Virtual power plant multiple space-time flexibility matching method, device, equipment and medium

Abstract

The invention relates to the technical field of power systems, in particular to a virtual power plant multi-spatio-temporal flexibility matching method and device, equipment and a medium, and the method comprises the steps: obtaining a power resource data set of a distributed resource user; extracting time features and space features of power resources in the power resource data set; clustering the power resource data set according to the time features and the space features; constructing an equivalent model of a plurality of virtual power plants according to a clustering result, taking the current power grid flow and the current power distribution as constraint conditions of the equivalent model, and taking target transaction values of the virtual power plants participating in different power grid levels as optimization targets of the equivalent model; and based on the equivalent model, the constraint condition and the optimization target, adjusting the priority and the operation strategy of the virtual power plant in response to different levels of power grid dispatching instructions so as to meet the current energy consumption demand. Therefore, the problem that the resource utilization rate is low due to the fact that the virtual power plant cannot meet the multi-level consumption requirement of the power grid in the related technology is solved.

Description

Technical Field

[0001] The present application relates to the technical field of power systems, and in particular to a method, device, equipment and medium for multi-temporal and spatial flexibility matching of a virtual power plant. Background Art

[0002] Taking the provinces of Northwest my country as an example, the overall situation is characterized by a high proportion of installed new energy capacity but a relatively low absorption rate. Furthermore, the scale of high-energy-consuming industrial users continues to grow, but idle capacity accounts for a high proportion. The flexibility potential of demand-side resources is not fully realized, and the mismatch between flexible supply and demand is prominent.

[0003] Against this backdrop, virtual power plants (VPPs), a business model that effectively taps into the potential for demand-side flexibility, offer a novel solution for absorbing new energy. To fully unleash the flexibility potential of vast heterogeneous resources, numerous researchers have conducted a series of studies on the effective aggregation of distributed resources. These studies focus on refining the external characteristics of VPPs after aggregating vast heterogeneous resources, as well as developing spot market trading strategies that maximize overall economic benefits.

[0004] After aggregating massive resources, a virtual power plant is represented externally as a power plant consisting of multiple virtual groups. In theory, it can also meet the new energy consumption needs of other provinces through inter-provincial channels. However, existing results usually only consider the virtual power plant as a whole, and study its trading strategy declaration or trading mechanism design method in the provincial spot market. In the actual process of market-based transactions, there may be periods when the provincial power grid has achieved a balance between power supply and demand while the surrounding provinces still have a demand for flexible resources. At the same time, the flexibility potential of the resources aggregated by the provincial virtual power plant has not yet been fully utilized. Therefore, the virtual power plant cannot meet the multi-level consumption needs of the power grid, resulting in low resource utilization. Summary of the Invention

[0005] The present application provides a virtual power plant multi-time and space flexibility matching method, device, equipment and medium to solve the problem in related technologies that virtual power plants cannot meet the multi-level consumption needs of the power grid, resulting in low resource utilization.

[0006] The first aspect of the present application provides a method for multi-temporal and spatial flexibility matching of a virtual power plant, comprising the following steps: obtaining a power resource data set of distributed resource users; extracting the time characteristics and spatial characteristics of the power resources in the power resource data set, and clustering the power resource data set according to the time characteristics and the spatial characteristics; constructing equivalent models of multiple virtual power plants based on the clustering results, taking the current power grid flow and the current power distribution as constraints of the equivalent model, and taking the target transaction value of the virtual power plant participating in different power grid levels as the optimization target of the equivalent model; based on the equivalent model, the constraints and the optimization target, adjusting the priority and operation strategy of the virtual power plant in responding to dispatching instructions of power grids at different levels to meet the current energy consumption demand.

[0007] Optionally, clustering the electric power resource data set according to the time characteristics and the spatial characteristics includes: calculating the local density of all data points in the electric power resource data set according to the time characteristics and the spatial characteristics; determining the corresponding cluster center distance according to the local density of all data points; and screening target data points that meet preset conditions as cluster centers according to the local density and the cluster center distance, so as to cluster the electric power resource data within the cluster center distance of the target data point to generate a clustering result.

[0008] Optionally, constructing equivalent models of multiple virtual power plants based on the clustering results includes: identifying target parameters of each cluster cluster in the clustering results; constructing an circumscribed hypercube model and equivalent characteristic parameters of the virtual power plant based on the target parameters; determining the coupling relationship between the time characteristics and spatial characteristics of the virtual power plant based on the circumscribed hypercube model, and constructing multiple virtual power plant equivalent models based on the equivalent characteristic parameters and the coupling relationship.

