A photovoltaic power station cluster operation and maintenance efficiency analysis method, device, equipment and medium

Abstract

The application discloses a photovoltaic power station cluster operation and maintenance efficiency analysis method and device, equipment and medium, relates to the photovoltaic power station operation and maintenance field, and the technical scheme main points are: obtaining the data of each photovoltaic power station in four dimensions of production, operation and maintenance, fault and environment;According to the data of each photovoltaic power station in four dimensions of production, operation and maintenance, fault and environment, the analysis index of each photovoltaic power station in four dimensions of production, operation and maintenance, fault and environment is determined;The analysis index of each photovoltaic power station in four dimensions of production, operation and maintenance, fault and environment is processed by adopting the space-time range entropy weight method, and the comprehensive value of each photovoltaic power station is obtained;The comprehensive value of each photovoltaic power station is decomposed by adopting the Dagum Gini coefficient decomposition method, and the Gini coefficient of photovoltaic power station cluster operation and maintenance efficiency analysis is obtained;Wherein, a plurality of photovoltaic power stations constitute a photovoltaic power station cluster;According to the interval range of the preconfigured Gini coefficient, the analysis result of photovoltaic power station cluster operation and maintenance efficiency is determined.

Description

Technical Field

[0001] This invention relates to the field of photovoltaic power plant operation and maintenance, and more specifically, to a method, apparatus, equipment, and medium for analyzing the operation and maintenance efficiency of a photovoltaic power plant cluster. Background Technology

[0002] Collecting and evaluating power plant operation indicators in the background provides a basis for adjusting and improving power plant operation and maintenance strategies, which is one of the important means to ensure the safe and effective operation of power plants.

[0003] However, the different locations of power plants, varying levels of irradiance received by photovoltaic panels in different regions, and differences in the degree of corrosion of components and equipment due to environmental factors such as humidity, temperature, and pollutants, as well as the varying qualifications of operation and maintenance personnel, all pose challenges to the standardized assessment of power plants. Currently, research on evaluation indicators and methods for photovoltaic power plants has progressed from single-indicator evaluation to comprehensive evaluation indicator systems. Single-indicator evaluations generally consider only a limited number of dimensions, often exhibiting excessive subjectivity and reliance on data characteristics. Comprehensive evaluation methods can be divided into mathematical methods and machine learning methods. Mathematical methods, unable to optimize models based on actual operational sample data, rely on subjective experience in the modeling process. Machine learning methods, on the other hand, require prior human knowledge to screen a large number of samples, heavily relying on sample data, and often suffer from insufficient model generalization ability.

[0004] In summary, current photovoltaic power plant evaluations either focus on a single dimension or involve collecting a large number of indicators before conducting secondary screening, lacking effectiveness and universality. Secondly, the evaluation results are not usable enough, as they are not modified or explored in light of actual application scenarios. Furthermore, the evaluation results only consider the power plant itself and do not take into account the characteristics of power plant cluster distribution, making them unsuitable for the overall management of the power plant. Summary of the Invention

[0005] The purpose of this invention is to provide a method, device, equipment, and medium for analyzing the operation and maintenance efficiency of photovoltaic power plant clusters. This method can accurately evaluate the operating status of photovoltaic power plants and, by analyzing the differences between different operation and maintenance areas and among photovoltaic power plants within different operation and maintenance areas, can incentivize and assess power plant operation and maintenance personnel, thereby improving the operation and maintenance level and power generation efficiency of photovoltaic power plants.

[0006] In a first aspect, the present invention provides a method for analyzing the operation and maintenance efficiency of a photovoltaic power plant cluster, the method comprising:

[0007] Acquire data for each photovoltaic power station across four dimensions: production, operation and maintenance, faults, and environment.

[0008] Based on the data of each photovoltaic power station in four dimensions—production, operation and maintenance, failure, and environment—analysis indicators for each photovoltaic power station in these four dimensions are determined.

