Photovoltaic power distribution method based on spectral clustering and multi-mode stable matching

Abstract

The invention discloses a photovoltaic power distribution method based on spectral clustering and multi-modal stable matching, which is applied to the technical field of photovoltaic power generation, and comprises the following steps: acquiring multi-criterion information of a user, and extracting feature data of the multi-criterion information; establishing a similarity matrix according to the feature data, and generating an adjacent matrix; classifying the users through spectral clustering and the adjacent matrix to obtain a user classification result; establishing a first preference list of a user group and a second preference list of a photovoltaic power station according to the user classification result; and based on the first preference list, the second preference list and a multi-modal stable matching algorithm, matching the user group and the photovoltaic power station, outputting a matching scheme, and completing optimal matching of the photovoltaic power station and the user group.

Description

Technical Field

[0001] The present invention relates to the technical field of photovoltaic power generation, and in particular to a photovoltaic power distribution method based on spectrum clustering and multi-modal stable matching. Background Art

[0002] With the widespread application of distributed energy, especially photovoltaic power generation systems, how to efficiently utilize photovoltaic power and achieve a reasonable match with user loads has become an important issue in power system optimization. The intermittent and volatile nature of photovoltaic power generation, as well as the diversity and time-varying nature of user loads, increase the complexity of matching power supply and demand.

[0003] In the existing power dispatching and load matching technologies, traditional methods usually rely on a single criterion for power distribution. This method is difficult to meet the matching needs of photovoltaic power generation fluctuations and user load imbalance under complex multi-criteria conditions. Especially in the distributed photovoltaic power generation scenario, due to the influence of multiple factors such as geographical dispersion and transmission loss, the matching method of a single criterion often cannot effectively optimize the overall performance of the power system.

[0004] In order to overcome these defects, this application proposes a photovoltaic power distribution method based on spectral clustering and multi-modal stable matching to ensure efficient consumption of photovoltaic power, load balancing and the stability of the power system, thereby improving the overall energy utilization efficiency. Summary of the invention

[0005] The purpose of this application is to provide a photovoltaic power distribution method based on spectral clustering and multi-modal stable matching, aiming to solve the problem that traditional methods are insufficient in dealing with the volatility of photovoltaic power generation and the diversity of user load demand.

[0006] To achieve the above objectives, this application provides the following technical solutions:

[0007] In a first aspect, the present application provides a photovoltaic power distribution method based on spectrum clustering and multi-modal stable matching, comprising:

[0008] Acquire multi-criteria information of the user, and extract feature data of the multi-criteria information;

[0009] Establishing a similarity matrix based on the feature data to generate an adjacency matrix;

[0010] Classifying users through spectral clustering and the adjacency matrix to obtain user classification results;

[0011] According to the user classification result, establishing a first preference list of user groups and a second preference list of photovoltaic power plants;

[0012] Based on the first preference list, the second preference list and a multi-modal stable matching algorithm, the user group is matched with the photovoltaic power station, a matching solution is output, and the optimal matching between the photovoltaic power station and the user group is completed.

[0013] In a second aspect, the present application provides a photovoltaic power distribution system based on spectrum clustering and multi-modal stable matching, comprising:

[0014] Feature extraction module: obtains multi-criteria information of the user and extracts feature data of the multi-criteria information;

[0015] Matrix establishment module: establishes a similarity matrix according to the feature data and generates an adjacency matrix;

[0016] Clustering module: classifying users through spectral clustering and the adjacency matrix to obtain user classification results;

[0017] Matching and output module: according to the user classification results, establish a first preference list of user groups and a second preference list of photovoltaic power stations; based on the first preference list, the second preference list and the use of a multi-modal stable matching algorithm, match the user group with the photovoltaic power station, output a matching solution, and complete the optimal matching between the photovoltaic power station and the user group.

[0018] In a third aspect, the present application provides a device, comprising a processor and a memory coupled to the processor, wherein the memory stores program instructions for implementing a photovoltaic power distribution method based on spectral clustering and multi-modal stable matching; and the processor is used to execute the program instructions stored in the memory to implement photovoltaic power distribution based on spectral clustering and multi-modal stable matching.

