Distribution area distributed photovoltaic cluster division method and device, medium and electronic equipment

Abstract

The invention discloses a transformer area distributed photovoltaic cluster division method and device, a medium and electronic equipment, and relates to the technical field of distributed photovoltaic regulation and control. The method comprises the following steps: acquiring parameter data respectively corresponding to a plurality of photovoltaic power supplies; based on the parameter data, determining an initial centroid and the number of photovoltaic clusters during photovoltaic cluster division; based on the initial centroid and the number of photovoltaic clusters, carrying out cluster division on the plurality of photovoltaic power supplies to obtain each photovoltaic cluster; based on each photovoltaic cluster, updating the initial centroid to obtain an updated centroid; calculating a comprehensive performance index commonly corresponding to each photovoltaic cluster; if the updated centroid change or the comprehensive performance index does not meet the corresponding condition, performing cluster division on the plurality of photovoltaic power supplies again based on the updated centroid; and repeating the process of dividing the photovoltaic clusters until the updated mass center change and the comprehensive performance index meet the corresponding conditions, and outputting each photovoltaic cluster. According to the invention, the overall division effect of the photovoltaic cluster can be ensured.

Description

Technical Field

[0001] The present application relates to the field of distributed photovoltaic control technology, and in particular to a method, device, medium and electronic equipment for dividing a distributed photovoltaic cluster in an area. Background Art

[0002] The output of photovoltaic power sources is random and uncertain. The decentralized access of many small and medium-power photovoltaic power sources to the substation will greatly change the operating characteristics of the substation. When faced with the access of a large number of decentralized photovoltaic power sources, the traditional substation energy management system has disadvantages such as communication delay, large amount of calculation, and too many control devices. Cluster division provides a new idea for handling a large number of decentralized photovoltaic power sources. A distributed photovoltaic cluster refers to a collection of distributed photovoltaic units, energy storage and loads that are geographically close or electrically similar or complementary in a substation area. Clustered distributed power sources not only effectively utilize new energy, but also alleviate the volatility and uncertainty brought to the system by distributed photovoltaic power generation. It is the future development direction of renewable energy.

[0003] At present, photovoltaic power sources are usually divided into clusters based on their geographical locations. However, this cluster division method takes into account relatively single factors and is difficult to ensure the overall division effect of photovoltaic clusters. Summary of the invention

[0004] In view of this, the present application provides a method, device, medium and electronic equipment for dividing a distributed photovoltaic cluster in a substation, which mainly enables multi-dimensional comprehensive consideration when dividing the photovoltaic cluster, thereby ensuring the overall division effect of the photovoltaic cluster.

[0005] According to the first aspect of the present application, a method for dividing a distributed photovoltaic cluster in an area is provided, the method comprising: Obtain parameter data corresponding to multiple photovoltaic power sources; Based on the parameter data, determining the initial centroid and the number of photovoltaic clusters when dividing the photovoltaic clusters; Based on the initial centroid and the number of photovoltaic clusters, the multiple photovoltaic power sources are divided into clusters to obtain photovoltaic clusters; Based on the respective photovoltaic clusters, the initial centroid is updated to obtain an updated centroid; Calculating the comprehensive performance index corresponding to each photovoltaic cluster, wherein the comprehensive performance index is determined by a cluster structure strength index, a cluster power balance index and a cluster scale index; If the updated centroid changes or the comprehensive performance index does not meet the corresponding conditions, re-clustering the multiple photovoltaic power sources based on the updated centroid; The process of updating the centroid, calculating the comprehensive performance index and dividing the photovoltaic clusters is repeated until the centroid change after the update and the comprehensive performance index both meet corresponding conditions, and the photovoltaic clusters finally divided are output.

[0006] According to a second aspect of the present application, a distributed photovoltaic cluster division device is provided, the device comprising: An acquisition unit, used to acquire parameter data corresponding to a plurality of photovoltaic power sources; A determination unit, used to determine the initial centroid and the number of photovoltaic clusters when dividing the photovoltaic clusters based on the parameter data; A division unit, configured to divide the plurality of photovoltaic power sources into clusters based on the initial centroid and the number of photovoltaic clusters to obtain individual photovoltaic clusters; An updating unit, configured to update the initial centroid based on each photovoltaic cluster to obtain an updated centroid; A calculation unit, used to calculate the comprehensive performance index corresponding to each photovoltaic cluster, wherein the comprehensive performance index is determined by a cluster structure strength index, a cluster power balance index and a cluster scale index; The division unit is further configured to re-cluster the plurality of photovoltaic power sources based on the updated centroid if the updated centroid changes or the comprehensive performance index does not meet corresponding conditions; The output unit is used to repeat the process of updating the centroid, calculating the comprehensive performance index and dividing the photovoltaic clusters until the updated centroid change and the comprehensive performance index meet the corresponding conditions, and then output each photovoltaic cluster finally divided.

[0007] According to a third aspect of the present application, a storage medium is provided, on which a computer program is stored, and when the program is executed by a processor, the above-mentioned method for dividing a distributed photovoltaic cluster in an area is implemented.

[0008] According to a fourth aspect of the present application, an electronic device is provided, comprising a storage medium, a processor, and a computer program stored on the storage medium and executable on the processor, wherein the processor implements the above-mentioned method for dividing a distributed photovoltaic cluster in an area when executing the program.

[0009] By means of the above technical scheme, the present application provides a method, device, medium and electronic device for dividing a distributed photovoltaic cluster in a substation. By calculating the cluster structure strength index, cluster power balance index and cluster scale index of the photovoltaic cluster, the photovoltaic cluster can be balanced in size and have a certain voltage regulation capability on the basis of ensuring the reasonable matching of the source and load within the photovoltaic cluster and the close connection between the nodes, so as to facilitate the subsequent operation adjustment. That is, the present application can make multi-dimensional comprehensive considerations when dividing the cluster, so as to ensure the overall division effect of the photovoltaic cluster. In addition, the present application can automatically determine the initial centroid and the number of photovoltaic clusters by improving the traditional clustering algorithm, so as to avoid falling into the local optimal solution, achieve global optimization, and improve the rationality, efficiency and accuracy of photovoltaic cluster division.

