Virtual power plant resource classification and aggregation method, system, equipment and medium

Abstract

The invention belongs to the technical field of power grid optimization operation, and discloses a virtual power plant resource classification and aggregation method, system and device and a medium, and the method comprises the following steps: obtaining virtual power plant distributed resources, and carrying out the feature extraction of the virtual power plant distributed resources to obtain distributed resource features; constructing a numerical representation model of the distributed resource characteristics according to the distributed resource characteristics; performing normalization processing on the distributed resource features by using a normalization method; the distributed resources are classified through a clustering algorithm and a second-order Minkowski distance; minkowski summation is carried out on the distributed resources of the same type, feasible regions of the distributed resources of the multiple types are obtained, and the feasible region of the total aggregation power of the virtual power plant is determined according to the feasible regions of the distributed resources of the multiple types. According to the method, massive resources in the virtual power plant can be equivalent to few different types of resources, and the solving difficulty of an aggregation method based on vertex search is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of power grid optimization operation, and in particular to a virtual power plant resource classification and aggregation method, system, equipment and medium. Background Art

[0002] At present, new energy sources such as wind and solar are booming, and the installed capacity is increasing year by year. However, the random, intermittent, and fluctuating characteristics of new energy sources pose a challenge to the security of the power grid. The uncertainty of the power system is gradually increasing, while the flexibility resources are gradually decreasing. With the construction of new power systems, the number and types of distributed flexibility resources in the distribution network are gradually increasing. Through virtual power plant technology, unified management of distributed resources can be achieved, providing the system with available regulation capabilities.

[0003] Among them, the research on the feasible domain aggregation method of distributed resources in virtual power plants mainly focuses on the characterization of the feasible domain of active and reactive power, the characterization of the feasible domain under uncertain environment, the feasible domain aggregation of multiple energy sources, and the scheduling of virtual power plants based on feasible domain aggregation. For aggregation methods, there are methods such as Minkowski summation and feasible domain projection. However, the above research did not consider the impact of the differences in heterogeneous resources in virtual power plants, unified modeling of different types of distributed resources, and mechanically aggregated massive heterogeneous distributed resources to obtain external feasible domains, which had defects such as low aggregation accuracy and long solution time.

[0004] Therefore, how to provide a virtual power plant resource classification and aggregation method, system, equipment and medium is a problem that needs to be solved urgently. Summary of the invention

[0005] The embodiments of the present invention provide a virtual power plant resource classification and aggregation method, system, device and medium to solve the problems in the prior art.

[0006] In order to have a basic understanding of some aspects of the disclosed embodiments, a brief summary is given below. This summary is not intended to be a general review, nor is it intended to identify key / important components or to delineate the scope of protection of these embodiments. Its only purpose is to present some concepts in a simple form as a preface to the detailed description that follows.

[0007] According to a first aspect of an embodiment of the present invention, a method for classifying and aggregating resources of a virtual power plant is provided.

[0008] In one embodiment, a virtual power plant resource classification and aggregation method includes the following steps:

[0009] Obtain distributed resources of the virtual power plant, extract features of the distributed resources of the virtual power plant, and obtain the features of the distributed resources; and construct a numerical representation model of the distributed resource features based on the features of the distributed resources;

[0010] Based on the numerical representation model of distributed resource characteristics, the distributed resource characteristics are normalized using the normalization method; and according to the normalization results, the distributed resources are classified by clustering algorithm and second-order Minkowski distance to obtain different types of distributed resources;

[0011] Through the vertex search aggregation method, the distributed resources of the same type are Minkowski summed to obtain the feasible domains of multiple types of distributed resources, and based on the feasible domains of multiple types of distributed resources, the feasible domain of the total aggregated power of the virtual power plant is determined.

[0012] In one embodiment, the distributed resource characteristics include: resource type, rated capacity, production and sales characteristics, response type, advance notice time, response adjustment time, response duration, response capacity and response period.

[0013] In one embodiment, the numerical representation model based on distributed resource features uses a normalization method to normalize the distributed resource features; and according to the normalization results, the distributed resources are classified by a clustering algorithm and a second-order Minkowski distance to obtain different types of distributed resources, including the following steps:

[0014] According to the numerical representation model of distributed resource characteristics, the distributed resource characteristics are normalized using the min-max normalization method to obtain the normalized processing results;

[0015] According to the normalized processing result, the second-order Minkowski distance between different distributed resources is calculated by the second-order Minkowski distance;

[0016] Based on the K-means clustering algorithm, the distributed resources are classified according to the second-order Minkowski distance between the distributed resources to obtain different types of distributed resources.

[0017] In one embodiment, the calculation formula for calculating the second-order Minkowski distance between different distributed resources by using the second-order Minkowski distance according to the normalization processing result is:

[0018]

[0019] Where, d i,j represents the second-order Minkowski distance between the i-th distributed resource and the j-th distributed resource, Cn represents the total number of distributed resource features, represents the cth type of distributed resource characteristic value of the ith distributed resource, Represents the cth type of distributed resource characteristics of the jth distributed resource.