[0019] In a fourth aspect, the present application provides a storage medium storing program instructions executable by a processor, wherein the program instructions are used to execute a photovoltaic power distribution method based on spectral clustering and multi-modal stable matching.

[0020] The present application provides a photovoltaic power distribution method based on spectrum clustering and multi-modal stable matching, which has the following beneficial effects:

[0021] (1) Improving the global stability of matching results: By introducing a multi-modal stable matching algorithm, the matching results between PV power stations and user groups under multiple criteria are ensured to be consistent and stable, thus avoiding the instability problem caused by single-standard matching in the existing technology. In particular, when facing complex PV power generation fluctuations, the matching results are more robust and less susceptible to interference from external factors.

[0022] (2) Multi-criteria optimization to improve matching accuracy: This application can simultaneously process multiple matching criteria, such as user load pattern, photovoltaic power generation capacity, geographical distance, etc., and is no longer limited to a single power generation capacity or distance calculation; by comprehensively considering these criteria, the matching process can more accurately allocate photovoltaic power resources, ensure that the demand and supply between each photovoltaic power station and the user group are optimally balanced, and adapt to complex scenarios in distributed energy management;

[0023] (3) Strong adaptability and high robustness: Compared with the traditional matching method based on a single standard, this application can still maintain high robustness when facing changes in load demand and fluctuations in photovoltaic power generation. The matching results are insensitive to changes in external conditions and have a high degree of consistency; no matter how the user load and photovoltaic power generation fluctuate, the present invention can adaptively adjust to ensure stable operation of the system;

[0024] (4) Reduce power transmission losses and improve energy utilization: Through multi-criteria matching optimization, while ensuring the balance between supply and demand, it also minimizes the long-distance transmission losses of photovoltaic power; prioritizes the allocation of power generation capacity to user groups with close geographical distances, significantly improving energy utilization and reducing the operating costs of the power system;

[0025] (5) Improve economic benefits and resource efficiency: Through precise matching and optimization processes, unnecessary electricity waste and resource mismatch problems caused by unreasonable matching are reduced; for scenarios with large-scale distributed photovoltaic power stations and complex user groups, this application can achieve optimal matching in a relatively short time, reduce scheduling costs, and improve economic benefits. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 This is a flow chart of a photovoltaic power distribution method based on spectrum clustering and multi-modal stable matching according to Example 1 of the present application;

[0027] Figure 2 The meta-graph structure of Example 1 of the present application is C 8 Schematic diagram of the spectral clustering effect using different numbers of feature vectors;

[0028] Figure 3 The meta-graph structure of Example 1 of the present application is P 8 Schematic diagram of the spectral clustering effect using different numbers of feature vectors;

[0029] Figure 4 This is a flow chart of executing the multi-modal stable matching algorithm of Example 1 of the present application;

[0030] Figure 5 This is a schematic structural diagram of a photovoltaic power distribution system based on spectral clustering and multi-modal stable matching according to Example 2 of the present application;

[0031] Figure 6 This is a schematic diagram of the device structure of Example 3 of the present application;

[0032] Figure 7 This is a schematic diagram of the storage medium structure of Example 4 of the present application. DETAILED DESCRIPTION

[0033] It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0034] The following is an analysis of the solutions in the prior art in combination with related technologies.

[0035] In order to better achieve the consumption of photovoltaic power generation and balance supply and demand in complex power networks, researchers have gradually explored load matching methods based on multi-criteria optimization and clustering. These methods hope to achieve more accurate and stable power matching by considering multiple key factors, such as user load patterns, geographical locations, and photovoltaic power station power generation capacity. However, existing methods still have challenges such as unstable matching results, insufficient flexibility, and difficulty in adapting to dynamic changes in supply and demand.

[0036] Existing power load clustering technology solutions: At present, the research on power load clustering and matching mainly focuses on a single clustering method and a simple scheduling method based on load forecasting. Commonly used clustering algorithms in the existing technology include k-means, hierarchical clustering, and density-based DBSCAN. Although these methods perform well in traditional load analysis, their application has many shortcomings in the face of the multi-dimensional characteristics of photovoltaic power generation and load fluctuations.

