A distributed photovoltaic power station clustering method and system considering objective weighting

Abstract

The present invention relates to a distributed photovoltaic power station clustering method and system considering objective weighting, which belongs to the field of photovoltaic clustering technology. The method comprises the following steps: by acquiring the operating data of the distributed photovoltaic power station, a resource clustering control index system is constructed, and the resource clustering control index system includes technical indicators and economic indicators. After normalizing each indicator, the proportion of each indicator of the distributed photovoltaic power station in the distributed photovoltaic power station group is calculated, and the anti-entropy value and entropy weight are calculated based on the proportion. The standard deviation of the indicator value of the photovoltaic group is determined, and the threshold is calculated using the standard deviation. The photovoltaic group is input into the clustering algorithm, and the threshold, anti-entropy value and entropy weight are combined to output the clustering result. The present invention ensures that the weight distribution of each photovoltaic in the clustering process is reasonable and accurate by objectively weighting different indicators, thereby improving the accuracy of the clustering results and better reflecting the actual operating characteristics and regulation requirements of photovoltaics.

Description

Technical Field

[0001] The present invention relates to a distributed photovoltaic power station clustering method and system considering objective weighting, belonging to the technical field of photovoltaic clustering. Background Art

[0002] With the acceleration of global energy transformation, distributed photovoltaic power generation, as a clean, renewable energy source, has seen widespread adoption and rapid development. Numerous distributed photovoltaic power station systems are deployed across diverse regions and scenarios, such as urban buildings, industrial parks, and rural residences. They provide a powerful supplement to energy supply and significantly impact the operation and management of power grids. With the large-scale integration and operation of distributed photovoltaic power stations, clustering them has become a key issue in order to effectively manage and control their resources, improve energy efficiency, optimize grid performance, and reduce operating costs. Clustering aims to group distributed photovoltaic power stations with similar characteristics and operating patterns, enabling the development of targeted regulation strategies and operational management plans.

[0003] When constructing a resource clustering control indicator system, traditional distributed photovoltaic power station clustering methods often do not consider comprehensive indicators and may only focus on one or two aspects, such as photovoltaic power generation or installation location. They ignore the multi-dimensional characteristics of distributed photovoltaic power station operation, including technical indicators (such as downsizing capacity and regulation time) and economic indicators (such as regulation cost). As a result, the clustering results cannot accurately reflect their comprehensive characteristics and are difficult to meet the needs of refined management and optimized regulation.

[0004] Prior art, such as the Chinese invention patent application with publication number CN118313496A, discloses a distributed photovoltaic cluster power prediction method based on deep similarity clustering. The method comprises the following steps: obtaining power data for a distributed photovoltaic power station cluster, performing preliminary clustering of the distributed photovoltaic power station cluster using a clustering algorithm, and obtaining multiple cluster centers as representative power stations; determining the deep power characteristics of the multiple representative power stations by training multiple preset autoencoders based on the representative power stations and their power data; using the representative power stations as cluster centers for secondary clustering based on their power characteristics, and obtaining the optimal clustering result based on the deep similarity between the distributed photovoltaic power station clusters; and performing regional distributed photovoltaic power prediction using a pre-built graph convolutional neural network prediction model based on the optimal clustering result. However, the aforementioned patent relies heavily on historical power data from distributed photovoltaic power stations to train the autoencoder and construct the graph convolutional neural network prediction model. If the historical data is missing, noisy, or has large errors, the model training effect and prediction accuracy will be affected. Summary of the Invention

[0005] In order to solve the above problems in the prior art, the present invention proposes a distributed photovoltaic power station clustering method and system considering objective weighting.

[0006] The technical solutions of the present invention are as follows:

[0007] In one aspect, the present invention provides a distributed photovoltaic power station clustering method considering objective weighting, comprising the following steps:

[0008] Acquiring operating data of distributed photovoltaic power stations and building a resource clustering control indicator system based on the operating data;

[0009] Normalize each indicator in the resource clustering control indicator system;

[0010] Calculating the proportion of each normalized indicator of the distributed photovoltaic power station in the sum of the corresponding indicators of the distributed photovoltaic power station group, and calculating the anti-entropy value and entropy weight of each indicator of the distributed photovoltaic power station group based on the proportion;

[0011] Determining a standard deviation of an indicator value of a distributed photovoltaic power station group, and calculating a threshold value of the distributed photovoltaic power station group based on the standard deviation of the indicator value;

[0012] The distributed photovoltaic power station group is used as an input of a clustering algorithm, and a distributed photovoltaic power station clustering result is output based on the threshold, the anti-entropy value and the entropy weight.

[0013] As a preferred implementation, a resource clustering control indicator system is constructed based on the operation data, and the specific steps are as follows:

[0014] Determine technical indicators, including the reduction capacity of distributed photovoltaic power stations and the regulation time of distributed photovoltaic power stations;

[0015] The reduced capacity of the distributed photovoltaic power station is calculated based on the operating data, and is expressed as follows:

[0016] ;

[0017] ;

[0018] ;

[0019] Where, Indicates the total number of distributed photovoltaic power stations in the distributed photovoltaic power station group, Indicates the Distributed photovoltaic power stations in Operating power at all times, Indicates the The capacity reduction of distributed photovoltaic power stations, Indicates the The minimum operating boundary of a distributed photovoltaic power station, Represents the time index, Indicates the index of the number of distributed photovoltaic power stations. Indicates the The control time of each distributed photovoltaic power station;

[0020] Determine economic indicators, including the regulation costs of distributed photovoltaic power plants;

[0021] The control cost of the distributed photovoltaic power station is calculated based on the operating data and is expressed as follows:

[0022] ;

[0023] Where, Indicates the The cost of abandoned light in a distributed photovoltaic power station is Indicates the The amount of abandoned light from distributed photovoltaic power stations, Indicates the The regulation cost of a distributed photovoltaic power station;

[0024] A resource clustering control indicator system is constructed based on the technical indicators and economic indicators.