[0020] In one embodiment, the method of classifying distributed resources based on the K-means clustering algorithm and according to the second-order Minkowski distance between distributed resources to obtain different types of distributed resources includes the following steps:

[0021] Randomly select several data points from the distributed resources of the virtual power plant as cluster centers, and assign each distributed resource to the resource category represented by the nearest cluster center according to the Minkowski distance between different distributed resources to form a preliminary clustering result;

[0022] For each resource category, calculate the average value of all distributed resources in the resource category, and use the average value of distributed resources as the new cluster center;

[0023] Compare the change value of the cluster center. If the change value of the cluster center is less than the set threshold, output the clustering result of the distributed resources to obtain different types of distributed resources. Otherwise, recalculate the Minkowski distance between different distributed resources and update the cluster center according to the recalculated result. When the change value of the cluster center is less than the set threshold, stop updating and output the clustering result of the distributed resources to obtain different types of distributed resources.

[0024] In one embodiment, the aggregation method through vertex search performs Minkowski summation on distributed resources of the same type to obtain feasible domains of multiple types of distributed resources, and determines the feasible domain of the aggregated total power of the virtual power plant according to the feasible domains of the multiple types of distributed resources, including the following steps:

[0025] The feasible domains of different types of distributed resources are determined by the Chino polyhedron method, and the overall feasible domain of the same type of distributed resources is calculated by the Minkowski summation method.

[0026] Based on the vertex search method, the feasible domains of multiple types of distributed resources are aggregated, and the vertices of the feasible domains of distributed resources are iteratively searched. According to the vertices of the feasible domains of multiple types of distributed resources, the feasible domain of the aggregated total power of the virtual power plant is calculated by the feasible domain calculation formula of the aggregated total power of the virtual power plant.

[0027] In one embodiment, the method of aggregating multiple types of distributed resource feasible domains based on the vertex search method, iteratively searching for vertices of the distributed resource feasible domain, and calculating the feasible domain of the virtual power plant aggregated total power according to the vertices of the multiple types of distributed resource feasible domains through the feasible domain calculation formula of the virtual power plant aggregated total power includes the following steps:

[0028] Randomly select a distributed resource type as the starting point, and use the overall feasible domain of the distributed resource of this type as the initial convex hull;

[0029] Taking the outer normal vector of the hyperplane of the initial convex hull as the search direction, based on the vertex search model, the overall feasible domain vertex of the distributed resources is searched in an iterative manner;

[0030] When the total feasible domain vertex of vertex distributed resources reaches a preset threshold, the feasible domain of the virtual power plant aggregated total power is calculated by the feasible domain calculation formula of the virtual power plant aggregated total power.

[0031] In one embodiment, the vertex search model is expressed as:

[0032] maxη Tran P total

[0033]

[0034] In the formula, max means finding the maximum value, η means the search direction, P total represents the vertex of the feasible region of the aggregated total power of the virtual power plant, represents the aggregate power of the kth type of distributed resources, K represents the number of distributed resource types, represents the feasible domain of the aggregate power of the kth type of distributed resources.

[0035] In one embodiment, the feasible domain calculation formula for the aggregated total power of the virtual power plant is:

[0036]

[0037] In the formula, F VPP represents the feasible domain of the total aggregated power of the virtual power plant, represents the feasible region vertex, α q represents the convex combination coefficient, N vpp represents the number of vertices in the feasible region of the virtual power plant, and q represents the qth vertex.

[0038] According to a second aspect of an embodiment of the present invention, a virtual power plant resource classification and aggregation system is provided.

[0039] In one embodiment, a virtual power plant resource classification and aggregation system includes:

[0040] The data processing module is used to obtain the distributed resources of the virtual power plant, extract the characteristics of the distributed resources of the virtual power plant, and construct a numerical representation model of the distributed resource characteristics according to the distributed resource characteristics;

[0041] The resource classification module is used to normalize the distributed resource characteristics based on the numerical representation model of the distributed resource characteristics by using the normalization method; and according to the normalization results, the distributed resources are classified by the clustering algorithm and the second-order Minkowski distance to obtain different types of distributed resources;

[0042] The feasible domain determination module is used to perform Minkowski summation on distributed resources of the same type through a vertex search aggregation method to obtain feasible domains of multiple types of distributed resources, and determine the feasible domain of the total aggregated power of the virtual power plant based on the feasible domains of multiple types of distributed resources.

[0043] In one embodiment, the distributed resource characteristics include: resource type, rated capacity, production and sales characteristics, response type, advance notice time, response adjustment time, response duration, response capacity and response period.

[0044] In one embodiment, the resource classification module uses a normalization method to normalize the distributed resource characteristics based on a numerical representation model of distributed resource characteristics; and according to the normalization result, the distributed resources are classified by a clustering algorithm and a second-order Minkowski distance to obtain different types of distributed resources. The distributed resource characteristics can be normalized by a min-max normalization method according to the numerical representation model of the distributed resource characteristics to obtain a normalization result; according to the normalization result, the second-order Minkowski distance between different distributed resources is calculated by the second-order Minkowski distance; based on the K-means clustering algorithm, the distributed resources are classified according to the second-order Minkowski distance between the distributed resources to obtain different types of distributed resources.

