Controllable load and virtual power plant bilateral matching method and system

Abstract

The invention provides a controllable load and virtual power plant bilateral matching method and system, and belongs to the technical field of virtual power plants. The method comprises the following steps: in response to a selected selection intention request of a current VPP, obtaining a controllable load set composed of controllable loads selecting the current VPP; clustering the controllable capacities of the controllable loads in the controllable load set to obtain a controllable load clustering combination with the maximum function value of the VPP target function, receiving the selection intention of each controllable load in the controllable load clustering combination with the maximum function value of the VPP target function, and according to the controllable capacities of the controllable loads received by the current VPP, selecting the controllable loads in the controllable load clustering combination with the maximum function value of the VPP target function; regulating and controlling the capacity of the current VPP; and when the regulation and control capacity of the VPP meets the regulation and control capacity requirement, taking each controllable load accepted by the current VPP as a bilateral matching result of the current VPP. And establishing a bilateral matching mechanism of the VPP and the controllable load, and realizing efficient aggregation of the VPP and the controllable load.

Description

Technical Field

[0001] The present invention relates to the technical field of virtual power plants, and in particular to a controllable load and virtual power plant bilateral matching method, a controllable load and virtual power plant bilateral matching system, a machine-readable storage medium and an electronic device. Background Art

[0002] With the access of a large number of distributed resources such as renewable energy, energy storage and controllable loads to the power grid, giving full play to the potential of power grid regulation has become the key to building a new power system. In this context, virtual power plants (VPPs) aggregate multiple types of distributed resources through advanced communication, regulation and metering technologies to achieve stable and reliable overall output, which is a flexible way to manage distributed resources.

[0003] As a specific form and basic unit of the energy Internet, the virtual power plant organically combines distributed power sources, controllable loads and energy storage systems within a certain range, and merges them into a whole through the control center to participate in the operation of the power grid. The dispatch optimization mechanism of the virtual power plant under the energy Internet mainly includes three aspects: natural aggregation, economic incentives and operational coordination. Natural aggregation refers to the use of data obtained by the information-physical system in the context of the Internet of Things, and the introduction of artificial intelligence technology in the aggregation process of the virtual power plant to cluster the load curve. It mainly includes two parts: one is to analyze data characteristics and reduce the dimension of data; the other is to study the corresponding clustering analysis algorithm to obtain load curve clusters with relevant characteristics. By analyzing the characteristics of different clusters, multiple resources are aggregated into a whole with stable output and in line with the operation requirements of the power grid. Natural aggregation is a prerequisite for economic incentives and operational coordination of virtual power plants.

[0004] In recent years, the reform of the power market and the construction of the energy Internet have greatly promoted the development of virtual power plants. Driven by the scale benefits of aggregation, virtual power plants aggregate cross-regional and multi-type controllable distributed resources to give full play to the flexibility and complementarity of resources. The controllable distributed resources involved in the aggregation have the characteristics of large number and large performance differences. Therefore, it is of great significance to improve the aggregation management capabilities of internal resources and obtain aggregation characteristics. The existing technology is usually based on the one-way selection of VPP to controllable load or controllable load to VPP. However, in reality, VPP and controllable load are both rational subjects, and both parties of the aggregation have the right to choose and refuse, that is, the aggregation of VPP and controllable load should be a bilateral matching problem. In addition, in the incomplete information market, some VPPs and controllable loads do not have the ability to search for information and negotiate, resulting in the spontaneous bilateral matching of VPP and controllable loads, which is often difficult to aggregate due to high transaction costs. Therefore, how to fully consider the matching cooperation tendency of VPP and controllable loads and construct a bilateral matching mechanism for the control interaction system of VPP and controllable loads to achieve efficient aggregation of VPP and controllable loads is an urgent problem to be solved. Summary of the invention

[0005] The purpose of the embodiments of the present invention is to provide a method and system for bilateral matching of controllable loads and virtual power plants, so as to at least solve the above-mentioned problem of how to fully consider the matching cooperation tendency of VPP and controllable loads, construct a bilateral matching mechanism of VPP and controllable loads, and realize efficient aggregation of VPP and controllable loads.

[0006] In order to achieve the above object, the first aspect of the present invention provides a controllable load and virtual power plant bilateral matching method, comprising:

[0007] In response to a selection intention request of a current VPP being selected, a controllable load set consisting of controllable loads of the current VPP is obtained;

[0008] Cluster the controllable capacities of the controllable loads in the controllable load set, obtain the controllable load cluster combination with the largest function value of the VPP objective function based on the clustering results and the controllable capacity demand, and accept the selection intention of each controllable load in the controllable load cluster combination with the largest function value of the VPP objective function, so as to control the capacity of the current VPP according to the controllable capacity of each controllable load accepted by the current VPP; wherein the VPP objective function is constructed based on the aggregated income data and cooperation tendency index data of the controllable load cluster combination, and the cooperation tendency index data is used to characterize the degree of cooperation willingness of each controllable load in the controllable load cluster combination with the VPP;

[0009] When the control capacity of the VPP meets the control capacity demand, the controllable loads accepted by the current VPP are taken as the bilateral matching result of the current VPP.

[0010] Optionally, the controllable load performs VPP selection to generate the selection intention request rules including:

[0011] A1: According to the aggregated revenue generated by the controllable load joining each VPP, determine the intended VPP corresponding to the controllable load, and sort the cooperation tendency of the controllable load to each intended VPP according to the aggregated revenue generated by the controllable load joining each intended VPP, and obtain the ranking result of the cooperation tendency corresponding to the controllable load; among which, the greater the aggregated revenue generated by the controllable load joining the intended VPP, the greater the cooperation tendency of the controllable load to the intended VPP;

[0012] A2: Based on the cooperation tendency ranking results corresponding to the controllable loads, a selection intention request is sent to each VPP in turn until the current controllable load is matched or all VPPs are matched.