[0025] As a preferred implementation, normalization is performed on each indicator in the resource clustering control indicator system. The specific steps are as follows:

[0026] The downward adjustment capacity is normalized in the positive direction and expressed as follows:

[0027] ;

[0028] Where, Represents the first The capacity reduction of distributed photovoltaic power stations, Indicates the maximum value of the reduced capacity of the distributed photovoltaic power station group, Indicates the minimum value of the reduced capacity of the distributed photovoltaic power station group;

[0029] The control time and control cost are negatively normalized and expressed as follows:

[0030] ;

[0031] ;

[0032] Where, Represents the first The regulation cost of a distributed photovoltaic power station or the The control time of a distributed photovoltaic power station, Indicates the The regulation cost of a distributed photovoltaic power station or the The control time of a distributed photovoltaic power station, Indicates the minimum control cost or control time of the distributed photovoltaic power station group, Indicates the maximum value of the regulation cost or regulation time of a distributed photovoltaic power station group.

[0033] As a preferred embodiment, the proportion of each normalized indicator of the distributed photovoltaic power station in the sum of the corresponding indicators of the distributed photovoltaic power station group is calculated, and the anti-entropy value and entropy weight of each indicator of the distributed photovoltaic power station group are calculated based on the proportion. The specific steps are:

[0034] Calculate the proportion of each normalized indicator of the distributed photovoltaic power station in the sum of the corresponding indicators of the distributed photovoltaic power station group, and express it as follows:

[0035] ;

[0036] ;

[0037] ;

[0038] ;

[0039] Where, Indicates the The first distributed photovoltaic power station after normalization The proportion of the corresponding indicators in the distributed photovoltaic power station group. Indicates the The first distributed photovoltaic power station after normalization indicators, Indicates the indicator index, Represents the first The indicators of the indicators and;

[0040] Based on the above proportions, the anti-entropy value of the corresponding indicator of the distributed photovoltaic power station group is calculated and expressed as follows:

[0041] ;

[0042] Where, Indicates the first The anti-entropy value of an indicator, represents the logarithmic function;

[0043] The entropy weight of the corresponding indicator of the distributed photovoltaic power station group is calculated based on the anti-entropy value, which is expressed as follows:

[0044] ;

[0045] Where, Indicates the first The entropy weight of an indicator.

[0046] As a preferred embodiment, the standard deviation of the index values of the distributed photovoltaic power station group is determined, and the threshold value of the distributed photovoltaic power station group is calculated based on the standard deviation of the index values. The specific steps are:

[0047] Determine the standard deviation of the index values of the distributed photovoltaic power station group, which can be expressed as follows:

[0048] ;

[0049] ;

[0050] ;

[0051] Where, Indicates the standard deviation of the indicator values of the distributed photovoltaic power station group, Indicates the first The standard deviation of the indicator values of the indicators, Indicates the first The mean value of each indicator;

[0052] The bandwidth of the distributed photovoltaic power station group is calculated based on the standard deviation of the indicator values, which can be expressed as follows:

[0053] ;

[0054] Where, Indicates the indicator dimension, Indicates the bandwidth of the distributed photovoltaic power station group;

[0055] The threshold of distributed photovoltaic power station group Set to bandwidth of .

[0056] As a preferred embodiment, a distributed photovoltaic power station group is used as an input of a clustering algorithm, and a distributed photovoltaic power station clustering result is output based on the threshold, the anti-entropy value and the entropy weight. The specific steps are as follows:

[0057] S1. Mark each distributed photovoltaic power station in the distributed photovoltaic power station group as unclassified;

[0058] S2. Create an empty cluster set , randomly select a distributed photovoltaic power station as the initial center point ;

[0059] S3, with the initial center point As the center of the circle, the bandwidth of the distributed photovoltaic power station group Build a collection for distributed photovoltaic power stations within the radius search ;

[0060] S4. Calculation Set Distributed photovoltaic power station to the initial center point The vector is expressed as:

[0061] ;

[0062] Where, represents the exponential function, Representing a collection Middle Distributed photovoltaic power stations to the initial center point vector, Representing a collection Middle The coordinate points of a distributed photovoltaic power station, represents the norm operator;

[0063] S5. Calculate a set based on the vector and entropy weight The weighted vector sum of the distributed photovoltaic power station group in is expressed as follows:

[0064] ;

[0065] Where, Representing a collection The weighted vector sum of the distributed photovoltaic power station group in Representing a collection Middle The capacity reduction of distributed photovoltaic power stations, Representing a collection Middle The control time of a distributed photovoltaic power station, Representing a collection Middle The regulation cost of a distributed photovoltaic power station, represents the entropy weight of the capacity reduction of the distributed photovoltaic power station group, represents the entropy weight of the control time of the distributed photovoltaic power station group, The entropy weight representing the control cost of distributed photovoltaic power station group, Indicates the initial center point The downgrade capacity, Indicates the initial center point The control time, Indicates the initial center point the cost of regulation;

[0066] S6. Calculate the initial center point based on the weighted vector The offset vector is expressed as:

[0067] ;

[0068] Where, Indicates the initial center point The offset vector of

[0069] S7, based on the initial center point Update the initial center point with the offset vector , expressed as:

[0070] ;

[0071] Where, represents the updated center point;

[0072] If the initial center point The offset vector The modulus value is less than the threshold , then execute step S8, otherwise execute step S3 with the updated center point;

[0073] S8. If the empty cluster set There is satisfaction Ideal cluster , then the collection Merge into ideal cluster Otherwise, the collection Add to the empty cluster set as a new cluster ;

[0074] in, Indicates calculation of Euclidean distance;

[0075] S9: Step completed, outputting the clustering results of distributed photovoltaic power stations.