[0010] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings: Figure 1 A schematic diagram of a process for dividing a distributed photovoltaic cluster in an area provided in an embodiment of the present application is shown; Figure 2 A schematic diagram of a process of dividing another distributed photovoltaic cluster in an area provided in an embodiment of the present application is shown; Figure 3 A schematic diagram of the structure of a distributed photovoltaic cluster division device in a metropolitan area provided in an embodiment of the present application is shown; Figure 4 A schematic diagram of the structure of another distributed photovoltaic cluster division device in an area provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0012] The present application will be described in detail below with reference to the accompanying drawings and in combination with embodiments. It should be noted that the embodiments and features in the embodiments of the present application can be combined with each other without conflict.

[0013] The existing cluster division method takes into account relatively simple factors and it is difficult to ensure the overall division effect of the photovoltaic cluster.

[0014] In order to solve the above problems, the embodiment of the present invention provides a method for dividing a distributed photovoltaic cluster in a station area, such as Figure 1 As shown, the method includes: Step 101: Obtain parameter data corresponding to a plurality of photovoltaic power sources.

[0015] The parameter data of each photovoltaic power source specifically includes geographical location, peak power, open circuit voltage, short circuit current, etc.

[0016] The embodiment of the present invention is mainly applicable to the scenario of clustering photovoltaic power sources. The execution subject of the embodiment of the present invention is a device or equipment capable of clustering photovoltaic power sources, which can be specifically set on the server side.

[0017] According to the embodiment of the present invention, in order to divide a plurality of photovoltaic power sources into clusters, it is necessary to obtain parameter data such as the geographical location, peak power, open circuit voltage, short circuit current, etc. of each photovoltaic power source in advance.

[0018] Step 102: Determine the initial centroid and the number of photovoltaic clusters when dividing the photovoltaic clusters based on the parameter data.

[0019] In the existing clustering algorithm (K-Means++), the initial centroid is randomly selected, and the number of photovoltaic clusters needs to be manually specified, which will bring certain uncertainties and easily fall into the local optimal solution during clustering. In order to overcome the above defects, the embodiment of the present invention improves the clustering algorithm (K-Means++) based on the simulated annealing algorithm (SA) and median threshold segmentation, so that the improved clustering algorithm can automatically determine the initial centroid and the number of clusters (the number of photovoltaic clusters), thereby avoiding falling into the local optimal solution, achieving global optimization, and improving the rationality, efficiency and accuracy of cluster division.

[0020] For the process of automatically determining the initial centroid and the number of photovoltaic clusters, step 102 specifically includes: determining a target photovoltaic power source from the multiple photovoltaic power sources based on the parameter data; calculating the distances between the multiple photovoltaic power sources and the target photovoltaic power source, and determining the median distance from the distances between the multiple photovoltaic power sources and the target photovoltaic power source; using the median distance as a first segmentation threshold, segmenting a target sample set consisting of the multiple photovoltaic power sources to obtain a first sample set and a second sample set, wherein the distance between each photovoltaic power source in the first sample set and the target photovoltaic power source is less than the median distance, and the distance between each photovoltaic power source in the second sample set and the target photovoltaic power source is greater than or equal to the median distance; determining the first photovoltaic power source in the first sample set that is closest to the target photovoltaic power source, and using the first photovoltaic power source as the sample center; determining a second segmentation threshold corresponding to the second sample set, and continuing to segment the second sample set based on the second segmentation threshold, while accumulating the number of segmentations; Repeat the segmentation threshold determination process and the sample set segmentation process until the segmentation times accumulate to a preset number of times and the change rate of the segmentation threshold before and after meets the preset conditions, then output each sample center; use each sample center as the initial centroid, and determine the number of photovoltaic clusters according to the accumulated segmentation times.

[0021] When determining a target photovoltaic power source, based on the parameter data, a center point corresponding to the multiple photovoltaic power sources is calculated; based on the parameter data, distances between the multiple photovoltaic power sources and the center point are calculated; and based on the distances between the multiple photovoltaic power sources and the center point, a target photovoltaic power source closest to the center point is determined from the multiple photovoltaic power sources.

[0022] The distance calculated in the embodiment of the present invention may specifically refer to the Euclidean distance.

[0023] Specifically, the parameter data of the photovoltaic power source is first subjected to preprocessing operations such as normalization, and then the mean of the parameter data of multiple photovoltaic power sources is calculated based on the processed parameter data, and the center point corresponding to the multiple photovoltaic power sources is determined based on the mean of the parameter data. For example, the parameter data includes the geographical location and the peak power, and the geographical location includes the longitude data and the latitude data. Based on the parameter data, the multiple photovoltaic power sources are respectively mapped to the corresponding dimensional space, and each photovoltaic power source is regarded as a point in the space, and then the mean of the longitude data, the mean of the latitude data and the mean of the peak power of the multiple photovoltaic power sources are respectively calculated, and the center point corresponding to the multiple photovoltaic power sources is determined based on the mean of the longitude data, the mean of the latitude data and the mean of the peak power.

[0024] After determining the center point, the Euclidean distance between each photovoltaic power source and the center point is calculated based on the parameter data, and the minimum Euclidean distance is determined based on the calculated multiple Euclidean distances. The photovoltaic power source corresponding to the minimum Euclidean distance is determined as the target photovoltaic power source c1 closest to the center point.

[0025] Then, the Euclidean distances between all photovoltaic power sources and the target photovoltaic power source c1 are calculated, and the calculated Euclidean distances are sorted from large to small or from small to large. According to the sorting result, the median distance m1 is determined.