[0013] Optionally, the determination rule of the intended VPP corresponding to the controllable load includes:

[0014] Get the tolerance U of the controllable load m ; Among them, the tolerance of controllable load U m The number of VPPs that the controllable load is willing to join is U m ;

[0015] According to the aggregated benefits generated by adding controllable loads to each VPP, the ranking value of the aggregated benefits is not greater than U m The VPP with the highest aggregated revenue value greater than U m The cooperation tendency of the VPP is set to zero.

[0016] Optionally, the above rule for clustering the adjustable capacities of the controllable loads in the controllable load set includes:

[0017] B1: Perform agglomerative hierarchical clustering analysis on the controllable capacity of the controllable loads in the controllable load set to obtain the controllable capacity data of the controllable loads of a preset number of clusters, and calculate the average value of the controllable capacity data of the controllable loads of each cluster, and determine the cluster center of each cluster based on the average value of the controllable capacity data of each cluster;

[0018] B2: Using k-means clustering, calculate the distance between the controllable capacity data of each controllable load and each cluster center, and classify each controllable load into the cluster corresponding to the cluster center with the closest distance;

[0019] B3: Recalculate the cluster centers of each cluster to determine whether the cluster centers of each cluster have changed. If the cluster center of any cluster has changed, use the calculated cluster centers of each cluster to update the cluster centers. Repeat B2 to B3 until the cluster centers no longer change or there is no cluster to which the controllable load is reallocated.

[0020] Optionally, after clustering the adjustable capacities of the controllable loads in the controllable load set, the method further includes:

[0021] The clustering results were evaluated based on the Davies-Bouldin index;

[0022] Among them, the calculation rules of the Davies-Bouldin indicator include:

[0023] According to the formula Calculate the ratio of the average distance between each data point in the cluster and the cluster center of the corresponding cluster to the distance between the cluster centers of each cluster. Based on the ratio calculation results, evaluate the clustering results. Where k is the number of clusters, h is the distance between the cluster centers of each cluster. i is the average distance from the data point of the controllable capacity data of each controllable load in the i-th cluster to the cluster center of the cluster, g ij is the distance between the cluster center of the i-th cluster and the cluster center of the j-th cluster, I DBI The smaller the value, the better the clustering effect.

[0024] Optionally, the construction rules of the above VPP objective function include:

[0025] According to the aggregated revenue data and cooperation tendency index data of the controllable load cluster combination, the formula for determining the VPP objective function is: in, is the maximum aggregated benefit of the nth VPP in all controllable load cluster combinations, is the correction coefficient of the cooperation tendency index, represents the aggregated benefit of the cooperation tendency indicator, It represents the aggregated revenue data after the controllable load in the nth VPP and controllable load cluster combination is aggregated. It represents the cooperation tendency index, which represents the average value of the cooperation tendency degree of each controllable load in the controllable load cluster combination to the nth VPP.

[0026] Optionally, the construction rules of the above VPP objective function also include:

[0027] Determine the threshold constraints of the cooperation tendency indicator;

[0028] Among them, the threshold constraints of the cooperation tendency index include:

[0029] If the controllable load cooperation tendency index value of the controllable load cluster combination is lower than the preset VPP cooperation tendency index threshold value I0, it indicates that the VPP refuses to cooperate with the controllable load cluster combination.

[0030] A second aspect of the present invention provides a controllable load and virtual power plant bilateral matching system, comprising:

[0031] A request response module, used to respond to the selection intention request of the current VPP to obtain a controllable load set consisting of controllable loads that select the current VPP;

[0032] A clustering module is used to cluster the adjustable capacities of the controllable loads in the controllable load set, obtain the controllable load cluster combination with the maximum function value of the VPP objective function based on the clustering results and the adjustable capacity demand, and accept the selection intention of each controllable load in the controllable load cluster combination with the maximum function value of the VPP objective function, so as to adjust the capacity of the current VPP according to the adjustable capacity of each controllable load accepted by the current VPP; wherein the VPP objective function is constructed based on the aggregated income data and cooperation tendency index data of the controllable load cluster combination, and the cooperation tendency index data is used to characterize the degree of cooperation willingness of each controllable load in the controllable load cluster combination with the VPP;

[0033] The control capacity judgment module is used to take each controllable load accepted by the current VPP as the bilateral matching result of the current VPP when the control capacity of the VPP meets the control capacity demand.

[0034] In a third aspect of the present invention, a machine-readable storage medium is provided, on which instructions are stored. When the instructions are executed by a processor, the processor is configured to execute the above-mentioned controllable load and virtual power plant bilateral matching method.

[0035] In a fourth aspect of the present invention, an electronic device is provided, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the controllable load and virtual power plant bilateral matching method when executing the computer program.

[0036] Through the above technical scheme, a controllable load and virtual power plant bilateral matching method and system are provided. According to the selection intention request of each controllable load that selects the current VPP, a controllable load set that selects the current VPP is obtained. After clustering the adjustable capacity of the controllable loads in the controllable load set, based on the clustering results and the control capacity demand, the controllable load cluster combination with the largest function value of the VPP objective function is obtained, and the selection intention of each controllable load in the controllable load cluster combination with the largest function value of the VPP objective function is accepted. According to the adjustable capacity of each controllable load accepted by the current VPP, the capacity of the current VPP is regulated. The VPP objective function is constructed based on the aggregated income data and cooperation tendency index data of the controllable load cluster combination. Therefore, in the process of selecting the optimal controllable load cluster combination, in addition to taking economic benefits as the main goal, the VPP also needs to consider the willingness of each controllable load in the controllable load cluster combination to cooperate, so as to further ensure that the VPP and the controllable load complete matching and cooperation. When the control capacity of the VPP meets the control capacity demand, the controllable loads accepted by the current VPP are taken as the bilateral matching results of the current VPP. The method and system fully consider the matching cooperation tendency of VPP and controllable loads. The aggregation of VPP and controllable loads is a mutual selection process. Both parties of the aggregation have the right to choose and refuse. Each VPP and each controllable load independently selects each other's cooperation objects under their own constraints with the goal of maximizing the aggregation benefits. Thus, a bilateral matching mechanism for VPP and controllable loads is established, and efficient aggregation of VPP and controllable loads is achieved.