[0009] Optionally, after constructing multiple virtual power plant equivalent models based on the equivalent characteristic parameters and the coupling relationship, it includes: identifying the approximation of the virtual power plant equivalent model to the circumscribed hypercube and the actual cluster distribution; evaluating whether the virtual power plant model meets the preset standard based on the approximation; if the preset standard is not met, iteratively updating the equivalent characteristic parameters until the virtual power plant model meets the preset standard.

[0010] Optionally, before clustering the power resource data set according to the time characteristics and the spatial characteristics, the method includes: calculating the covariance characteristic matrix of each power resource data according to the power resource data set; calculating the eigenvalues ​​and corresponding eigenvectors of the covariance matrix; and sorting the eigenvalues ​​and corresponding eigenvectors to generate the power resource data set after dimensionality reduction processing.

[0011] Optionally, based on the equivalent model, the constraints and the optimization objective, the priority and operation strategy of the virtual power plant in responding to dispatch instructions from different levels of power grids are adjusted to meet the current energy consumption demand, including: calculating the corresponding objective function value according to all operation strategies of the virtual power plant; determining the corresponding target solution of each operation strategy according to the objective function value; if the target solution does not meet the global optimal solution, then iteratively updating the output priority weights and operation strategies of the virtual power plant to different power grid levels in each operation strategy according to the equivalent model, the constraints and the optimization objective, until the objective function value reaches the global optimal solution.

[0012] The second aspect of the present application provides a multi-temporal and spatial flexibility matching device for a virtual power plant, including: an acquisition module for acquiring a power resource data set of distributed resource users; an extraction module for extracting the time characteristics and spatial characteristics of power resources in the power resource data set, and clustering the power resource data set according to the time characteristics and the spatial characteristics; a construction module for constructing an equivalent model of multiple virtual power plants based on the clustering results, taking the current power grid flow and the current power distribution as constraints of the equivalent model, and taking the target transaction value of the virtual power plant participating in different power grid levels as the optimization target of the equivalent model; an adjustment module for adjusting the priority and operation strategy of the virtual power plant in responding to dispatching instructions of power grids at different levels based on the equivalent model, the constraints and the optimization target, so as to meet the current energy consumption demand.

[0013] The third aspect of the present application provides an electronic device, comprising: a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor executes the program to perform the multi-temporal and spatial flexibility matching method of a virtual power plant as described in the above embodiment.

[0014] The fourth aspect of the present application provides a computer-readable storage medium having a computer program stored thereon, which is executed by a processor to perform the virtual power plant multi-temporal and spatial flexibility matching method as described in the above embodiment.

[0015] The fifth embodiment of the present application provides a computer program product, including a computer program or instructions, which, when executed, implements the virtual power plant multi-temporal and spatial flexibility matching method as described in the above embodiments.

[0016] Therefore, this application has at least the following beneficial effects:

[0017] (1) The embodiment of the present application can extract the temporal characteristics and spatial characteristics of the power resources in the power resource data set, and cluster the power resource data set according to the temporal characteristics and spatial characteristics; construct equivalent models of multiple virtual power plants based on the clustering results, which can significantly improve the flexibility and economic benefits of the power system, improve the absorption capacity by fine-tuning the scheduling of distributed energy resources, and adjust the priority and operation strategy of the virtual power plant in responding to the dispatching instructions of different levels of power grids with the goal of maximizing the overall economic benefits while meeting the constraints of power grid flow and power allocation, thereby realizing the flexible adaptation and efficient response of the virtual power plant in the multi-level power grid, and significantly improving the new energy absorption capacity and system economy.

[0018] (2) The embodiment of the present application can use the density peak clustering algorithm to divide resource users with similar characteristics in the multi-dimensional space region into the same cluster and construct a virtual power plant equivalent model, with the goal of simultaneously responding to the comprehensive economic optimization under the power grid absorption demand of different levels of the provincial distribution network, main network, and inter-provincial power grid. The particle swarm algorithm is used to optimize and solve the operation strategies for different power grid levels in the same time period, which can solve the limitation of the virtual power plant focusing on the dispatching demand of a single level of the distribution network or the provincial main network, and provide theoretical guidance and model support for subsequent virtual power plants to help achieve resource mutual assistance in a larger time and space range and at the power grid level.

[0019] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0021] Figure 1 A flowchart of a virtual power plant multi-temporal and spatial flexibility matching method provided according to an embodiment of the present application;

[0022] Figure 2 A flow chart of a method for matching the spatiotemporal aggregation flexibility of a virtual power plant with the multi-level consumption requirements of a power grid according to an embodiment of the present application;

[0023] Figure 3 A method for dividing distributed resources with similar characteristics into the same cluster based on a density peak clustering model provided in an embodiment of the present application;

[0024] Figure 4 This is an example diagram of a multi-temporal and spatial flexibility matching device for a virtual power plant provided according to an embodiment of the present application;

[0025] Figure 5 A schematic diagram of the structure of an electronic device provided according to an embodiment of the present application. DETAILED DESCRIPTION

[0026] The following describes in detail embodiments of the present application, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0027] The following describes the virtual power plant multi-temporal and spatiotemporal flexibility matching method, device, electronic device, storage medium and program of the embodiments of the present application with reference to the accompanying drawings.