[0026] Furthermore, the median distance is used as the first segmentation threshold to segment the target sample set consisting of all photovoltaic power sources to obtain the first sample set U j and the second sample set U j+1 , this segmentation is the first segmentation, where the first sample set U j The Euclidean distance between each photovoltaic power source in and the target photovoltaic power source c1 is less than the median distance m1. The second sample set U j+1The Euclidean distance between each photovoltaic power source in and the target photovoltaic power source c1 is equal to or greater than the median distance m1. Then, the first sample set U is determined respectively. j The first photovoltaic power source c closest to the target photovoltaic power source c1 j , and the second sample set U j+1 The second photovoltaic power source c closest to the target photovoltaic power source c1 j+1 and the first photovoltaic power source c j and the second photovoltaic power source c j+1 They are used as two sample centers respectively.

[0027] After the first segmentation is completed, the number of segmentations is increased by 1, and the second sample set U is continued. j+1 When performing the first segmentation, the above process is repeated to determine the second sample set U j+1 The corresponding center point is then calculated for the second sample set U j+1 The Euclidean distance between each photovoltaic power source and the center point in the second sample set U is obtained based on the Euclidean distance. j+1 The target photovoltaic power source c2 closest to the center point is determined. Then the second sample set U is calculated respectively. j+1 The Euclidean distance between each photovoltaic power source and the target photovoltaic power source c2 is calculated, and the calculated Euclidean distances are sorted from large to small or from small to large, and the median distance m2 is determined according to the sorting result.

[0028] Furthermore, the median distance m2 is used as the second segmentation threshold, and the second sample set U j+1 Split and get and U j+2 , and add 1 to the number of divisions. Repeat the above process until the cumulative number of divisions reaches i Not less than 3 times, segmentation threshold m i-1 Compared with the segmentation threshold m i-2 The rate of change of is greater than 1, and the segmentation threshold m i Compared with the segmentation threshold m i-1 When the rate of change is less than 1, stop segmentation and output i +1 sample center C k =(c1, c2, …, c i+1 ), otherwise, continue with the split.

[0029] The sample center C that will be output eventually k =(c1, c2, …, c i+1 ) is used as the initial centroid of the photovoltaic cluster division, and the number of photovoltaic clusters (number of clusters) is i +1.

[0030] The embodiment of the present invention improves the clustering algorithm K-Means++ based on the simulated annealing algorithm and the median threshold. The improved clustering algorithm can automatically determine the optimal initial number of clusters and cluster centroids, solves the problem of uncertainty of the initial centroid and the number of clusters of K-Means++, and makes the distributed photovoltaic clusters clustered and divided by the method more reasonable.

[0031] Step 103: Based on the initial centroid and the number of photovoltaic clusters, the plurality of photovoltaic power sources are divided into clusters to obtain photovoltaic clusters.

[0032] For the embodiment of the present invention, after determining the initial centroid and the number of photovoltaic clusters, multiple photovoltaic power sources can be clustered. For this process, step 103 specifically includes: based on the parameter data, calculating the distances between the multiple photovoltaic power sources and the initial centroid respectively; based on the distances between the multiple photovoltaic power sources and the initial centroid respectively, and the number of photovoltaic clusters, clustering the multiple photovoltaic power sources to obtain the individual photovoltaic power sources.

[0033] Specifically, for any photovoltaic power source, the Euclidean distance between the photovoltaic power source and each initial mass center is calculated respectively, the minimum Euclidean distance is selected from the calculated Euclidean distances, and the photovoltaic power source is divided into the photovoltaic cluster of the initial mass center corresponding to the minimum Euclidean distance. Thus, according to the above process, all photovoltaic power sources can be divided into corresponding photovoltaic clusters.

[0034] Step 104: Based on the photovoltaic clusters, the initial centroid is updated to obtain an updated centroid.

[0035] After the preliminary division of the photovoltaic clusters is completed, the embodiment of the present invention adopts the mean to update the centroid. For this process, step 104 specifically includes: calculating the average parameter value corresponding to each photovoltaic cluster according to the parameter data; and updating the initial centroid based on the average parameter value to obtain the updated centroid.

[0036] Step 105: Calculate the comprehensive performance index corresponding to each photovoltaic cluster.

[0037] Among them, the comprehensive performance index is determined by the cluster structure strength index, cluster power balance index and cluster scale index. The cluster structure strength index is used to measure the structural strength of the photovoltaic cluster and quantify the community structure strength in the complex network. The larger the cluster structure strength index is, the higher the degree of internal coupling in the cluster is. On the contrary, the smaller the cluster structure strength index is, the lower the degree of internal coupling in the cluster is. The cluster power balance index is used to measure the balance between active power and reactive power in the photovoltaic cluster. The larger the cluster power balance index is, the higher the balance between active power and reactive power in the cluster is. The cluster scale index, also known as the node similarity index, is used to evaluate the rationality of the scale of each photovoltaic cluster. The larger the cluster scale index is, the more reasonable the scale of the photovoltaic cluster is.

[0038] In order to ensure the overall division effect of the photovoltaic cluster, the embodiment of the present invention calculates the comprehensive performance index of the photovoltaic cluster during the photovoltaic cluster division process, that is, respectively calculates the cluster structure strength index, the cluster power balance index and the cluster scale index to verify the rationality of the photovoltaic cluster division, thereby ensuring the overall division effect of the photovoltaic cluster. For the specific calculation process of the cluster structure strength index, the cluster power balance index and the cluster scale index, see step 205 for details.

[0039] Step 106: If the updated centroid changes or the comprehensive performance index does not meet corresponding conditions, the plurality of photovoltaic power sources are re-divided into clusters based on the updated centroid.

[0040] For the embodiment of the present invention, if the updated centroid changes too much compared with the centroid before updating (initial centroid) or the calculated comprehensive performance index is less than or equal to the preset index threshold, the multiple photovoltaic power sources are re-clustered based on the updated centroid.

[0041] Step 107 , repeating the process of updating the centroid, calculating the comprehensive performance index and dividing the photovoltaic clusters until the updated centroid change and the comprehensive performance index meet corresponding conditions, and outputting each photovoltaic cluster finally divided.