[0037] Other features and advantages of the embodiments of the present invention will be described in detail in the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] The accompanying drawings are used to provide a further understanding of the embodiments of the present invention and constitute a part of the specification. Together with the following specific embodiments, they are used to explain the embodiments of the present invention, but do not constitute a limitation on the embodiments of the present invention. In the accompanying drawings:

[0039] Figure 1 It is a flow chart of a controllable load and virtual power plant bilateral matching method provided by one embodiment of the present invention;

[0040] Figure 2 It is a VPP control interaction system architecture diagram provided by an embodiment of the present invention;

[0041] Figure 3 is a schematic diagram of a clustering rule provided by an embodiment of the present invention;

[0042] Figure 4 A VPP and controllable load bilateral matching selection flow chart provided in one embodiment of the present invention;

[0043] Figure 5 It is a block diagram of a controllable load and virtual power plant bilateral matching system provided by one embodiment of the present invention;

[0044] Figure 6 It is a schematic diagram of the structure of an electronic device provided by a preferred embodiment of the present invention.

[0045] Description of Reference Numerals

[0046] 10 - electronic device, 100 - processor, 101 - memory, 102 - computer program. DETAILED DESCRIPTION

[0047] The specific implementation of the present invention is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described here is only used to illustrate and explain the present invention, and is not used to limit the present invention.

[0048] Figure 1 FIG. 1 is a flow chart of a controllable load and virtual power plant bilateral matching method provided by an embodiment of the present invention. Figure 1 As shown, an embodiment of the present invention provides a controllable load and a virtual power plant bilateral matching method, comprising:

[0049] S110: In response to a selection intention request of the current VPP being selected, a controllable load set consisting of controllable loads of the current VPP is obtained;

[0050] Please refer to Figure 2 , Figure 2It is a VPP control interaction system architecture diagram provided by an embodiment of the present invention. Virtual power plant (VPP) aggregates various types of distributed resources through advanced communication technology, control technology and metering technology, thereby improving the reliability and stability of the overall output of the system. It is a flexible distributed resource management method. In this application, the virtual power plant model is mainly composed of photovoltaic power generation units, wind power generation units, battery energy storage units and local controllable load units. These local controllable load units are collectively referred to as controllable loads in this application according to their characteristics of participating in VPP regulation. Among them, photovoltaic power generation units and wind power generation units will have controllable characteristics by combining with energy storage power stations. In this application, the battery energy storage unit is mainly composed of battery energy storage stations, user energy storage batteries, electric vehicle batteries, etc. The battery energy storage unit can perform battery charging / discharging operations according to the regulation needs of VPP, wherein the state of the battery can be described by the change of the state of charge SOC caused by its own charging / discharging, and SOC is the ratio of the remaining power of the battery to the rated capacity. The local controllable load unit in this application mainly refers to loads with load adjustable characteristics, including residential users, commercial users, public resource users, and industrial users. In order to take into account the competitiveness of VPP centralized control and the computing power of distributed control, this application adopts a "centralized + decentralized" VPP hybrid control mode. The VPP control interaction system architecture constructed by this application is shown in the figure below. Figure 2 As shown. First, a master controller is set in the VPP. The master controller clusters the loads participating in VPP regulation through a clustering algorithm to form multiple virtual machine groups. A sub-controller is set for the regional load. The sub-controller organizes the information of the controllable loads in the area. At the same time, all controllable loads in the area are equipped with intelligent control switches. The sub-controller controls the controllable loads through the intelligent control switches and adjusts the adjustable capacity of the controllable loads according to the regulation requirements. The main tasks of the VPP sub-controller in this application include the following three aspects: (1) Performance evaluation and classification of the controllable loads belonging to the sub-controller; (2) Recording the adjustable capacity information of the controllable loads belonging to the sub-controller; (3) Intelligent control and management of the controllable loads, and at the same time has the function of recording the willingness of the controllable loads to participate in VPP regulation, and reporting to the master controller.

[0051] Specifically, from a practical analysis, the aggregation of VPP and controllable loads is a process of mutual selection. In the process of mutual matching and selection of VPP and controllable loads, it is necessary to fully consider the selection tendency of both VPP and controllable load subjects for cooperation objects. At the same time, considering that controllable loads are usually distributed resources, this method can adjust the load capacity of controllable loads through intelligent control switches. Controllable loads can independently choose VPPs to join according to their own cooperation tendencies to obtain aggregated benefits, and VPPs can also choose to cooperate with multiple controllable loads at the same time. For example, it is assumed that there are N independent VPPs and M independent controllable loads in the region, and each VPP and each controllable load independently selects each other's cooperation objects under their respective constraints with the goal of maximizing aggregated benefits.

[0052] In some implementations of this embodiment, the controllable load performs VPP selection to generate a selection intention request rule including:

[0053] A1: According to the aggregated revenue generated by the controllable load joining each VPP, determine the intended VPP corresponding to the controllable load, and sort the cooperation tendency of the controllable load to each intended VPP according to the aggregated revenue generated by the controllable load joining each intended VPP, and obtain the ranking result of the cooperation tendency corresponding to the controllable load; among which, the greater the aggregated revenue generated by the controllable load joining the intended VPP, the greater the cooperation tendency of the controllable load to the intended VPP;

[0054] The ranking result of the cooperation tendency corresponding to the controllable load is the result of ranking each intended VPP in descending order of cooperation tendency.

