A virtual power plant construction method, device, electronic device and readable storage medium

Abstract

The present application discloses a method, device, electronic device and readable storage medium for constructing a virtual power plant. The method includes: for each type of distributed power source in a power supply partition, obtaining first location information and first output power of multiple first distributed power sources, and second location information of multiple second distributed power sources; based on the first location information and first output power, and the second location information, aggregating multiple first distributed power sources and multiple second distributed power sources to obtain multiple aggregates; based on the first output power of the first distributed power source in each aggregate, determining the second output power of the second distributed power source in each aggregate; based on the first output power of the first distributed power source and the second output power of the second distributed power source in each aggregate corresponding to the different types of distributed power sources, and preset targets, aggregating each aggregate corresponding to different types of distributed power sources to obtain multiple virtual power plants.

Description

Technical Field

[0001] The present application relates to the technical field of virtual power plant construction, and in particular to a virtual power plant construction method, device, electronic device and readable storage medium. Background Art

[0002] The consensus on environmental protection and the increasing demand for energy have brought great opportunities for the development of distributed power sources. The combination of distributed power sources and conventional power sources will be the trend of power system development.

[0003] When a small number of distributed generation units are connected to the grid, their impact on grid operation and control can be mitigated through the grid's own active control. However, when a large number of distributed generation units are connected to the grid, their presence can have a significant impact on grid scheduling. This is primarily due to the many characteristics of distributed generation units, such as their output power fluctuations in time, their spatial dispersion, and their massive number. This makes it difficult for the grid to directly manage and schedule these distributed generation units. Summary of the Invention

[0004] In view of this, embodiments of the present application provide a method, device, electronic device and readable storage medium for constructing a virtual power plant.

[0005] According to the first aspect of the present application, an embodiment of the present application provides a method for constructing a virtual power plant, including:

[0006] For each type of distributed power source in the power supply zone, obtaining first location information and first output power of multiple first distributed power sources, and second location information of multiple second distributed power sources; the output voltage of the first distributed power source is greater than or equal to a first threshold, and the output voltage of the second distributed power source is less than the first threshold;

[0007] Based on the first location information and the first output power of the plurality of first distributed power sources and the second location information of the plurality of second distributed power sources, the plurality of first distributed power sources and the plurality of second distributed power sources are aggregated to obtain a plurality of aggregates;

[0008] Determining a second output power of a second distributed power source in each aggregate based on a first output power of a first distributed power source in each aggregate;

[0009] Based on the first output power of the first distributed power source and the second output power of the second distributed power source in each aggregate corresponding to the different types of distributed power sources, and the preset targets, the aggregates corresponding to the different types of distributed power sources are aggregated to obtain multiple virtual power plants; the preset targets include a first target, a second target and a third target; the first target includes that when the power consumption of the virtual power plant is used as the load condition of the power supply partition, the first standard deviation of the total load of the power supply partition meets the first condition; the second target includes that under the target condition, the second standard deviation of the exchange power between the virtual power plant and the power grid in the power supply partition meets the second condition; the third target includes determining the number of virtual power plants and the aggregates contained in each virtual power plant, so that the sum of the second standard deviation of the exchange power between each virtual power plant and the power grid in the power supply partition and the first standard deviation meets the third condition.

[0010] Optionally, based on the first location information and the first output power of the plurality of first distributed power sources and the second location information of the plurality of second distributed power sources, the plurality of first distributed power sources and the plurality of second distributed power sources are aggregated to obtain a plurality of aggregates, including:

[0011] Aggregating the plurality of first distributed power sources based on first output powers of the plurality of first distributed power sources to obtain a plurality of aggregated partitions;

[0012] Based on the first location information and the second location information, the plurality of second distributed power sources are aggregated into a plurality of aggregation partitions to obtain a plurality of aggregates.

[0013] Optionally, based on the first output powers of the plurality of first distributed power sources, the plurality of first distributed power sources are aggregated to obtain a plurality of aggregated partitions, including:

[0014] Selecting a plurality of target first output powers from the plurality of first output powers as feature vectors of a plurality of cluster centers;

[0015] Clustering the plurality of first output powers to corresponding cluster centers based on the eigenvector of each cluster center and the eigenvector distance constraint condition;

[0016] Re-determine the eigenvector corresponding to each cluster center, and iteratively execute the eigenvector based on each cluster center and the eigenvector distance constraint condition to cluster the multiple first output powers to the corresponding cluster centers until the difference between the eigenvector corresponding to each re-determined cluster center and the eigenvector corresponding to each cluster center determined in the previous iteration is less than the second threshold.

[0017] Optionally, based on the first location information and the second location information, aggregating the plurality of second distributed power sources into a plurality of aggregation partitions includes:

[0018] Determining a distance between each second distributed power source and each first distributed power source based on the first location information and the second location information;

[0019] Determining, based on the distance, an aggregation partition corresponding to each second distributed power source;

[0020] Aggregate each second distributed power source into a corresponding aggregation partition.

[0021] Optionally, determining the second output power of the second distributed power source in each aggregate based on the first output power of the first distributed power source in each aggregate includes:

[0022] Determine a first output power corresponding to a first distributed power source and a second output power corresponding to a second distributed power source in each aggregate;

[0023] determining a correlation parameter between a first output quantity and a second output quantity in each aggregate;

[0024] Based on the first output power of the first distributed power source in each aggregate and corresponding related parameters, the second output power of the second distributed power source in each aggregate is determined.