[0076] In another aspect, the present invention further provides a distributed photovoltaic power station clustering system considering objective weighting, comprising:

[0077] System construction module: obtains the operating data of the distributed photovoltaic power station and constructs a resource clustering control indicator system based on the operating data;

[0078] Preprocessing module: normalizes each indicator in the resource clustering control indicator system;

[0079] Objective weighting module: calculates the proportion of each normalized indicator of the distributed photovoltaic power station in the sum of the corresponding indicators of the distributed photovoltaic power station group, and calculates the anti-entropy value and entropy weight of each indicator of the distributed photovoltaic power station group based on the proportion;

[0080] Threshold setting module: determining the standard deviation of the indicator values of the distributed photovoltaic power station group, and calculating the threshold value of the distributed photovoltaic power station group based on the standard deviation of the indicator values;

[0081] The clustering module takes the distributed photovoltaic power station group as the input of the clustering algorithm, and outputs the distributed photovoltaic power station clustering result based on the threshold, the anti-entropy value and the entropy weight.

[0082] As a preferred implementation, a resource clustering control indicator system is constructed based on the operation data, and the specific steps are as follows:

[0083] Determine technical indicators, including the reduction capacity of distributed photovoltaic power stations and the regulation time of distributed photovoltaic power stations;

[0084] The reduced capacity of the distributed photovoltaic power station is calculated based on the operating data, and is expressed as follows:

[0085] ;

[0086] ;

[0087] ;

[0088] Where, Indicates the total number of distributed photovoltaic power stations in the distributed photovoltaic power station group, Indicates the Distributed photovoltaic power stations in Operating power at all times, Indicates the The capacity reduction of distributed photovoltaic power stations, Indicates the The minimum operating boundary of a distributed photovoltaic power station, Represents the time index, Indicates the index of the number of distributed photovoltaic power stations. Indicates the The control time of each distributed photovoltaic power station;

[0089] Determine economic indicators, including the regulation costs of distributed photovoltaic power plants;

[0090] The control cost of the distributed photovoltaic power station is calculated based on the operating data and is expressed as follows:

[0091] ;

[0092] Where, Indicates the The cost of abandoned light in a distributed photovoltaic power station is Indicates the The amount of abandoned light from distributed photovoltaic power stations, Indicates the The regulation cost of a distributed photovoltaic power station;

[0093] A resource clustering control indicator system is constructed based on the technical indicators and economic indicators.

[0094] As a preferred implementation, normalization is performed on each indicator in the resource clustering control indicator system. The specific steps are as follows:

[0095] The downward adjustment capacity is normalized in the positive direction and expressed as follows:

[0096] ;

[0097] Where, Represents the first The capacity reduction of distributed photovoltaic power stations, Indicates the maximum value of the reduced capacity of the distributed photovoltaic power station group, Indicates the minimum value of the reduced capacity of the distributed photovoltaic power station group;

[0098] The control time and control cost are negatively normalized and expressed as follows:

[0099] ;

[0100] ;

[0101] Where, Represents the first The regulation cost of a distributed photovoltaic power station or the The control time of a distributed photovoltaic power station, Indicates the The regulation cost of a distributed photovoltaic power station or the The control time of a distributed photovoltaic power station, Indicates the minimum control cost or control time of the distributed photovoltaic power station group, Indicates the maximum value of the regulation cost or regulation time of a distributed photovoltaic power station group.

[0102] As a preferred embodiment, the proportion of each normalized indicator of the distributed photovoltaic power station in the sum of the corresponding indicators of the distributed photovoltaic power station group is calculated, and the anti-entropy value and entropy weight of each indicator of the distributed photovoltaic power station group are calculated based on the proportion. The specific steps are:

[0103] Calculate the proportion of each normalized indicator of the distributed photovoltaic power station in the sum of the corresponding indicators of the distributed photovoltaic power station group, and express it as follows:

[0104] ;

[0105] ;

[0106] ;

[0107] ;

[0108] Where, Indicates the The first distributed photovoltaic power station after normalization The proportion of the corresponding indicators in the distributed photovoltaic power station group. Indicates the The first distributed photovoltaic power station after normalization indicators, Indicates the indicator index, Represents the first The indicators of the indicators and;

[0109] Based on the above proportions, the anti-entropy value of the corresponding indicator of the distributed photovoltaic power station group is calculated and expressed as follows:

[0110] ;

[0111] Where, Indicates the first The anti-entropy value of an indicator, represents the logarithmic function;

[0112] The entropy weight of the corresponding indicator of the distributed photovoltaic power station group is calculated based on the anti-entropy value, which is expressed as follows:

[0113] ;

[0114] Where, Indicates the first The entropy weight of an indicator.

[0115] The present invention has the following beneficial effects:

[0116] 1. This invention achieves objective weighting of various key indicators of distributed photovoltaic power plants by calculating inverse entropy values and entropy weights for each of them (technical indicators such as downsizing capacity and regulation time, and economic indicators such as regulation cost). This method fully considers the importance of each indicator in measuring the characteristics and adaptability of distributed photovoltaic power plants, making the weight allocation for each distributed photovoltaic power plant more reasonable and accurate during the clustering process. This improves the accuracy of the clustering results and more accurately reflects the actual operating characteristics and regulation requirements of distributed photovoltaic power plants.

[0117] 2. The present invention normalizes each indicator in the resource clustering control indicator system, eliminating the impact of differences in dimensions and orders of magnitude between different indicators, so that each indicator can be compared and analyzed on a unified scale, further improving the accuracy of clustering and avoiding deviations in clustering results caused by excessive differences in indicator values.

[0118] 3. The present invention constructs a resource clustering control index system based on the actual operation data of distributed photovoltaic power stations, which can truly reflect the performance and characteristics of distributed photovoltaic power stations in the actual operation process, making the basis for clustering more objective and scientific. The obtained clustering results are more in line with the actual operation conditions of distributed photovoltaic power stations, providing a more targeted and effective basis for the subsequent management and regulation of distributed photovoltaic power station groups.