[0055] For example, taking the mth controllable load as an example, the goal is to maximize the aggregated benefit generated after the mth controllable load is added to the VPP. The formula corresponding to the maximum aggregated benefit is: In the formula is the aggregated revenue generated by the aggregation of the mth controllable load and the nth VPP; are the income after and before aggregation respectively; C n,{m} The aggregation cost generated by the aggregation of the mth controllable load. This application defines the controllable load benefit as the aggregation benefit, so the aggregation benefit obtained by the controllable load in this application is essentially the same as the aggregation benefit obtained by the VPP. The difference lies in that the cost of the controllable load participating in different VPP aggregations is different, which leads to differences in the cooperation tendency performance indicators.

[0056] A2: Based on the ranking result of the cooperation tendency corresponding to the controllable load, a selection intention request is sent to the intended VPP with the highest cooperation tendency, and a cooperation intention signal fed back by the intended VPP with the highest cooperation tendency is received; A3: If the cooperation intention signal is an acceptance cooperation signal, it is determined that the controllable load has completed matching; if the cooperation intention signal is a rejection cooperation signal, the cooperation tendency of the intended VPP that rejects cooperation is set to zero, and the ranking result of the cooperation tendency corresponding to the controllable load is updated, and A2 to A3 are repeatedly executed until the controllable load is matched or each VPP is matched.

[0057] Specifically, in the process of two-way selection between controllable load and VPP, there is a possibility that VPP refuses to match with controllable load. When controllable load is rejected by the intended VPP with the best cooperation tendency (i.e., the intended VPP with the highest cooperation tendency), controllable load can only reduce the expected aggregated benefit and choose other intended VPPs for cooperation. However, controllable load has tolerance for the reduction of aggregated benefit, that is, controllable load has a minimum value requirement for cooperation benefit. This method defines tolerance U m represents the number of VPPs that the mth controllable load is willing to join. The controllable loads respond to U according to the aggregated benefits generated by joining each intended VPP. m The intention VPPs form a cooperation tendency ranking, and the cooperation tendency ranking result corresponding to the controllable load is obtained. Define h n,m It represents the cooperation tendency of the m-th controllable load to the n-th VPP. This method establishes the mapping relationship between the aggregated benefit of the m-th controllable load joining each VPP and the cooperation tendency as follows: In the formula, h n,m The larger the value, the greater the aggregate benefit after the mth controllable load joins the nth VPP. m When the cooperation tendency of the corresponding VPP is set to 0, that is, h n,m =0, indicating that the mth controllable load has no tendency to cooperate with the VPP.

[0058] In some implementations of this embodiment, the method provides an interactive function of whether the controllable load participates in VPP regulation. If the controllable load considers its own power consumption and confirms to participate in VPP regulation at this stage, the intelligent switch control word will be set to 1 through the sub-controller, and then participate in the subsequent regulation process. If the controllable load does not want to participate in VPP regulation at this stage due to its own reasons, the intelligent switch control word will be set to 0 through the sub-controller, and the controllable load will no longer participate in the subsequent regulation process.

[0059] In some implementations of this embodiment, the determination rule of the intended VPP corresponding to the controllable load includes: obtaining the tolerance U of the controllable load m ; Among them, the tolerance of controllable load U mThe number of VPPs that the controllable load is willing to join is U m ; According to the aggregated benefits generated by adding controllable loads to each VPP, the ranking value of the aggregated benefits is not greater than U m The VPP with the highest aggregated revenue value greater than U m The cooperation tendency of the VPP is set to zero.

[0060] S120: clustering the controllable capacities of the controllable loads in the controllable load set, obtaining a controllable load cluster combination with the maximum function value of the VPP objective function based on the clustering result and the controllable capacity demand, and accepting the selection intention of each controllable load in the controllable load cluster combination with the maximum function value of the VPP objective function, so as to control the capacity of the current VPP according to the controllable capacity of each controllable load accepted by the current VPP; wherein the VPP objective function is constructed based on the aggregated income data and the cooperation tendency index data of the controllable load cluster combination, and the cooperation tendency index data is used to characterize the degree of cooperation willingness of each controllable load in the controllable load cluster combination with the VPP;

[0061] In some implementations of this embodiment, the above-mentioned rule for clustering the adjustable capacity of the controllable loads in the controllable load set includes: B1: performing agglomerative hierarchical clustering analysis on the adjustable capacity of the controllable loads in the controllable load set to obtain adjustable capacity data of the controllable loads of a preset number of clusters, and calculating the average value of the adjustable capacity data of the controllable loads of each cluster, and determining the clustering center of each cluster based on the average value of the adjustable capacity data of each cluster;

[0062] Specifically, for the controllable loads involved in regulation, since most of the controllable loads are distributed resource characteristics, there are many types of load resources and their output characteristics are also quite different. In order to efficiently identify the controllable capacity of different controllable loads and find the common characteristics between controllable loads, this application uses the k-means clustering algorithm to cluster the top U m The controllable loads that tend to join a VPP are clustered to lay the foundation for the effective aggregation of VPP in the next step. Among them, in order to optimize the k-means clustering algorithm process, this application first uses agglomerative hierarchical clustering to divide the original data of the controllable capacity of the controllable loads, determines the initial clustering center, and then performs k-means clustering. First, the n controllable loads participating in the aggregation are regarded as n clusters, and the Euclidean distance d between the clusters is calculated. ij : Where, d ij represents the distance between the i-th controllable capacity curve and the j-th controllable capacity curve; z i1 、z j1 、z i2 、z j2 、z im、z jm is the corresponding principal component in the Z matrix; there are n(n-1) / 2 distances for n clusters. Arrange the distances from small to large, and the arrangement includes the labels of n objects. In order, in each stage, the two clusters with the smallest distance are condensed into one cluster until the total number of clusters is k.