[0028] Specifically, Figure 1 A flow chart of a virtual power plant multi-time and space flexibility matching method provided in an embodiment of the present application.

[0029] like Figure 1 As shown, the virtual power plant multi-temporal and spatial flexibility matching method includes the following steps:

[0030] In step S101 , a power resource dataset of a distributed resource user is obtained.

[0031] It is understandable that the embodiment of the present application can obtain the power resource data set of the distributed resource user, so as to facilitate the subsequent extraction of the temporal characteristics and spatial characteristics of the power resources in the power resource data set.

[0032] It should be noted that the power resource dataset includes historical data on the installed capacity of new energy resources, energy storage installed capacity, new power load capacity, and new energy consumption demand and corresponding spot market prices of distributed resource users in the target provinces, including the provincial distribution network, main network, and inter-provincial power grid at different times.

[0033] In step S102 , the temporal characteristics and spatial characteristics of the power resources in the power resource dataset are extracted, and the power resource dataset is clustered according to the temporal characteristics and spatial characteristics.

[0034] It can be understood that the embodiments of the present application can extract the time characteristics and spatial characteristics of power resources in the power resource data set, and cluster the power resource data set according to the time characteristics and spatial characteristics, so as to facilitate the subsequent construction of equivalent models of multiple virtual power plants based on the clustering results.

[0035] It should be noted that temporal characteristics can refer to the dynamic behavior data of power resources changing over time, reflecting their periodicity, trend and volatility at different time scales (such as hours, days and months); spatial characteristics refer to the geographical distribution attributes of power resources and their positional relationship in the power grid hierarchy, reflecting the regional differences of resources and the topological constraints of the power grid.

[0036] In an embodiment of the present application, before clustering the power resource data set according to time characteristics and spatial characteristics, it includes: calculating the covariance characteristic matrix of each power resource data according to the power resource data set; calculating the eigenvalues ​​and corresponding eigenvectors of the covariance matrix; and sorting the eigenvalues ​​and corresponding eigenvectors to generate the power resource data set after dimensionality reduction processing.

[0037] It can be understood that the embodiment of the present application can calculate the covariance characteristic matrix of each power resource data based on the power resource data set; calculate the eigenvalues ​​and corresponding eigenvectors of the covariance matrix; sort the eigenvalues ​​and corresponding eigenvectors to generate a power resource data set after dimensionality reduction processing. The power resource data set after dimensionality reduction has a more compact data distribution and a clearer cluster structure, can retain key features, improve computing efficiency, and meet real-time requirements.

[0038] Specifically, if Figure 2 As shown in the figure, since the density peak clustering method does not perform well when facing high-dimensional data, the principal component analysis method is first used to reduce the dimensionality of the data collected from the power resource data set. Assuming that each set of data in the data set has n-dimensional features, the specific method of using principal component analysis to reduce the data to k dimensions is as follows:

[0039] (1) Centralize all data, that is, subtract the mean value of each dimension from the data of that dimension:

[0040]

[0041] Among them, for a set of data x, i is any data in the set of data, and n is the characteristic dimension of the set of data. The number of data in this group.

[0042] On this basis, we get the new matrix

[0043] (2) Secondly, calculate the covariance matrix C of the sample data. Each covariance value in the matrix is ​​composed of the characteristics of the sample. The expression of the covariance matrix is ​​as follows:

[0044]

[0045] (3) Calculate the eigenvalues ​​and corresponding eigenvectors of the covariance matrix C, then sort the eigenvalues ​​and eigenvectors in descending order, and use the first k eigenvectors to form the eigenvector matrix W. The specific expression is as follows:

[0046] W={u1,u2,…,u k}

[0047] (4) Projecting the original features onto the selected feature vector matrix W to obtain a new k-dimensional feature dataset and the corresponding dataset D after dimensionality reduction.

[0048]

[0049] in, It represents the i-th data obtained after the centralization operation in step (1), (n×1) means that the number of rows in the matrix is ​​n and the number of columns is 1. It is represented by the eigenvector matrix obtained by step (3), (k×n) means that the number of rows of the matrix is ​​k and the number of columns is n. Represented as a matrix of eigenvectors With the original data The i-th data reduced to k dimensions obtained by multiplication, Represented as the mth data in the final reduced k-dimensional data.