[0119] 4. This invention uses inverse entropy to calculate the entropy weight of each indicator in a distributed photovoltaic power plant cluster. The entropy weight reflects the amount of information and importance of each indicator in the distributed photovoltaic power plant cluster. This weighting objectively measures the role of each indicator in the clustering process, avoiding the influence of human factors on weight allocation, and making the clustering process more scientific and reasonable.

[0120] 5. The clustering algorithm employed in this invention rapidly divides a distributed photovoltaic power plant cluster into distinct clusters by setting an initial center point, calculating vectors, and updating the center point using offset vectors. This algorithm fully considers factors such as the weights and thresholds of various indicators within the distributed photovoltaic power plant during the calculation process, achieving ideal clustering results within a relatively small number of iterations. This improves clustering efficiency, saves computational time and resources, and is suitable for clustering large-scale distributed photovoltaic power plant clusters. BRIEF DESCRIPTION OF THE DRAWINGS

[0121] Figure 1 The present invention is a flowchart for implementing the method. DETAILED DESCRIPTION

[0122] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0123] It should be understood that the step numbers used herein are only for convenience of description and are not intended to limit the order in which the steps are to be executed.

[0124] It should be understood that the terms used in the present specification are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the present specification and the appended claims, the singular forms "a", "an" and "the" are intended to include the plural forms unless the context clearly indicates otherwise.

[0125] The terms “include” and “comprising” indicate the presence of described features, integers, steps, operations, elements and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or groups thereof.

[0126] The term "and / or" refers to and includes any and all possible combinations of one or more of the associated listed items.

[0127] Example 1:

[0128] See also Figure 1 This embodiment provides a distributed photovoltaic power station clustering method considering objective weighting, including the following steps:

[0129] Obtaining operating data of a distributed photovoltaic power station and constructing a resource clustering control indicator system based on the operating data; wherein the operating data includes operating power, curtailment cost, and curtailment amount;

[0130] Normalize each indicator in the resource clustering control indicator system;

[0131] Calculating the proportion of each normalized indicator of the distributed photovoltaic power station in the sum of the corresponding indicators of the distributed photovoltaic power station group, and calculating the anti-entropy value and entropy weight of each indicator of the distributed photovoltaic power station group based on the proportion;

[0132] Determining a standard deviation of an indicator value of a distributed photovoltaic power station group, and calculating a threshold value of the distributed photovoltaic power station group based on the standard deviation of the indicator value;

[0133] The distributed photovoltaic power station group is used as an input of a clustering algorithm, and a distributed photovoltaic power station clustering result is output based on the threshold, the anti-entropy value and the entropy weight.

[0134] The reduction capacity, regulation time and regulation cost are selected as the resource clustering control indicator system because they can comprehensively and efficiently measure the efficiency, economy and feasibility of photovoltaic participation in grid regulation.

[0135] As a preferred implementation, a resource clustering control indicator system is constructed based on the operation data, and the specific steps are as follows:

[0136] Determine technical indicators, including the reduction capacity of distributed photovoltaic power stations and the regulation time of distributed photovoltaic power stations;

[0137] The reduced capacity of the distributed photovoltaic power station is calculated based on the operating data, and is expressed as follows:

[0138] ;

[0139] ;

[0140] ;

[0141] Where, Indicates the total number of distributed photovoltaic power stations in the distributed photovoltaic power station group, Indicates the Distributed photovoltaic power stations in Operating power at all times, Indicates the The capacity reduction of distributed photovoltaic power stations, Indicates the The minimum operating boundary of a distributed photovoltaic power station, Represents the time index, Indicates the index of the number of distributed photovoltaic power stations. Indicates the The control time of each distributed photovoltaic power station;

[0142] Determine economic indicators, including the regulation costs of distributed photovoltaic power plants;

[0143] The control cost of the distributed photovoltaic power station is calculated based on the operating data and is expressed as follows:

[0144] ;

[0145] Where, Indicates the The cost of abandoned light in a distributed photovoltaic power station is Indicates the The amount of abandoned light from distributed photovoltaic power stations, Indicates the The regulation cost of a distributed photovoltaic power station;

[0146] A resource clustering control indicator system is constructed based on the technical indicators and economic indicators.

[0147] The larger the adjustable capacity and the shorter the regulation time, the stronger the ability of photovoltaics to participate in grid regulation, and the lower the regulation cost, the greater the benefits of photovoltaics participating in grid regulation.

[0148] As a preferred implementation, normalization is performed on each indicator in the resource clustering control indicator system. The specific steps are as follows:

[0149] The downward adjustment capacity is normalized in the positive direction and expressed as follows:

[0150] ;

[0151] Where, Represents the first The capacity reduction of distributed photovoltaic power stations, Indicates the maximum value of the reduced capacity of the distributed photovoltaic power station group, Indicates the minimum value of the reduced capacity of the distributed photovoltaic power station group;

[0152] The control time and control cost are negatively normalized and expressed as follows:

[0153] ;

[0154] ;

[0155] Where, Represents the first The regulation cost of a distributed photovoltaic power station or the The control time of a distributed photovoltaic power station, Indicates the The regulation cost of a distributed photovoltaic power station or the The control time of a distributed photovoltaic power station, Indicates the minimum control cost or control time of the distributed photovoltaic power station group, Indicates the maximum value of the regulation cost or regulation time of a distributed photovoltaic power station group.