[0025] Optionally, the virtual power plant construction method further includes:

[0026] Determining an estimated output power of the second distributed power source in each aggregate based on the second output power of the second distributed power source in each aggregate;

[0027] If it is determined based on the estimated output power and the second output power that the second distributed power sources in each aggregate need to be reaggregated, the second distributed power sources in each aggregate are reaggregated and the second output power of the second distributed power sources in each aggregate is re-determined.

[0028] Optionally, based on the first output power of the first distributed power source and the second output power of the second distributed power source in each aggregate corresponding to the different types of distributed power sources, and a preset target, the aggregates corresponding to the different types of distributed power sources are aggregated to obtain multiple virtual power plants, including:

[0029] Determine a first function corresponding to the first objective, a second function corresponding to the second objective, and a third function corresponding to the third objective;

[0030] Based on the first output power of the first distributed power source and the second output power of the second distributed power source in each aggregate corresponding to the different types of distributed power sources, the first function, the second function and the third function are solved to obtain the number of virtual power plants in the power supply zone and the aggregates included in each virtual power plant;

[0031] Based on the number of virtual power plants in the power supply zone and the aggregates contained in each virtual power plant, the aggregates are aggregated to obtain a plurality of virtual power plants corresponding to the number.

[0032] According to a second aspect of the present application, an embodiment of the present application provides a virtual power plant construction device, including:

[0033] an acquisition module, configured to acquire, for each type of distributed power source in the power supply zone, first location information and first output power of a plurality of first distributed power sources, and second location information of a plurality of second distributed power sources; an output voltage of the first distributed power source is greater than or equal to a first threshold, and an output voltage of the second distributed power source is less than the first threshold;

[0034] a first aggregation module, configured to aggregate the plurality of first distributed power sources and the plurality of second distributed power sources based on first location information and first output powers of the plurality of first distributed power sources and second location information of the plurality of second distributed power sources to obtain a plurality of aggregates;

[0035] a determination module, configured to determine a second output power of a second distributed power source in each aggregate based on a first output power of a first distributed power source in each aggregate;

[0036] The second aggregation module is used to aggregate the aggregates corresponding to different types of distributed power sources based on the first output power of the first distributed power source and the second output power of the second distributed power source in each aggregate corresponding to the different types of distributed power sources, and preset targets, to obtain multiple virtual power plants; the preset targets include a first target, a second target and a third target; the first target includes that when the power consumption of the virtual power plant is used as the load condition of the power supply partition, the first standard deviation of the total load of the power supply partition meets the first condition; the second target includes that under the target condition, the second standard deviation of the exchange power between the virtual power plant and the power grid in the power supply partition meets the second condition; the third target includes determining the number of virtual power plants and the aggregates contained in each virtual power plant, so that the sum of the second standard deviation of the exchange power between each virtual power plant and the power grid in the power supply partition and the first standard deviation meets the third condition.

[0037] According to a third aspect of the present application, an embodiment of the present application provides an electronic device, including:

[0038] At least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so as to enable the at least one processor to execute the virtual power plant construction method as described in the first aspect or any embodiment of the first aspect.

[0039] According to the fourth aspect of the present application, an embodiment of the present application provides a computer-readable storage medium, which stores computer instructions, and the computer instructions are used to enable a computer to execute a virtual power plant construction method as in the first aspect or any embodiment of the first aspect.

[0040] The virtual power plant construction method, device, electronic device and readable storage medium provided in the embodiments of the present application obtain multiple virtual power plants by aggregating the aggregates corresponding to different types of distributed power sources based on the first output power of the first distributed power source and the second output power of the second distributed power source in each aggregate corresponding to different types of distributed power sources, as well as preset targets; in this way, a large number of different types of distributed power sources can be aggregated into a virtual power plant, and the power grid can coordinate the scheduling of a large number of different types of distributed power sources by scheduling the virtual power plant, thereby improving the controllability of the power grid within the power supply zone for a large number of different types of distributed power sources, reducing the impact of distributed power sources on power grid scheduling, and ensuring the safe and stable operation of the power grid; and, when constructing a virtual power plant based on the aggregates corresponding to different types of distributed power sources, the power consumption of the virtual power plant is comprehensively considered. The requirements for the total load of the power supply partition and the requirements for the power exchange between the virtual power plant and the power grid can improve the security of the virtual power plant grid-connected scheduling and the economy of the internal scheduling of the virtual power plant; and, considering the large number of distributed power sources, based on the first position information and first output power of multiple first distributed power sources, and the second position information of multiple second distributed power sources, multiple first distributed power sources and multiple second distributed power sources are aggregated to obtain multiple aggregates. Multiple distributed power sources of the same type with similar output power and close distance can be aggregated into one aggregate, reducing the complexity of aggregating a large number of distributed power sources, and a large number of distributed power sources with lower output voltage can be included in the power grid management, so as to more comprehensively and accurately reflect the response capability of the distributed power sources in the power supply partition, and further improve the power grid's regulation and control capabilities of the distributed power sources. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 A flowchart of a method for constructing a virtual power plant in an embodiment of the present application;

[0042] Figure 2 A flow chart of another method for constructing a virtual power plant according to an embodiment of the present application;

[0043] Figure 3 A flow chart of another method for constructing a virtual power plant according to an embodiment of the present application;

[0044] Figure 4 This is a structural diagram of a data access device according to an embodiment of the present application;

[0045] Figure 5This is a schematic diagram of the hardware structure of an electronic device in an embodiment of the present application. DETAILED DESCRIPTION

[0046] To make the purpose, technical solutions, and advantages of the embodiments of the present application more clear, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without making creative efforts shall fall within the scope of protection of this application.

