A virtual power plant hierarchical control method and system based on resource clustering

Abstract

The application discloses a virtual power plant hierarchical control method and system based on resource clustering. The method comprises the following steps: clustering user resources according to basic data of the virtual power plant user resources to obtain a plurality of user resource groups; repeatedly performing an optimization operation according to the basic data of the plurality of user resource groups, taking the basic data corresponding to each user resource group when a preset target function converges as the output of each user resource group, and scheduling the virtual power plant according to the output of different user resource groups; wherein the optimization operation comprises the following steps: performing in-group optimization on the clustering center corresponding to each user resource group according to the basic data of the current user resource group to obtain an in-group optimized clustering center; performing hierarchical optimization on the in-group optimized clustering center according to a preset level, and updating the clustering center and the basic data of the corresponding user resource group according to the hierarchical optimized clustering center; and the efficiency of virtual power plant management and operation control is improved by implementing the method.

Description

Technical Field

[0001] This invention relates to the field of power system dispatching technology, and in particular to a hierarchical control method and system for virtual power plants based on resource clustering. Background Technology

[0002] To build a clean, low-carbon, safe, and efficient energy system, we must control the total amount of fossil fuels, focus on improving utilization efficiency, implement renewable energy substitution initiatives, deepen power system reform, and construct a new power system with new energy sources as the mainstay. In this new power system, virtual power plants promote the optimal allocation of power resources, maintain normal power supply and consumption, meet the electricity needs of the entire society, and provide reliable power security for socio-economic development and people's lives. Virtual power plants do not change the way each distributed power source is connected to the grid; instead, they aggregate different types of distributed energy sources such as distributed power sources, energy storage systems, controllable loads, and electric vehicles through advanced control, metering, and communication technologies. Through a higher-level software architecture, they achieve coordinated and optimized operation of multiple distributed energy sources, which is more conducive to the rational and optimized allocation and utilization of resources.

[0003] Numerous effective pilot projects of virtual power plants have been conducted in China. In pilot areas such as Jiangsu and Shenzhen, virtual power plants (aggregators) have organized resources (primarily adjustable loads) to respond. However, existing virtual power plants, based on the characteristics of individual users or power sources and demand-side load targets, primarily engage in transactions with users and power sources through single-point or aggregator-based demand response to grid regulation. This approach lacks optimization methods and experience for larger, more complex user resources in the future. Given current technological conditions, most virtual power plant pilot projects directly participate in grid dispatch and operation, controlling user resources, distributed energy sources, and energy storage devices in real time through dispatch and operation management platforms. This lack of overall coordination and optimization results in low management and operation control efficiency for virtual power plants. Summary of the Invention

[0004] This invention provides a hierarchical control method and system for virtual power plants based on resource clustering, which can effectively solve the problems of lack of overall coordination and optimization in existing virtual power plants and low management and operation control efficiency.

[0005] One embodiment of the present invention provides a hierarchical control method for virtual power plants based on resource clustering, comprising:

[0006] Acquire and statistically analyze basic data on virtual power plant user resources; wherein, the basic data includes the load regulation status, power connection status, input costs, input status, and output characteristics of user resources at different time periods;

[0007] Based on the aforementioned basic data, user resources are clustered to obtain several user resource groups;

[0008] Based on the basic data of several user resource groups, the optimization operation is repeatedly performed until the preset objective function converges. When the preset objective function converges, the basic data corresponding to each user resource group is used as the output of each user resource group.

[0009] Virtual power plant scheduling is performed based on the output of different user resource groups;

[0010] The optimization operations include:

[0011] Obtain the cluster center corresponding to each user resource group;

[0012] For each user resource group, the cluster center is optimized within the group based on the basic data of the current user resource group to obtain the optimized cluster center; the optimized cluster center is then further optimized at a preset level to obtain the hierarchically optimized cluster center.

[0013] Update the basic data of the corresponding user resource group based on the hierarchical optimized cluster centers;

[0014] The cluster centers optimized by the hierarchical structure will be used as the cluster centers corresponding to the current user resource group in the next optimization operation, and the updated basic data will be used as the basic data corresponding to the current user resource group in the next optimization operation.

[0015] Furthermore, based on the aforementioned basic data, user resources are clustered to obtain several user resource groups, including:

[0016] Obtain the optimization weights corresponding to each basic data point;

[0017] Based on the basic data and the optimization weights corresponding to each basic data point, user resources are clustered to obtain several user resource groups.