[0156] As a preferred embodiment, the proportion of each normalized indicator of the distributed photovoltaic power station in the sum of the corresponding indicators of the distributed photovoltaic power station group is calculated, and the anti-entropy value and entropy weight of each indicator of the distributed photovoltaic power station group are calculated based on the proportion. The specific steps are:

[0157] Calculate the proportion of each normalized indicator of the distributed photovoltaic power station in the sum of the corresponding indicators of the distributed photovoltaic power station group, and express it as follows:

[0158] ;

[0159] ;

[0160] ;

[0161] ;

[0162] Where, Indicates the The first distributed photovoltaic power station after normalization The proportion of the corresponding indicators in the distributed photovoltaic power station group. Indicates the The first distributed photovoltaic power station after normalization indicators, Indicates the indicator index, When it is 1, it means to lower the capacity index. Indicates the The normalized reduced capacity of distributed photovoltaic power stations is: When it is 2, it indicates the control time index. Indicates the The control time of a distributed photovoltaic power station after normalization, When it is 3, it indicates the control cost index. Indicates the The normalized control cost of a distributed photovoltaic power station is Represents the first The indicators of the indicators and;

[0163] Based on the above proportions, the anti-entropy value of the corresponding indicator of the distributed photovoltaic power station group is calculated and expressed as follows:

[0164] ;

[0165] Where, Indicates the first The anti-entropy value of an indicator, represents the logarithmic function;

[0166] The entropy weight of the corresponding indicator of the distributed photovoltaic power station group is calculated based on the anti-entropy value, which is expressed as follows:

[0167] ;

[0168] Where, Indicates the first The entropy weight of an indicator.

[0169] As a preferred embodiment, the standard deviation of the index values of the distributed photovoltaic power station group is determined, and the threshold value of the distributed photovoltaic power station group is calculated based on the standard deviation of the index values. The specific steps are:

[0170] Determine the standard deviation of the index values of the distributed photovoltaic power station group, which can be expressed as follows:

[0171] ;

[0172] ;

[0173] ;

[0174] Where, Indicates the standard deviation of the indicator values of the distributed photovoltaic power station group, Indicates the first The standard deviation of the indicator values of the indicators, Indicates the first The mean value of each indicator;

[0175] The bandwidth of the distributed photovoltaic power station group is calculated based on the standard deviation of the indicator values, which can be expressed as follows:

[0176] ;

[0177] Where, Indicates the indicator dimension, Indicates the bandwidth of the distributed photovoltaic power station group;

[0178] The threshold of distributed photovoltaic power station group Set to bandwidth of .

[0179] As a preferred embodiment, a distributed photovoltaic power station group is used as an input of a clustering algorithm, and a distributed photovoltaic power station clustering result is output based on the threshold, the anti-entropy value and the entropy weight. The specific steps are as follows:

[0180] S1. Mark each distributed photovoltaic power station in the distributed photovoltaic power station group as unclassified;

[0181] S2. Create an empty cluster set , randomly select a distributed photovoltaic power station as the initial center point ;

[0182] S3, with the initial center point As the center of the circle, the bandwidth of the distributed photovoltaic power station group Build a collection for distributed photovoltaic power stations within the radius search ;

[0183] S4. Calculation Set Distributed photovoltaic power station to the initial center point The vector is expressed as:

[0184] ;

[0185] Where, represents the exponential function, Representing a collection Middle Distributed photovoltaic power stations to the initial center point vector, Representing a collection Middle The coordinate points of a distributed photovoltaic power station, represents the norm operator;

[0186] S5. Calculate a set based on the vector and entropy weight The weighted vector sum of the distributed photovoltaic power station group in is expressed as follows:

[0187] ;

[0188] Where, Representing a collection The weighted vector sum of the distributed photovoltaic power station group in Representing a collection Middle The capacity reduction of distributed photovoltaic power stations, Representing a collection Middle The control time of a distributed photovoltaic power station, Representing a collection Middle The regulation cost of a distributed photovoltaic power station, represents the entropy weight of the capacity reduction of the distributed photovoltaic power station group, represents the entropy weight of the control time of the distributed photovoltaic power station group, The entropy weight representing the control cost of distributed photovoltaic power station group, Indicates the initial center point The downgrade capacity, Indicates the initial center point The control time, Indicates the initial center point the cost of regulation;

[0189] S6. Calculate the initial center point based on the weighted vector The offset vector is expressed as:

[0190] ;

[0191] Where, Indicates the initial center point The offset vector of

[0192] S7, based on the initial center point Update the initial center point with the offset vector , expressed as:

[0193] ;

[0194] Where, represents the updated center point;

[0195] If the initial center point The offset vector The modulus value is less than the threshold , then execute step S8, otherwise execute step S3 with the updated center point;

[0196] S8. If the empty cluster set There is satisfaction Ideal cluster , then the collection Merge into ideal cluster Otherwise, the collection Add to the empty cluster set as a new cluster ;

[0197] in, Indicates the calculation of Euclidean distance, which is expressed as follows:

[0198] ;

[0199] Where, represents an ideal cluster No. indicators, The updated center point indicators;

[0200] S9. Record the updated center points of all distributed photovoltaic power stations The number of visits is calculated and assigned to the cluster to which the center point with the most visits belongs. If the number of visits is the same, the cluster to which the center point with the shortest Euclidean distance belongs is selected.

[0201] S10: Step completed, outputting the clustering results of distributed photovoltaic power stations.

[0202] Example 2:

[0203] This embodiment provides a distributed photovoltaic power station clustering system considering objective weighting, including:

[0204] System construction module: obtains the operating data of the distributed photovoltaic power station and constructs a resource clustering control indicator system based on the operating data;

[0205] Preprocessing module: normalizes each indicator in the resource clustering control indicator system;

[0206] Objective weighting module: calculates the proportion of each normalized indicator of the distributed photovoltaic power station in the sum of the corresponding indicators of the distributed photovoltaic power station group, and calculates the anti-entropy value and entropy weight of each indicator of the distributed photovoltaic power station group based on the proportion;

[0207] Threshold setting module: determining the standard deviation of the indicator values of the distributed photovoltaic power station group, and calculating the threshold value of the distributed photovoltaic power station group based on the standard deviation of the indicator values;

[0208] The clustering module takes the distributed photovoltaic power station group as the input of the clustering algorithm, and outputs the distributed photovoltaic power station clustering result based on the threshold, the anti-entropy value and the entropy weight.