[0047] The present application embodiment provides a method for constructing a virtual power plant, such as Figure 1 As shown, including:

[0048] S101, for each type of distributed power supply in the power supply zone, obtain first location information and first output power of multiple first distributed power supplies, and second location information of multiple second distributed power supplies; the output voltage of the first distributed power supply is greater than or equal to a first threshold, and the output voltage of the second distributed power supply is less than the first threshold.

[0049] In this embodiment, the types of distributed power sources include distributed photovoltaic power sources, distributed wind power sources, distributed hydropower sources, distributed energy storage system power sources, and distributed loads.

[0050] In this embodiment, the output voltage of the first distributed power supply may be greater than or equal to 10 KV, and the output voltage of the second distributed power supply may be less than 10 KV.

[0051] In this embodiment, the first output power and the first output quantity of the first distributed power supply have been automatically collected, while the second output power of the second distributed power supply has not yet been automatically collected, but the second output quantity of the second distributed power supply has been automatically collected. The first output power can be the first output power time series data, for example, the first output power , where N is the number of distributed power sources; The distributed power supply at t j Output power in a time period, where T is the number of time periods.

[0052] S102 , based on the first location information and the first output power of the plurality of first distributed power sources and the second location information of the plurality of second distributed power sources, aggregate the plurality of first distributed power sources and the plurality of second distributed power sources to obtain a plurality of aggregates.

[0053] In this embodiment, based on the first location information and first output power of multiple first distributed power sources, and the second location information of multiple second distributed power sources, it is possible to aggregate the first distributed power sources whose first output power difference is less than the first threshold, and to aggregate the second distributed power sources with the corresponding first distributed power sources according to the distance between the first distributed power sources and the second distributed power sources to obtain multiple aggregates.

[0054] S103: Determine the second output power of the second distributed power source in each aggregate based on the first output power of the first distributed power source in each aggregate.

[0055] In this embodiment, since the second distributed power sources have been aggregated into an aggregate, to facilitate subsequent aggregation of the aggregate, it is necessary to determine the second output power of the second distributed power sources in each aggregate. However, automated data collection of the second output power of the second distributed power sources has not yet been implemented. Given that natural conditions within the same geographic region are generally consistent, the active output of distributed power sources should also be consistent. Therefore, the first output power of distributed power sources for which automated data collection has been implemented can be used to estimate the second output power of other distributed power sources within the same aggregate that have not yet implemented automated data collection.

[0056] S104, based on the first output power of the first distributed power source and the second output power of the second distributed power source in each aggregate corresponding to the different types of distributed power sources, and the preset targets, aggregate the aggregates corresponding to the different types of distributed power sources to obtain multiple virtual power plants; the preset targets include a first target, a second target and a third target; the first target includes that when the power consumption of the virtual power plant is used as the load condition of the power supply partition, the first standard deviation of the total load of the power supply partition meets the first condition; the second target includes that under the target condition, the second standard deviation of the exchange power between the virtual power plant and the power grid in the power supply partition meets the second condition; the third target includes determining the number of virtual power plants and the aggregates contained in each virtual power plant, so that the sum of the second standard deviation of the exchange power between each virtual power plant and the power grid in the power supply partition and the first standard deviation meets the third condition.

[0057] In this embodiment, the number of aggregates generated by output power similarity aggregation is often still large, making direct participation in main grid scheduling and operation relatively complex. More importantly, the aggregates do not utilize the complementarity between distributed power sources, resulting in uneven control capabilities and the inability to achieve unified control. Therefore, the aggregates can be further aggregated to form virtual power plants to participate in grid scheduling and operation.

[0058] In this embodiment, the virtual power plant may include aggregations corresponding to different types of distributed power sources.

[0059] In this embodiment, in the process of aggregating aggregates into virtual power plants, it is necessary to determine the number of virtual power plants and which virtual power plant each aggregate belongs to. At the same time, after aggregating into virtual power plants, both the power grid and the virtual power plant should be able to achieve certain scheduling and operation goals.

[0060] In this embodiment, the first objective is the grid dispatching and operating objective, which can be equivalent to minimizing the peak-to-valley difference of the equivalent load of the power supply partition and smoothing the equivalent load curve, that is, minimizing the standard deviation of the equivalent load curve. Here, equivalent load refers to the total power supply load of the power supply partition, taking into account the power consumption of the virtual power plant. The second objective is the virtual power plant dispatching and operating objective, which can be equivalent to minimizing the standard deviation of the power exchange curve between the virtual power plant and the external power grid under extreme load conditions within the virtual power plant. The third objective is to determine the number of virtual power plants and the aggregates contained in each virtual power plant, so that based on the first and second objectives, the dispatching and operating objectives of the power grid and each virtual power plant are optimized.

[0061] The virtual power plant construction method provided in the embodiment of the present application obtains multiple virtual power plants by aggregating the aggregates corresponding to different types of distributed power sources based on the first output power of the first distributed power source and the second output power of the second distributed power source in each aggregate corresponding to different types of distributed power sources, as well as preset targets; in this way, a large number of different types of distributed power sources can be aggregated into a virtual power plant, and the power grid can coordinate and dispatch a large number of different types of distributed power sources by dispatching the virtual power plant, thereby improving the controllability of the power grid within the power supply zone for a large number of different types of distributed power sources, reducing the impact of distributed power sources on power grid dispatch, and ensuring the safe and stable operation of the power grid; and, when constructing the virtual power plant based on the aggregates corresponding to different types of distributed power sources, the impact of the power consumption of the virtual power plant on the total load of the power supply zone is comprehensively considered. The requirements of the virtual power plant and the power exchange requirements between the virtual power plant and the power grid can improve the security of the virtual power plant grid-connected scheduling and the economy of the virtual power plant internal scheduling; and, taking into account the large number of distributed power sources, based on the first position information and first output power of multiple first distributed power sources, and the second position information of multiple second distributed power sources, multiple first distributed power sources and multiple second distributed power sources are aggregated to obtain multiple aggregates, and multiple distributed power sources of the same type with similar output power and close distance are aggregated into one aggregate, reducing the complexity of aggregating a large number of distributed power sources, and a large number of distributed power sources with low output voltage can be included in the power grid management, so as to more comprehensively and accurately reflect the response capability of the distributed power sources in the power supply zone, and further improve the power grid's regulation and control capabilities of the distributed power sources.