[0037] (1) k-means clustering algorithm: k-means is a common clustering algorithm based on Euclidean distance, which performs classification by minimizing the distance between the cluster center and the data point. However, k-means performs clustering based on only a single criterion and lacks multi-criteria support. As a result, in complex load scenarios, the clustering results may not effectively reflect the diversity of user load patterns, especially when the PV power generation fluctuates greatly, and cannot adapt to the changes in the load demand of different users in real time. In addition, the k-means algorithm is sensitive to the initial cluster center and is prone to fall into local optimality, making it unsuitable for processing load data with irregular distribution [1].

[0038] (2) Hierarchical clustering algorithm: Hierarchical clustering recursively divides the data set into multiple subsets to form a tree-structured clustering result. Although hierarchical clustering can adapt to load data of different scales and is insensitive to initial conditions, its computational complexity is high when processing large-scale high-dimensional data, and it is difficult to adapt to the real-time and flexibility required for photovoltaic power generation and load matching [2]. At the same time, hierarchical clustering performs poorly in a multi-criteria environment and cannot balance the constraints of multiple different criteria.

[0039] (3) DBSCAN clustering algorithm: DBSCAN is a density-based clustering algorithm that can discover clusters of arbitrary shapes and distinguish noisy data points. It has advantages in processing spatial data and can identify high-density areas. However, DBSCAN has a strong dependence on parameters, especially under multi-criteria matching conditions. It is difficult to simultaneously consider the power generation characteristics, geographical location and user load requirements of photovoltaic power plants, resulting in limited application effect in photovoltaic power generation scenarios [3].

[0040] Challenges of multi-criteria load matching in existing technologies: Some studies have attempted to achieve load matching through weighted multi-criteria optimization methods, such as weighting power generation capacity, load demand, and transmission distance to obtain a matching solution. However, these weighted methods often rely on manually set weights and lack global adaptive capabilities. In the actual scenario of photovoltaic power generation, this approach cannot ensure the global optimal matching results under multi-dimensional conditions. Especially when facing changes in power generation and load, it is easy to cause unstable matching results, affecting the stability and economy of the power system [4].

[0041] Introduction of multimodal stable matching: In recent years, the multimodal stable matching problem has evolved from the classic marriage matching problem (Gale-Shapley algorithm) and has been widely used in fields such as resource allocation and task scheduling. The core advantage of the multimodal stable matching model is that it can achieve globally stable matching results under multiple preferences or multiple criteria, avoiding the emergence of local optimality [5]. By combining this algorithm with photovoltaic power load matching, a globally optimal and stable matching solution can be found based on multiple dimensions such as power generation, load demand, and geographical location. For example, in the power dispatching system, photovoltaic power stations can be matched with different user groups in multiple dimensions to ensure that each photovoltaic power station can supply power to the most suitable load area, reduce transmission losses, and optimize the utilization rate of photovoltaic power generation. This application uses spectral clustering to classify loads and combines multimodal stable matching technology to achieve supply and demand matching under multi-criteria conditions to improve the global stability and energy efficiency of the system.

[0042] [1]Hartigan, JA, & Wong, MA (1979). Algorithm AS136: A K-meansclustering algorithm. Journal of the Royal Statistical Society: Series C (Applied Statistics), 28 (1), 100-108.

[0043] [2]Ester, M., Kriegel, HP, Sander, J., & Xu,

[0044] [3]Kaufman,L.,&Rousseeuw,PJ(2009).Finding Groups in Data: AnIntroduction to Cluster Analysis.John Wiley&Sons.

[0045] [4]Gale, D., & Shapley, LS (1962). College admissions and the stability of marriage. The American Mathematical Monthly, 69 (1), 9-15.

[0046] [5]Chen, Jiehua, Rolf Niedermeier, and Piotr Skowron. "Stable marriage with multi-modal preferences." Proceedings of the 2018ACM Conference on Economics and Computation. 2018.

[0047] In summary, in the existing photovoltaic power station and user load matching and clustering technologies, traditional algorithms such as load forecasting-based scheduling methods, k-means clustering, and geographic distance-based matching methods mainly rely on a single standard for load classification and matching. However, in the face of the volatility of distributed photovoltaic power generation, the diversity of user loads, and the complexity of geographical distribution, these methods have many shortcomings, especially under multi-criteria conditions, it is difficult to ensure the global stability of clustering and matching results, supply and demand balance, and efficient consumption. Specific shortcomings include:

[0048] (1) Limitations of a single criterion: Traditional clustering and matching algorithms are mostly based on a single criterion and cannot handle complex multi-dimensional, multi-criteria data. For example, user load is not only affected by power demand, but also closely related to changes in geographic location and load patterns. Clustering and matching under a single criterion can easily ignore other key factors, leading to an imbalance in power supply and demand and unreasonable matching.