[0209] As a preferred implementation, a resource clustering control indicator system is constructed based on the operation data, and the specific steps are as follows:

[0210] Determine technical indicators, including the reduction capacity of distributed photovoltaic power stations and the regulation time of distributed photovoltaic power stations;

[0211] The reduced capacity of the distributed photovoltaic power station is calculated based on the operating data, and is expressed as follows:

[0212] ;

[0213] ;

[0214] ;

[0215] Where, Indicates the total number of distributed photovoltaic power stations in the distributed photovoltaic power station group, Indicates the Distributed photovoltaic power stations in Operating power at all times, Indicates the The capacity reduction of distributed photovoltaic power stations, Indicates the The minimum operating boundary of a distributed photovoltaic power station, Represents the time index, Indicates the index of the number of distributed photovoltaic power stations. Indicates the The control time of each distributed photovoltaic power station;

[0216] Determine economic indicators, including the regulation costs of distributed photovoltaic power plants;

[0217] The control cost of the distributed photovoltaic power station is calculated based on the operating data and is expressed as follows:

[0218] ;

[0219] Where, Indicates the The cost of abandoned light in a distributed photovoltaic power station is Indicates the The amount of abandoned light from distributed photovoltaic power stations, Indicates the The regulation cost of a distributed photovoltaic power station;

[0220] A resource clustering control indicator system is constructed based on the technical indicators and economic indicators.

[0221] As a preferred implementation, normalization is performed on each indicator in the resource clustering control indicator system. The specific steps are as follows:

[0222] The downward adjustment capacity is normalized in the positive direction and expressed as follows:

[0223] ;

[0224] Where, Represents the first The capacity reduction of distributed photovoltaic power stations, Indicates the maximum value of the reduced capacity of the distributed photovoltaic power station group, Indicates the minimum value of the reduced capacity of the distributed photovoltaic power station group;

[0225] The control time and control cost are negatively normalized and expressed as follows:

[0226] ;

[0227] ;

[0228] Where, Represents the first The regulation cost of a distributed photovoltaic power station or the The control time of a distributed photovoltaic power station, Indicates the The regulation cost of a distributed photovoltaic power station or the The control time of a distributed photovoltaic power station, Indicates the minimum control cost or control time of the distributed photovoltaic power station group, Indicates the maximum value of the regulation cost or regulation time of a distributed photovoltaic power station group.

[0229] As a preferred embodiment, the proportion of each normalized indicator of the distributed photovoltaic power station in the sum of the corresponding indicators of the distributed photovoltaic power station group is calculated, and the anti-entropy value and entropy weight of each indicator of the distributed photovoltaic power station group are calculated based on the proportion. The specific steps are:

[0230] Calculate the proportion of each normalized indicator of the distributed photovoltaic power station in the sum of the corresponding indicators of the distributed photovoltaic power station group, and express it as follows:

[0231] ;

[0232] ;

[0233] ;

[0234] ;

[0235] Where, Indicates the The first distributed photovoltaic power station after normalization The proportion of the corresponding indicators in the distributed photovoltaic power station group. Indicates the The first distributed photovoltaic power station after normalization indicators, Indicates the indicator index, Represents the first The indicators of the indicators and;

[0236] Based on the above proportions, the anti-entropy value of the corresponding indicator of the distributed photovoltaic power station group is calculated and expressed as follows:

[0237] ;

[0238] Where, Indicates the first The anti-entropy value of an indicator, represents the logarithmic function;

[0239] The entropy weight of the corresponding indicator of the distributed photovoltaic power station group is calculated based on the anti-entropy value, which is expressed as follows:

[0240] ;

[0241] Where, Indicates the first The entropy weight of an indicator.

[0242] In the embodiments of the present application, "at least one" refers to one or more, and "more" refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent the existence of A alone, the existence of A and B at the same time, and the existence of B alone. Among them, A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following" and similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b and c can represent: a, b, c, a and b, a and c, b and c or a and b and c, where a, b, c can be single or multiple.

[0243] Those skilled in the art will appreciate that the various units and algorithm steps described in the embodiments disclosed herein can be implemented using a combination of electronic hardware, computer software, and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0244] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0245] In the several embodiments provided in this application, if any function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of this application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory; hereinafter referred to as: ROM), random access memory (Random Access Memory; hereinafter referred to as: RAM), magnetic disk or optical disk, and other media that can store program code.

[0246] The above descriptions are merely embodiments of the present invention and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention's description and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A distributed photovoltaic power station clustering method considering objective weighting, characterized by: The following steps are involved: Acquiring operating data of distributed photovoltaic power stations and building a resource clustering control indicator system based on the operating data; Normalize each indicator in the resource clustering control indicator system; Calculating the proportion of each normalized indicator of the distributed photovoltaic power station in the sum of the corresponding indicators of the distributed photovoltaic power station group, and calculating the anti-entropy value and entropy weight of each indicator of the distributed photovoltaic power station group based on the proportion; Determining a standard deviation of an indicator value of a distributed photovoltaic power station group, and calculating a threshold value of the distributed photovoltaic power station group based on the standard deviation of the indicator value; The distributed photovoltaic power station group is used as the input of the clustering algorithm, and the distributed photovoltaic power station clustering result is output based on the threshold, the anti-entropy value and the entropy weight. The specific steps are as follows: S1. Mark each distributed photovoltaic power station in the distributed photovoltaic power station group as unclassified; S2. Create an empty cluster set , randomly select a distributed photovoltaic power station as the initial center point ; S3, with the initial center point As the center of the circle, the bandwidth of the distributed photovoltaic power station group Build a collection for distributed photovoltaic power stations within the radius search ; S4. Calculation Set Distributed photovoltaic power station to the initial center point The vector is expressed as: ； Where, represents the exponential function, Representing a collection Middle Distributed photovoltaic power stations to the initial center point vector, Representing a collection Middle The coordinate points of a distributed photovoltaic power station, represents the norm operator; S5. Calculate a set based on the vector and entropy weight The weighted vector sum of the distributed photovoltaic power station group in is expressed as follows: ； Where, Representing a collection The weighted vector sum of the distributed photovoltaic power station group in Representing a collection Middle The capacity reduction of distributed photovoltaic power stations, Representing a collection Middle The control time of a distributed photovoltaic power station, Representing a collection Middle The regulation cost of a distributed photovoltaic power station, represents the entropy weight of the capacity reduction of the distributed photovoltaic power station group, represents the entropy weight of the control time of the distributed photovoltaic power station group, The entropy weight representing the control cost of distributed photovoltaic power station group, Indicates the initial center point The downgrade capacity, Indicates the initial center point The control time, Indicates the initial center point the cost of regulation; S6. Calculate the initial center point based on the weighted vector The offset vector is expressed as: ； Where, Indicates the initial center point The offset vector of S7, based on the initial center point Update the initial center point with the offset vector , expressed as: ； Where, represents the updated center point; If the initial center point The offset vector The modulus value is less than the threshold , then execute step S8, otherwise execute step S3 with the updated center point; S8. If the empty cluster set There is satisfaction Ideal cluster , then the collection Merge into ideal cluster Otherwise, the collection Add to the empty cluster set as a new cluster ; in, Indicates calculation of Euclidean distance; S9: Step completed, outputting the clustering results of distributed photovoltaic power stations.