[0018] Furthermore, virtual power plant scheduling is performed based on the output of different user resource groups, including:

[0019] The total dispatch value of the virtual power plant is determined based on the output of different user resource groups;

[0020] Based on the total virtual power plant scheduling value, determine the regional scheduling value for each region in the regional layer;

[0021] Based on the regional scheduling value, determine the aggregator scheduling value for each aggregator in the aggregator layer;

[0022] Based on the aggregator scheduling value and the output of different user resource groups, the output of each user in the user layer is determined.

[0023] Furthermore, for each user resource group's corresponding cluster center, the cluster center is optimized within the group based on the current user resource group's basic data, resulting in optimized cluster centers, including:

[0024] The optimized cluster centers within the group are calculated using the following formula:

[0025] C = argminL(c);

[0026]

[0027] Where L(c) represents the distance of each user resource group from the cluster center; n is the number of user resource groups; Lh is the weighting coefficient of the center integration of each user resource group; β i β represents the location value of a data point within the current user resource group. k This is the location value of another data point within the current user resource group.

[0028] Furthermore, based on the hierarchically optimized cluster centers, the basic data of the corresponding user resource groups are updated, including:

[0029] Based on the hierarchical optimized cluster centers, extract the corresponding first load regulation status, first power connection status, first input cost, first input status, and first output characteristics;

[0030] The extracted first load adjustment status, first power connection status, first input cost, first input status, and first output characteristics are used as update data to update the basic data of the corresponding user resource group.

[0031] Furthermore, the optimized cluster centers within the group are further optimized hierarchically according to a preset level to obtain hierarchically optimized cluster centers, including:

[0032] The cluster centers optimized within the group are then optimized between different user resource groups to obtain cluster centers optimized between groups.

[0033] Update the basic data of the corresponding user resource group based on the optimized cluster centers between groups;

[0034] The cluster centers optimized between groups are used as the cluster centers corresponding to the user resource groups during hierarchical optimization, and the updated basic data are used as the basic data corresponding to the user resource groups during hierarchical optimization.

[0035] For each cluster center optimized between groups, the cluster centers are further optimized in a hierarchical manner according to the basic data of the user resource groups after the optimization between groups, so as to obtain the hierarchically optimized cluster centers.

[0036] Furthermore, the preset layers include: user layer, aggregator layer, and region layer.

[0037] As an improvement to the above solution, another embodiment of the present invention provides a hierarchical control system for a virtual power plant based on resource clustering, comprising:

[0038] The data acquisition module is used to acquire and statistically analyze the basic data of the virtual power plant user resources; wherein, the basic data includes the load regulation status, power connection status, input cost, input status and output characteristics of the user resources at different time periods;

[0039] The user resource group generation module is used to cluster user resources based on the basic data to obtain several user resource groups.

[0040] The optimization operation module is used to repeatedly perform optimization operations based on the basic data of several user resource groups until the preset objective function converges. When the preset objective function converges, the basic data corresponding to each user resource group is used as the output of each user resource group.

[0041] The scheduling module is used to schedule virtual power plants based on the output of different user resource groups.

[0042] The optimized operation module includes:

[0043] The current cluster center acquisition unit is used to acquire the cluster centers corresponding to each user resource group at present;

[0044] The hierarchical optimization unit is used to optimize the cluster centers corresponding to each user resource group within the group based on the basic data of the current user resource group, and obtain the optimized cluster centers within the group; then, the optimized cluster centers within the group are further optimized hierarchically according to a preset level to obtain the hierarchically optimized cluster centers.

[0045] The basic data update unit is used to update the basic data of the corresponding user resource group based on the hierarchically optimized cluster centers;

[0046] The center and data preparation unit are used to use the hierarchically optimized cluster centers as the cluster centers corresponding to the current user resource group in the next optimization operation, and to update the basic data as the basic data corresponding to the current user resource group in the next optimization operation.

[0047] Another embodiment of the present invention provides a terminal device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements a resource clustering-based hierarchical control method for virtual power plants as described in the above embodiments.

[0048] Another embodiment of the present invention provides a computer-readable storage medium including a stored computer program, wherein, when the computer program is executed, it controls the device where the computer-readable storage medium is located to perform a virtual power plant hierarchical control method based on resource clustering as described in the above embodiment.