[0045] In one embodiment, the distributed resources are classified based on the K-means clustering algorithm and according to the second-order Minkowski distance between the distributed resources, and different types of distributed resources are obtained, including:

[0046] Randomly select several data points from the distributed resources of the virtual power plant as cluster centers, and assign each distributed resource to the resource category represented by the nearest cluster center according to the Minkowski distance between different distributed resources to form a preliminary clustering result;

[0047] For each resource category, calculate the average value of all distributed resources in the resource category, and use the average value of distributed resources as the new cluster center;

[0048] Compare the change value of the cluster center. If the change value of the cluster center is less than the set threshold, output the clustering result of the distributed resources to obtain different types of distributed resources. Otherwise, recalculate the Minkowski distance between different distributed resources and update the cluster center according to the recalculated result. When the change value of the cluster center is less than the set threshold, stop updating and output the clustering result of the distributed resources to obtain different types of distributed resources.

[0049] In one embodiment, the feasible domain determination module performs Minkowski summation on the same type of distributed resources through the vertex search aggregation method to obtain the feasible domains of multiple types of distributed resources, and determines the feasible domain of the aggregated total power of the virtual power plant based on the feasible domains of multiple types of distributed resources. The feasible domains of different types of distributed resources can be determined through the Chino polyhedron method, and the overall feasible domain of the same type of distributed resources can be calculated through the Minkowski summation method; the feasible domains of multiple types of distributed resources are aggregated based on the vertex search method, and the vertices of the feasible domain of distributed resources are iteratively searched, and according to the vertices of the feasible domains of multiple types of distributed resources, the feasible domain of the aggregated total power of the virtual power plant is calculated through the feasible domain calculation formula of the aggregated total power of the virtual power plant.

[0050] According to a third aspect of an embodiment of the present invention, a computer device is provided.

[0051] In some embodiments, the computer device includes a memory and a processor, the memory stores a computer program, and the processor implements the steps of the above method when executing the computer program.

[0052] According to a fourth aspect of embodiments of the present invention, a computer-readable storage medium is provided.

[0053] In one embodiment, a computer program is stored on a computer-readable storage medium, and when the computer program is executed by a processor, the steps of the above method are implemented.

[0054] The technical solution provided by the embodiment of the present invention may have the following beneficial effects:

[0055] The present invention extracts features of distributed resources and classifies them based on K-meas and Minkowski distance, thereby realizing efficient feasible domain aggregation of different types of distributed resources. For the same type of distributed resources, an aggregation method based on Chino polyhedron is adopted to reduce the solution time and improve the solution accuracy. The massive resources in the virtual power plant can be equivalent to a few fewer different types of resources, which reduces the solution difficulty for the aggregation method based on vertex search.

[0056] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0058] Figure 1 is a flow chart showing a method for classifying and aggregating virtual power plant resources according to an exemplary embodiment;

[0059] Figure 2 is a principle block diagram of a virtual power plant resource classification and aggregation system according to an exemplary embodiment;

[0060] Figure 3 is a flow chart of distributed resource clustering in a virtual power plant resource classification and aggregation method according to an exemplary embodiment;

[0061] Figure 4 It is a schematic diagram of a feasible domain of distributed resources based on Chino polyhedron in a method for classifying and aggregating virtual power plant resources according to an exemplary embodiment;

[0062] Figure 5 The figure is a schematic diagram showing the structure of a computer device according to an exemplary embodiment. DETAILED DESCRIPTION

[0063] The following description and accompanying drawings fully illustrate the specific embodiments of this article so that those skilled in the art can practice them. Parts and features of some embodiments may be included in or replace parts and features of other embodiments. The scope of the embodiments of this article includes the entire scope of the claims, as well as all available equivalents of the claims. Herein, the terms "first", "second", etc. are only used to distinguish one element from another, without requiring or implying any actual relationship or order between these elements. In fact, the first element can also be called the second element, and vice versa. Moreover, the terms "include", "comprise" or any other variant thereof are intended to cover non-exclusive inclusion, so that the structure, device or equipment including a series of elements includes not only those elements, but also other elements that are not explicitly listed, or also include elements inherent to such structure, device or equipment. In the absence of more restrictions, the elements defined by the sentence "including one..." do not exclude the existence of other identical elements in the structure, device or equipment including the elements. Each embodiment is described in a progressive manner herein, and each embodiment focuses on the differences from other embodiments, and the same and similar parts between the embodiments can be referred to each other.

[0064] The terms "longitudinal", "lateral", "upper", "lower", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc. in this document indicate the orientation or position relationship based on the orientation or position relationship shown in the drawings, and are only for the convenience of describing this document and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operate in a specific orientation, and therefore cannot be understood as a limitation on the present invention. In the description of this document, unless otherwise specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a mechanical connection or an electrical connection, it can also be the internal communication of two elements, it can be a direct connection, or it can be an indirect connection through an intermediate medium. For ordinary technicians in this field, the specific meanings of the above terms can be understood according to specific circumstances.

[0065] As used herein, the term "plurality" means two or more than two, unless otherwise specified.

[0066] In this document, the character " / " indicates that the preceding and following objects are in an "or" relationship. For example, A / B means: A or B.

[0067] In this article, the term "and / or" is a description of the association relationship between objects, indicating that three relationships may exist. For example, A and / or B means: A or B, or, A and B.