[0050] In an embodiment of the present application, the electric power resource data set is clustered according to the time characteristics and spatial characteristics, including: calculating the local density of all data points in the electric power resource data set according to the time characteristics and spatial characteristics; determining the corresponding cluster center distance according to the local density of all data points; screening the target data points that meet the preset conditions as cluster centers according to the local density and cluster center distance, so as to cluster the electric power resource data within the cluster center distance of the target data point to generate a clustering result.

[0051] It can be understood that the embodiments of the present application can calculate the local density of all data points in the power resource data set; determine the corresponding cluster center distance based on the local density of all data points; screen the target data points that meet the preset conditions as cluster centers based on the local density and cluster center distance, and cluster the power resource data within the cluster center distance of the target data point to generate clustering results. By calculating the local density and cluster center distance based on the density peak clustering method of spatiotemporal characteristics, the core pattern of power resources can be efficiently identified to support flexible scheduling of multi-level power grids.

[0052] Specifically, if Figure 2 As shown in Figure 3, the density peak clustering algorithm is used to cluster t data points. The implementation of the density peak clustering algorithm is mainly based on two key parameters, namely the local density ρ and the cluster center distance δ.

[0053] For given data points i and j, the local density is calculated as follows:

[0054]

[0055] Where, ρ iis the local density of data point i, X(x) is the piecewise function that determines the local density of the data point; d ij ——Euclidean distance between data points i and j; d c ——cutoff distance. Usually, d c Set to a value that makes the average number of data points surrounding each data point approximately 1% to 2% of the total number of points in the dataset.

[0056] Cluster center distance δ i The calculation of needs to be divided into two cases: after calculating the local density of all data points, if i is the data point with the largest local density, then max j d ij Calculate the distance between cluster centers; if i is not the point with the largest local density, then Perform calculations.

[0057] Then, by constructing a decision graph with ρ as the x-axis and δ as the y-axis, the data point in the upper right corner of the decision graph is selected as the cluster center, and the other points that are not cluster centers are classified according to the Euclidean distance between the two, and each point is divided into the cluster closest to its own cluster center. Figure 3 shown.

[0058] In step S103, equivalent models of multiple virtual power plants are constructed based on the clustering results, the current grid flow and the current power distribution are used as constraints of the equivalent model, and the target transaction values ​​of the virtual power plants participating in different grid levels are used as optimization targets of the equivalent model.

[0059] It can be understood that the embodiment of the present application can construct equivalent models of multiple virtual power plants based on the clustering results, take the current grid flow and current power distribution as constraints of the equivalent model, and take the target transaction value of the virtual power plant participating in different grid levels as the optimization target of the equivalent model. By constructing an equivalent model and embedding the physical constraints of the grid, the virtual power plant can dynamically optimize the resource allocation strategy with the goal of maximizing multi-level transaction profits, so as to achieve temporal and spatial adaptation of resource characteristics and grid demand, and balance maximization of profits with minimization of costs.

[0060] Specifically, if Figure 2 As shown in the figure, considering the grid flow and power allocation constraints, with the goal of maximizing the overall economic benefits of virtual power plants participating in market-based transactions at different grid levels, a particle swarm optimization algorithm is used to optimize the priority and operation strategy of virtual power plants in responding to grid dispatch instructions at different levels. The specific process is as follows:

[0061] 1) First, define the overall economic benefit function of virtual power plants participating in spot trading:

[0062]

[0063] Where M is the grid level set of main grid, distribution grid and inter-provincial grid; T is the total number of time periods for market operation; is the electricity spot price of level m in time period t; is the output reported by the virtual power plant to the grid level m during time period t; C om is the operation and maintenance cost, k om is the unit operation and maintenance cost coefficient; is the energy storage loss cost, θ is the economic loss cost per unit charge and discharge capacity of energy storage, are the charge and discharge amounts of the equivalent energy storage model at time t; C penalty P is the output deviation penalty; act,t 、P bid,t are the actual output value and the declared output value of the virtual power plant at time t, δ is the output deviation penalty coefficient; ξ t Contribute confidence to new energy, is the equivalent new energy capacity of the virtual power plant corresponding to the kth cluster, is the discharge power of the equivalent energy storage model at time t, is the charging power of the equivalent energy storage model at time t.

[0064] 2) Construct necessary external constraints for the optimization model:

[0065] Grid flow constraints:

[0066]

[0067] Power allocation constraints across grid levels:

[0068]

[0069] Where G l,k is the power transfer distribution factor of virtual power plant k for line l; For any virtual power plant k, the declared output to level m, is the maximum transmission capacity of line l, π m is the priority weight of grid level m, For t is the weight factor of time period t, is the output reported by the virtual power plant to the grid level m during time period t.

[0070] In an embodiment of the present application, equivalent models of multiple virtual power plants are constructed based on the clustering results, including: identifying target parameters for each cluster cluster in the clustering results; constructing an circumscribed hypercube model and equivalent characteristic parameters of the virtual power plant based on the target parameters; determining the coupling relationship between the time characteristics and spatial characteristics of the virtual power plant based on the circumscribed hypercube model, and constructing multiple virtual power plant equivalent models based on the equivalent characteristic parameters and the coupling relationship.