[0009] The spatiotemporal range entropy weight method is used to process the analytical indicators of each photovoltaic power station in four dimensions: production, operation and maintenance, failure and environment, to obtain the comprehensive value of each photovoltaic power station;

[0010] The comprehensive value of each photovoltaic power station is decomposed using the Dagum Gini coefficient decomposition method to obtain the Gini coefficient for the operation and maintenance efficiency analysis of the photovoltaic power station cluster; where multiple photovoltaic power stations constitute a photovoltaic power station cluster.

[0011] The analysis results of the operation and maintenance efficiency of the photovoltaic power plant cluster are determined based on the pre-configured range of the Gini coefficient.

[0012] In one implementation scheme, the analytical indicators of the photovoltaic power station in terms of production dimension include power generation completion rate, plant power consumption rate, and system efficiency;

[0013] The operational and maintenance indicators for the photovoltaic power plant include fault return rate, planned cleaning completion rate, log reporting completion rate, event recording completeness rate, and fault handling timeliness rate.

[0014] The analysis indicators for the photovoltaic power plant in terms of fault dimension include the number of equipment failures, the number of times the equipment is damaged and cannot be repaired, the equipment availability rate, and the inverter conversion efficiency.

[0015] The environmental analysis indicators for the photovoltaic power station include the number of minor personal injury accidents, the number of fire accidents, the number of pollution and damage incidents, and the number of power outages.

[0016] In one implementation scheme, the spatiotemporal range entropy weight method is used to process the analytical indicators of the photovoltaic power station in four dimensions: production, operation and maintenance, failure, and environment, to obtain the comprehensive value of the photovoltaic power station, specifically:

[0017] Obtain the initial values, global minimum values, and global maximum values ​​of the analysis indicators for all photovoltaic power plants within a time period;

[0018] The initial value, global minimum value, and global maximum value are normalized to calculate the positive and negative results for each analysis indicator.

[0019] Calculate the global mean of each analytical indicator. Subtract the global maximum value from the global mean to obtain the positive range of each analytical indicator. Subtract the global mean from the global minimum value to obtain the negative range of each analytical indicator.

[0020] The positive and negative results of each analytical indicator are shifted to calculate the weight of each analytical indicator.

[0021] Based on the weight of each analytical indicator, the entropy value of each analytical indicator is calculated.

[0022] The entropy value of each analytical indicator is corrected based on its positive and negative ranges to calculate the corrected entropy value of each analytical indicator.

[0023] The weight of each analytical indicator is calculated based on the correction results;

[0024] The weighted average of each analytical index of each photovoltaic power station under time decay is calculated using the time decay function;

[0025] The comprehensive value of each photovoltaic power station is calculated based on the weighted average and weight of each analytical indicator.

[0026] In one implementation scheme, the Dagum Gini coefficient decomposition method is used to decompose the comprehensive value of the photovoltaic power station to obtain the Gini coefficient for the operation and maintenance efficiency analysis of the photovoltaic power station cluster, specifically:

[0027] Multiple operation and maintenance areas are divided based on the location information of each photovoltaic power station; one operation and maintenance area contains multiple photovoltaic power stations.

[0028] Based on the comprehensive value of each photovoltaic power station and the number of photovoltaic power stations in each operation and maintenance area, the first sub-Gini coefficient of each operation and maintenance area is calculated, and the first sub-Gini coefficient of each operation and maintenance area is weighted and averaged according to the number of photovoltaic power stations to calculate the first difference value between each photovoltaic power station in each operation and maintenance area.

[0029] Based on the comprehensive value of each photovoltaic power station and the number of photovoltaic power stations in each operation and maintenance area, the second sub-Gini coefficient between the two operation and maintenance areas is calculated, and the second sub-Gini coefficient between the two operation and maintenance areas is weighted and averaged according to the number of photovoltaic power stations to calculate the second difference value between the two operation and maintenance areas.

[0030] The supervariable density between two operation and maintenance areas is calculated based on the number and comprehensive value of photovoltaic power stations in each operation and maintenance area.

[0031] The Gini coefficient for analyzing the operation and maintenance efficiency of photovoltaic power plant clusters is calculated based on the first difference value, the second difference value, and the supervariable density.