[0042] According to the embodiment of the present invention, for each re-divided photovoltaic cluster, the centroid is continuously updated, and the comprehensive performance index of the photovoltaic cluster is calculated at the same time. If the centroid after this round of update changes little and the calculated comprehensive performance index is greater than the preset index threshold, the divided photovoltaic clusters are directly outputted. Otherwise, the above process is repeated.

[0043] The embodiment of the present invention provides a distributed photovoltaic cluster division method for a substation. By calculating the cluster structure strength index, cluster power balance index and cluster scale index of the photovoltaic cluster, it can ensure the reasonable matching of the source and load within the photovoltaic cluster and the close connection between the nodes, so that the size of the photovoltaic cluster is balanced and has a certain voltage regulation capability, which is convenient for subsequent operation adjustment. That is, the present application can make multi-dimensional comprehensive considerations when dividing the cluster, so as to ensure the overall division effect of the photovoltaic cluster. In addition, the embodiment of the present invention can automatically determine the initial centroid and the number of photovoltaic clusters by improving the traditional clustering algorithm, so as to avoid falling into the local optimal solution, achieve global optimization, and improve the rationality, efficiency and accuracy of photovoltaic cluster division.

[0044] Further, as a refinement and extension of the specific implementation of the above embodiment, in order to fully illustrate the implementation of this embodiment, this embodiment also provides another distributed photovoltaic cluster division method in the substation area, such as Figure 2 As shown, the method includes: Step 201: Obtain parameter data corresponding to a plurality of photovoltaic power sources.

[0045] The parameter data of each photovoltaic power source specifically includes geographical location, peak power, open circuit voltage, short circuit current, etc.

[0046] According to the embodiment of the present invention, in order to divide a plurality of photovoltaic power sources into clusters, it is necessary to obtain parameter data such as the geographical location, peak power, open circuit voltage, short circuit current, etc. of each photovoltaic power source in advance.

[0047] Step 202: Determine the initial centroid and the number of photovoltaic clusters when dividing the photovoltaic clusters based on the parameter data.

[0048] The process of determining the initial centroid and the number of photovoltaic clusters in the embodiment of the present invention is exactly the same as step 102 and will not be described in detail herein.

[0049] Step 203: Based on the initial centroid and the number of photovoltaic clusters, the plurality of photovoltaic power sources are divided into clusters to obtain photovoltaic clusters.

[0050] In the embodiment of the present invention, for any photovoltaic power source, the Euclidean distance between the photovoltaic power source and each initial mass center is calculated respectively, the minimum Euclidean distance is selected from the calculated Euclidean distances, and the photovoltaic power source is divided into the photovoltaic cluster of the initial mass center corresponding to the minimum Euclidean distance. Thus, according to the above process, all photovoltaic power sources can be divided into corresponding photovoltaic clusters.

[0051] Step 204: Based on the photovoltaic clusters, the initial centroid is updated to obtain an updated centroid.

[0052] According to the embodiment of the present invention, after the photovoltaic clusters are initially divided, the centroid of each photovoltaic cluster is updated by using the mean value to obtain an updated centroid.

[0053] Step 205 : respectively calculating the cluster structure strength index, cluster power balance index and cluster scale index corresponding to each of the photovoltaic clusters.

[0054] For the embodiment of the present invention, with respect to the process of calculating the cluster structure strength index corresponding to each photovoltaic cluster, the method includes: for each photovoltaic cluster in each photovoltaic cluster, calculating the electrical distance between any two photovoltaic power sources in each photovoltaic cluster; constructing an electrical distance matrix based on the electrical distance between any two photovoltaic power sources; calculating the edge weight between any two photovoltaic power sources based on the electrical distance matrix and the electrical distance between any two photovoltaic power sources; calculating the sum of the edge weights of each of the any two photovoltaic power sources; calculating the cluster structure strength index corresponding to each photovoltaic cluster based on the edge weight between the two photovoltaic power sources and the sum of the edge weights of each of the any two photovoltaic power sources; and determining the cluster structure strength index corresponding to each photovoltaic cluster based on the cluster structure strength index corresponding to each photovoltaic cluster. The specific formula is as follows:

[0055] in, Represents the cluster structure strength index corresponding to each photovoltaic cluster, m Represents the sum of the edge weights of all photovoltaic power nodes in the network corresponding to each photovoltaic cluster, represents the edge weight between any two photovoltaic power sources, and Represents photovoltaic power nodes i The sum of all edge weights and photovoltaic power node j The sum of all edge weights between any two photovoltaic power sources. The calculation formula is as follows:

[0056]

[0057] in, Represents the electrical distance between any two photovoltaic sources, q Is The electrical distance matrix, max( q ) represents the maximum electrical distance in the electrical distance matrix, Represents photovoltaic power source node i When the reactive power changes, the photovoltaic power nodej The voltage change of the photovoltaic power node i The ratio of the voltage change.

[0058] Therefore, according to the above formula, the cluster structure strength index corresponding to each photovoltaic cluster can be calculated: By calculating the average value of the structural strength index, the cluster structural strength index corresponding to each photovoltaic cluster can be obtained. .

[0059] Regarding the process of calculating the cluster power balance index corresponding to each photovoltaic cluster, the method includes: calculating the active power balance index corresponding to each photovoltaic cluster based on the net power characteristics of each photovoltaic cluster and the number of photovoltaic clusters; calculating the reactive power index corresponding to each photovoltaic cluster based on the reactive balance of each photovoltaic cluster and the number of photovoltaic clusters; calculating the cluster power balance index corresponding to each photovoltaic cluster based on the active power balance index and the reactive power index. The specific formula is as follows:

[0060]

[0061]

[0062] in, Represents the active power balance index corresponding to each photovoltaic cluster. Represents the reactive power index corresponding to each photovoltaic cluster. Represents the cluster power balance index corresponding to each photovoltaic cluster. Representing the photovoltaic cluster i The net power characteristics of T is the running time of the scene, c represents the number of PV clusters, Representing the photovoltaic cluster i Reactive power balance.