[0071] It can be understood that the embodiments of the present application can identify the target parameters of each cluster in the clustering results; construct an circumscribed hypercube model and equivalent characteristic parameters of the virtual power plant based on the target parameters; determine the coupling relationship between the time characteristics and spatial characteristics of the virtual power plant based on the circumscribed hypercube model, and construct multiple virtual power plant equivalent models based on the equivalent characteristic parameters and coupling relationships, clarify the time and space boundaries and economic response patterns of each cluster, and realize multi-level collaborative scheduling based on the coupling matrix; maximize market benefits while ensuring the stability of the power grid.

[0072] Specifically, if Figure 2 As shown in the figure, for each cluster in different spatial dimensions, the circumscribed approximation method is used to construct a virtual power plant equivalent model, analyze the comprehensive correlation matching degree between the different levels of grid absorption demand and the virtual power plant equivalent model, and adjust and reconstruct the relevant models that have not passed the validity verification.

[0073] The specific process of constructing multiple virtual power plant equivalent models using the circumscribed approximation method is as follows:

[0074] 1) Construct a user cluster C containing k clusters k :

[0075] C k ={u i |u i ∈U,i=1,…,N k}

[0076] u i =[P re,i ,P ess,i ,D t,i ,λ t,i ]

[0077] Where u i is the feature vector of user i; P re,i is the installed capacity of new energy for user i; P ess,i is the energy storage installed capacity of user i; D t,i is the consumption demand range of user i in time period t; t,i is the electricity price parameter corresponding to user i in time period t.

[0078] 2) Construct a circumscribed hypercube model to achieve minimum circumscribed hypercube model optimization:

[0079]

[0080] Where D is the number of feature dimensions; w d is the weight coefficient of feature dimension d; △d is the width of the circumscribed hypercube of the d-th dimension feature of the circumscribed method; X d and are the minimum and maximum boundary values ​​of the d-th dimension feature respectively.

[0081] 3) Calculate the equivalent characteristic parameters of the virtual power plant:

[0082]

[0083] Where, is the equivalent new energy capacity of the virtual power plant; d i,k For user i to cluster C k Euclidean distance to the center; is the average distance within the cluster; β is the attenuation coefficient, P re,i is the installed capacity of new energy for user i.

[0084]

[0085] Where, is the equivalent energy storage capacity of the virtual power plant; SOC i,t is the energy storage equivalent SOC capacity of user i at time t, P ess,i is the energy storage installed capacity of user i.

[0086]

[0087] Where, is the equivalent consumption demand range of the virtual power plant in period t; D t,i and are the lower and upper limits of the consumption demand of user i at time t; is the equivalent electricity price of the virtual power plant in period t, P re,i is the installed capacity of new energy for user i.

[0088] 4) Construct a coupling model that considers the spatiotemporal characteristics of virtual power plants:

[0089]

[0090] Where, φ mn is the spatiotemporal coupling matrix between time period m and grid level n; Indicates the output regulation speed of the virtual power plant; α is the regulation rate coefficient, is the equivalent absorption demand range of the virtual power plant in period t, is the equivalent electricity price of the virtual power plant in period t, D vpp,m is the consumption demand of the virtual power plant in m dimension, λ n is the electricity price, λ vpp,n is the equivalent electricity price of the virtual power plant in dimension n, D m To meet demand, is the gradient operator along the direction of the spatiotemporal correlation matrix.

[0091] It should be noted that Indicates the rate of change of consumption demand when electricity price changes; It represents the response rate of change of electricity price when the consumption demand changes; and the above formula quantifies the coupling relationship between electricity price and consumption demand.

[0092] In an embodiment of the present application, after constructing multiple virtual power plant equivalent models based on equivalent characteristic parameters and coupling relationships, it includes: identifying the approximation of the virtual power plant equivalent model to the circumscribed hypercube and the actual cluster distribution; evaluating whether the virtual power plant model meets the preset standard based on the approximation; if the preset standard is not met, iteratively updating the equivalent characteristic parameters until the virtual power plant model meets the preset standard.

[0093] The preset standard is that the degree of approximation between the circumscribed hypercube and the actual cluster distribution is less than or equal to a preset threshold, wherein the preset threshold is 0.15 and is not specifically limited.

[0094] It can be understood that the embodiments of the present application can identify the approximation of the virtual power plant equivalent model to the circumscribed hypercube and the actual cluster distribution; evaluate whether the virtual power plant model meets the preset standard based on the approximation; if it does not meet the preset standard, iteratively update the equivalent characteristic parameters until the virtual power plant model meets the preset standard to improve the effectiveness and robustness of the model.

