set matrix. Generally, if it can be satisfied, the method with the least number of impacts is selected;

[0061] Calculation method: Substitute (P best ,C best ) columns are taken out to form an array of value pairs with a length of m:

[0063] [(P0′,C0′); (P i ′,C i ′)...(P m ′,C m ′)];

[0064] Set the array length to P de The array dp[x], which is rounded up and added by 1, is used to record the minimum cost value that can be achieved when the sum of the loads of the selected value pairs is exactly equal to x. Since 0 represents no selection, the array subscript starts at 1 and is added by 1 to prevent the array from crossing the boundary during the calculation process.

[0065] Initially, except for dp[0]=0, which means there is no choice, the cost value is 0, and all other dp[x] are initialized to infinity, which means an impossible state;

[0066] For each value pair, that is, [(P'0,C'0); (P' i ,C' i )...(P' m ,C' m )], update all possible states dp[x], where x is from P' i All possible sums to the target value (i.e. Pde-P' i ), the state transfer equation is as follows:

[0067] dp[x]=min(dp[x],dp[xP' i ]+C' i )

[0068] In the formula, dp[xP' i ]+C' i Indicates that some value pairs have been selected so that the sum of their P is xP' i In the case of i ,C' i ) after the new state;

[0069] Traverse all given value pairs, for each value pair, update the array of all possible states from large to small, and obtain the dp[Pde] corresponding to each value pair. At the same time, use the selected[Pde+1] array to record the best selected value pair for each state. dp[Pde] is the final minimum cost result. During the solution process, the value pair recorded by selected[Pde+1] is the selected combination result, that is, the virtual power plant combination with the lowest cost is selected to participate in the dispatch and regulation.

[0070] In actual operation, the sum of the results selected by the candidate set is guaranteed to be equal to P de or slightly larger than P de ; Usually there is a slightly larger situation, because in actual operation, the candidate set may not be able to accurately match Pde, so it is necessary to select an additional virtual power plant to participate in the rounding.

[0071] If the total amount of optimal values ​​returned by each virtual power plant is significantly different from the current load demand, that is, m P best Adding the values ​​does not satisfy P de , the master station fine-tunes the baseline based on the optimal value, calculates the load combination of each virtual power plant that has the lowest overall cost and meets the load demand in the complete candidate set, and sends the fine-tuned results to each virtual power plant;

[0072] Its calculation method: The calculation method under the conditions is extended to a two-dimensional problem, and additional constraints are set: only one value pair can be selected in each row to ensure that each virtual power plant can only have one operating mode in a certain period of time;

[0073] Let dp[i][j] represent the minimum cost value that can be achieved when selecting value pairs from the first i rows of the matrix so that the sum of the loads of the selected value pairs is exactly j;

[0074] Initially, except for dp[0][0] = 0, which means there is no choice, the value of C is 0, and the other dp[i][j] are initialized to infinity, which means an impossible state;

[0075] For each value pair in each row, all possible states dp[i+1][j] are updated, where j is the sum of all possible values ​​from 0 to the target value. The state transition equation is as follows. In this embodiment, j=Pde, i=m;

[0076] dp[i][j]=min(dp[i+1][j],dp[i][jP n ]+C n )

[0077] Where dp[i+1][j] represents the minimum cost value with the sum of loads j after considering the first i+1 rows; dp[i][jP n ]+C n Indicates that some value pairs have been selected so that the sum of their loads is jP n In the case of n ,C n ) after the new state;

[0078] Traverse all rows, and for each value pair (Pn, Cn) in each row, update all possible states dp[i+1][Pde] from large to small. At the same time, use the selected[m+1][Pde+1] array to record the best selected value pair for each state. Finally, the value pair recorded in selected[m+1][Pde+1] is the combination result of the selection, and the result with the minimum cost is dp[m][P de ].

[0079] The final result is dp[m][P]. In actual operation, the sum of the results selected from the candidate set is guaranteed to be equal to P. de or slightly larger than P de .

[0080] The algorithm first exhaustively lists the sum of the loads of each virtual electric field and other virtual electric fields equal to P deAll possibilities are considered, and the one with the lowest cost is selected as a candidate answer. Multiple virtual power plants can be fully coordinated for unified dispatching to avoid the imbalance of local power supply in the distribution network. There are many optimal results, and the optimal dispatching plan can be selected based on real-time weather, future weather changes, equipment operating status, personnel location arrangements, etc., with high flexibility.