[0062] In an optional embodiment, step S102, based on the first location information and first output power of the plurality of first distributed power sources and the second location information of the plurality of second distributed power sources, the plurality of first distributed power sources and the plurality of second distributed power sources are aggregated to obtain a plurality of aggregates, such as Figure 2 As shown, including:

[0063] S1021: Aggregate the multiple first distributed power sources based on the first output powers of the multiple first distributed power sources to obtain multiple aggregated partitions.

[0064] In this embodiment, the output powers of first distributed power sources of the same type and in the same region generally have significant similarity. Therefore, they can be aggregated for easier regulation and management. The approach to aggregating multiple first distributed power sources can be as follows: using the first output power of the first distributed power source as a feature vector, using the L2 norm distance as a similarity criterion, and lumping two first distributed power sources whose L2 norm distance is less than a certain threshold into the same aggregated partition.

[0065] In an optional embodiment, step S1021, based on the first output powers of the plurality of first distributed power sources, aggregating the plurality of first distributed power sources to obtain a plurality of aggregated partitions includes:

[0066] A plurality of target first output powers are selected from a plurality of first output powers as characteristic vectors of a plurality of cluster centers; based on the characteristic vector of each cluster center and the characteristic vector distance constraint, the plurality of first output powers are clustered to corresponding cluster centers; the characteristic vector corresponding to each cluster center is re-determined, and the plurality of first output powers are clustered to corresponding cluster centers based on the characteristic vector of each cluster center and the characteristic vector distance constraint, until the difference between the characteristic vector corresponding to each re-determined cluster center and the characteristic vector corresponding to each cluster center determined in the previous iteration is less than a second threshold value.

[0067] In a specific implementation, the characteristic vector distance constraint condition can be that the L2 norm distance between the target first output power and other first output powers is less than a target threshold. The first output powers of k first distributed power supplies can be randomly extracted from all first distributed power supplies and used as the characteristic vectors of their cluster centers. Then, the remaining first distributed power supplies are traversed and, based on the characteristic vector distance constraint condition, the cluster centers closest to each of them are found and added to the cluster centers, thereby forming an initial clustering result. In this way, each cluster center has at least one first distributed power supply, and the characteristic vector of each cluster center can be calculated as a new characteristic vector. Then, all first distributed power supplies are traversed to find the cluster center closest to it and add it to the cluster center, thereby updating the aggregate partition. This is then iterated so that each cluster center has at least one first distributed power supply, and the characteristic vector of each cluster center can be calculated as a new characteristic vector. Then, all first distributed power supplies are traversed to find the cluster center closest to it and add it to the cluster center, thereby updating the aggregate partition. This is then repeated until the characteristic vector error of the cluster centers obtained from two iterations is less than a second threshold.

[0068] In this embodiment, by selecting multiple target first output powers from multiple first output powers as the characteristic vectors of multiple cluster centers and presetting the characteristic vector distance constraint conditions, multiple first distributed power sources with similar output powers can be quickly and accurately aggregated into a whole, which can simplify the aggregation complexity of a large number of distributed power sources into a virtual power plant.

[0069] S1022: Aggregate the plurality of second distributed power sources into a plurality of aggregation partitions based on the first location information and the second location information to obtain a plurality of aggregates.

[0070] In this embodiment, for the second distributed power source, its aggregation zone may be determined based on its second location information or the feeder to which it belongs. For example, the second distributed power source may be included in the aggregation zone corresponding to the first distributed power source that is closest to it.

[0071] In an optional embodiment, based on the first location information and the second location information, aggregating the plurality of second distributed power sources into a plurality of aggregation partitions includes:

[0072] Based on the first location information and the second location information, the distance between each second distributed power source and each first distributed power source is determined; based on the distance, the aggregation partition corresponding to each second distributed power source is determined; and each second distributed power source is aggregated into the corresponding aggregation partition.

[0073] In a specific implementation, the distance between each second distributed power source and each first distributed power source is determined based on the first location information and the second location information. When there is a first distributed power source within a distance of 3 km, the second distributed power source is included in the aggregation zone where the first distributed power source that is within 3 km and the closest distance is located; if there is no first distributed power source within a distance of 3 km, but there is a first distributed power source within a distance of 9 km, the second distributed power source is included in the aggregation zone where the first distributed power source that is on the same feeder and within a distance of 9 km and the closest distance is located; and if there is no first distributed power source on the same feeder, the second distributed power source is included in the aggregation zone where the first distributed power source that is within a distance of 9 km and the closest distance is located; otherwise, the second distributed power source is not included in any aggregation zone.

[0074] In this embodiment, since distributed power sources of the same type and in the same area have similar output power, the aggregation partition corresponding to each second distributed power source is determined based on the distance between each second distributed power source and each first distributed power source, so that the second distributed power sources can be aggregated to the aggregation partition closest to the distance, thereby improving the output power similarity between the first distributed power source and the second distributed power source in the aggregation partition.