[0095] Specifically, if Figure 2 As shown, the effectiveness of the virtual power plant equivalent model is verified:

[0096]

[0097] Where,∈ k The approximation between the circumscribed hypercube and the actual cluster distribution is not met. If the requirements are not met, the virtual power plant equivalent model needs to be rebuilt; vol(C k ) is the hypervolume of the original cluster in the feature space, represents the eigenvalue of user i in the dth dimension; D is the number of eigenvalues; vol(vpp k ∩C k ) is the intersection volume of the virtual power plant equivalent model and the actual cluster, u i is the feature vector of user i, is the maximum value of the d-th dimension feature, Xd is the minimum value of the d-th dimension feature.

[0098] In step S104, based on the equivalent model, constraints and optimization objectives, the priority and operation strategy of the virtual power plant in responding to grid dispatch instructions at different levels are adjusted to meet the current energy consumption demand.

[0099] It can be understood that the embodiments of the present application can, based on equivalent models, constraints and optimization objectives, adjust the priority and operation strategy of the virtual power plant in responding to different levels of power grid dispatching instructions to meet the current energy consumption needs. Through dynamic priority adjustment driven by equivalent models and optimization strategies under constraints, the virtual power plant can efficiently respond to multi-level power grid dispatching needs and achieve coordinated optimization of energy consumption, economic benefits and power grid security.

[0100] In an embodiment of the present application, based on an equivalent model, constraints and optimization objectives, the priority and operation strategy of the virtual power plant in responding to dispatch instructions from different levels of power grids are adjusted to meet the current energy consumption demand, including: calculating the corresponding objective function value according to all operation strategies of the virtual power plant; determining the corresponding target solution of each operation strategy according to the objective function value; if the target solution does not meet the global optimal solution, then iteratively updating the output priority weights and operation strategies of the virtual power plant to different power grid levels in each operation strategy based on the equivalent model, constraints and optimization objectives until the objective function value reaches the global optimal solution.

[0101] It can be understood that the embodiment of the present application can adjust the priority and operation strategy of responding to the dispatch instructions of power grids at different levels based on the equivalent model, constraints and optimization objectives of the virtual power plant, and determine the output priority weights and operation strategies of the virtual power plant to different power grid levels by continuously iteratively updating the global optimal solution, thereby balancing the flexibility resources of the virtual power plant and the absorption needs of power grids at different levels, making it possible to more efficiently utilize distributed energy resources and improve the access and absorption capabilities of new energy.

[0102] Specifically, if Figure 2 As shown in Figure 2, the particle swarm optimization algorithm is used to solve the optimization problem of the output priority weights and operation strategies of virtual power plants to different grid levels:

[0103] (1) For the overall economic benefit function F of the virtual power plant set in this step, assume that there are n particles in the D-dimensional space and the position x of the i-th particle is i =(x i1 ,x i2 ,…,x iD ) represents a potential solution vector of the problem in D-dimensional space (i.e., a potential solution of the virtual power plant to allocate its operation strategies for different power grids at different time periods), and its speed is v i =(vi1 ,v i2 ,…,v iD ), each particle position X i The encoding expression is as follows:

[0104]

[0105] Where π1, π2, and π3 are the priority weights of the virtual power plant's output reported to the distribution network, main grid, and inter-provincial grid respectively; ρ t The specific steps for solving the weight factor of the output reported during period t using the particle swarm optimization algorithm are as follows:

[0106] (2) Bring particle i into F(x) to solve the function value, and record the best position pbest=(p i1 ,p i2 ,…,p iD ) and gbest=(g i1 ,g i2 ,…,g iD ).

[0107] (3) Update the particle's d-dimensional velocity and position:

[0108]

[0109] Where: k is the current iteration number; w is the inertia weight; is the velocity of particle i in the kth iteration; c1, c2 are acceleration constants; is the position of particle i after the kth iteration; r1 and r2 are random constants in the range of (0,1).

[0110] (4) After each iteration, calculate whether the objective function F in the current state meets the global optimality. If not, repeat the above steps until the global optimality is met or the maximum number of iterations is reached.

[0111] After completing the clearing and settlement of electricity spot markets at different levels, analyze whether the economic benefits of participating in the virtual power plant transaction meet expectations. If not, update the time range and granularity of the collected historical data and adjust the truncation distance d. c .