[0049] (2) Lack of multimodal support: In the face of distributed photovoltaic power generation and diverse user loads, existing clustering and matching methods lack an effective mechanism to integrate information from multiple dimensions or modalities. The fluctuations in photovoltaic power generation, geographical distribution, and user load patterns are complex and changeable. Traditional methods cannot fully utilize the correlation between the various criteria, resulting in unstable clustering and matching results and difficulty in optimizing the performance of multiple dimensions at the same time.

[0050] (3) Unstable clustering and matching results: Existing clustering and matching algorithms are sensitive to initial conditions and are prone to falling into local optimality, resulting in inconsistent clustering or matching results. The volatility of photovoltaic power generation further exacerbates the problem, making it difficult to ensure the stability and robustness of clustering and matching under multiple criteria.

[0051] (4) Insufficient multi-criteria optimization: Existing technologies deal with the matching and clustering of photovoltaic power generation and user loads by weighting or setting parameters, but they rely on manually set weights and lack adaptability and global optimality. As the scale and complexity of the power grid increase, the efficiency, stability and accuracy of clustering and matching under multi-criteria of existing technologies have significantly decreased.

[0052] In view of the shortcomings of the existing technology, this application introduces spectral clustering and multimodal stable matching technology to optimize the clustering and matching process of photovoltaic power generation and user areas under multiple criteria, ensuring the global consistency of clustering results and the stability and supply-demand balance of matching.

[0053] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0054] Example 1

[0055] See also Figure 1 , is a flow chart of a photovoltaic power distribution method based on spectrum clustering and multi-modal stable matching according to Example 1 of the present application; the steps include:

[0056] S1: Acquire multi-criteria information of a user, and extract feature data of the multi-criteria information.

[0057] In this embodiment, the characteristic data includes but is not limited to: user demand, load fluctuation, geographical location, etc.

[0058] S2: Establish a similarity matrix based on the feature data to generate an adjacency matrix.

[0059] In this embodiment, the feature data is calculated by distance measurement, such as Euclidean distance, cosine similarity, etc. to establish an N×N similarity matrix A; wherein N is the number of users, and the element a of the similarity matrix ij is the similarity between user i and user j.

[0060] The similarity matrix A is converted into an adjacency matrix, in which users with the highest similarity are connected by edges to form a graph structure.

[0061] S3: Classify users through spectral clustering and the adjacency matrix to obtain user classification results.

[0062] In this embodiment, spectral clustering is used to classify users. Spectral clustering is a graph theory-based method that identifies the global structure in the data by decomposing the eigenvalues ​​of the similarity matrix. The specific steps include:

[0063] According to the adjacency matrix, a graph Laplacian matrix L is constructed.

[0064] Perform eigenvalue decomposition on the graph Laplacian matrix L, extract the first k smallest eigenvectors, and form user embedding in a low-dimensional space.

[0065] The feature vectors are clustered by a clustering algorithm to divide users into several categories, each of which includes user groups with similar load characteristics, that is, generating user classification results. Each user group includes users with x similar load characteristics, laying the foundation for subsequent matching of photovoltaic power stations.

[0066] See also Figure 2 , the metagraph structure of Example 1 of the present application is C 8 Schematic diagram of the spectral clustering effect using different numbers of feature vectors; Figure 3 The meta-graph structure of Example 1 of the present application is P 8 Schematic diagram of the spectral clustering effect using different numbers of feature vectors.

[0067] For instances where the optimal clusters have special inter-class structures, using a smaller number of feature vectors can not only reduce the computational overhead but also improve the clustering accuracy. Figure 2 and Figure 3 Shows that the metagraph structure is C 8 and P 8Based on the randomly generated examples of the stochastic blockmodel, the spectral clustering effect using different numbers of feature vectors. Among them, p is the probability of adding edges within a cluster, q is the probability of adding edges between clusters, and t is the number of feature vectors used. It can be seen that in a specific metagraph structure, spectral clustering using a smaller number of feature vectors has a better clustering effect. Figure 2 In , when t = 3, the probability of adding edges inside the cluster is the lowest; when t = 8, the probability of adding edges inside the cluster is the highest; Figure 3 In the example, when t=5, the probability of adding edges inside the cluster is the lowest; when t=8, the probability of adding edges inside the cluster is the highest.