[0063] B2: Use k-means clustering to calculate the distance from the controllable capacity data of each controllable load to each cluster center, and classify each controllable load into the cluster corresponding to the cluster center with the closest distance; B3: Recalculate the cluster center of each cluster to determine whether the cluster center of each cluster has changed. If the cluster center of any cluster has changed, use the calculated cluster center of each cluster to update the cluster center, and repeat B2 to B3 until the cluster center no longer changes or there is no cluster to which the controllable load is reallocated.

[0064] Specifically, this method uses an improved k-means clustering algorithm. The algorithm flow is as follows: Figure 3 As shown, Figure 3 This is a schematic diagram of a clustering rule provided by an embodiment of the present invention. The specific steps are as follows:

[0065] Step 1: Determine the number of clusters k;

[0066] Step 2: Input the Z matrix and perform agglomerative hierarchical clustering analysis on the controllable load and controllable capacity data set;

[0067] Step 3: Calculate the average value of the data of the k clusters obtained to obtain the initial cluster center;

[0068] Step 4: Use k-means clustering to calculate the distance between each controllable load controllable capacity data and all cluster centers, and classify the controllable load into the cluster with the cluster center closest to it;

[0069] Step 5: After the cluster division is completed, recalculate the cluster center of each cluster;

[0070] Step 6: Repeat steps 4 to 5 until the cluster center no longer changes or no data is reallocated to another cluster.

[0071] In the above implementation process, the present application divides all controllable loads participating in VPP regulation into k clusters by improving the k-means clustering algorithm, thereby reducing the data dimension of the controllable loads and facilitating VPP to carry out unified regulation of the controllable loads. And the controllable loads in these k clusters are sorted from high to low according to their cooperation tendency with the VPP. After sorting, each VPP master controller can obtain its own controllable load cluster, and the relevant cluster contains the cooperation tendency information of each controllable load with this VPP. This method improves the clustering algorithm for controllable loads. When using this method to cluster controllable loads, the clustering effect is better and the volatility is small, which reduces the uncertainty of clustering.

[0072] In some implementations of this embodiment, after clustering the adjustable capacities of the controllable loads in the controllable load set, the method further includes: evaluating the clustering results based on the Davies-Bouldin index; wherein the calculation rule of the Davies-Bouldin index includes: according to the formula Calculate the ratio of the average distance between each data point in the cluster and the cluster center of the corresponding cluster to the distance between the cluster centers of each cluster. Based on the ratio calculation results, evaluate the clustering results. Where k is the number of clusters, h is the distance between the cluster centers of each cluster. i is the average distance from the data point of the controllable capacity data of each controllable load in the i-th cluster to the cluster center of the cluster, g ij is the distance between the cluster center of the i-th cluster and the cluster center of the j-th cluster, I DBI The smaller the value, the better the clustering effect.

[0073] Specifically, the method uses the Davies-Bouldin index to evaluate the clustering effect. The Davies-Bouldin index calculates the ratio of the average intra-cluster distance to the inter-cluster distance, and is suitable as an effectiveness indicator for power load curve clustering.

[0074] In some implementations of this embodiment, the construction rules of the above VPP objective function include: according to the aggregated revenue data and cooperation tendency index data of the controllable load cluster combination, the formula of the VPP objective function is determined as follows: in, is the maximum aggregated benefit of the nth VPP in all controllable load cluster combinations, is the correction coefficient of the cooperation tendency index, represents the aggregated benefit of the cooperation tendency indicator, It represents the aggregated revenue data after the controllable load in the nth VPP and controllable load cluster combination is aggregated. It represents the cooperation tendency index, which represents the average value of the cooperation tendency degree of each controllable load in the controllable load cluster combination to the nth VPP.

[0075] In some implementations of this embodiment, the construction rules of the above-mentioned VPP objective function also include: determining a threshold constraint condition of the cooperation tendency index; wherein the threshold constraint condition of the cooperation tendency index includes: if the controllable load cooperation tendency index value of the controllable load cluster combination is lower than a preset VPP cooperation tendency index threshold value I0, it indicates that the VPP refuses to cooperate with the controllable load cluster combination.

[0076] Specifically, this application assumes that there are M n The controllable loads are willing to make matching selections with the nth VPP, and define M n 0-1 variable x n,m (m=1,2,…,M n ) represents the selection of each controllable load by the nth VPP, x n,m =1 means that the nth VPP selects the mth controllable load as the cooperation object, x n,m =0 means no selection. Therefore, the goal of the nth VPP is to maximize the cooperative benefit after aggregation with the controllable load, and its expression is: In the formula, C K The aggregation cost generated by VPP aggregating the controllable load set K (i.e., the controllable load cluster combination). In addition, in the process of selecting the optimal controllable load combination scheme, VPP, in addition to taking economic benefits as the main goal, also needs to consider the willingness of each controllable load in the controllable load cluster combination to cooperate, which is directly related to the stability of the final cooperation (i.e., after VPP selects a controllable load cluster combination composed of different controllable loads, while calculating the aggregation benefits, it also needs to calculate the cooperation tendency index of the controllable load cluster combination composed of different controllable loads). For controllable loads with a smaller tendency to cooperate, even if cooperation is finally achieved, the stability of the cooperative relationship is poor. Define cooperation tendency index The cooperation tendency index represents the average value of the cooperation tendency of each controllable load in the controllable load set K to the nth VPP, which is specifically expressed as: Among them, the larger the cooperation tendency index is, the more satisfied each controllable load in the controllable load set K is with the aggregated benefit after joining the nth VPP, and the more stable the cooperation relationship is. At the same time, to ensure the stability of the cooperation relationship, this application sets the VPP cooperation tendency index threshold I0. If the controllable load cooperation tendency index is lower than I0, the VPP refuses to cooperate with it. In addition, while VPP attaches importance to cooperation benefits, it also considers the stability of cooperation. Therefore, the VPP objective function is revised to:

[0077] S130: When the control capacity of the VPP meets the control capacity requirement, each controllable load accepted by the current VPP is used as a bilateral matching result of the current VPP.