[0032] In one implementation scheme, the supervariable density between two operation and maintenance areas is calculated based on the number and comprehensive value of photovoltaic power plants in each operation and maintenance area, specifically:

[0033] Based on the cumulative distribution function of each of the two operation and maintenance regions, the total analysis value of one operation and maintenance region relative to the other operation and maintenance region is calculated, and the relative analysis value of one operation and maintenance region relative to the other operation and maintenance region is calculated based on the total analysis value.

[0034] Calculate the percentage of the comprehensive value and the percentage of the number of power plants in each of the two operation and maintenance regions under the photovoltaic power generation cluster;

[0035] The supervariable density between the two operation and maintenance areas is calculated based on the comprehensive value ratio, the power station number ratio, and the relative analysis value.

[0036] In one implementation, the range includes a first interval, a second interval, a third interval, a fourth interval, and a fifth interval whose values ​​increase sequentially.

[0037] Based on the pre-configured range of the Gini coefficient, the analysis results of the operation and maintenance efficiency of the photovoltaic power station cluster are determined. Specifically, the distribution results are determined based on the range of the Gini coefficient, and the analysis results of the operation and maintenance efficiency of the photovoltaic power station cluster are determined based on the corresponding distribution results.

[0038] In one implementation, when the Gini coefficient is in the first interval, the Gini coefficient of the photovoltaic power station cluster is adjusted by increasing the incentive indicators of the month-on-month growth rate and the ranking of the same operation and maintenance area.

[0039] Among them, the month-on-month growth rate is the ratio of the Gini coefficient of the photovoltaic power station in the current statistical period to that in the previous statistical period, and the ranking in the same operation and maintenance area is the ratio of the Gini coefficient ranking of the photovoltaic power station in its operation and maintenance area to the total number of power stations in the operation and maintenance area of ​​the photovoltaic power station.

[0040] A second aspect of the present invention provides a photovoltaic power plant cluster operation and maintenance efficiency analysis device, the device comprising:

[0041] The data acquisition module is used to acquire data for each photovoltaic power station in four dimensions: production, operation and maintenance, faults, and environment.

[0042] The indicator calculation module is used to determine the analytical indicators for each photovoltaic power station in the four dimensions of production, operation and maintenance, failure and environment based on the data of each photovoltaic power station in the four dimensions of production, operation and maintenance, failure and environment.

[0043] The comprehensive value calculation module is used to process the analysis indicators of each photovoltaic power station in four dimensions: production, operation and maintenance, failure and environment, using the spatiotemporal range entropy weight method to obtain the comprehensive value of each photovoltaic power station.

[0044] The coefficient decomposition module is used to decompose the comprehensive value of each photovoltaic power station using the Dagum Gini coefficient decomposition method to obtain the Gini coefficient for the operation and maintenance efficiency analysis of the photovoltaic power station cluster; where multiple photovoltaic power stations constitute a photovoltaic power station cluster.

[0045] The efficiency analysis module is used to determine the analysis results of the operation and maintenance efficiency of photovoltaic power plant clusters based on the pre-configured range of the Gini coefficient.

[0046] In one implementation scheme, the analytical indicators of the photovoltaic power station in terms of production dimension include power generation completion rate, plant power consumption rate, and system efficiency;

[0047] The operational and maintenance indicators for the photovoltaic power plant include fault return rate, planned cleaning completion rate, log reporting completion rate, event recording completeness rate, and fault handling timeliness rate.

[0048] The analysis indicators for the photovoltaic power plant in terms of fault dimension include the number of equipment failures, the number of times the equipment is damaged and cannot be repaired, the equipment availability rate, and the inverter conversion efficiency.

[0049] The environmental analysis indicators for the photovoltaic power station include the number of minor personal injury accidents, the number of fire accidents, the number of pollution and damage incidents, and the number of power outages.

[0050] In one implementation, the comprehensive value calculation module is specifically used for:

[0051] Obtain the initial values, global minimum values, and global maximum values ​​of the analysis indicators for all photovoltaic power plants within a certain time period;

[0052] The initial value, global minimum value, and global maximum value are normalized to calculate the positive and negative results for each analysis indicator.