[0068] S4: establishing a first preference list of user groups and a second preference list of photovoltaic power stations according to the user classification results.

[0069] In this embodiment, after obtaining the user classification results, preference lists based on different standards are constructed for user groups and photovoltaic power stations respectively; specifically, the following are included:

[0070] Establish the first preference list of user groups: based on the total load demand of the user group, including daily electricity peak, volatility, etc.; the distance between the user group and the photovoltaic power station, which directly affects the loss and efficiency of power transmission; the power generation of the photovoltaic power station.

[0071] Establish a second preference list for photovoltaic power stations: according to the load demand of the user group, select the user group that matches its power generation capacity, and give priority to the group with a higher match with its own power generation; according to the geographical distance to the user group, give priority to the user group closest to reduce power transmission losses; give priority to the user group with the smallest load fluctuation to improve the stability of power supply.

[0072] Based on the above criteria, a first preference list of the user group and a second preference list of the photovoltaic power station are generated respectively for use in the subsequent matching process.

[0073] S5: Based on the first preference list, the second preference list and a multi-modal stable matching algorithm, the user group is matched with the photovoltaic power station, a matching solution is output, and an optimal matching between the photovoltaic power station and the user group is completed.

[0074] In this embodiment, after the preference list is generated, a multi-modal stable matching algorithm is used to achieve global matching between user groups and photovoltaic power stations by optimizing the matching process under multiple criteria. The specific steps include:

[0075] Construct the constraints of the multimodal stable matching problem to satisfy:

[0076]

[0077] Among them, x ij Indicates whether participant i matches participant j, where i and j both belong to participant set A; if i matches j, then x ij =1; otherwise x ij =0; C is a set of preference criteria; L(j|i,k) is a set of options that rank lower than j in i's preference list under criterion k; where participants refer to users who participate in matching.

[0078] Construct the corresponding set of bad events, that is, the opposite events of the events corresponding to the constraints of the original problem;

[0079] Perform random opposition sampling on the constraint variables and determine whether a bad event occurs; if a bad event occurs, resample;

[0080] The Lovász local lemma is used to analyze the probability of correct sampling; by analyzing the probability of bad events, the number of sampling rounds required for the algorithm to obtain the optimal solution after random sampling of variables is derived.

[0081] See also Figure 4 , which is a flow chart of executing the multimodal stable matching algorithm of Example 1 of the present application. Through the multimodal stable matching algorithm, it is possible to ensure that the desired match is obtained with a certain probability within the polynomial time. If there is no variable assignment that meets the preset conditions within the preset time threshold, the variable that is assigned a value of 1 and appears the most times among all violated constraints is assigned a value of 0 until there are no violated constraints; the final variable assignment is converted into the corresponding match.

[0082] Furthermore, for unmatched nodes, each node regenerates a new preference list based on the existing matching situation, and matches the unmatched nodes through the Gale-Shapley algorithm. Specifically, the user group sends matching requests to the photovoltaic power station in turn according to the first preference list, and gives priority to the photovoltaic power station that best meets its needs; the photovoltaic power station selects the user group's request according to the second preference list, and selects the user group whose load demand is most matched with its power generation capacity and geographical distance. Through the stable matching mechanism of the Gale-Shapley algorithm, the matching between the user group and the photovoltaic power station is optimized until a preset stable matching state is reached, that is, the optimal matching between the photovoltaic power station and the user group is completed.

[0083] This stable matching process ensures the matching stability between the photovoltaic power station and the user group under multiple criteria, avoids local optimality, and maximizes the consumption of photovoltaic power and the balance between supply and demand. The final output matching solution can ensure the efficient consumption of the photovoltaic power station's power generation, reduce power transmission losses, and maintain the dynamic balance of user loads.