[0049] By implementing this invention, at least the following beneficial effects are achieved:

[0050] This invention provides a hierarchical control method and system for virtual power plants based on resource clustering. The method acquires and statistically analyzes basic data of virtual power plant user resources. This basic data includes load regulation, power connection status, input costs, input characteristics, and output features of user resources at different time periods. Based on this basic data, user resources are clustered to obtain several user resource groups. Based on the basic data of these user resource groups, optimization operations are repeatedly performed until a preset objective function converges. When the preset objective function converges, the basic data corresponding to each user resource group is used as the output of that user resource group. Virtual power plant scheduling is performed based on the output of different user resource groups. The optimization operations include: acquiring the cluster centers corresponding to each user resource group; for each user resource group's cluster center, based on the current user... The basic data of user resource groups is used to optimize the cluster centers within the group, resulting in optimized cluster centers. These optimized cluster centers are then further optimized hierarchically according to a preset level, resulting in hierarchically optimized cluster centers. Based on these hierarchically optimized cluster centers, the basic data of the corresponding user resource groups is updated. The hierarchically optimized cluster centers are then used as the cluster centers for the current user resource groups in the next optimization operation, and the updated basic data is used as the basic data for the current user resource groups in the next optimization operation. By clustering similar user resources while performing hierarchical optimization on different types of user resources, the overall convergence is effectively enhanced. Then, based on the optimization results, hierarchical control of the virtual power plant is scheduled, providing a more comprehensive technical solution and strategy for the management and control of virtual power plant aggregators, thereby improving the efficiency of virtual power plant management and operation control. Attached Figure Description

[0051] Figure 1 This is a flowchart illustrating a hierarchical control method for a virtual power plant based on resource clustering, provided in an embodiment of the present invention.

[0052] Figure 2 This is a schematic diagram of the first structure of a hierarchical control system for a virtual power plant based on resource clustering, provided in an embodiment of the present invention.

[0053] Figure 3 This is a schematic diagram of the second structure of a hierarchical control system for a virtual power plant based on resource clustering, provided in an embodiment of the present invention.

[0054] Figure 4 This is a schematic diagram of an existing virtual power plant integration provided by an embodiment of the present invention.

[0055] Figure 5 This is a schematic diagram of a virtual power plant integration method based on resource clustering, provided by an embodiment of the present invention.

[0056] Figure 6 This is a flowchart of a hierarchical control method for a virtual power plant based on resource clustering, provided by an embodiment of the present invention.

[0057] Figure 7 This is an optimized operation flowchart of a hierarchical control method for virtual power plants based on resource clustering, provided by an embodiment of the present invention. Detailed Implementation

[0058] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0059] See Figure 1 This is a flowchart illustrating a hierarchical control method for a virtual power plant based on resource clustering, according to an embodiment of the present invention, comprising:

[0060] S1. Acquire and statistically analyze the basic data of virtual power plant user resources; wherein, the basic data includes the load regulation status, power connection status, input cost, input status and output characteristics of user resources at different time periods;

[0061] Specifically, a virtual power plant refers to a virtual consortium constructed using advanced communication, measurement, control technologies, and software systems. It achieves clustered aggregation and optimized control of resources such as distributed power sources, energy storage, controllable loads, and electric vehicles, and participates as a whole in grid dispatching and electricity market transactions. Its internal resources are spatially distributed rather than a centralized physical entity, hence the term "virtual." However, it functions collaboratively as a whole, achieving the same functions as a traditional power plant, hence the term "power plant." User resources within a virtual power plant refer to the distributed energy resources participating in the virtual power plant, including distributed power sources, controllable loads, microgrids, and electric vehicles. These user resources can function as part of a power coordination and management system within the virtual power plant, enabling the aggregation and collaborative optimization of distributed energy resources to participate in the electricity market and grid operation as a special type of power plant. By rationally allocating and optimizing these user resources, virtual power plants can alleviate grid pressure, provide local consumption capacity, and achieve more efficient energy utilization.

[0062] In a preferred embodiment of the present invention, the load regulation of resources at different times refers to the regulation of power supply by resources according to changes in power demand at different times (such as peak and off-peak periods), which is crucial for the stability of power supply; power linkage (the ability to resolve local congestion) involves the connection status between different parts of the power network system, and how to solve local congestion problems caused by power surplus or shortage in some parts; input refers to the amount of funds and manpower required to acquire and use user resources; input cost refers to the total cost of the invested resources; output characteristics refer to the characteristics of the output power after certain processing or transformation of user resources, such as voltage, current, and frequency. Acquiring basic data on virtual power plant user resources, and analyzing it using basic data such as the load regulation capability, power linkage, input cost, input situation, and output characteristics of user resources at different times, provides a data foundation for subsequent hierarchical control of the virtual power plant.