[0068] It should be understood that, although the various steps in the flow chart are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear description in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the figure may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these sub-steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.

[0069] Each module in the device or system of the present application can be implemented in whole or in part by software, hardware, or a combination thereof. The above modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to the above modules.

[0070] In the absence of conflict, the embodiments of the present invention and the features of the embodiments may be combined with each other.

[0071] Figure 1An embodiment of the virtual power plant resource classification and aggregation method of the present invention is shown.

[0072] Specifically, a classification method for distributed resources within a virtual power plant is proposed, and they are clustered according to their feasible domain characteristics. Secondly, based on the characteristics of the feasible domain, a high-precision Chino polyhedron is determined to approximate the feasible domain. Finally, based on the Minkowski sum and vertex search hybrid method, the feasible domains of multiple distributed resources are added together to obtain the feasible domain of the aggregated virtual power plant.

[0073] In this optional embodiment, the virtual power plant resource classification and aggregation method includes the following steps:

[0074] Step S101, obtaining distributed resources of a virtual power plant, extracting features of the distributed resources of the virtual power plant, and obtaining features of the distributed resources; and constructing a numerical representation model of the distributed resource features according to the features of the distributed resources;

[0075] Step S103, based on the numerical representation model of distributed resource characteristics, the distributed resource characteristics are normalized by using a normalization method; and according to the normalization result, the distributed resources are classified by using a clustering algorithm and a second-order Minkowski distance to obtain different types of distributed resources;

[0076] Step S105, through the vertex search aggregation method, the distributed resources of the same type are Minkowski summed to obtain the feasible domains of multiple types of distributed resources, and based on the feasible domains of multiple types of distributed resources, the feasible domain of the aggregated total power of the virtual power plant is determined.

[0077] In this optional embodiment, the distributed resource characteristics include: resource type, rated capacity, production and sales characteristics, response type, advance notice time, response adjustment time, response duration, response capacity and response period.

[0078] Among them, resource types include photovoltaics, energy storage, electric vehicles, industrial loads, commercial loads, residential loads, etc. Rated capacity is the maximum power of the resource. Production and sales characteristics include three types: electricity consumption, power generation, and producers and sellers. Response types include direct response and market-based response. Advance notice time is the minimum advance time for distributed resources to make corresponding preparations. Response adjustment time is the time it takes for distributed resources to complete the response after the virtual power plant issues an instruction. Response duration is the time it takes for distributed resources to maintain instruction response. Response capacity is the maximum power and energy response that can be achieved by distributed resources. Response period is the period during which distributed resources can provide responses.

[0079] Specifically, the characteristics of the i-th distributed resource are as follows:

[0080]

[0081] in, They respectively represent resource type, rated capacity, production and sales characteristics, response type, advance notice time, response adjustment time, response duration, response capacity, and response period, and I represents the total number of distributed resources.

[0082] In addition, it should be noted that a numerical representation model of distributed resource characteristics is constructed to represent the above characteristics in numerical form to facilitate subsequent classification processing.

[0083] For resource type, photovoltaic is converted to 1, energy storage is converted to 2, electric vehicles are converted to 3, industrial load is converted to 4, commercial load is converted to 5, and residential load is converted to 6. For production and marketing characteristics, producers are converted to -1, consumers are converted to 1, and prosumers are converted to 0. For response type, market-based response is converted to 0, and direct response is converted to 1.

[0084] For rated capacity, advance notice time, response adjustment time, response duration, response capacity, and response period, their original values ​​shall be maintained.

[0085] In this optional embodiment, based on the numerical characterization model of distributed resource characteristics, the distributed resource characteristics are normalized using a normalization method; and based on the normalization results, the distributed resources are classified by a clustering algorithm and a second-order Minkowski distance to obtain different types of distributed resources. The distributed resource characteristics can be normalized using a min-max normalization method based on the numerical characterization model of the distributed resource characteristics to obtain a normalization result; based on the normalization result, the second-order Minkowski distance between different distributed resources is calculated; based on the K-means clustering algorithm, the distributed resources are classified according to the second-order Minkowski distance between the distributed resources to obtain different types of distributed resources.

[0086] Specifically, the above features are normalized using the min-max method. Based on the second-order Minkowski distance, the similarity between different distributed resources is defined.

[0087] The expression normalized by the min-max method is:

[0088]

[0089] in, represents the jth feature of the i-th distributed resource, represents the normalized value of the jth feature of the ith distributed resource, represents the minimum value of the jth feature, Represents the maximum value of the j-th feature.

[0090] Based on K-means and Minkowski distance, massive distributed resources are clustered. The basic idea of ​​K-means clustering is to analyze the similarity between different distributed resources in the virtual power plant and classify samples with high similarity into one category, thereby realizing automatic classification of distributed resources based on response characteristics. Based on the above method, distributed resources are divided into K categories. The flow chart is as follows Figure 3 shown.

[0091] In this optional embodiment, the calculation formula for calculating the second-order Minkowski distance between different distributed resources by using the second-order Minkowski distance according to the normalization processing result is:

[0092]

[0093] Where, d i,j represents the second-order Minkowski distance between the i-th distributed resource and the j-th distributed resource, Cn represents the total number of distributed resource features, represents the cth type of distributed resource characteristic value of the ith distributed resource, Represents the cth type of distributed resource characteristics of the jth distributed resource.