[0075] In this embodiment, since there is no measured data on the second output power of the second distributed power supply, the multiple first distributed power supplies are first aggregated based on their first output powers, so that the multiple first distributed power supplies in each aggregated partition have similar first output powers. Then, based on the location information of the second distributed power supplies and the first distributed power supplies, the second distributed power supplies are aggregated, taking into account that distributed power supplies of the same type and in the same area have similar output powers, thereby achieving a high output power similarity between the first distributed power supply and the second distributed power supply in each aggregate.

[0076] In an optional embodiment, step S103, determining the second output power of the second distributed power source in each aggregate based on the first output power of the first distributed power source in each aggregate, includes:

[0077] Determine the first output power corresponding to the first distributed power supply in each aggregate and the second output power corresponding to the second distributed power supply; determine the relevant parameters between the first output power and the second output power in each aggregate; based on the first output power of the first distributed power supply in each aggregate and the corresponding relevant parameters, determine the second output power of the second distributed power supply in each aggregate.

[0078] In this embodiment, the availability of the second output power corresponding to the second distributed power supply is taken into account, and the correlation between the distributed power supply power data and the correlation between the power data are basically consistent. Therefore, the second output power of the second distributed power supply in each aggregate can be determined based on the first output power of the first distributed power supply in each aggregate.

[0079] In specific implementation, determining the second output power of the second distributed power source in each aggregate includes the following steps: (1) recording the set of output power of the distributed power source, that is, ; Where N is the number of distributed power sources contained in an aggregate, S i (2) Record the set of the first output power of the first distributed power source collected automatically, that is, Wherein, M is the number of the first distributed power sources that realize automatic collection of output power contained in an aggregate, P i is the first output power collected; (3) record the set of the second output power of the second distributed power source to be estimated, that is, ,in, is the second output power to be estimated; (4) the second output power is estimated using a linear estimation model, namely: , where F （N-M,M） is the relevant parameter to be solved, its subscript represents the number of rows and columns of the matrix, and the solution formula is as follows:

[0080] ,

[0081] in, inv is the matrix inversion operator; T (T>M) The number of data for output power; F(i) , i=M+1,…N , which means the matrix i The second distributed power supply i Related parameters.

[0082] In this embodiment, since the correlation between the distributed power supply power data and the correlation between the power data are basically consistent, by determining the relevant parameters between the first output power and the second output power in each aggregate; based on the first output power of the first distributed power supply in each aggregate, and the corresponding relevant parameters, the second output power of the second distributed power supply in each aggregate is determined, the second output power of the second distributed power supply in each aggregate can be determined more accurately.

[0083] In an optional embodiment, the output power similarity between the first distributed power source and the second distributed power source in the aggregate needs to be rolled over at regular intervals to accurately determine the second output power of the second distributed power source. Therefore, after determining the second output power of the second distributed power source in each aggregate, the virtual power plant construction method further includes:

[0084] Based on the second output power of the second distributed power supply in each aggregate, the estimated output power of the second distributed power supply in each aggregate is determined; if it is determined that the second distributed power supply in each aggregate needs to be re-aggregated based on the estimated output power and the second output power, the second distributed power supply in each aggregate is re-aggregated, and the second output power of the second distributed power supply in each aggregate is re-determined.

[0085] In this embodiment, based on the second output power of the second distributed power sources in each aggregate and the duration of the second output power collection, an estimated output power of the second distributed power sources in each aggregate can be calculated. The root mean square sum of the difference between the estimated output power and the second output power can then be calculated and compared with a third threshold. If the root mean square sum is less than the third threshold, there is no need to re-aggregate the second distributed power sources in each aggregate or perform calculations related to the first and second output powers in each aggregate. Otherwise, the second distributed power sources in each aggregate are re-aggregated, and the related parameters between the first and second output powers in each aggregate are re-calculated to redetermine the second output power of the second distributed power sources in each aggregate.

[0086] In an optional embodiment, step S104, based on the first output power of the first distributed power source and the second output power of the second distributed power source in each aggregate corresponding to the different types of distributed power sources, and the preset target, the aggregates corresponding to the different types of distributed power sources are aggregated to obtain multiple virtual power plants, such as Figure 3 As shown, including:

[0087] S1041, determining a first function corresponding to the first objective, a second function corresponding to the second objective, and a third function corresponding to the third objective.

[0088] S1042, based on the first output power of the first distributed power source and the second output power of the second distributed power source in each aggregate corresponding to different types of distributed power sources, solve the first function, the second function and the third function to obtain the number of virtual power plants in the power supply zone and the aggregates contained in each virtual power plant.

[0089] S1043 , based on the number of virtual power plants in the power supply zone and the aggregates contained in each virtual power plant, aggregate the aggregates to obtain a plurality of virtual power plants corresponding to the number.

[0090] In this embodiment, the first function corresponding to the first objective includes:

[0091] ;

[0092] in, is the equivalent load of the power supply partition, and the calculation formula is as follows. is its average value. T is the number of time periods in the day-ahead scheduling cycle.

[0093] ;

[0094] in, is the total load outside the virtual power plant in the power supply zone, is the power consumption of the virtual power plant g in the power supply zone, N VPP It is the number of virtual power plants formed by the aggregation of distributed power sources.

[0095] The second function includes:

[0096] ;

[0097] in, It is the interaction power between the virtual power plant and the external power grid under internal extreme load conditions.

[0098] ;

[0099] Among them, N WT is the number of wind power similarity aggregates, N PV is the number of photovoltaic similarity aggregates, N ES Represents the number of energy storage similarity aggregates, N HP Represents the number of hydroelectric similarity aggregates, N FL is the number of adjustable load similarity aggregates, N NFL is the number of unadjustable load similarity aggregates; It is the sign that the distributed generation corresponding to the subscript x belongs to the virtual power plant g; 、 、 They are the power of wind power, photovoltaic power and non-adjustable load under extreme load conditions. They are the optimized power of energy storage, hydropower and flexible loads respectively.