[0063] Therefore, according to the above formula, the cluster power balance index corresponding to each photovoltaic cluster can be calculated.

[0064] Regarding the process of calculating the cluster scale index corresponding to each photovoltaic cluster, the method includes: For each photovoltaic cluster in each photovoltaic cluster, calculate the similarity of any two photovoltaic power sources in each photovoltaic cluster in different characteristic dimensions; based on the weights of the different characteristic dimensions, add the similarities of any two photovoltaic power sources in different dimensions to obtain the total similarity between the any two photovoltaic power sources; based on the total similarity between the any two photovoltaic power sources and the similarities of any two photovoltaic power sources in different characteristic dimensions, calculate the index values ​​of any two photovoltaic power sources in different characteristic dimensions; add the index values ​​of any two photovoltaic power sources in different characteristic dimensions to obtain the cluster scale index corresponding to each photovoltaic cluster; based on the cluster scale index corresponding to each photovoltaic cluster, determine the cluster scale index corresponding to each photovoltaic cluster. The specific formula is as follows:

[0065]

[0066]

[0067] in, and Respectively represent i The photovoltaic power node and j The characteristic vector of a photovoltaic power node in the mth characteristic dimension, the characteristic dimension includes electrical distance characteristic, power balance characteristic and geographical location characteristic. For any photovoltaic power node i , its characteristic vector under the electrical distance characteristic It can be expressed as the electrical distance to all other photovoltaic power nodes, such as ; Photovoltaic power supply node i Eigenvector under power balance characteristics It can be expressed as the active power balance index, reactive power index and power balance index of the photovoltaic power node, such as ; Photovoltaic power supply node i Feature vector under geographic location feature It can be represented based on the geographical location coordinates of the photovoltaic power source node, such as . Represents the weight of the mth feature dimension. R Representative i The photovoltaic power node and j The total similarity between photovoltaic power nodes in different specific dimensions. Representative i The photovoltaic power node and j The similarity between the PV power nodes in the mth characteristic dimension. Representative iThe photovoltaic power node and j The index value of a photovoltaic power node under the mth characteristic dimension. Represents the cluster size indicator corresponding to each PV cluster.

[0068] Therefore, according to the above formula, the cluster scale index corresponding to each photovoltaic cluster can be calculated: By calculating the average value of cluster scale index, the cluster structure strength index corresponding to each photovoltaic cluster can be obtained. .

[0069] Step 206 : performing weighted summation of the cluster structure strength index, cluster power balance index, and cluster scale index corresponding to each of the photovoltaic clusters to obtain a comprehensive performance index corresponding to each of the photovoltaic clusters.

[0070] For the embodiment of the present invention, after calculating the cluster structure strength index, cluster power balance index and cluster scale index corresponding to each photovoltaic cluster, the cluster structure strength index, cluster power balance index and cluster scale index corresponding to each photovoltaic cluster are weighted and summed to obtain the comprehensive performance index corresponding to each photovoltaic cluster. The specific formula is as follows:

[0071] in, As a comprehensive performance indicator, , and are the weights corresponding to the cluster structure strength index, cluster power balance index and cluster scale index respectively. The sum of the three is 1. By selecting different weight coefficients according to different photovoltaic cluster division objectives, the corresponding photovoltaic cluster division results can be obtained. is the cluster structure strength index, is the cluster power balance index, is the cluster size indicator.

[0072] The embodiments of the present invention, by calculating the cluster structure strength index, cluster power balance index and cluster scale index of the photovoltaic cluster, can ensure the reasonable matching of sources and loads within the photovoltaic cluster and the close connection between nodes, so that the scale of the photovoltaic cluster is balanced and has a certain voltage regulation capability, which is convenient for subsequent operation adjustment. That is, the present application can make multi-dimensional comprehensive considerations when dividing the cluster, so as to ensure the overall division effect of the photovoltaic cluster.

[0073] Step 207: If the updated centroid changes or the comprehensive performance index does not meet the corresponding conditions, the plurality of photovoltaic power sources are re-divided into clusters based on the updated centroid.

[0074] For the embodiment of the present invention, if the updated centroid changes too much compared with the centroid before updating (initial centroid) or the calculated comprehensive performance index is less than or equal to the preset index threshold, the multiple photovoltaic power sources are re-clustered based on the updated centroid.

[0075] Step 208 , repeating the process of updating the centroid, calculating the comprehensive performance index and dividing the photovoltaic clusters until the updated centroid change and the comprehensive performance index meet corresponding conditions, and outputting each photovoltaic cluster finally divided.

[0076] According to the embodiment of the present invention, for each re-divided photovoltaic cluster, the centroid is continuously updated, and the comprehensive performance index of the photovoltaic cluster is calculated at the same time. If the centroid after this round of update changes little and the calculated comprehensive performance index is greater than the preset index threshold, the divided photovoltaic clusters are directly outputted. Otherwise, the above process is repeated.

[0077] Another distributed photovoltaic cluster division method provided by the embodiment of the present invention can balance the size of the photovoltaic cluster and have a certain voltage regulation capability on the basis of ensuring the reasonable matching of the source and load within the photovoltaic cluster and the close connection between the nodes, by calculating the cluster structure strength index, cluster power balance index and cluster scale index of the photovoltaic cluster, so as to facilitate the subsequent operation adjustment. That is, the present application can make multi-dimensional comprehensive considerations when dividing the cluster, so as to ensure the overall division effect of the photovoltaic cluster. In addition, the embodiment of the present invention can automatically determine the initial centroid and the number of photovoltaic clusters by improving the traditional clustering algorithm, so as to avoid falling into the local optimal solution, achieve global optimization, and improve the rationality, efficiency and accuracy of photovoltaic cluster division. .

[0078] Further, as Figure 1 and Figure 2 The specific implementation of the method shown in the embodiment provides a distributed photovoltaic cluster division device in the area, such as Figure 3 As shown, the device includes: an acquisition unit 31, a determination unit 32, a division unit 33, an update unit 34, a calculation unit 35 and an output unit 36.