[0063] S2. Cluster the user resources based on the basic data to obtain several user resource groups;

[0064] In a preferred embodiment of the present invention, cluster analysis, also known as group analysis, is a statistical analysis method for studying the classification of (samples or indicators). It divides a dataset into different classes and clusters according to a certain indicator, maximizing the similarity of elements within each class. Clustering can help analysts distinguish different groups from a database, serving as a standalone tool to discover deeper information distributed within the database and to summarize the characteristics of each class, or to focus attention on a specific class for further analysis. In other words, it divides a large number of user resources into several groups, each group called a "user resource group" or "cluster." These user resource groups share certain common characteristics, allowing for optimization operations on different user resource groups.

[0065] Specifically, user resources are clustered based on the aforementioned basic data to obtain several user resource groups. This includes: obtaining the optimization weights corresponding to each piece of basic data; and clustering user resources based on the basic data and the corresponding optimization weights to obtain several user resource groups. User resources can be categorized into distributed energy resources, industrial users, commercial users, energy storage, and others. Based on scheduling requirements and expert evaluation, optimization weights are assigned to basic data such as load regulation, power link status, input costs, input conditions, and output characteristics. Then, based on the basic data and the corresponding optimization weights, user resources are weighted and clustered to obtain several user resource groups.

[0066] S3. Based on the basic data of several user resource groups, repeatedly perform optimization operations until the preset objective function converges. When the preset objective function converges, the basic data corresponding to each user resource group is used as the output of each user resource group.

[0067] The optimization operations include:

[0068] Obtain the cluster center corresponding to each user resource group;

[0069] For each user resource group, the cluster center is optimized within the group based on the basic data of the current user resource group to obtain the optimized cluster center; the optimized cluster center is then further optimized at a preset level to obtain the hierarchically optimized cluster center.

[0070] Update the basic data of the corresponding user resource group based on the hierarchical optimized cluster centers;

[0071] The cluster centers optimized by the hierarchical structure will be used as the cluster centers corresponding to the current user resource group in the next optimization operation, and the updated basic data will be used as the basic data corresponding to the current user resource group in the next optimization operation.

[0072] Specifically, intra-group optimization refers to continuously adjusting the cluster center of each user resource group; hierarchical optimization refers to dividing the virtual power plant into multiple layers of different sizes and optimizing according to the preset layers, which include: user layer, aggregator layer, and regional layer; aggregator (energy planning institute power aggregator) refers to a service provider that aggregates the electricity load on the user side to achieve more efficient power operation and utilization. Its main functions include load forecasting, scheduling, and control. It aggregates scattered small-amount electricity loads through technical means to realize energy and electricity trading such as virtual power plants and assist users in participating in electricity market competition; the overall optimization objective is MinF(x), xx∈D, where F(x) is the preset objective function, which often refers to the weighted average of the costs paid when the cost is lowest and the overall benefit is highest, x are various user resource variables, and D is the feasible region of user resource variables. That is, within the feasible region D, the preset objective function is solved to converge, and the basic data corresponding to each user resource group when the preset objective function converges is used as the output of each user resource group.

[0073] In a preferred embodiment of the present invention, such as Figure 7 As shown, the user resource network is initialized. The intra-cluster matching degree is calculated based on the cluster centers of the clustered user resource groups. Appropriate vectors and resources are selected for iterative intra-group learning. The distance between each cluster center is calculated by obtaining the cluster centers corresponding to the current user resource group. The initial cluster center values ​​for the user resource group are:

[0074] Where C0 is the feature vector value of the basic data of the cluster center; k is the initial number of user resources in the virtual power plant; Xn is the response vector value of a certain user resource; starting from the initial cluster center, intra-cluster optimization is first performed around the cluster centers of the user resource groups. For the cluster centers corresponding to each user resource group, intra-cluster optimization is performed on the cluster centers based on the basic data of the current user resource group to obtain the intra-cluster optimized cluster centers, including: the intra-cluster optimized cluster centers are calculated using the following formula:

[0075]

[0076] Where L(c) represents the distance of each user resource group from the cluster center; n is the number of user resource groups; Lh is the weighting coefficient of the center integration of each user resource group; β i β represents the location value of a data point within the current user resource group (the location value represents the state of various basic data values); k This is the location value of another data point within the current user resource group.