[0094] In this optional embodiment, when the distributed resources are classified based on the K-means clustering algorithm and according to the second-order Minkowski distance between the distributed resources to obtain different types of distributed resources, a number of data points can be randomly selected from the distributed resources of the virtual power plant as cluster centers, and each distributed resource is assigned to the resource category represented by the nearest cluster center according to the Minkowski distance between different distributed resources to form a preliminary clustering result; for each resource category, the average value of all distributed resources in the resource category is calculated, and the average value of the distributed resources is used as the new cluster center; the change value of the cluster center is compared, if the change value of the cluster center is less than the set threshold, the clustering result of the distributed resources is output to obtain different types of distributed resources, otherwise, the Minkowski distance between different distributed resources is recalculated, and the cluster center is updated according to the recalculated result until the change value of the cluster center is less than the set threshold, then the updating is stopped, and the clustering result of the distributed resources is output to obtain different types of distributed resources.

[0095] In this optional embodiment, when the same type of distributed resources are subjected to Minkowski summation through the vertex search aggregation method to obtain the feasible domains of multiple types of distributed resources, and the feasible domain of the aggregated total power of the virtual power plant is determined based on the feasible domains of multiple types of distributed resources, the feasible domains of different types of distributed resources can be determined through the Chino polyhedron method, and the overall feasible domain of the same type of distributed resources can be calculated through the Minkowski summation method; the feasible domains of multiple types of distributed resources are aggregated based on the vertex search method, and the vertices of the feasible domain of distributed resources are iteratively searched, and based on the vertices of the feasible domains of multiple types of distributed resources, the feasible domain of the aggregated total power of the virtual power plant is calculated through the feasible domain calculation formula of the aggregated total power of the virtual power plant.

[0096] In this optional embodiment, when aggregating the feasible domains of multiple types of distributed resources based on the vertex search method, and iteratively searching the vertices of the feasible domains of distributed resources, and calculating the feasible domain of the aggregated total power of the virtual power plant through the feasible domain calculation formula of the aggregated total power of the virtual power plant based on the vertices of the feasible domains of multiple types of distributed resources, the distributed resource type can be randomly selected as the starting point, and the overall feasible domain of the distributed resources of this type is used as the initial convex hull; using the outer normal vector of the hyperplane of the initial convex hull as the search direction, based on the vertex search model, the vertices of the overall feasible domain of the distributed resources are searched in an iterative manner; when the vertices of the overall feasible domain of the vertex distributed resources reach a preset threshold, the feasible domain of the aggregated total power of the virtual power plant is calculated through the feasible domain calculation formula of the aggregated total power of the virtual power plant.

[0097] In addition, it should be noted that the distributed resource feasible domain approximation method based on Chino polyhedron can reduce the irregularity of the distributed resource feasible domain and reduce the difficulty of subsequent feasible domain aggregation. Figure 4 As shown, and the expression method is as follows:

[0098]

[0099] P i G =[P i G(1) ,P i G(2) ,…,P i G(M) ]∈R T×M ;

[0100] ||P i G(m) ||2=1m=1,2,…,M;

[0101] λ i =[λ i,1 ,λi,2 ,…,λ i,M ] Tran ;

[0102] In the formula, F i represents the feasible domain of active power of the ith distributed resource in T time periods, T represents the number of time periods, P i c represents the center point of the feasible region of the i-th distributed resource, P i G Represents the direction matrix of the feasible region extending from the center point to all directions, consisting of M vectors P i G(m) The modulus of the direction vector remains 1, and λ represents the extension length of the feasible domain of distributed resources in each direction. Indicates the maximum extension length, P i represents the active power of the i-th distributed resource, R T represents the T-dimensional real number space, R T×M represents the T*M-dimensional real number space, λ i,M represents the extension length of the i-th distributed resource in M ​​directions, m represents the extension vector count, and Tran represents matrix transpose.

[0103] Different types of distributed resources have different feasible domain characteristics and correspond to different Chino polyhedra. The selection method of Chino polyhedra is as follows:

[0104] For resources without time-period coupling characteristics, their characteristics are mainly reflected in the upper and lower power limits of a single time period. Therefore, the direction vector is selected as follows:

[0105]

[0106] In the formula, It represents the extension vector of the m-th direction of the resource with no period coupling characteristic, T represents the maximum value of m, and Tran represents matrix transpose.

[0107] For distributed energy storage resources, the feasible domain also has upper and lower limits on the sum of power in multiple time periods, so the direction vector is selected as follows:

[0108]

[0109] In the formula, Represents the extension vector of the energy storage resource in the mth direction, It represents the extension vector of the energy storage resource in the T+mth direction, Tran represents the matrix transpose, and T represents the maximum value of m.

[0110] For ramp-constrained resources, the feasible domain also has upper and lower limits of the power difference in multiple time periods. Therefore, the direction vector is selected as follows:

[0111]

[0112] In the formula, Represents the extension vector of the climbing resource in the mth direction, It represents the extension vector of the climbing resource in the T+mth direction, Tran represents the matrix transpose, and T represents the maximum value of m.