[0100] It is the interaction power between the virtual power plant and the external grid under normal internal load conditions, calculated through the virtual power plant's internal optimal scheduling. The objective function of the virtual power plant's internal optimal scheduling is to minimize the total power generation cost for the next day.

[0101] For the first and second objectives, the solution that makes the first and second objectives as balanced as possible is selected as the multi-objective optimal solution. The balance of the multi-objective optimal solution is achieved by calculating the information entropy of the solution:

[0102] ;

[0103] in, IS It is the information entropy dispersion of the multi-objective optimization solution, reflecting the differences in the values ​​of each objective function when the multi-objective optimization solution is adopted; p g Virtual Power Plant g The proportion of the objective function value in the total objective function value reflects the proportion of its target benefit; p sys It is the proportion of the objective function value of the power grid system in the total objective function value, reflecting the proportion of its target benefit;

[0104] .

[0105] The third function includes:

[0106] ;

[0107] Among them, the number of virtual power plants N VPP is a variable to be solved, and the virtual power plant ownership flag of the similarity aggregate is also a variable to be solved.

[0108] The first, second, and third functions should also satisfy the following constraints:

[0109] (1) Constraints of hydropower units: ① Upper and lower power limits; ② State transition constraints; ③ Minimum downtime constraints; ④ Minimum continuous operation time constraints.

[0110] (2) Energy storage constraints: ① Power upper and lower limit constraints; ② Charge and discharge state constraints; ③ SOC constraints.

[0111] (3) Constraints on the power purchased by virtual power plants.

[0112] (4) Virtual power plant identification constraint: An aggregate x can only belong to one virtual power plant or not belong to a virtual power plant.

[0113] In this embodiment, a genetic algorithm can be used to solve the first, second, and third functions. The specific solution process may include: A. Initializing the population: Initializing the number of individuals in the population, Npop, and the binary encoding value of each individual. The number of virtual power plants is encoded using a four-bit binary number (the maximum number of virtual power plants is 16), and the flag indicating whether each aggregate belongs to a virtual power plant is a 0-1 decision variable, encoded using a single binary number. B. Fitness calculation: For any individual in the population, decode its coding value to obtain the solution of the third function, that is, the number of virtual power plants and the sign of each aggregate belonging to the virtual power plant, and then perform the first function and second function calculations to determine the fitness function of each solution, that is, the information entropy discreteness IS of the multi-objective optimization solution; C. Convergence judgment: whether the fitness reaches the expected value or the number of iterations reaches the maximum value, if so, jump to G to end, otherwise continue; D. Selection: Sort by fitness from large to small, and select a certain proportion of individuals to enter the next generation; E. Crossover: Use a random crossover operator, that is, randomly select the cut position from the binary coding sequence of each individual, and cross the front and back to obtain a new individual; F. Mutation: Select individuals from the population for mutation with a certain probability. For the selected individuals, use a random mutation operator to randomly select one bit from its binary coding sequence for displacement, and then return to B; G. Output the optimal solution and end.

[0114] In this embodiment, by determining a first function corresponding to the first target, a second function corresponding to the second target, and a third function corresponding to the third target; then based on the first output power of the first distributed power source and the second output power of the second distributed power source in each aggregate corresponding to different types of distributed power sources, the first function, the second function, and the third function are solved to obtain the number of virtual power plants in the power supply partition and the aggregates contained in each virtual power plant, so that the number of virtual power plants in the power supply partition and the aggregates contained in each virtual power plant can be quickly determined, thereby quickly forming multiple virtual power plants.

[0115] The embodiment of the present application provides a virtual power plant construction device, such as Figure 4 As shown, including:

[0116] The acquisition module 41 is used to obtain the first location information and first output power of multiple first distributed power sources, and the second location information of multiple second distributed power sources for each type of distributed power source in the power supply zone; the output voltage of the first distributed power source is greater than or equal to the first threshold, and the output voltage of the second distributed power source is less than the first threshold.

[0117] The first aggregation module 42 is configured to aggregate the plurality of first distributed power sources and the plurality of second distributed power sources to obtain a plurality of aggregates based on the first location information and the first output power of the plurality of first distributed power sources and the second location information of the plurality of second distributed power sources.

[0118] The determination module 43 is configured to determine the second output power of the second distributed power source in each aggregate based on the first output power of the first distributed power source in each aggregate.

[0119] The second aggregation module 44 is used to aggregate the aggregates corresponding to different types of distributed power sources based on the first output power of the first distributed power source and the second output power of the second distributed power source in each aggregate corresponding to the different types of distributed power sources, and preset targets, to obtain multiple virtual power plants; the preset targets include a first target, a second target and a third target; the first target includes that when the power consumption of the virtual power plant is used as the load condition of the power supply partition, the first standard deviation of the total load of the power supply partition satisfies the first condition; the second target includes that under the target condition, the second standard deviation of the exchange power between the virtual power plant and the power grid in the power supply partition satisfies the second condition; the third target includes determining the number of virtual power plants and the aggregates contained in each virtual power plant, so that the sum of the second standard deviation of the exchange power between each virtual power plant and the power grid in the power supply partition and the first standard deviation satisfies the third condition.