[0077] Preferably, the optimized cluster centers within the group are further optimized hierarchically according to a preset level to obtain hierarchically optimized cluster centers, including:

[0078] The cluster centers optimized within the group are then optimized between different user resource groups to obtain cluster centers optimized between groups.

[0079] Update the basic data of the corresponding user resource group based on the optimized cluster centers between groups;

[0080] The cluster centers optimized between groups are used as the cluster centers corresponding to the user resource groups during hierarchical optimization, and the updated basic data are used as the basic data corresponding to the user resource groups during hierarchical optimization.

[0081] For each cluster center optimized between groups, the cluster centers optimized between groups are further optimized in a hierarchical manner according to the basic data of the user resource groups after optimization between groups, so as to obtain the hierarchically optimized cluster centers.

[0082] After optimizing the cluster centers of user resource groups within the group, perform inter-group optimization according to different types of user resource groups, coordinate the basic data between various user resource groups, and obtain the inter-group optimized cluster centers. At this time, based on the inter-group optimized cluster centers, update the basic data of the corresponding user resource groups, and use the inter-group optimized cluster centers as the cluster centers corresponding to the subsequent hierarchical optimization of user resource groups. Use the updated basic data as the basic data corresponding to the user resource groups during hierarchical optimization. After inter-group optimization, for each inter-group optimized cluster center, perform hierarchical optimization based on the basic data of the inter-group optimized user resource groups, according to the user layer, aggregator layer, and region layer, to obtain the hierarchical optimized cluster centers.

[0083] Preferably, based on the hierarchically optimized cluster centers, the basic data of the corresponding user resource group is updated, including:

[0084] Based on the hierarchical optimized cluster centers, extract the corresponding first load regulation status, first power connection status, first input cost, first input status, and first output characteristics;

[0085] The extracted first load adjustment status, first power connection status, first input cost, first input status, and first output characteristics are used as update data to update the basic data of the corresponding user resource group.

[0086] Then, the cluster centers optimized by the hierarchical structure are used as the cluster centers corresponding to the current user resource group in the next optimization operation, and the updated basic data is used as the basic data corresponding to the current user resource group in the next optimization operation.

[0087] By clustering user resources and employing neural network technology based on the integrated structure of the virtual power plant, a process of classification, grouping, hierarchical iteration, and comprehensive optimization is constructed to effectively enhance the overall learning ability and convergence of the virtual power plant. Figure 5 As shown, the main system equipment includes distributed power sources, commercial loads, energy storage devices, electric vehicles, and industrial loads at the user layer. The aggregator platform at the aggregator layer controls these user resources, including distributed power sources, commercial loads, energy storage devices, electric vehicles, and industrial loads. Several aggregators then form a regional control and management platform, creating regional-level control and enabling more accurate and timely scheduling of various user resources. This differs from existing technologies. Figure 4 Virtual power plants mostly participate directly in grid dispatch and operation, controlling user resources in real time through the dispatch and operation management platform. When there are too many types and numbers of user resources, direct control and coordination lack overall optimization, and the control mode is relatively simple. When the dispatch of a certain user resource differs greatly from that of other user resources, due to the large number of controlled user resources, timely dispatch cannot be carried out, and personalized response is lacking. Over time, problems such as low market participation rate, low user-side participation rate, and low user-side response willingness will also emerge. Moreover, this direct control mode has corresponding technical bottlenecks in key operational technologies, such as flexible aggregation, information forecasting, capacity estimation, and benefit assessment, making it difficult to meet the future growth demand for user-side load regulation. The method in this embodiment finds the data structure in a low-dimensional space (two-dimensional or three-dimensional space) using basic data. A fully connected neural network is used in the user resource layer, and weight vectors are used to connect the input and competition layers. The neurons in the competition layer become the nodes most similar to the input nodes, preserving the topological nodes of the input space while achieving clustering. The processing status of each node (user, aggregator, region) is gradually adjusted by competing for neighboring neurons. Clustering effectively improves computational efficiency and reduces the number of calculations through comparisons between nodes of the same type. Simultaneously, considering the data transmission and computational capabilities of aggregator devices and smart terminals, the method of this invention can be effectively integrated into specific devices, improving the overall coordination capability and adaptability of the virtual power plant to the user side.