[0079] The acquisition unit 31 may be used to acquire parameter data corresponding to a plurality of photovoltaic power sources.

[0080] The determination unit 32 may be configured to determine the initial centroid and the number of photovoltaic clusters when dividing the photovoltaic clusters based on the parameter data.

[0081] The division unit 33 may be used to divide the plurality of photovoltaic power sources into clusters based on the initial centroid and the number of photovoltaic clusters to obtain individual photovoltaic clusters.

[0082] The updating unit 34 may be configured to update the initial centroid based on each photovoltaic cluster to obtain an updated centroid.

[0083] The calculation unit 35 may be used to calculate the comprehensive performance index commonly corresponding to each of the photovoltaic clusters, wherein the comprehensive performance index is determined by a cluster structure strength index, a cluster power balance index and a cluster scale index.

[0084] The division unit 33 may also be configured to re-cluster the plurality of photovoltaic power sources based on the updated centroid if the updated centroid changes or the comprehensive performance index does not meet corresponding conditions; The output unit 36 ​​may be used to repeat the process of updating the centroid, calculating the comprehensive performance index and dividing the photovoltaic clusters until the updated centroid change and the comprehensive performance index meet corresponding conditions, and then output each photovoltaic cluster finally divided.

[0085] In some embodiments, the determining unit 32, such as Figure 4 As shown, it includes: a determination module 321 and a segmentation module 322.

[0086] The determination module 321 may be configured to determine a target photovoltaic power source from among the plurality of photovoltaic power sources based on the parameter data.

[0087] The determination module 321 may also be used to calculate the distances between the plurality of photovoltaic power sources and the target photovoltaic power source, and determine the median of the distances between the plurality of photovoltaic power sources and the target photovoltaic power source.

[0088] The segmentation module 322 can be used to use the median distance as a first segmentation threshold to segment the target sample set composed of the multiple photovoltaic power sources to obtain a first sample set and a second sample set, wherein the distance between each photovoltaic power source in the first sample set and the target photovoltaic power source is less than the median distance, and the distance between each photovoltaic power source in the second sample set and the target photovoltaic power source is greater than or equal to the median distance.

[0089] The determination module 321 may also be used to determine a first photovoltaic power source in the first sample set that is closest to the target photovoltaic power source, and use the first photovoltaic power source as the sample center.

[0090] The determination module 321 may also be used to determine a second segmentation threshold corresponding to the second sample set, and continue to segment the second sample set based on the second segmentation threshold, while accumulating the number of segmentation times.

[0091] The segmentation module 322 may also be used to repeat the segmentation threshold determination process and the sample set segmentation process until the segmentation times are accumulated to a preset number of times and the change rate of the segmentation threshold before and after meets a preset condition, and then output each sample center.

[0092] The determination module 321 may also be configured to use the centers of the samples as the initial centroids and determine the number of photovoltaic clusters according to the accumulated number of divisions.

[0093] In some embodiments, the determination module 321 can be specifically used to calculate the center point corresponding to the multiple photovoltaic power sources based on the parameter data; calculate the distances between the multiple photovoltaic power sources and the center point respectively according to the parameter data; and determine the target photovoltaic power source closest to the center point from the multiple photovoltaic power sources based on the distances between the multiple photovoltaic power sources and the center point respectively.

[0094] In some embodiments, the division unit 33 can be specifically used to calculate the distances between the multiple photovoltaic power sources and the initial centroid based on the parameter data; based on the distances between the multiple photovoltaic power sources and the initial centroid, and the number of photovoltaic clusters, the multiple photovoltaic power sources are clustered to obtain the individual photovoltaic power sources.

[0095] In some embodiments, the updating unit 34 may be specifically configured to calculate an average parameter value corresponding to each photovoltaic cluster according to the parameter data; and update the initial centroid based on the average parameter value to obtain the updated centroid.

[0096] In some embodiments, the calculation unit 35 includes: a calculation module 351 and a summation module 352 .

[0097] The calculation module 351 may be used to respectively calculate the cluster structure strength index, cluster power balance index and cluster scale index corresponding to each of the photovoltaic clusters.

[0098] The summing module 352 may be used to weightedly sum the cluster structure strength index, cluster power balance index and cluster scale index corresponding to each photovoltaic cluster to obtain a comprehensive performance index corresponding to each photovoltaic cluster.

[0099] In some embodiments, the calculation module 351 can be specifically used to calculate the electrical distance between any two photovoltaic power sources in each photovoltaic cluster for each photovoltaic cluster; construct an electrical distance matrix based on the electrical distance between any two photovoltaic power sources; calculate the edge weight between any two photovoltaic power sources based on the electrical distance matrix and the electrical distance between any two photovoltaic power sources; calculate the sum of the edge weights of each of the any two photovoltaic power sources; calculate the cluster structure strength index corresponding to each photovoltaic cluster based on the edge weight between the two photovoltaic power sources and the sum of the edge weights of each of the any two photovoltaic power sources; Based on the cluster structure strength index corresponding to each photovoltaic cluster, the cluster structure strength index commonly corresponding to each photovoltaic cluster is determined.

[0100] In some embodiments, the calculation module 351 can also be specifically used to calculate the active power balance index corresponding to each photovoltaic cluster based on the net power characteristics of each photovoltaic cluster and the number of photovoltaic clusters; calculate the reactive power index corresponding to each photovoltaic cluster based on the reactive balance of each photovoltaic cluster and the number of photovoltaic clusters; calculate the cluster power balance index corresponding to each photovoltaic cluster based on the active power balance index and the reactive power index.