[0113] By performing Minkowski summation on each type of distributed resources, the overall feasible domain of each type of distributed resources can be obtained, and the formula is as follows:

[0114]

[0115] In the formula, represents the center point of the feasible region after aggregation, P i c represents the center point of the feasible region of the i-th distributed resource, represents the extension length in each direction after polymerization, λ i represents the extension length of the i-th distributed resource in each direction, I k Represents the total number of distributed resources of the kth type.

[0116] Among them, the feasible domain aggregation method of multiple types of distributed resources based on the vertex search method obtains the feasible domain of multiple distributed resources through the form of Minkowski summation of distributed resources of the same type. The essence of this algorithm is to approximate the feasible domain of the virtual power plant from the inside to the outside, and only search some vertices to obtain a conservative approximation of the convex hull. The outer normal vector of the hyperplane of the convex hull is used as the search direction, and new vertices are enumerated in each iteration until the accuracy requirements are met. When the number of vertices reaches the set threshold, the feasible domain of the total power of the virtual power plant can be obtained.

[0117] In this optional embodiment, the vertex search model is expressed as:

[0118] maxη Tran P total

[0119]

[0120] In the formula, max means finding the maximum value, η means the search direction, P total represents the vertex of the feasible region of the aggregated total power of the virtual power plant, represents the aggregate power of the kth type of distributed resources, K represents the number of distributed resource types, represents the feasible domain of the aggregate power of the kth type of distributed resources.

[0121] In this optional embodiment, the feasible domain calculation formula for the aggregated total power of the virtual power plant is:

[0122]

[0123] In the formula, F VPP represents the feasible domain of the total aggregated power of the virtual power plant, represents the feasible region vertex, α q represents the convex combination coefficient, N vpp represents the number of vertices in the feasible region of the virtual power plant, and q represents the qth vertex.

[0124] In summary, this method has the advantages of fast solution speed and high solution accuracy for the feasible domain aggregation of massive distributed resources in virtual power plants.

[0125] Figure 2 An embodiment of a virtual power plant resource classification and aggregation system of the present invention is shown.

[0126] In this optional embodiment, the virtual power plant resource classification and aggregation system includes:

[0127] The data processing module 201 is used to obtain the distributed resources of the virtual power plant, extract the characteristics of the distributed resources of the virtual power plant, and construct a numerical representation model of the distributed resource characteristics according to the distributed resource characteristics;

[0128] The resource classification module 203 is used to normalize the distributed resource characteristics based on the numerical representation model of the distributed resource characteristics by using a normalization method; and according to the normalization processing result, the distributed resources are classified by a clustering algorithm and a second-order Minkowski distance to obtain different types of distributed resources;

[0129] The feasible domain determination module 205 is used to perform Minkowski summation on distributed resources of the same type through a vertex search aggregation method to obtain feasible domains of multiple types of distributed resources, and determine the feasible domain of the aggregated total power of the virtual power plant based on the feasible domains of multiple types of distributed resources.

[0130] In this optional embodiment, the distributed resource characteristics include: resource type, rated capacity, production and sales characteristics, response type, advance notice time, response adjustment time, response duration, response capacity and response period.

[0131] In this optional embodiment, the resource classification module normalizes the distributed resource characteristics using a normalization method based on a numerical representation model of distributed resource characteristics; and according to the normalization result, the distributed resources are classified by a clustering algorithm and a second-order Minkowski distance to obtain different types of distributed resources. The distributed resource characteristics can be normalized using a min-max normalization method according to the numerical representation model of the distributed resource characteristics to obtain a normalization result; according to the normalization result, the second-order Minkowski distance between different distributed resources is calculated by the second-order Minkowski distance; based on the K-means clustering algorithm, the distributed resources are classified according to the second-order Minkowski distance between the distributed resources to obtain different types of distributed resources.

[0132] In this optional embodiment, the K-means clustering algorithm is used to classify the distributed resources according to the second-order Minkowski distance between the distributed resources to obtain different types of distributed resources, including: randomly selecting a number of data points from the distributed resources of the virtual power plant as cluster centers, and according to the Minkowski distance between different distributed resources, each distributed resource is assigned to the resource category represented by the nearest cluster center to form a preliminary clustering result; for each resource category, the average value of all distributed resources in the resource category is calculated, and the average value of the distributed resources is used as the new cluster center; comparing the change value of the cluster center, if the change value of the cluster center is less than the set threshold, the clustering result of the distributed resources is output to obtain different types of distributed resources, otherwise, the Minkowski distance between different distributed resources is recalculated, and the cluster center is updated according to the recalculated result until the change value of the cluster center is less than the set threshold, then the updating is stopped, and the clustering result of the distributed resources is output to obtain different types of distributed resources.

[0133] In this optional embodiment, when the feasible domain determination module performs Minkowski summation on the same type of distributed resources through the vertex search aggregation method to obtain the feasible domains of multiple types of distributed resources, and determines the feasible domain of the aggregated total power of the virtual power plant based on the feasible domains of multiple types of distributed resources, the feasible domains of different types of distributed resources can be determined through the Chino polyhedron method, and the overall feasible domain of the same type of distributed resources can be calculated through the Minkowski summation method; the feasible domains of multiple types of distributed resources are aggregated based on the vertex search method, and the vertices of the feasible domains of distributed resources are iteratively searched, and based on the vertices of the feasible domains of multiple types of distributed resources, the feasible domain of the aggregated total power of the virtual power plant is calculated through the feasible domain calculation formula of the aggregated total power of the virtual power plant.