2. The distributed photovoltaic power station clustering method considering objective weighting according to claim 1 is characterized in that: A resource clustering control indicator system is constructed based on the operation data, with the specific steps being: Determine technical indicators, including the reduction capacity of distributed photovoltaic power stations and the regulation time of distributed photovoltaic power stations; The reduced capacity of the distributed photovoltaic power station is calculated based on the operating data, and is expressed as follows: ； ； ； Where, Indicates the total number of distributed photovoltaic power stations in the distributed photovoltaic power station group, Indicates the Distributed photovoltaic power stations in Operating power at all times, Indicates the The capacity reduction of distributed photovoltaic power stations, Indicates the The minimum operating boundary of a distributed photovoltaic power station, Represents the time index, Indicates the index of the number of distributed photovoltaic power stations. Indicates the The control time of each distributed photovoltaic power station; Determine economic indicators, including the regulation costs of distributed photovoltaic power plants; The control cost of the distributed photovoltaic power station is calculated based on the operating data and is expressed as follows: ； Where, Indicates the The cost of abandoned light in a distributed photovoltaic power station is Indicates the The amount of abandoned light from distributed photovoltaic power stations, Indicates the The regulation cost of a distributed photovoltaic power station; A resource clustering control indicator system is constructed based on the technical indicators and economic indicators.

3. The distributed photovoltaic power station clustering method considering objective weighting according to claim 2 is characterized in that: Normalize each indicator in the resource clustering control indicator system. The specific steps are as follows: The downward adjustment capacity is normalized in the positive direction and expressed as follows: ； Where, Represents the first The capacity reduction of distributed photovoltaic power stations, Indicates the maximum value of the reduced capacity of the distributed photovoltaic power station group, Indicates the minimum value of the reduced capacity of the distributed photovoltaic power station group; The control time and control cost are negatively normalized and expressed as follows: ； ； Where, Represents the first The regulation cost of a distributed photovoltaic power station or the The control time of a distributed photovoltaic power station, Indicates the The regulation cost of a distributed photovoltaic power station or the The control time of a distributed photovoltaic power station, Indicates the minimum control cost or control time of the distributed photovoltaic power station group, Indicates the maximum value of the regulation cost or regulation time of a distributed photovoltaic power station group.

4. The distributed photovoltaic power station clustering method considering objective weighting according to claim 3 is characterized in that: Calculate the proportion of each normalized indicator of the distributed photovoltaic power station in the sum of the corresponding indicators of the distributed photovoltaic power station group, and calculate the anti-entropy value and entropy weight of each indicator of the distributed photovoltaic power station group based on the proportion. The specific steps are as follows: Calculate the proportion of each normalized indicator of the distributed photovoltaic power station in the sum of the corresponding indicators of the distributed photovoltaic power station group, and express it as follows: ； ； ； Where, Indicates the The first distributed photovoltaic power station after normalization The proportion of the corresponding indicators in the distributed photovoltaic power station group. Indicates the The first distributed photovoltaic power station after normalization indicators, Indicates the indicator index, Represents the first The indicators of the indicators and; Based on the above proportions, the anti-entropy value of the corresponding indicator of the distributed photovoltaic power station group is calculated and expressed as follows: ； Where, Indicates the first The anti-entropy value of an indicator, represents the logarithmic function; The entropy weight of the corresponding indicator of the distributed photovoltaic power station group is calculated based on the anti-entropy value, which is expressed as follows: ； Where, Indicates the first The entropy weight of an indicator.

5. The distributed photovoltaic power station clustering method considering objective weighting according to claim 4 is characterized in that: Determine the standard deviation of the indicator values of the distributed photovoltaic power station group, and calculate the threshold value of the distributed photovoltaic power station group based on the standard deviation of the indicator values. The specific steps are as follows: Determine the standard deviation of the index values of the distributed photovoltaic power station group, which can be expressed as follows: ； ； ； Where, Indicates the standard deviation of the indicator values of the distributed photovoltaic power station group, Indicates the first The standard deviation of the indicator values of the indicators, Indicates the first The mean value of each indicator; The bandwidth of the distributed photovoltaic power station group is calculated based on the standard deviation of the indicator values, which can be expressed as follows: ； Where, Indicates the indicator dimension, Indicates the bandwidth of the distributed photovoltaic power station group; The threshold of distributed photovoltaic power station group Set to bandwidth of .