[0081] The dispatching master station performs unified fine-tuning calculations based on the integrated data and the overall operation of the power system; the fine-tuning calculations are to adjust the load distribution of each virtual power plant to achieve the optimal operating state of the power system, including but not limited to minimizing system costs, improving the utilization rate of renewable energy, and maintaining system stability.

[0082] During the calculation process, a variety of optimization algorithms may be used, such as linear programming, genetic algorithm, particle swarm optimization algorithm, etc., to find the optimal solution. After unified fine-tuning calculations, the dispatching master station will disassemble the optimized load results into specific load distribution plans for each virtual power plant; the disassembled load results will be reasonably allocated according to the characteristics and capabilities of each virtual power plant to ensure that each virtual power plant can effectively implement the dispatching strategy. The dispatching master station will send the disassembled load results to the corresponding virtual power plant, usually using a secure and reliable data transmission protocol to ensure the security and timeliness of data transmission.

[0083] In step 3) of this embodiment, after each virtual power plant receives the load results sent by the dispatching master station, it executes according to its own situation and dispatching strategy. During the execution process, the virtual power plant needs to monitor its own operating status in real time to ensure that it is adjusted according to the dispatching strategy.

[0084] If special circumstances occur during the execution process, such as equipment failure or changes in the external environment, the virtual power plant needs to promptly provide feedback to the dispatching master station so that the dispatching master station can make adjustments.

[0085] This embodiment provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it is based on the aforementioned multi-virtual power plant scheduling method based on cloud-edge collaboration.

[0086] This embodiment also provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, it is based on the aforementioned multi-virtual power plant scheduling method based on cloud-edge collaboration.

[0087] The application of this method aims to improve the insufficient coordination of multiple virtual power plants in the existing method, avoid the imbalance of local power supply in the distribution network, and give priority to the consumption of distributed clean energy within the virtual power plant. The dispatching master station system serves as a unified cloud computing center, and each virtual power plant serves as an edge computing unit to achieve cloud-edge coordination between the master station and the virtual power plant.

[0088] The present invention is not limited to the above-mentioned embodiments. On the basis of the technical solution disclosed in the present invention, technicians in this field can make some substitutions and deformations to some technical features therein according to the disclosed technical content without creative labor, and these substitutions and deformations are all within the protection scope of the present invention.

Claims

1. A multi-virtual power plant scheduling method based on cloud-edge collaboration, characterized in that: The following steps are involved: 1) The dispatching master station in the power system cloud is connected to multiple virtual power plants and establishes a unified management ledger data; 2) Each virtual power plant calculates its own maximum and minimum values ​​of adjustable load in the period, as well as the optimal solution, according to the demand indicators issued by the master station, and returns the results to the cloud dispatching master station; 3) The dispatching master station performs unified fine-tuning calculations based on the results reported by each virtual power plant, and sends the adjusted load results to the corresponding virtual power plants. Each virtual power plant generates electricity according to the sent load results and then sends electricity into the grid.

2. According to the multi-virtual power plant scheduling method based on cloud-edge collaboration according to claim 1, it is characterized in that: In step 1), the basic archive management data of the virtual power plant resource access process includes different partitions and different types, and the resource information under different dimensions is integrated. According to the grid access criteria and protection requirements, the virtual power plant resources are connected to the dispatching master station system in accordance with the access method and interaction format specifications.

3. According to claim 1, a multi-virtual power plant scheduling method based on cloud-edge collaboration is characterized in that: Step 2) is as follows: 2.1) The master station system sends a load request for a certain period of time to each virtual power plant, and issues the load demand P that needs to be responded to in that period of time de ; 2.2) The virtual power plant calculates the maximum load P that can be adjusted during this period based on the distributed resource characteristics of its own operation and management. max , minimum value P min and the optimal value P best , where the optimal solution is the one with the minimum cost; Then, (P max -P min ) / n as the step length, the value range of n is 5 to 15, in the interval [P min , P max ] insert n-1 values ​​and calculate the cost value corresponding to each output power. Finally, the data format of the result returned by each virtual power plant to the dispatching master station is: [(P0,C0);(P1,C1);.(P best ,C best )..(P n ,C n )]; 2.3) The dispatching master station constructs an m×n candidate set matrix based on the data reported by each virtual power plant, where m is the number of virtual power plants and n is the length of the above output power-cost vector group.