[0084] In summary, Example 1 of the present application combines spectral clustering with multimodal stable matching technology to optimize the matching relationship between photovoltaic power generation and user load. Through the spectral clustering algorithm, users are accurately classified to form user groups with similar load requirements; through the multimodal stable matching algorithm, the optimal matching between photovoltaic power stations and user groups is achieved on the basis of comprehensive consideration of multiple criteria such as user load, photovoltaic power station power generation capacity and geographical distance. This application not only improves the global stability and accuracy of matching, but also reduces the loss during power transmission, realizes accurate matching and efficient scheduling in distributed photovoltaic power generation systems, and is suitable for complex load management and scheduling scenarios of distributed photovoltaic power generation.

[0085] Example 2

[0086] See also Figure 5 , is a structural diagram of a photovoltaic power distribution system based on spectrum clustering and multi-modal stable matching according to Example 2 of the present application; the specific contents include:

[0087] Feature extraction module: obtains multi-criteria information of the user and extracts feature data of the multi-criteria information;

[0088] Matrix establishment module: establishes a similarity matrix according to the feature data and generates an adjacency matrix;

[0089] Clustering module: classifying users through spectral clustering and the adjacency matrix to obtain user classification results;

[0090] Matching and output module: according to the user classification results, establish a first preference list of user groups and a second preference list of photovoltaic power stations; based on the first preference list, the second preference list and the use of a multi-modal stable matching algorithm, match the user group with the photovoltaic power station, output a matching solution, and complete the optimal matching between the photovoltaic power station and the user group.

[0091] Example 3

[0092] See also Figure 6 , is a schematic diagram of the device structure of Embodiment 3 of the present application. The device 50 includes a processor 51 and a memory 52 coupled to the processor 51 .

[0093] The memory 52 stores program instructions for implementing the above-mentioned photovoltaic power distribution method based on spectrum clustering and multi-modal stable matching.

[0094] The processor 51 is used to execute program instructions stored in the memory 52 to implement photovoltaic power distribution based on spectrum clustering and multi-modal stability matching.

[0095] The processor 51 may also be referred to as a CPU (Central Processing Unit).

[0096] The processor 51 may be an integrated circuit chip with signal processing capabilities. The processor 51 may also be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0097] Example 4

[0098] See also Figure 7 , which is a schematic diagram of the structure of the storage medium of Example 4 of the present application. The storage medium of the embodiment of the present application stores a program file 61 that can implement all the above methods, wherein the program file 61 can be stored in the above storage medium in the form of a software product, including a number of instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) or a processor (processor) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, or a computer, a server, a mobile phone, a tablet, and other devices.

[0099] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, device, article or method including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, device, article or method. In the absence of further restrictions, an element defined by the sentence "includes a ..." does not exclude the presence of other identical elements in the process, device, article or method including the element.

[0100] The above description is only a preferred embodiment of the present application, and does not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly used in other related technical fields, are also included in the patent protection scope of the present application.

[0101] Although the embodiments of the present application have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present application, and that the scope of the present application is defined by the appended claims and their equivalents.

[0102] Of course, the present invention may have many other implementations. Based on this implementation, other implementations obtained by ordinary technicians in this field without any creative work are all within the scope of protection of the present invention.

Claims

1. A photovoltaic power distribution method based on spectrum clustering and multi-modal stable matching, characterized in that: include: Acquire multi-criteria information of the user, and extract feature data of the multi-criteria information; Establishing a similarity matrix based on the feature data to generate an adjacency matrix; Classifying users through spectral clustering and the adjacency matrix to obtain user classification results; According to the user classification result, establishing a first preference list of user groups and a second preference list of photovoltaic power plants; Based on the first preference list, the second preference list and a multi-modal stable matching algorithm, the user group is matched with the photovoltaic power station, a matching solution is output, and the optimal matching between the photovoltaic power station and the user group is completed.

2. The photovoltaic power distribution method based on spectral clustering and multi-modal stable matching according to claim 1, characterized in that: The step of establishing a similarity matrix and generating an adjacency matrix according to the feature data specifically includes the following steps: The feature data is calculated by distance measurement to establish an N×N similarity matrix A; where N is the number of users, and the element a of the similarity matrix ij is the similarity between user i and user j; The similarity matrix A is converted into an adjacency matrix, in which users with the highest similarity are connected by edges to form a graph structure.