6. A distributed photovoltaic power station clustering system considering objective weighting, characterized by: include: System construction module: obtains the operating data of the distributed photovoltaic power station and constructs a resource clustering control indicator system based on the operating data; Preprocessing module: normalizes each indicator in the resource clustering control indicator system; Objective weighting module: calculates the proportion of each normalized indicator of the distributed photovoltaic power station in the sum of the corresponding indicators of the distributed photovoltaic power station group, and calculates the anti-entropy value and entropy weight of each indicator of the distributed photovoltaic power station group based on the proportion; Threshold setting module: determining the standard deviation of the indicator values of the distributed photovoltaic power station group, and calculating the threshold value of the distributed photovoltaic power station group based on the standard deviation of the indicator values; The clustering module takes the distributed photovoltaic power station group as the input of the clustering algorithm and outputs the distributed photovoltaic power station clustering result based on the threshold, the anti-entropy value and the entropy weight. The specific steps are as follows: S1. Mark each distributed photovoltaic power station in the distributed photovoltaic power station group as unclassified; S2. Create an empty cluster set , randomly select a distributed photovoltaic power station as the initial center point ; S3, with the initial center point As the center of the circle, the bandwidth of the distributed photovoltaic power station group Build a collection for distributed photovoltaic power stations within the radius search ; S4. Calculation Set Distributed photovoltaic power station to the initial center point The vector is expressed as: ； Where, represents the exponential function, Representing a collection Middle Distributed photovoltaic power stations to the initial center point vector, Representing a collection Middle The coordinate points of a distributed photovoltaic power station, represents the norm operator; S5. Calculate a set based on the vector and entropy weight The weighted vector sum of the distributed photovoltaic power station group in is expressed as follows: ； Where, Representing a collection The weighted vector sum of the distributed photovoltaic power station group in Representing a collection Middle The capacity reduction of distributed photovoltaic power stations, Representing a collection Middle The control time of a distributed photovoltaic power station, Representing a collection Middle The regulation cost of a distributed photovoltaic power station, represents the entropy weight of the capacity reduction of the distributed photovoltaic power station group, represents the entropy weight of the control time of the distributed photovoltaic power station group, The entropy weight representing the control cost of distributed photovoltaic power station group, Indicates the initial center point The downgrade capacity, Indicates the initial center point The control time, Indicates the initial center point the cost of regulation; S6. Calculate the initial center point based on the weighted vector The offset vector is expressed as: ； Where, Indicates the initial center point The offset vector of S7, based on the initial center point Update the initial center point with the offset vector , expressed as: ； Where, represents the updated center point; If the initial center point The offset vector The modulus value is less than the threshold , then execute step S8, otherwise execute step S3 with the updated center point; S8. If the empty cluster set There is satisfaction Ideal cluster , then the collection Merge into ideal cluster Otherwise, the collection Add to the empty cluster set as a new cluster ; in, Indicates calculation of Euclidean distance; S9: Step completed, outputting the clustering results of distributed photovoltaic power stations.

7. The distributed photovoltaic power station clustering system considering objective weighting according to claim 6, characterized in that: A resource clustering control indicator system is constructed based on the operation data, with the specific steps being: Determine technical indicators, including the reduction capacity of distributed photovoltaic power stations and the regulation time of distributed photovoltaic power stations; The reduced capacity of the distributed photovoltaic power station is calculated based on the operating data, and is expressed as follows: ； ； ； Where, Indicates the total number of distributed photovoltaic power stations in the distributed photovoltaic power station group, Indicates the Distributed photovoltaic power stations in Operating power at all times, Indicates the The capacity reduction of distributed photovoltaic power stations, Indicates the The minimum operating boundary of a distributed photovoltaic power station, Represents the time index, Indicates the index of the number of distributed photovoltaic power stations. Indicates the The control time of each distributed photovoltaic power station; Determine economic indicators, including the regulation costs of distributed photovoltaic power plants; The control cost of the distributed photovoltaic power station is calculated based on the operating data and is expressed as follows: ； Where, Indicates the The cost of abandoned light in a distributed photovoltaic power station is Indicates the The amount of abandoned light from distributed photovoltaic power stations, Indicates the The regulation cost of a distributed photovoltaic power station; A resource clustering control indicator system is constructed based on the technical indicators and economic indicators.

8. The distributed photovoltaic power station clustering system considering objective weighting according to claim 7, characterized in that: Normalize each indicator in the resource clustering control indicator system. The specific steps are as follows: The downward adjustment capacity is normalized in the positive direction and expressed as follows: ； Where, Represents the first The capacity reduction of distributed photovoltaic power stations, Indicates the maximum value of the reduced capacity of the distributed photovoltaic power station group, Indicates the minimum value of the reduced capacity of the distributed photovoltaic power station group; The control time and control cost are negatively normalized and expressed as follows: ； ； Where, Represents the first The regulation cost of a distributed photovoltaic power station or the The control time of a distributed photovoltaic power station, Indicates the The regulation cost of a distributed photovoltaic power station or the The control time of a distributed photovoltaic power station, Indicates the minimum control cost or control time of the distributed photovoltaic power station group, Indicates the maximum value of the regulation cost or regulation time of a distributed photovoltaic power station group.

9. The distributed photovoltaic power station clustering system considering objective weighting according to claim 8, characterized in that: Calculate the proportion of each normalized indicator of the distributed photovoltaic power station in the sum of the corresponding indicators of the distributed photovoltaic power station group, and calculate the anti-entropy value and entropy weight of each indicator of the distributed photovoltaic power station group based on the proportion. The specific steps are as follows: Calculate the proportion of each normalized indicator of the distributed photovoltaic power station in the sum of the corresponding indicators of the distributed photovoltaic power station group, and express it as follows: ； ； ； Where, Indicates the The first distributed photovoltaic power station after normalization The proportion of the corresponding indicators in the distributed photovoltaic power station group. Indicates the The first distributed photovoltaic power station after normalization indicators, Indicates the indicator index, Represents the first The indicators of the indicators and; Based on the above proportions, the anti-entropy value of the corresponding indicator of the distributed photovoltaic power station group is calculated and expressed as follows: ； Where, Indicates the first The anti-entropy value of an indicator, represents the logarithmic function; The entropy weight of the corresponding indicator of the distributed photovoltaic power station group is calculated based on the anti-entropy value, which is expressed as follows: ； Where, Indicates the first The entropy weight of an indicator.

Images