[0078] Specifically, the method obtains a set of controllable loads that select the current VPP according to the selection intention request of each controllable load that selects the current VPP. After clustering the controllable capacities of the controllable loads in the controllable load set, based on the clustering results and the control capacity requirements, a controllable load cluster combination with the largest function value of the VPP objective function is obtained, and the selection intention of each controllable load in the controllable load cluster combination with the largest function value of the VPP objective function is accepted, and the capacity of the current VPP is regulated according to the controllable capacity of each controllable load accepted by the current VPP. The VPP objective function is constructed based on the aggregated income data and cooperation tendency index data of the controllable load cluster combination. Therefore, in the process of selecting the optimal controllable load cluster combination, in addition to taking economic benefits as the main goal, the VPP also needs to consider the willingness of each controllable load in the controllable load cluster combination to cooperate, so as to further ensure that the VPP and the controllable loads complete matching and cooperation. When the control capacity of the VPP meets the control capacity requirements, the controllable loads accepted by the current VPP are used as the bilateral matching results of the current VPP. This method provides a "centralized + decentralized" VPP hybrid control mode. VPP and controllable loads exchange information and control signals through the master controller and sub-controller. This method takes into account the competitive ability of VPP centralized control and the computing power of distributed control, reduces the control burden of VPP, and improves the control ability of each controllable load. In addition, this method fully considers the matching and cooperation tendency of VPP and controllable loads. The aggregation of VPP and controllable loads is a process of mutual selection. Both parties of the aggregation have the right to choose and refuse. Each VPP and each controllable load independently selects each other's cooperation objects under their own constraints with the goal of maximizing the aggregation benefits. Thus, a bilateral matching mechanism between VPP and controllable loads is established, and efficient aggregation of VPP and controllable loads is achieved.

[0079] In some implementations of this embodiment, since there is a situation in which a controllable load has a tendency to cooperate with multiple VPPs during the process of matching and selecting controllable loads and VPPs, the method also establishes a bilateral matching and selection mechanism between VPPs and controllable loads. The implementation method of the bilateral matching and selection mechanism between VPPs and controllable loads proposed by the method is as follows: the VPP master controller is responsible for collecting the information of VPPs and controllable loads themselves, and the master controller obtains and publishes the matching results based on the controllable load decision model, the controllable load clustering method and the bilateral matching mechanism. In the one-to-many bilateral matching problem between VPPs and controllable loads, the method sets the "multiple parties", i.e., the controllable load party, as the selection party, and the "one party", i.e., the VPP party, as the receiving party, and supervises and manages the information provided by VPPs during the bilateral matching process through the power regulatory agency. In the bilateral matching process between VPPs and controllable loads, the method sets that VPPs do not have restrictions on the number of controllable loads they can accept, but fully considers the market benefits, aggregation costs and bilateral cooperation tendency indicators after aggregation, and selectively accepts controllable loads with the goal of maximizing aggregation benefits. Figure 4 is a VPP and controllable load bilateral matching selection flow chart provided by an embodiment of the present invention, such as Figure 4 As shown in the figure, the process of bilateral matching selection of VPP and controllable load proposed by this method is as follows:

[0080] Step 1: Matching round e = 1, calculate the aggregated benefits of M controllable loads joining N VPPs, and the mth controllable load selects the top U in the aggregated benefits ranking according to its own interests. m VPPs, and rank the cooperation tendency index of the controllable load to each VPP according to the revenue situation;

[0081] Step 2: In the e-th round of matching, all controllable loads select the VPP with the highest cooperation tendency and submit their cooperation intention;

[0082] Step 3: Each VPP clusters the controllable capacity of the controllable loads in the set based on the controllable load set with the cooperation intention of the controllable loads collected by the master controller through the k-means clustering algorithm. According to the control capacity demand, the controllable load set with the maximum aggregation benefit and cooperation tendency index, that is, the maximum VPP objective function, is selected;

[0083] Step 4: VPP calculates the selection of controllable loads by all VPPs according to the system control capacity demand and the cooperation tendency index in the decision model, and rejects all unaccepted controllable loads in the cluster. The controllable load sets the cooperation tendency index of the VPP that refuses to cooperate to 0, and the matching round e=e+1;

[0084] Step 5: Repeat steps 2 to 4 until all controllable loads are accepted or no VPP can submit cooperation intentions. At this point, the acceptance result of each VPP is the final bilateral matching result.

[0085] Figure 5 FIG. 1 is a block diagram of a controllable load and virtual power plant bilateral matching system provided by an embodiment of the present invention. Figure 5 As shown, an embodiment of the present invention provides a controllable load and virtual power plant bilateral matching system, including:

[0086] A request response module, used to respond to the selection intention request of the current VPP to obtain a controllable load set consisting of controllable loads that select the current VPP;

[0087] A clustering module is used to cluster the adjustable capacities of the controllable loads in the controllable load set, obtain the controllable load cluster combination with the maximum function value of the VPP objective function based on the clustering results and the adjustable capacity demand, and accept the selection intention of each controllable load in the controllable load cluster combination with the maximum function value of the VPP objective function, so as to adjust the capacity of the current VPP according to the adjustable capacity of each controllable load accepted by the current VPP; wherein the VPP objective function is constructed based on the aggregated income data and cooperation tendency index data of the controllable load cluster combination, and the cooperation tendency index data is used to characterize the degree of cooperation willingness of each controllable load in the controllable load cluster combination with the VPP;

[0088] The control capacity judgment module is used to take each controllable load accepted by the current VPP as the bilateral matching result of the current VPP when the control capacity of the VPP meets the control capacity demand.