[0134] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 5 As shown. The computer device includes a processor, a memory and a network interface connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store static information and dynamic information data. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, the steps in the above method embodiment are implemented.

[0135] Those skilled in the art will understand that Figure 5 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present invention, and does not constitute a limitation on the computer device to which the solution of the present invention is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0136] In addition, the present invention also provides a computer device, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiment when executing the computer program.

[0137] In addition, the present invention further provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps in the above method embodiment are implemented.

[0138] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided by the present invention can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory or optical memory, etc. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0139] The present invention is not limited to the structures which have been described above and shown in the drawings, and various modifications and changes may be made without departing from the scope thereof. The scope of the present invention is limited only by the appended claims.

Claims

1. A virtual power plant resource classification and aggregation method, characterized in that: The following steps are involved: Obtain distributed resources of the virtual power plant, and obtain distributed resource features by extracting features of the distributed resources of the virtual power plant; And build a numerical representation model of distributed resource characteristics based on the distributed resource characteristics; Based on the numerical representation model of distributed resource characteristics, the distributed resource characteristics are normalized using the normalization method; and according to the normalization results, the distributed resources are classified by clustering algorithm and second-order Minkowski distance to obtain different types of distributed resources; Through the vertex search aggregation method, the distributed resources of the same type are Minkowski summed to obtain the feasible domains of multiple types of distributed resources, and based on the feasible domains of multiple types of distributed resources, the feasible domain of the total aggregated power of the virtual power plant is determined.

2. The virtual power plant resource classification and aggregation method according to claim 1 is characterized in that: The distributed resource characteristics include: resource type, rated capacity, production and sales characteristics, response type, advance notice time, response adjustment time, response duration, response capacity and response period.

3. The virtual power plant resource classification and aggregation method according to claim 1, characterized in that: The numerical representation model based on distributed resource characteristics uses a normalization method to normalize the distributed resource characteristics; and according to the normalization processing result, the distributed resources are classified by a clustering algorithm and a second-order Minkowski distance to obtain different types of distributed resources, including the following steps: According to the numerical representation model of distributed resource characteristics, the distributed resource characteristics are normalized using the min-max normalization method to obtain the normalized processing results; According to the normalized processing result, the second-order Minkowski distance between different distributed resources is calculated by the second-order Minkowski distance; Based on the K-means clustering algorithm, the distributed resources are classified according to the second-order Minkowski distance between the distributed resources to obtain different types of distributed resources.

4. The virtual power plant resource classification and aggregation method according to claim 3 is characterized in that: The calculation formula for calculating the second-order Minkowski distance between different distributed resources by the second-order Minkowski distance according to the normalization processing result is: Where, d i,j represents the second-order Minkowski distance between the i-th distributed resource and the j-th distributed resource, Cn represents the total number of distributed resource features, represents the cth type of distributed resource characteristic value of the ith distributed resource, Represents the cth type of distributed resource characteristics of the jth distributed resource.

5. The virtual power plant resource classification and aggregation method according to claim 3 is characterized in that: The method of classifying distributed resources based on the K-means clustering algorithm and according to the second-order Minkowski distance between distributed resources to obtain different types of distributed resources includes the following steps: Randomly select several data points from the distributed resources of the virtual power plant as cluster centers, and assign each distributed resource to the resource category represented by the nearest cluster center according to the Minkowski distance between different distributed resources to form a preliminary clustering result; For each resource category, calculate the average value of all distributed resources in the resource category, and use the average value of distributed resources as the new cluster center; Compare the change value of the cluster center. If the change value of the cluster center is less than the set threshold, output the clustering result of the distributed resources to obtain different types of distributed resources. Otherwise, recalculate the Minkowski distance between different distributed resources and update the cluster center according to the recalculated result. When the change value of the cluster center is less than the set threshold, stop updating and output the clustering result of the distributed resources to obtain different types of distributed resources.

6. The virtual power plant resource classification and aggregation method according to claim 1, characterized in that: The aggregation method through vertex search performs Minkowski summation on the distributed resources of the same type to obtain the feasible domains of multiple types of distributed resources, and determines the feasible domain of the aggregated total power of the virtual power plant according to the feasible domains of the multiple types of distributed resources, including the following steps: The feasible domains of different types of distributed resources are determined by the Chino polyhedron method, and the overall feasible domain of the same type of distributed resources is calculated by the Minkowski summation method. Based on the vertex search method, the feasible domains of multiple types of distributed resources are aggregated, and the vertices of the feasible domains of distributed resources are iteratively searched. According to the vertices of the feasible domains of multiple types of distributed resources, the feasible domain of the aggregated total power of the virtual power plant is calculated by the feasible domain calculation formula of the aggregated total power of the virtual power plant.