[0088] S4. Perform virtual power plant scheduling based on the output of different user resource groups;

[0089] Specifically, the total dispatch value of the virtual power plant is determined based on the output of different user resource groups;

[0090] Based on the total virtual power plant scheduling value, determine the regional scheduling value for each region in the regional layer;

[0091] Based on the regional scheduling value, determine the aggregator scheduling value for each aggregator in the aggregator layer;

[0092] Based on the aggregator scheduling value and the output of different user resource groups, determine the output of each user in the user layer;

[0093] In a preferred embodiment of the present invention, a suitable scheduling strategy is selected based on the output and optimization objectives of different user resource groups. The output of user resource groups is monitored in real time, and the scheduling strategy is adjusted based on this information to determine the total scheduling value of the virtual power plant. Based on the total scheduling value of the virtual power plant, the data that needs to be adjusted for each region in the regional layer is determined. The regional layer can summarize the actual situation of aggregators and user resources in the region, and then coordinate according to the regional scheduling value. For example, the power demand and load characteristics of different regions may be different. These characteristics may be peak and valley times, power consumption types, etc. The scheduling value allocated to each region is determined based on the total scheduling value and the power demand of the region, and the status of the energy storage system in the region also needs to be considered. Then each region obtains the regional scheduling value. The regional dispatch value is determined based on the number of aggregators responsible for the region and the actual situation of the aggregators, such as cost and dispatch costs between the region and the aggregators. When there are discrepancies in the dispatch values ​​among aggregators, the dispatch scheme of the aggregators is comprehensively considered based on cost. Controllers and computing modules are installed on the aggregator platform, and the regional dispatch value signal is processed through resource configuration sensors to obtain the aggregator dispatch value of each aggregator at the aggregator layer. The aggregator integrates user resources at the user layer and introduces these resources into market transactions. Based on the aggregator dispatch value and the output of different user groups, it can more accurately predict the electricity demand of each user and make real-time adjustments and controls according to changes in the actual electricity market and power system to determine the output of each user at the user layer.

[0094] By implementing this embodiment, the efficiency of virtual power plant aggregator management and operation control is effectively improved, resulting in better stability of the dispatching process, ensuring users' economic benefits, and demonstrating strong universality. It provides technical support for the application of virtual power plants and plays a positive role in promoting the virtual power plant model under the new energy structure. Figure 6 Based on the basic data of virtual power plant user resources, clustering is performed to obtain user resource groups of the same type. Then, the cluster centers of the user resource groups are optimized within the group to obtain optimized cluster centers. The optimized cluster centers are then further optimized hierarchically according to a preset level. Based on the cluster centers obtained after hierarchical optimization, the output of each user resource group is obtained, and the virtual power plant is then scheduled. By clustering user resources of the same type and performing hierarchical optimization on user resources of different types, the overall convergence is effectively enhanced. This provides a more complete technical solution and strategy for the management and control of virtual power plant aggregators, thereby improving the efficiency of virtual power plant management and operation control.

[0095] See Figure 2 This is a first structural schematic diagram of a hierarchical control system for a virtual power plant based on resource clustering, provided in an embodiment of the present invention, comprising:

[0096] The data acquisition module is used to acquire and statistically analyze the basic data of the virtual power plant user resources; wherein, the basic data includes the load regulation status, power connection status, input cost, input status and output characteristics of the user resources at different time periods;

[0097] The user resource group generation module is used to cluster user resources based on the basic data to obtain several user resource groups.

[0098] The optimization operation module is used to repeatedly perform optimization operations based on the basic data of several user resource groups until the preset objective function converges. When the preset objective function converges, the basic data corresponding to each user resource group is used as the output of each user resource group.

[0099] The scheduling module is used to schedule virtual power plants based on the output of different user resource groups.

[0100] Among them, such as Figure 3 As shown, the optimized operation module includes:

[0101] The current cluster center acquisition unit is used to acquire the cluster centers corresponding to each user resource group at present;

[0102] The hierarchical optimization unit is used to optimize the cluster centers corresponding to each user resource group within the group based on the basic data of the current user resource group, and obtain the optimized cluster centers within the group; then, the optimized cluster centers within the group are further optimized hierarchically according to a preset level to obtain the hierarchically optimized cluster centers.

[0103] The basic data update unit is used to update the basic data of the corresponding user resource group based on the hierarchically optimized cluster centers;

[0104] The center and data preparation unit are used to use the hierarchically optimized cluster centers as the cluster centers corresponding to the current user resource group in the next optimization operation, and to update the basic data as the basic data corresponding to the current user resource group in the next optimization operation.