[0112] According to the multi-temporal and spatial flexibility matching method of virtual power plants proposed in the embodiment of the present application, the time characteristics and spatial characteristics of the power resources in the power resource data set are extracted, and the power resource data set is clustered according to the time characteristics and spatial characteristics; based on the clustering results, equivalent models of multiple virtual power plants are constructed, which can significantly improve the flexibility and economic benefits of the power system, improve the absorption capacity through refined scheduling of distributed energy resources, and adjust the priority and operation strategy of the virtual power plant in response to the dispatching instructions of different levels of power grids with the goal of maximizing overall economic benefits while meeting the constraints of power grid flow and power distribution, thereby realizing the flexible adaptation and efficient response of virtual power plants in multi-level power grids, and significantly improving the new energy absorption capacity and system economy.

[0113] Next, the multi-temporal and spatial flexibility matching device of a virtual power plant proposed according to an embodiment of the present application will be described with reference to the accompanying drawings.

[0114] Figure 4 It is a block diagram of a virtual power plant multi-time and space flexibility matching device according to an embodiment of the present application.

[0115] like Figure 4 As shown, the virtual power plant multi-temporal and spatial flexibility matching device 10 includes: an acquisition module 100, an extraction module 200, a construction module 300 and an adjustment module 400.

[0116] Among them, the acquisition module 100 is used to obtain the power resource data set of distributed resource users; the extraction module 200 is used to extract the time characteristics and spatial characteristics of the power resources in the power resource data set, and cluster the power resource data set according to the time characteristics and spatial characteristics; the construction module 300 is used to construct an equivalent model of multiple virtual power plants based on the clustering results, taking the current power grid flow and the current power distribution as constraints of the equivalent model, and taking the target transaction value of the virtual power plant participating in different power grid levels as the optimization target of the equivalent model; the adjustment module 400 is used to adjust the priority and operation strategy of the virtual power plant in responding to the dispatching instructions of different levels of power grids based on the equivalent model, constraints and optimization targets, so as to meet the current energy consumption needs.

[0117] It should be noted that the above explanation of the embodiment of the virtual power plant multi-temporal and spatial flexibility matching method is also applicable to the virtual power plant multi-temporal and spatial flexibility matching device of this embodiment, and will not be repeated here.

[0118] According to the multi-temporal and spatial flexibility matching device of a virtual power plant proposed in the embodiment of the present application, the time characteristics and spatial characteristics of the power resources in the power resource data set are extracted, and the power resource data set is clustered according to the time characteristics and spatial characteristics; an equivalent model of multiple virtual power plants is constructed according to the clustering results, which can significantly improve the flexibility and economic benefits of the power system, improve the absorption capacity through refined scheduling of distributed energy resources, and adjust the priority and operation strategy of the virtual power plant in response to the dispatching instructions of different levels of power grids with the goal of maximizing overall economic benefits while meeting the constraints of power grid flow and power distribution, thereby realizing the flexible adaptation and efficient response of virtual power plants in multi-level power grids, and significantly improving the new energy absorption capacity and system economy.

[0119] Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. The electronic device may include:

[0120] Memory 501 , processor 502 , and computer programs stored in the memory 501 and executable on the processor 502 .

[0121] When the processor 502 executes the program, the virtual power plant multi-temporal and spatial flexibility matching method provided in the above embodiment is implemented.

[0122] Furthermore, the electronic device further includes:

[0123] The communication interface 503 is used for communication between the memory 501 and the processor 502 .

[0124] The memory 501 is used to store computer programs that can be run on the processor 502 .

[0125] The memory 501 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0126] If the memory 501, the processor 502, and the communication interface 503 are implemented independently, the communication interface 503, the memory 501, and the processor 502 can be connected to each other via a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 5Only one thick line is used in the diagram, but this does not mean that there is only one bus or one type of bus.

[0127] Optionally, in a specific implementation, if the memory 501, the processor 502 and the communication interface 503 are integrated on a chip, the memory 501, the processor 502 and the communication interface 503 can communicate with each other through an internal interface.

[0128] The processor 502 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application.

[0129] An embodiment of the present application also provides a computer-readable storage medium on which a computer program or instruction is stored. When the computer program or instruction is executed by a processor, the multi-temporal and spatial flexibility matching method of the virtual power plant as described above is implemented.

[0130] An embodiment of the present application also provides a computer program product, including a computer program or instructions, which, when executed, implements the above-mentioned virtual power plant multi-temporal and spatial flexibility matching method.

[0131] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or N embodiments or examples in a suitable manner. In addition, those skilled in the art can combine and combine different embodiments or examples described in this specification and features of different embodiments or examples without contradiction.

[0132] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be understood to indicate or imply relative importance or implicitly specify the number of technical features indicated. Thus, a feature specified as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of this application, "N" means at least two, for example, two, three, etc., unless otherwise specifically defined.

[0133] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or N executable instructions for implementing a custom logical function or process step, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may be performed in a different order than shown or discussed, including performing functions in a substantially simultaneous manner or in a reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present application pertain.

[0134] It should be understood that various parts of the present application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiment, the N steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, it can be implemented using any one or a combination of the following technologies known in the art: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application-specific integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0135] Those skilled in the art will understand that all or part of the steps in the method of the above embodiment can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiment.