7. The virtual power plant resource classification and aggregation method according to claim 6 is characterized in that: The method of aggregating multiple types of distributed resource feasible domains based on the vertex search method, iteratively searching for vertices of the distributed resource feasible domain, and calculating the feasible domain of the aggregated total power of the virtual power plant according to the vertices of the feasible domains of the multiple types of distributed resources by the feasible domain calculation formula of the aggregated total power of the virtual power plant includes the following steps: Randomly select a distributed resource type as the starting point, and use the overall feasible domain of the distributed resource of this type as the initial convex hull; Taking the outer normal vector of the hyperplane of the initial convex hull as the search direction, based on the vertex search model, the overall feasible domain vertex of the distributed resources is searched in an iterative manner; When the total feasible domain vertex of vertex distributed resources reaches a preset threshold, the feasible domain of the virtual power plant aggregated total power is calculated by the feasible domain calculation formula of the virtual power plant aggregated total power.

8. The virtual power plant resource classification and aggregation method according to claim 7 is characterized in that: The expression of the vertex search model is: maxη Tran P total In the formula, max means finding the maximum value, η means the search direction, and P total represents the vertex of the feasible region of the aggregated total power of the virtual power plant, represents the aggregate power of the kth type of distributed resources, K represents the number of distributed resource types, represents the feasible domain of the aggregate power of the kth type of distributed resources.

9. The virtual power plant resource classification and aggregation method according to claim 7, characterized in that: The feasible domain calculation formula for the total aggregated power of the virtual power plant is: In the formula, F VPP represents the feasible domain of the total aggregated power of the virtual power plant, represents the feasible region vertex, α q represents the convex combination coefficient, N vpp represents the number of vertices in the feasible region of the virtual power plant, and q represents the qth vertex.

10. A virtual power plant resource classification and aggregation system, characterized in that: include: A data processing module is used to obtain distributed resources of a virtual power plant and obtain distributed resource features by extracting features of the distributed resources of the virtual power plant; And build a numerical representation model of distributed resource characteristics based on the distributed resource characteristics; Resource classification module, which is used for the numerical representation model based on distributed resource characteristics and uses the normalization method to normalize the distributed resource characteristics; According to the normalized processing results, the distributed resources are classified by clustering algorithm and second-order Minkowski distance to obtain different types of distributed resources; The feasible domain determination module is used to perform Minkowski summation on distributed resources of the same type through a vertex search aggregation method to obtain feasible domains of multiple types of distributed resources, and determine the feasible domain of the total aggregated power of the virtual power plant based on the feasible domains of multiple types of distributed resources.

11. The virtual power plant resource classification and aggregation system according to claim 10, characterized in that: The distributed resource characteristics include: resource type, rated capacity, production and sales characteristics, response type, advance notice time, response adjustment time, response duration, response capacity and response period.

12. The virtual power plant resource classification and aggregation system according to claim 11, characterized in that: The resource classification module uses a normalization method to normalize the distributed resource characteristics based on a numerical representation model of distributed resource characteristics; and according to the normalization processing result, the distributed resources are classified by a clustering algorithm and a second-order Minkowski distance to obtain different types of distributed resources. The distributed resource characteristics can be normalized by a min-max normalization method according to the numerical representation model of the distributed resource characteristics to obtain a normalization processing result; according to the normalization processing result, the second-order Minkowski distance between different distributed resources is calculated by the second-order Minkowski distance; based on the K-means clustering algorithm, the distributed resources are classified according to the second-order Minkowski distance between the distributed resources to obtain different types of distributed resources.

13. The virtual power plant resource classification and aggregation system according to claim 12, characterized in that: Based on the K-means clustering algorithm, the distributed resources are classified according to the second-order Minkowski distance between the distributed resources, and different types of distributed resources are obtained, including: Randomly select several data points from the distributed resources of the virtual power plant as cluster centers, and assign each distributed resource to the resource category represented by the nearest cluster center according to the Minkowski distance between different distributed resources to form a preliminary clustering result; For each resource category, calculate the average value of all distributed resources in the resource category, and use the average value of distributed resources as the new cluster center; Compare the change value of the cluster center. If the change value of the cluster center is less than the set threshold, output the clustering result of the distributed resources to obtain different types of distributed resources. Otherwise, recalculate the Minkowski distance between different distributed resources and update the cluster center according to the recalculated result. When the change value of the cluster center is less than the set threshold, stop updating and output the clustering result of the distributed resources to obtain different types of distributed resources.

14. The virtual power plant resource classification and aggregation system according to claim 10, characterized in that: The feasible domain determination module performs Minkowski summation on the same type of distributed resources through the vertex search aggregation method to obtain the feasible domains of multiple types of distributed resources, and determines the feasible domain of the aggregated total power of the virtual power plant based on the feasible domains of multiple types of distributed resources. The feasible domains of different types of distributed resources can be determined through the Chino polyhedron method, and the overall feasible domain of the same type of distributed resources can be calculated through the Minkowski summation method; the feasible domains of multiple types of distributed resources are aggregated based on the vertex search method, and the vertices of the feasible domains of distributed resources are iteratively searched, and according to the vertices of the feasible domains of multiple types of distributed resources, the feasible domain of the aggregated total power of the virtual power plant is calculated through the feasible domain calculation formula of the aggregated total power of the virtual power plant.

15. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 9 are implemented.

16. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 9 are implemented.

Images