3. The photovoltaic power distribution method based on spectrum clustering and multi-modal stable matching according to claim 1, characterized in that: The step of classifying users by using spectral clustering and the adjacency matrix to obtain user classification results specifically includes the following steps: According to the adjacency matrix, construct a graph Laplacian matrix L; Performing eigenvalue decomposition on the graph Laplacian matrix L, extracting the first k smallest eigenvectors, and forming user embedding in a low-dimensional space; The feature vectors are clustered by a clustering algorithm to divide users into several categories, each category including a user group with similar load characteristics, that is, to generate a user classification result.

4. The photovoltaic power distribution method based on spectrum clustering and multi-modal stable matching according to claim 1, characterized in that: The step of establishing a first preference list of user groups and a second preference list of photovoltaic power stations according to the user classification result specifically includes the following steps: Establishing a first preference list of the user group based on the total load demand of the user group, the distance between the user group and the photovoltaic power station, and the power generation of the photovoltaic power station; Establish a second preference list for photovoltaic power stations: select user groups that match their power generation capacity based on their load demands; give priority to the user groups that are closest based on their geographical distances; and give priority to user groups with the smallest load fluctuations.

5. The photovoltaic power distribution method based on spectrum clustering and multi-modal stable matching according to claim 1, characterized in that: In the step of matching the user group with the photovoltaic power station based on the first preference list, the second preference list and a multi-modal stable matching algorithm, outputting a matching solution, and completing the optimal matching between the photovoltaic power station and the user group, the following steps are specifically included: In the multimodal stable matching algorithm, the constraints of the multimodal stable matching problem are constructed to satisfy: Among them, x ij Indicates whether participant i matches participant j, where i and j both belong to participant set A; if i matches j, then x ij =1; otherwise x ij = 0; C is the set of preference criteria; L(j|i,k) is the set of options that rank lower than j in i's preference list under criterion k; Construct the corresponding set of bad events, that is, the opposite events of the events corresponding to the constraints of the original problem; Perform random opposition sampling on the constraint variables and determine whether a bad event occurs; if a bad event occurs, resample; Use Lovász local lemma to analyze the probability of correct sampling; If there is no variable assignment that meets the preset conditions within the preset time threshold, the variable that is assigned a value of 1 and appears the most times among all violated constraints is assigned a value of 0 until there are no violated constraints; the final variable assignment is converted into the corresponding match; For unmatched nodes, a new preference list is regenerated and the unmatched nodes are matched using the Gale-Shapley algorithm.

6. The photovoltaic power distribution method based on spectrum clustering and multi-modal stable matching according to claim 5, characterized in that: For unmatched nodes, a new preference list is regenerated, and the step of matching the unmatched nodes by using the Gale-Shapley algorithm specifically includes the following steps: The matching between the user group and the photovoltaic power station is optimized by the Gale-Shapley algorithm until a preset stable matching state is reached, that is, the optimal matching between the photovoltaic power station and the user group is completed.

7. A system for photovoltaic power distribution method based on spectrum clustering and multi-modal stable matching according to claim 1, characterized in that: include: Feature extraction module: obtains multi-criteria information of the user and extracts feature data of the multi-criteria information; Matrix establishment module: establishes a similarity matrix according to the feature data and generates an adjacency matrix; Clustering module: classifying users through spectral clustering and the adjacency matrix to obtain user classification results; Matching and output module: establishing a first preference list of user groups and a second preference list of photovoltaic power stations according to the user classification results; Based on the first preference list, the second preference list and a multi-modal stable matching algorithm, the user group is matched with the photovoltaic power station, a matching solution is output, and the optimal matching between the photovoltaic power station and the user group is completed.

8. A device, characterized in that The device includes a processor and a memory coupled to the processor, wherein the memory stores program instructions for implementing the photovoltaic power distribution method based on spectral clustering and multi-modal stable matching as described in any one of claims 1-6; the processor is used to execute the program instructions stored in the memory to implement photovoltaic power distribution based on spectral clustering and multi-modal stable matching.

9. A storage medium, characterized in that: Program instructions executable by a processor are stored, and the program instructions are used to execute the photovoltaic power distribution method based on spectrum clustering and multi-modal stable matching according to any one of claims 1 to 6.

Images