Claims

1. A virtual power plant multi-temporal and spatial flexibility matching method, characterized in that: The following steps are involved: Obtaining power resource datasets of distributed resource users; extracting temporal features and spatial features of electric resources in the electric resource dataset, and clustering the electric resource dataset according to the temporal features and the spatial features; Constructing equivalent models of multiple virtual power plants based on the clustering results, using the current grid flow and current power allocation as constraints of the equivalent models, and using the target transaction values ​​of the virtual power plants participating in different grid levels as optimization targets of the equivalent models; Based on the equivalent model, the constraints and the optimization objectives, the priority and operation strategy of the virtual power plant in responding to dispatching instructions of power grids at different levels are adjusted to meet the current energy consumption demand.

2. The virtual power plant multi-temporal and spatial flexibility matching method according to claim 1 is characterized in that: The clustering of the electric power resource dataset according to the temporal characteristics and the spatial characteristics includes: Calculating the local density of all data points in the power resource dataset according to the time feature and the spatial feature; Determine the corresponding cluster center distance according to the local density of all the data points; Target data points meeting preset conditions are selected as cluster centers according to the local density and the cluster center distance, so as to cluster the power resource data within the cluster center distance of the target data points to generate clustering results.

3. The virtual power plant multi-temporal and spatial flexibility matching method according to claim 2 is characterized in that: The equivalent models of multiple virtual power plants are constructed according to the clustering results, including: Identifying target parameters for each cluster in the clustering result; constructing a circumscribed hypercube model and equivalent characteristic parameters of a virtual power plant according to the target parameters; The coupling relationship between the time characteristics and the space characteristics of the virtual power plant is determined based on the circumscribed hypercube model, and a plurality of virtual power plant equivalent models are constructed according to the equivalent characteristic parameters and the coupling relationship.

4. The virtual power plant multi-temporal and spatial flexibility matching method according to claim 3 is characterized in that: After constructing a plurality of virtual power plant equivalent models according to the equivalent characteristic parameters and the coupling relationship, the method further includes: Identify the approximation of the virtual power plant equivalent model to the circumscribed hypercube and the actual cluster distribution; Whether the virtual power plant model meets the preset standard is evaluated according to the approximation degree. If it does not meet the preset standard, the equivalent characteristic parameters are iteratively updated until the virtual power plant model meets the preset standard.

5. The virtual power plant multi-temporal and spatial flexibility matching method according to claim 1 is characterized in that: Before clustering the power resource dataset according to the time characteristics and the spatial characteristics, the method includes: Calculate the covariance feature matrix of each power resource data according to the power resource data set; Calculate the eigenvalues ​​and corresponding eigenvectors of the covariance matrix; The eigenvalues ​​and corresponding eigenvectors are sorted to generate a power resource data set after dimensionality reduction processing.

6. The virtual power plant multi-temporal and spatial flexibility matching method according to claim 1 is characterized in that: The adjusting, based on the equivalent model, the constraints and the optimization objective, the priority and operation strategy of the virtual power plant in responding to grid dispatch instructions at different levels to meet current energy consumption needs includes: Calculate the corresponding objective function value based on all the operation strategies of the virtual power plant; Determining a corresponding target solution for each operation strategy according to the objective function value; If the objective solution does not satisfy the global optimal solution, the output priority weights and operating strategies of the virtual power plant to different grid levels in each operating strategy are iteratively updated using the equivalent model, the constraints and the optimization objective until the objective function value reaches the global optimal solution.

7. A virtual power plant multi-time and space flexibility matching device, characterized in that: include: An acquisition module, used to acquire a power resource dataset of a distributed resource user; An extraction module, configured to extract temporal and spatial characteristics of electric power resources from the electric power resource dataset; A clustering module, configured to cluster the power resource dataset according to the temporal characteristics and the spatial characteristics; a construction module for constructing equivalent models of multiple virtual power plants based on the clustering results, using the current grid flow and the current power distribution as constraints of the equivalent models, and using the target transaction values ​​of the virtual power plants participating in different grid levels as optimization targets of the equivalent models; An adjustment module is used to adjust the priority and operation strategy of the virtual power plant in responding to different levels of grid dispatch instructions based on the equivalent model, the constraints and the optimization objectives to meet the current energy consumption needs.

8. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the multi-temporal and spatial flexibility matching method for a virtual power plant as described in any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: The program is executed by a processor to implement the virtual power plant multi-temporal and spatial flexibility matching method as described in any one of claims 1 to 6.

10. A computer program product, characterized in that It includes a computer program, which, when executed by a processor, is used to implement the virtual power plant multi-time and space flexibility matching method described in any one of claims 1-6.

Images