[0120] The virtual power plant construction device provided in the embodiment of the present application obtains multiple virtual power plants by aggregating the aggregates corresponding to different types of distributed power sources based on the first output power of the first distributed power source and the second output power of the second distributed power source in each aggregate corresponding to different types of distributed power sources, as well as preset targets; in this way, a large number of different types of distributed power sources can be aggregated into a virtual power plant, and the power grid can coordinate and dispatch a large number of different types of distributed power sources through the dispatch of the virtual power plant, thereby improving the controllability of the power grid within the power supply zone for a large number of different types of distributed power sources, reducing the impact of distributed power sources on power grid dispatch, and ensuring the safe and stable operation of the power grid; and, when constructing the virtual power plant based on the aggregates corresponding to different types of distributed power sources, the impact of the power consumption of the virtual power plant on the total load of the power supply zone is comprehensively considered. The requirements of the virtual power plant and the power exchange requirements between the virtual power plant and the power grid can improve the security of the virtual power plant grid-connected scheduling and the economy of the virtual power plant internal scheduling; and, taking into account the large number of distributed power sources, based on the first position information and first output power of multiple first distributed power sources, and the second position information of multiple second distributed power sources, multiple first distributed power sources and multiple second distributed power sources are aggregated to obtain multiple aggregates, and multiple distributed power sources of the same type with similar output power and close distance are aggregated into one aggregate, reducing the complexity of aggregating a large number of distributed power sources, and a large number of distributed power sources with low output voltage can be included in the power grid management, so as to more comprehensively and accurately reflect the response capability of the distributed power sources in the power supply zone, and further improve the power grid's regulation and control capabilities of the distributed power sources.

[0121] According to an embodiment of the present application, the present application also provides an electronic device and a readable storage medium.

[0122] Figure 5 A schematic block diagram of an example electronic device 800 that can be used to implement an embodiment of the present application is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present application described and / or claimed herein.

[0123] like Figure 5As shown, electronic device 800 includes a computing unit 801, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 802 or a computer program loaded from a storage unit 808 into a random access memory (RAM) 803. RAM 803 may also store various programs and data required for the operation of electronic device 800. Computing unit 801, ROM 802, and RAM 803 are interconnected via a bus 804. An input / output (I / O) interface 805 is also connected to bus 804.

[0124] Multiple components in the electronic device 800 are connected to the I / O interface 805, including an input unit 806, such as a keyboard, a mouse, etc.; an output unit 807, such as various types of displays, speakers, etc.; a storage unit 808, such as a magnetic disk, an optical disk, etc.; and a communication unit 809, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 809 allows the electronic device 800 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0125] The computing unit 801 can be any general-purpose and / or specialized processing component with processing and computing capabilities. Some examples of the computing unit 801 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 801 performs the various methods and processes described above, such as the virtual power plant construction method. For example, in some embodiments, the virtual power plant construction method can be implemented as a computer software program tangibly embodied in a machine-readable medium, such as the storage unit 808. In some embodiments, part or all of the computer program can be loaded and / or installed onto the electronic device 800 via the ROM 802 and / or the communication unit 809. When the computer program is loaded into the RAM 803 and executed by the computing unit 801, one or more steps of the virtual power plant construction method described above can be performed. Alternatively, in other embodiments, the computing unit 801 can be configured to perform the virtual power plant construction method via any other suitable means (e.g., via firmware).

[0126] Various embodiments of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on a chip (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0127] The program code for implementing the methods of the present application can be written in any combination of one or more programming languages. Such program code can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the program code is executed by the processor or controller, the functions / operations specified in the flow charts and / or block diagrams are implemented. The program code can be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0128] In the context of this application, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or apparatus. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of machine-readable storage media may include an electrical connection based on one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), optical fibers, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0129] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0130] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), and the Internet.

[0131] A computer system may include a client and a server. The client and server are generally remote from each other and typically interact through a communication network. The client-server relationship arises through computer programs running on the respective computers and having a client-server relationship with each other. The server may be a cloud server, a server in a distributed system, or a server integrated with a blockchain.

[0132] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in this application can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions disclosed in this application can be achieved. This is not a limitation herein.

[0133] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features being referred to. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. Throughout the description of this application, "plurality" means two or more, unless otherwise specifically defined.

[0134] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A method for constructing a virtual power plant, characterized in that: include: For each type of distributed power source in the power supply zone, obtaining first location information and first output power of multiple first distributed power sources, and second location information of multiple second distributed power sources; the output voltage of the first distributed power source is greater than or equal to a first threshold, and the output voltage of the second distributed power source is less than the first threshold; Aggregating the plurality of first distributed power sources and the plurality of second distributed power sources based on the first location information and the first output power of the plurality of first distributed power sources and the second location information of the plurality of second distributed power sources to obtain a plurality of aggregates; Determining a second output power of a second distributed power source in each of the aggregates based on a first output power of a first distributed power source in each of the aggregates; Based on the first output power of the first distributed power source and the second output power of the second distributed power source in each of the aggregates corresponding to the different types of distributed power sources, and preset targets, the aggregates corresponding to the different types of distributed power sources are aggregated to obtain multiple virtual power plants; the preset targets include a first target, a second target and a third target; the first target is a grid dispatching operation target, which is equivalent to minimizing the peak-to-valley difference rate of the equivalent load of the power supply partition, smoothing the equivalent load curve, and minimizing the standard deviation of the equivalent load curve. The equivalent load refers to the total power supply load of the power supply partition taking into account the power consumption of the virtual power plant; The second goal is the virtual power plant scheduling and operation goal, which is equivalent to minimizing the standard deviation of the power exchange curve between the virtual power plant and the external power grid under extreme load conditions inside the virtual power plant. The third goal is to determine the number of virtual power plants and the aggregates contained in each virtual power plant, so that on the basis of the first and second goals, the scheduling and operation goals of the power grid and each virtual power plant can be optimized.