4. According to claim 3, a multi-virtual power plant scheduling method based on cloud-edge collaboration is characterized in that: In step 2.2), the unified constraints of the calculation process must include the priority of distributed new energy consumption.

5. According to claim 3, a multi-virtual power plant scheduling method based on cloud-edge collaboration is characterized in that: In step 3), if the total amount of the optimal values ​​returned by each virtual power plant meets the current load demand, then according to the candidate set matrix, the minimum number of virtual power plants is selected to participate in the dispatching and adjustment; Calculation method: Substitute (P best ,C best ) columns are taken out to form an array of value pairs with a length of m: [(P0′,C0′);(P i ′,C i ′)...(P m ′,C m ′)]; Set the array length to P de The array dp[x], which is rounded up and added with 1, is used to record the minimum cost value that can be achieved when the sum of the loads of the selected value pairs is exactly equal to x. Initially, except for dp[0]=0, the cost value is 0, and the other dp[x] are initialized to infinity; For each value pair, update all possible states dp[x], Let x = P de -P' i , that is, from P' i To the target value P de For all possible sums, the state transition equation is as follows: dp[x]=min(dp[x],dp[x-P′ i ]+C′ i ) In the formula, dp[xP' i ]+C' i Indicates that some value pairs have been selected so that the sum of their loads is xP' i In the case of , add the new state after the current value pair; Traverse all given value pairs, and for each value pair, update the array of all possible states from large to small to obtain the dp[Pde] corresponding to each value pair. At the same time, use the selected[Pde+1] array to record the best selected value pair for each state. dp[Pde] is the result of the final minimum cost calculation. During the solution process, the value pair recorded in selected[Pde+1] is the result of the selected combination, that is, the virtual power plant combination with the lowest cost is selected to participate in the dispatch adjustment. If the total amount of optimal values ​​returned by each virtual power plant is significantly different from the current load demand, that is, m P best Adding the values ​​does not satisfy P de , then the master station fine-tunes the baseline based on the optimal value; Calculation method: The calculation method under the conditions is extended to a two-dimensional problem, and additional constraints are set: only one value pair can be selected in each row to ensure that each virtual power plant can only have one operating mode in a certain period of time; Let dp[i][j] represent the minimum cost value that can be achieved when selecting value pairs from the first i rows of the matrix so that the sum of the loads of the selected value pairs is exactly j; Initially, except for dp[0][0]=0, the cost value is 0, and the other dp[i][j] are initialized to infinity; For each value pair in each row, update all possible states dp[i+1][j], where j is the sum of all possible values ​​from 0 to the target value, and set j = P de , i = m; The state transfer equation is as follows: dp[i][j]=min(dp[i+1][j],dp[i][j-P n ]+C n ) Among them, dp[i+1][j] represents the minimum cost value with the sum of loads equal to j after considering the first i+1 rows; dp[i][jP n ]+C n Indicates that some value pairs have been selected so that the sum of their loads is jP n In the case of , add the new state after the current value pair; Traverse all rows, and for each value pair in each row, update all possible states dp[i+1][Pde] from large to small. At the same time, use the selected[m+1][Pde+1] array to record the best selected value pair for each state. Finally, the value pair recorded in selected[m+1][Pde+1] is the combined result of the selection, and the result with the minimum cost is dp[m][Pde+1]. de ].

6. According to claim 1, a multi-virtual power plant scheduling method based on cloud-edge collaboration is characterized in that: Step 3) After receiving the load results sent by the dispatching master station, each virtual power plant executes according to its own situation and dispatching strategy. During the execution process, the virtual power plant needs to monitor its own operating status in real time to ensure that it is adjusted according to the dispatching strategy. If special circumstances occur during the execution process, such as equipment failure or changes in the external environment, the virtual power plant needs to promptly provide feedback to the dispatching master station so that the dispatching master station can make adjustments.

7. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, it is based on the multi-virtual power plant scheduling method based on cloud-edge collaboration as described in any one of claims 1-6.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, it is based on the multi-virtual power plant scheduling method based on cloud-edge collaboration as described in any one of claims 1-6.

Images