[0101] In some embodiments, the calculation module 351 can also be specifically used to calculate the similarity of any two photovoltaic power sources in each photovoltaic cluster in different characteristic dimensions; based on the weights of the different characteristic dimensions, add the similarities of the any two photovoltaic power sources in different dimensions to obtain the total similarity between the any two photovoltaic power sources; calculate the index values ​​of any two photovoltaic power sources in different characteristic dimensions according to the total similarity between the any two photovoltaic power sources and the similarities of the any two photovoltaic power sources in different characteristic dimensions; add the index values ​​of the any two photovoltaic power sources in different characteristic dimensions to obtain the cluster scale index corresponding to each photovoltaic cluster; based on the cluster scale index corresponding to each photovoltaic cluster, determine the cluster scale index corresponding to each photovoltaic cluster.

[0102] It should be noted that for other corresponding descriptions of the functional units involved in the distributed photovoltaic cluster division device provided in this embodiment, reference can be made to Figure 1 and Figure 2 The corresponding description in will not be repeated here.

[0103] Based on the above Figure 1 and Figure 2The method shown in the embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the above-mentioned Figure 1 and Figure 2 The distributed photovoltaic cluster division method in the substation is shown.

[0104] Based on this understanding, the technical solution of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, USB flash drive, mobile hard disk, etc.), including a number of instructions for enabling an electronic device (which can be a personal computer, server, or network device, etc.) to execute the methods of various implementation scenarios of the present application.

[0105] Based on the above Figure 1 and Figure 2 The method shown, and Figure 3 and Figure 4 In order to achieve the above-mentioned purpose, the embodiment of the present application also provides an electronic device, which can be a personal computer, a tablet computer, a server, or other network equipment, etc. The device includes a storage medium and a processor; the storage medium is used to store a computer program; the processor is used to execute the computer program to achieve the above-mentioned Figure 1 and Figure 2 The distributed photovoltaic cluster division method in the substation is shown.

[0106] Optionally, the above-mentioned physical device may also include a user interface, a network interface, a camera, a radio frequency (RF) circuit, a sensor, an audio circuit, a WI-FI module, etc. The user interface may include a display, an input unit such as a keyboard, etc., and the optional user interface may also include a USB interface, a card reader interface, etc. The network interface may optionally include a standard wired interface, a wireless interface (such as a WI-FI interface), etc.

[0107] Those skilled in the art will appreciate that the above-mentioned physical device structure provided in this embodiment does not constitute a limitation on the physical device, and may include more or fewer components, or a combination of certain components, or different arrangements of components.

[0108] The storage medium may also include an operating system and a network communication module. The operating system is a program that manages the hardware and software resources of the above-mentioned physical device, and supports the operation of the information processing program and other software and / or programs. The network communication module is used to realize the communication between the components inside the storage medium, and the communication with other hardware and software in the information processing physical device.

[0109] Through the description of the above implementation methods, those skilled in the art can clearly understand that the present application can be implemented by means of software plus a necessary general hardware platform, or by hardware.

[0110] The embodiment of the present invention calculates the cluster structure strength index, cluster power balance index and cluster scale index of the photovoltaic cluster, and can ensure the reasonable matching of the source and load within the photovoltaic cluster and the close connection between the nodes, so that the size of the photovoltaic cluster is balanced and has a certain voltage regulation capability, which is convenient for subsequent operation adjustment. That is, the present application can make multi-dimensional comprehensive considerations when dividing the cluster, so as to ensure the overall division effect of the photovoltaic cluster. In addition, the embodiment of the present invention improves the traditional clustering algorithm, and can automatically determine the initial centroid and the number of photovoltaic clusters, so as to avoid falling into the local optimal solution, achieve global optimization, and improve the rationality, efficiency and accuracy of photovoltaic cluster division.

[0111] Those skilled in the art will appreciate that the accompanying drawings are only schematic diagrams of a preferred implementation scenario, and the modules or processes in the accompanying drawings are not necessarily necessary for implementing the present application. Those skilled in the art will appreciate that the modules in the devices in the implementation scenario can be distributed in the devices of the implementation scenario according to the description of the implementation scenario, or can be changed accordingly and located in one or more devices different from the present implementation scenario. The modules of the above-mentioned implementation scenario can be combined into one module, or can be further split into multiple submodules.

[0112] The above serial numbers of this application are only for description and do not represent the advantages and disadvantages of the implementation scenarios. The above disclosure is only a few specific implementation scenarios of this application, but this application is not limited to them, and any changes that can be thought of by technicians in this field should fall within the scope of protection of this application.

Claims

1. A method for dividing distributed photovoltaic clusters in a metropolitan area, characterized in that: include: Obtain parameter data corresponding to multiple photovoltaic power sources; Based on the parameter data, determining the initial centroid and the number of photovoltaic clusters when dividing the photovoltaic clusters; Based on the initial centroid and the number of photovoltaic clusters, the multiple photovoltaic power sources are divided into clusters to obtain photovoltaic clusters; Based on the respective photovoltaic clusters, the initial centroid is updated to obtain an updated centroid; Calculating the comprehensive performance index corresponding to each photovoltaic cluster, wherein the comprehensive performance index is determined by a cluster structure strength index, a cluster power balance index and a cluster scale index; If the updated centroid changes or the comprehensive performance index does not meet the corresponding conditions, re-clustering the multiple photovoltaic power sources based on the updated centroid; The process of updating the centroid, calculating the comprehensive performance index and dividing the photovoltaic clusters is repeated until the centroid change after the update and the comprehensive performance index both meet corresponding conditions, and the photovoltaic clusters finally divided are output.