2. The method for constructing a virtual power plant according to claim 1, characterized in that: Based on the first location information and the first output power of the plurality of first distributed power sources and the second location information of the plurality of second distributed power sources, the plurality of first distributed power sources and the plurality of second distributed power sources are aggregated to obtain a plurality of aggregates, including: Aggregating the plurality of first distributed power sources based on the first output powers of the plurality of first distributed power sources to obtain a plurality of aggregated partitions; Based on the first location information and the second location information, a plurality of the second distributed power sources are aggregated into a plurality of the aggregation partitions to obtain a plurality of aggregates.

3. The method for constructing a virtual power plant according to claim 2, characterized in that: Aggregating the plurality of first distributed power sources based on the first output powers of the plurality of first distributed power sources to obtain a plurality of aggregated partitions, including: Selecting a plurality of target first output powers from the plurality of first output powers as feature vectors of a plurality of cluster centers; Clustering the plurality of first output powers to corresponding cluster centers based on the eigenvector of each cluster center and the eigenvector distance constraint; Re-determine the eigenvector corresponding to each cluster center, and iteratively execute the eigenvector based on each cluster center and the eigenvector distance constraint condition to cluster the multiple first output powers to the corresponding cluster centers until the difference between the eigenvector corresponding to each re-determined cluster center and the eigenvector corresponding to each cluster center determined in the previous iteration is less than the second threshold value.

4. The method for constructing a virtual power plant according to claim 2, wherein: Aggregating the plurality of second distributed power sources into the plurality of aggregation partitions based on the first location information and the second location information includes: determining, based on the first location information and the second location information, a distance between each of the second distributed power sources and each of the first distributed power sources; Determining, based on the distance, an aggregation partition corresponding to each of the second distributed power sources; Aggregate each of the second distributed power sources into the corresponding aggregation partition.

5. The method for constructing a virtual power plant according to claim 1, wherein: Determining, based on the first output power of the first distributed power source in each of the aggregates, the second output power of the second distributed power source in each of the aggregates, comprises: Determine a first output power corresponding to the first distributed power source and a second output power corresponding to the second distributed power source in each of the aggregates; determining a correlation parameter between the first output power and the second output power in each of the aggregates; Based on the first output power of the first distributed power source in each of the aggregates and the corresponding related parameters, the second output power of the second distributed power source in each of the aggregates is determined.

6. The method for constructing a virtual power plant according to claim 5, characterized in that: Also includes: Determining an estimated output power of the second distributed power source in each of the aggregates based on the second output power of the second distributed power source in each of the aggregates; If, based on the estimated output power and the second output power, it is determined that the second distributed power sources in each of the aggregates need to be reaggregated, the second distributed power sources in each of the aggregates are reaggregated, and the second output power of the second distributed power sources in each of the aggregates is re-determined.

7. The method for constructing a virtual power plant according to claim 1, wherein: Based on the first output power of the first distributed power source and the second output power of the second distributed power source in each of the aggregates corresponding to the different types of distributed power sources, and a preset target, the aggregates corresponding to the different types of distributed power sources are aggregated to obtain multiple virtual power plants, including: Determine a first function corresponding to the first objective, a second function corresponding to the second objective, and a third function corresponding to the third objective; Solving the first function, the second function, and the third function based on the first output power of the first distributed power source and the second output power of the second distributed power source in each of the aggregates corresponding to the different types of distributed power sources to obtain the number of virtual power plants in the power supply zone and the aggregates included in each virtual power plant; Based on the number of virtual power plants in the power supply partition and the aggregates contained in each virtual power plant, the aggregates are aggregated to obtain a plurality of virtual power plants corresponding to the number.

8. A virtual power plant construction device, characterized in that: include: an acquisition module, configured to acquire, for each type of distributed power source in a power supply zone, first location information and first output power of a plurality of first distributed power sources, and second location information of a plurality of second distributed power sources; an output voltage of the first distributed power source being greater than or equal to a first threshold, and an output voltage of the second distributed power source being less than the first threshold; a first aggregation module, configured to aggregate the plurality of first distributed power sources and the plurality of second distributed power sources based on the first location information and the first output power of the plurality of first distributed power sources and the second location information of the plurality of second distributed power sources to obtain a plurality of aggregates; a determining module, configured to determine a second output power of a second distributed power source in each of the aggregates based on the first output power of the first distributed power source in each of the aggregates; A second aggregation module is configured to aggregate the aggregates corresponding to different types of distributed power sources based on the first output power of the first distributed power source and the second output power of the second distributed power source in each of the aggregates corresponding to the different types of distributed power sources, and preset targets, to obtain multiple virtual power plants; the preset targets include a first target, a second target, and a third target; the first target is a grid dispatching operation target, which is equivalent to minimizing the peak-to-valley difference rate of the equivalent load of the power supply partition, smoothing the equivalent load curve, and minimizing the standard deviation of the equivalent load curve. The equivalent load refers to the total power supply load of the power supply partition taking into account the power consumption of the virtual power plant; The second goal is the virtual power plant scheduling and operation goal, which is equivalent to minimizing the standard deviation of the power exchange curve between the virtual power plant and the external power grid under extreme load conditions inside the virtual power plant. The third goal is to determine the number of virtual power plants and the aggregates contained in each virtual power plant, so that on the basis of the first and second goals, the scheduling and operation goals of the power grid and each virtual power plant can be optimized.

9. An electronic device, characterized in that: include: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor executes the virtual power plant construction method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the virtual power plant construction method according to any one of claims 1 to 7.

Images