[0105] This invention provides a hierarchical control system for a virtual power plant based on resource clustering. The system acquires and statistically analyzes basic data of virtual power plant user resources using a data acquisition module. This basic data includes load regulation, power connection status, input costs, input characteristics, and output features of user resources at different time periods. A user resource group generation module clusters the user resources based on this basic data to obtain several user resource groups. In an optimization operation module, optimization operations are repeatedly performed based on the basic data of these user resource groups until a preset objective function converges. When the preset objective function converges, the basic data corresponding to each user resource group is used as the output of that user resource group. Finally, in a scheduling module, virtual power plant scheduling is performed based on the output of different user resource groups. The optimization operation module... The module includes: a current cluster center acquisition unit, used to acquire the cluster centers corresponding to each user resource group; a hierarchical optimization unit, used to optimize the cluster centers for each user resource group within the group based on the basic data of the current user resource group, obtaining the optimized cluster centers; and then performing hierarchical optimization on the optimized cluster centers according to a preset hierarchy, obtaining the hierarchically optimized cluster centers; a basic data update unit, used to update the basic data of the corresponding user resource group based on the hierarchically optimized cluster centers; and a center and data preparation unit, used to use the hierarchically optimized cluster centers as the cluster centers corresponding to the current user resource group in the next optimization operation, and to use the updated basic data as the basic data corresponding to the current user resource group in the next optimization operation. By clustering similar user resources and performing hierarchical optimization operations on different types of user resources, the overall convergence is effectively enhanced, providing a more complete technical solution and strategy for the management and control of virtual power plant aggregators, and improving the efficiency of virtual power plant management and operation control.

[0106] It should be noted that the system embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Furthermore, in the accompanying drawings of the system embodiments provided by this invention, the connection relationships between modules indicate that they have communication connections, which can be specifically implemented as one or more communication buses or signal lines. Those skilled in the art can understand and implement this without any creative effort.

[0107] Those skilled in the art will understand that, for convenience and brevity, the specific working process of the system described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0108] Another embodiment of the present invention provides a terminal device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements a resource clustering-based hierarchical control method for virtual power plants as described in the above embodiments. The terminal device may be a desktop computer, laptop, handheld computer, or cloud server, etc. The terminal device may include, but is not limited to, a processor and a memory.

[0109] The processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor. The processor is the control center of the terminal device, connecting various parts of the terminal device via various interfaces and lines.

[0110] The memory can be used to store the computer program. The processor implements various functions of the terminal device by running or executing the computer program stored in the memory and calling data stored in the memory. The memory may mainly include a program storage area and a data storage area. The program storage area may store the operating system, at least one application program required for a function, etc.; the data storage area may store data created based on the use of the mobile phone, etc. In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as hard disk, RAM, plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0111] Another embodiment of the present invention provides a computer-readable storage medium including a stored computer program, wherein, when the computer program is executed, it controls the device where the computer-readable storage medium is located to perform a virtual power plant hierarchical control method based on resource clustering as described in the above embodiment.

[0112] The storage medium is a computer-readable storage medium, and the computer program is stored in the computer-readable storage medium. When executed by a processor, the computer program can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable file, or some intermediate form. The computer-readable medium can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc.

[0113] The above description represents the preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of the present invention, and these improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A hierarchical control method for virtual power plants based on resource clustering, characterized in that, include: Acquire and statistically analyze basic data on virtual power plant user resources; wherein, the basic data includes the load regulation status, power connection status, input costs, input status, and output characteristics of user resources at different time periods; Based on the aforementioned basic data, user resources are clustered to obtain several user resource groups; Based on the basic data of several user resource groups, the optimization operation is repeatedly performed until the preset objective function converges. When the preset objective function converges, the basic data corresponding to each user resource group is used as the output of each user resource group. Virtual power plant scheduling is performed based on the output of different user resource groups; The optimization operations include: Obtain the cluster center corresponding to each user resource group; For each user resource group, the cluster center is optimized within the group based on the basic data of the current user resource group to obtain the optimized cluster center; the optimized cluster center is then further optimized at a preset level to obtain the hierarchically optimized cluster center. Update the basic data of the corresponding user resource group based on the hierarchical optimized cluster centers; The cluster centers optimized by the hierarchical structure will be used as the cluster centers corresponding to the current user resource group in the next optimization operation, and the updated basic data will be used as the basic data corresponding to the current user resource group in the next optimization operation.