[0089] Specifically, the system obtains a set of controllable loads that select the current VPP according to the selection intention request of each controllable load that selects the current VPP. After clustering the controllable capacities of the controllable loads in the controllable load set, based on the clustering results and the control capacity requirements, the controllable load cluster combination with the largest function value of the VPP objective function is obtained, and the selection intention of each controllable load in the controllable load cluster combination with the largest function value of the VPP objective function is accepted. According to the controllable capacity of each controllable load accepted by the current VPP, the capacity of the current VPP is regulated. The VPP objective function is constructed based on the aggregated income data and cooperation tendency index data of the controllable load cluster combination. Therefore, in the process of selecting the optimal controllable load cluster combination, in addition to taking economic benefits as the main goal, the VPP also needs to consider the willingness of each controllable load in the controllable load cluster combination to cooperate, so as to further ensure that the VPP and the controllable loads complete matching and cooperation. When the control capacity of the VPP meets the control capacity requirements, the controllable loads accepted by the current VPP are used as the bilateral matching results of the current VPP. The system fully considers the matching and cooperation tendency of VPP and controllable load. The aggregation of VPP and controllable load is a process of mutual selection. Both parties of the aggregation have the right to choose and refuse. Each VPP and each controllable load independently selects each other's cooperation objects under their own constraints with the goal of maximizing the aggregation benefits. Thus, a bilateral matching mechanism for VPP and controllable load is established, and efficient aggregation of VPP and controllable load is achieved.

[0090] An embodiment of the present invention also provides a machine-readable storage medium, on which instructions are stored. When the instructions are executed by the processor 100, the processor 100 is configured to execute the above-mentioned controllable load and virtual power plant bilateral matching method.

[0091] Machine-readable storage media include permanent and non-permanent, removable and non-removable media, and can be implemented by any method or technology to store information. Information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include temporary computer-readable media (transitory media), such as modulated data signals and carrier waves.

[0092] An embodiment of the present invention also provides an electronic device 10, which includes a memory 101, a processor 100, and a computer program 102 stored in the memory 101 and executable on the processor 100. When the processor 100 executes the computer program 102, the above-mentioned controllable load and virtual power plant bilateral matching method is implemented.

[0093] like Figure 6 FIG. 1 is a schematic diagram of an electronic device provided by an embodiment of the present invention. Figure 6 As shown, the electronic device 10 of this embodiment includes: a processor 100, a memory 101, and a computer program 102 stored in the memory 101 and executable on the processor 100. When the processor 100 executes the computer program 102, the steps in the above method embodiment are implemented. Alternatively, when the processor 100 executes the computer program 102, the functions of each module / unit in the above device embodiment are implemented.

[0094] Exemplarily, the computer program 102 may be divided into one or more modules / units, one or more modules / units are stored in the memory 101, and are executed by the processor 100 to complete the present invention. One or more modules / units may be a series of computer program instruction segments capable of completing specific functions, and the instruction segments are used to describe the execution process of the computer program 102 in the electronic device 10. For example, the computer program 102 may be divided into a request response module, a clustering module, and a control capacity determination module.

[0095] The electronic device 10 may be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server. The electronic device 10 may include, but is not limited to, a processor 100 and a memory 101. Those skilled in the art will appreciate that Figure 6 It is only an example of the electronic device 10 and does not constitute a limitation of the electronic device 10. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the electronic device may also include input and output devices, network access devices, buses, etc.

[0096] The processor 100 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may be any conventional processor, etc.

[0097] The memory 101 may be an internal storage unit of the electronic device 10, such as a hard disk or memory of the electronic device 10. The memory 101 may also be an external storage device of the electronic device 10, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the electronic device 10. Further, the memory 101 may also include both an internal storage unit of the electronic device 10 and an external storage device. The memory 101 is used to store computer programs and other programs and data required by the electronic device 10. The memory 101 may also be used to temporarily store data that has been output or is to be output.

[0098] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0099] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program 102 products. Therefore, the present application may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may take the form of a computer program 102 product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0100] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program 102 products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by the computer program 102 instructions. These computer program 102 instructions can be provided to a processor 100 of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor 100 of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0101] These computer program 102 instructions may also be stored in a computer readable memory 101 that can direct a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory 101 produce an article of manufacture including an instruction device that implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0102] These computer program 102 instructions may also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for executing on the computer or other programmable device to implement the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0103] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0104] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A bilateral matching method for controllable load and virtual power plant, characterized in that: include: In response to a selection intention request of a current VPP being selected, a controllable load set consisting of controllable loads of the current VPP is obtained; Clustering the controllable capacities of the controllable loads in the controllable load set, obtaining a controllable load cluster combination with the maximum function value of the VPP objective function based on the clustering results and the controllable capacity demand, and accepting the selection intention of each controllable load in the controllable load cluster combination with the maximum function value of the VPP objective function, so as to control the capacity of the current VPP according to the controllable capacity of each controllable load accepted by the current VPP; wherein the VPP objective function is constructed based on the aggregated income data and cooperation tendency index data of the controllable load cluster combination, and the cooperation tendency index data is used to characterize the degree of cooperation willingness of each controllable load in the controllable load cluster combination with the VPP; When the control capacity of the VPP meets the control capacity demand, the controllable loads accepted by the current VPP are taken as the bilateral matching result of the current VPP.