2. The method according to claim 1, characterized in that: Based on the parameter data, the initial centroid and the number of photovoltaic clusters when dividing the photovoltaic clusters are determined, including: Based on the parameter data, determining a target photovoltaic power source from the plurality of photovoltaic power sources; Calculating the distances between the plurality of photovoltaic power sources and the target photovoltaic power source, and determining the median of the distances between the plurality of photovoltaic power sources and the target photovoltaic power source; Using the median of the distance as a first segmentation threshold, segmenting the target sample set consisting of the multiple photovoltaic power sources to obtain a first sample set and a second sample set, wherein the distance between each photovoltaic power source in the first sample set and the target photovoltaic power source is less than the median of the distance, and the distance between each photovoltaic power source in the second sample set and the target photovoltaic power source is greater than or equal to the median of the distance; Determine a first photovoltaic power source in the first sample set that is closest to the target photovoltaic power source, and use the first photovoltaic power source as a sample center; Determine a second segmentation threshold corresponding to the second sample set, and continue to segment the second sample set based on the second segmentation threshold, while accumulating the number of segmentations; Repeat the segmentation threshold determination process and the sample set segmentation process until the segmentation times accumulate to a preset number of times and the change rate of the segmentation threshold before and after meets the preset conditions, then output each sample center; The centers of the samples are taken as the initial centroids, and the number of photovoltaic clusters is determined according to the accumulated number of divisions.

3. The method according to claim 2, characterized in that Determining a target photovoltaic power source from the plurality of photovoltaic power sources based on the parameter data includes: Based on the parameter data, calculating a central point corresponding to the plurality of photovoltaic power sources; Calculating the distances between the plurality of photovoltaic power sources and the center point respectively according to the parameter data; Based on the distances between the multiple photovoltaic power sources and the center point, a target photovoltaic power source closest to the center point is determined from the multiple photovoltaic power sources.

4. The method according to claim 1, characterized in that Based on the initial centroid and the number of photovoltaic clusters, the plurality of photovoltaic power sources are divided into clusters to obtain photovoltaic clusters, including: Based on the parameter data, calculating the distances between the plurality of photovoltaic power sources and the initial centroid respectively; Based on the distances between the multiple photovoltaic power sources and the initial centroid, and the number of the photovoltaic clusters, the multiple photovoltaic power sources are clustered to obtain the individual photovoltaic power sources.

5. The method according to claim 1, characterized in that Based on the photovoltaic clusters, the initial centroid is updated to obtain an updated centroid, including: Calculating average parameter values ​​corresponding to each photovoltaic cluster according to the parameter data; Based on the average parameter value, the initial centroid is updated to obtain the updated centroid.

6. The method according to claim 1, characterized in that Calculate the comprehensive performance indicators corresponding to each photovoltaic cluster, including: Calculate the cluster structure strength index, cluster power balance index and cluster scale index corresponding to each photovoltaic cluster respectively; The cluster structure strength index, cluster power balance index and cluster scale index commonly corresponding to the various photovoltaic clusters are weighted and summed to obtain the comprehensive performance index commonly corresponding to the various photovoltaic clusters.

7. The method according to claim 1, characterized in that Calculating the cluster structure strength index corresponding to each of the photovoltaic clusters, including: For each photovoltaic cluster in each photovoltaic cluster, calculating the electrical distance between any two photovoltaic power sources in each photovoltaic cluster; Based on the electrical distance between any two photovoltaic power sources, construct an electrical distance matrix; Calculating the edge weight between the any two photovoltaic power sources based on the electrical distance matrix and the electrical distance between the any two photovoltaic power sources; Calculating the sum of the edge weights of any two photovoltaic power sources; Calculating a cluster structure strength index corresponding to each photovoltaic cluster based on the edge weight between the two photovoltaic power sources and the sum of the edge weights of any two photovoltaic power sources; Based on the cluster structure strength index corresponding to each photovoltaic cluster, determining the cluster structure strength index corresponding to each photovoltaic cluster; Calculating the cluster power balance index corresponding to each photovoltaic cluster, including: Based on the net power characteristics of each photovoltaic cluster and the number of photovoltaic clusters, calculating the active power balance index corresponding to each photovoltaic cluster; Based on the reactive balance degree of each photovoltaic cluster and the number of photovoltaic clusters, calculating the reactive power index corresponding to each photovoltaic cluster; Calculating the cluster power balance index corresponding to each photovoltaic cluster according to the active power balance index and the reactive power index; Calculate the cluster scale index corresponding to each photovoltaic cluster, including: For each photovoltaic cluster in each photovoltaic cluster, calculating the similarity between any two photovoltaic power sources in each photovoltaic cluster under different characteristic dimensions; Based on the weights of the different characteristic dimensions, the similarities of the two arbitrary photovoltaic power sources in different dimensions are added to obtain the total similarity between the two arbitrary photovoltaic power sources; Calculate the index values ​​of the arbitrary two photovoltaic power sources in different characteristic dimensions according to the total similarity between the arbitrary two photovoltaic power sources and the similarity of the arbitrary two photovoltaic power sources in different characteristic dimensions; Adding the index values ​​of any two photovoltaic power sources in different characteristic dimensions to obtain a cluster scale index corresponding to each photovoltaic cluster; Based on the cluster scale index corresponding to each photovoltaic cluster, the cluster scale index commonly corresponding to each photovoltaic cluster is determined.

8. A distributed photovoltaic cluster division device in an area, characterized in that: include: An acquisition unit, used to acquire parameter data corresponding to a plurality of photovoltaic power sources; A determination unit, used to determine the initial centroid and the number of photovoltaic clusters when dividing the photovoltaic clusters based on the parameter data; A division unit, configured to divide the plurality of photovoltaic power sources into clusters based on the initial centroid and the number of photovoltaic clusters to obtain individual photovoltaic clusters; An updating unit, configured to update the initial centroid based on each photovoltaic cluster to obtain an updated centroid; A calculation unit, used to calculate the comprehensive performance index corresponding to each photovoltaic cluster, wherein the comprehensive performance index is determined by a cluster structure strength index, a cluster power balance index and a cluster scale index; The division unit is further configured to re-cluster the plurality of photovoltaic power sources based on the updated centroid if the updated centroid changes or the comprehensive performance index does not meet corresponding conditions; The output unit is used to repeat the process of updating the centroid, calculating the comprehensive performance index and dividing the photovoltaic clusters until the updated centroid change and the comprehensive performance index meet the corresponding conditions, and then output each photovoltaic cluster finally divided.

9. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

10. An electronic device comprising a storage medium, a processor, and a computer program stored in the storage medium and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 7 is implemented.

Images