2. The hierarchical control method for virtual power plants based on resource clustering as described in claim 1, characterized in that, Based on the aforementioned basic data, user resources are clustered to obtain several user resource groups, including: Obtain the optimization weights corresponding to each basic data point; Based on the basic data and the optimization weights corresponding to each basic data point, user resources are clustered to obtain several user resource groups.

3. The hierarchical control method for virtual power plants based on resource clustering as described in claim 1, characterized in that, Virtual power plant scheduling is performed based on the output of different user resource groups, including: The total dispatch value of the virtual power plant is determined based on the output of different user resource groups; Based on the total virtual power plant scheduling value, determine the regional scheduling value for each region in the regional layer; Based on the regional scheduling value, determine the aggregator scheduling value for each aggregator in the aggregator layer; Based on the aggregator scheduling value and the output of different user resource groups, the output of each user in the user layer is determined.

4. The hierarchical control method for virtual power plants based on resource clustering as described in claim 1, characterized in that, For each user resource group, the cluster centers are optimized within the group based on the basic data of the current user resource group, resulting in optimized cluster centers, including: The optimized cluster centers within the group are calculated using the following formula: wherein L(c) is the position of each user resource group distance clustering center; n is the number of user resource groups; Lh is the weighted coefficient of the center integration of each user resource group; β i is the position value of a data point in the current user resource group; β k is the position value of another data point in the current user resource group.

5. The hierarchical control method for virtual power plants based on resource clustering as described in claim 1, characterized in that, Based on the optimized cluster centers, update the basic data for the corresponding user resource groups, including: Based on the hierarchical optimized cluster centers, extract the corresponding first load regulation status, first power connection status, first input cost, first input status, and first output characteristics; The extracted first load adjustment status, first power connection status, first input cost, first input status, and first output characteristics are used as update data to update the basic data of the corresponding user resource group.

6. The hierarchical control method for virtual power plants based on resource clustering as described in claim 1, characterized in that, The step of performing hierarchical optimization of the optimized cluster centers within the group according to a preset level to obtain hierarchically optimized cluster centers includes: The cluster centers optimized within the group are then optimized between different user resource groups to obtain cluster centers optimized between groups. Update the basic data of the corresponding user resource group based on the optimized cluster centers between groups; The cluster centers optimized between groups are used as the cluster centers corresponding to the user resource groups during hierarchical optimization, and the updated basic data are used as the basic data corresponding to the user resource groups during hierarchical optimization. For each cluster center optimized between groups, the cluster centers are further optimized in a hierarchical manner according to the basic data of the user resource groups after the optimization between groups, so as to obtain the hierarchically optimized cluster centers.

7. The hierarchical control method for virtual power plants based on resource clustering as described in claim 1, characterized in that, The preset layers include: user layer, aggregator layer, and region layer.

8. A hierarchical control system for a virtual power plant based on resource clustering, characterized in that, include: The data acquisition module is used to acquire and statistically analyze the basic data of the virtual power plant user resources; wherein, the basic data includes the load regulation status, power connection status, input cost, input status and output characteristics of the user resources at different time periods; The user resource group generation module is used to cluster user resources based on the basic data to obtain several user resource groups. The optimization operation module is used to repeatedly perform optimization operations based on the basic data of several user resource groups until the preset objective function converges. When the preset objective function converges, the basic data corresponding to each user resource group is used as the output of each user resource group. The scheduling module is used to schedule virtual power plants based on the output of different user resource groups. The optimized operation module includes: The current cluster center acquisition unit is used to acquire the cluster centers corresponding to each user resource group at present; The hierarchical optimization unit is used to optimize the cluster centers corresponding to each user resource group within the group based on the basic data of the current user resource group, and obtain the optimized cluster centers within the group; then, the optimized cluster centers within the group are further optimized hierarchically according to a preset level to obtain the hierarchically optimized cluster centers. The basic data update unit is used to update the basic data of the corresponding user resource group based on the hierarchically optimized cluster centers; The center and data preparation unit are used to use the hierarchically optimized cluster centers as the cluster centers corresponding to the current user resource group in the next optimization operation, and to update the basic data as the basic data corresponding to the current user resource group in the next optimization operation.

9. A terminal device, characterized in that, The system includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor, when executing the computer program, implements a resource clustering-based hierarchical control method for virtual power plants as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored computer program, wherein, when the computer program is executed, it controls the device where the computer-readable storage medium is located to perform a hierarchical control method for a virtual power plant based on resource clustering as described in any one of claims 1 to 7.

Images