2. The controllable load and virtual power plant bilateral matching method according to claim 1, characterized in that: The rules for the controllable load to perform VPP selection and generate selection intention requests include: A1: According to the aggregated revenue generated by the controllable load joining each VPP, determine the intended VPP corresponding to the controllable load, and sort the cooperation tendency of the controllable load to each intended VPP according to the aggregated revenue generated by the controllable load joining each intended VPP, and obtain the ranking result of the cooperation tendency corresponding to the controllable load; wherein, the greater the aggregated revenue generated by the controllable load joining the intended VPP, the greater the cooperation tendency of the controllable load to the intended VPP; A2: Based on the cooperation tendency ranking results corresponding to the controllable loads, a selection intention request is sent to each VPP in turn until the current controllable load is matched or all VPPs are matched.

3. The controllable load and virtual power plant bilateral matching method according to claim 2 is characterized in that: The determination rules of the intended VPP corresponding to the controllable load include: Get the tolerance U of the controllable load m ; Wherein, the tolerance of the controllable load U m The number of VPPs that the controllable load is willing to join is U m ; According to the aggregated benefits generated by adding controllable loads to each VPP, the ranking value of the aggregated benefits is not greater than U m The VPP with the highest aggregated revenue value greater than U m The cooperation tendency of the VPP is set to zero.

4. The controllable load and virtual power plant bilateral matching method according to claim 1, characterized in that: The rule for clustering the adjustable capacities of the controllable loads in the controllable load set includes: B1: Perform agglomerative hierarchical clustering analysis on the controllable capacity of the controllable loads in the controllable load set to obtain the controllable capacity data of the controllable loads of a preset number of clusters, and calculate the average value of the controllable capacity data of the controllable loads of each cluster, and determine the cluster center of each cluster based on the average value of the controllable capacity data of each cluster; B2: Using k-means clustering, calculate the distance between the controllable capacity data of each controllable load and each cluster center, and classify each controllable load into the cluster corresponding to the cluster center with the closest distance; B3: Recalculate the cluster centers of each cluster to determine whether the cluster centers of each cluster have changed. If the cluster center of any cluster has changed, use the calculated cluster centers of each cluster to update the cluster centers. Repeat B2 to B3 until the cluster centers no longer change or there is no cluster to which the controllable load is reallocated.

5. The controllable load and virtual power plant bilateral matching method according to claim 4, characterized in that: After clustering the adjustable capacities of the controllable loads in the controllable load set, the method further includes: The clustering results were evaluated based on the Davies-Bouldin index; The calculation rules of the Davies-Bouldin index include: According to the formula Calculate the ratio of the average distance between each data point in the cluster and the cluster center of the corresponding cluster to the distance between the cluster centers of each cluster. Based on the ratio calculation results, evaluate the clustering results. Where k is the number of clusters, h is the distance between the cluster centers of each cluster. i is the average distance from the data point of the controllable capacity data of each controllable load in the i-th cluster to the cluster center of the cluster, g ij is the distance between the cluster center of the i-th cluster and the cluster center of the j-th cluster, I DBI The smaller the value, the better the clustering effect.

6. The controllable load and virtual power plant bilateral matching method according to claim 1, characterized in that: The construction rules of the VPP objective function include: According to the aggregated revenue data and cooperation tendency index data of the controllable load cluster combination, the formula for determining the VPP objective function is: in, is the maximum aggregated benefit of the nth VPP in all controllable load cluster combinations, is the correction coefficient of the cooperation tendency index, represents the aggregated benefit of the cooperation tendency indicator, It represents the aggregated revenue data after the controllable load in the nth VPP and controllable load cluster combination is aggregated. represents a cooperation tendency index, and the cooperation tendency index represents an average value of the cooperation tendency degree of each controllable load in the controllable load cluster combination to the nth VPP.

7. The controllable load and virtual power plant bilateral matching method according to claim 6, characterized in that: The construction rules of the VPP objective function also include: Determine the threshold constraints of the cooperation tendency indicator; The threshold constraints of the cooperation tendency index include: If the controllable load cooperation tendency index value of the controllable load cluster combination is lower than the preset VPP cooperation tendency index threshold value I0, it indicates that the VPP refuses to cooperate with the controllable load cluster combination.

8. A bilateral matching system of controllable load and virtual power plant, characterized in that: include: A request response module, used to respond to the selection intention request of the current VPP to obtain a controllable load set consisting of controllable loads that select the current VPP; A clustering module is used to cluster the adjustable capacities of the controllable loads in the controllable load set, obtain the controllable load cluster combination with the maximum function value of the VPP objective function based on the clustering results and the adjustable capacity demand, and accept the selection intention of each controllable load in the controllable load cluster combination with the maximum function value of the VPP objective function, so as to adjust the capacity of the current VPP according to the adjustable capacity of each controllable load accepted by the current VPP; wherein the VPP objective function is constructed based on the aggregated income data and cooperation tendency index data of the controllable load cluster combination, and the cooperation tendency index data is used to characterize the degree of cooperation willingness of each controllable load in the controllable load cluster combination with the VPP; The control capacity judgment module is used to take each controllable load accepted by the current VPP as the bilateral matching result of the current VPP when the control capacity of the VPP meets the control capacity demand.

9. A machine-readable storage medium having instructions stored thereon, characterized in that: When the instruction is executed by a processor, the processor is configured to execute the controllable load and virtual power plant bilateral matching method as described in any one of claims 1 to 7.

10. An electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the controllable load and virtual power plant bilateral matching method described in any one of claims 1 to 7 is implemented.

Images