[0053] Calculate the global mean of each analytical indicator. Subtract the global maximum value from the global mean to obtain the positive range of each analytical indicator. Subtract the global mean from the global minimum value to obtain the negative range of each analytical indicator.

[0054] The positive and negative results of each analytical indicator are shifted to calculate the weight of each analytical indicator.

[0055] Based on the weight of each analytical indicator, the entropy value of each analytical indicator is calculated.

[0056] The entropy value of each analytical indicator is corrected based on its positive and negative ranges to calculate the corrected entropy value of each analytical indicator.

[0057] The weight of each analytical indicator is calculated based on the correction results;

[0058] The weighted average of each analytical index of each photovoltaic power station under time decay is calculated using the time decay function;

[0059] The comprehensive value of each photovoltaic power station is calculated based on the weighted average and weight of each analytical indicator.

[0060] In one implementation, the coefficient decomposition module is specifically used for:

[0061] Multiple operation and maintenance areas are divided based on the location information of each photovoltaic power station; one operation and maintenance area contains multiple photovoltaic power stations.

[0062] Based on the comprehensive value of each photovoltaic power station and the number of photovoltaic power stations in each operation and maintenance area, the first sub-Gini coefficient of each operation and maintenance area is calculated, and the first sub-Gini coefficient of each operation and maintenance area is weighted and averaged according to the number of photovoltaic power stations to calculate the first difference value between each photovoltaic power station in each operation and maintenance area.

[0063] Based on the comprehensive value of each photovoltaic power station and the number of photovoltaic power stations in each operation and maintenance area, the second sub-Gini coefficient between the two operation and maintenance areas is calculated, and the second sub-Gini coefficient between the two operation and maintenance areas is weighted and averaged according to the number of photovoltaic power stations to calculate the second difference value between the two operation and maintenance areas.

[0064] The supervariable density between two operation and maintenance areas is calculated based on the number and comprehensive value of photovoltaic power stations in each operation and maintenance area.

[0065] The Gini coefficient for analyzing the operation and maintenance efficiency of photovoltaic power plant clusters is calculated based on the first difference value, the second difference value, and the supervariable density.

[0066] In one implementation scheme, the supervariable density between two operation and maintenance areas is calculated based on the number and comprehensive value of photovoltaic power plants in each operation and maintenance area, specifically:

[0067] Based on the cumulative distribution function of each of the two operation and maintenance regions, the total analysis value of one operation and maintenance region relative to the other operation and maintenance region is calculated, and the relative analysis value of one operation and maintenance region relative to the other operation and maintenance region is calculated based on the total analysis value.

[0068] Calculate the percentage of the comprehensive value and the percentage of the number of power plants in each of the two operation and maintenance regions under the photovoltaic power generation cluster;

[0069] The supervariable density between the two operation and maintenance areas is calculated based on the comprehensive value ratio, the power station number ratio, and the relative analysis value.

[0070] A third aspect of the present invention provides an electronic device comprising a processor, a memory, and a computer program stored in the memory and executable by the processor, wherein the computer program, when executed by the processor, implements the steps of a photovoltaic power plant cluster operation and maintenance efficiency analysis method as provided in the first aspect of the present invention.

[0071] In a fourth aspect, the present invention provides a computer-readable storage medium storing a computer program, wherein when the computer program is executed by a processor, it implements the steps of a photovoltaic power plant cluster operation and maintenance efficiency analysis method as provided in the first aspect of the present invention.

[0072] Compared with the prior art, the present invention has the following beneficial effects:

[0073] In the photovoltaic power plant cluster operation and maintenance efficiency analysis method provided in this embodiment of the invention, addressing the current problem of insufficient effectiveness in power plant analysis dimensions, this method comprehensively considers various factors affecting the power generation level of the power plant and divides the evaluation into four dimensions: production operation quality evaluation, operation and maintenance management quality evaluation, equipment operation quality evaluation, and operating environment quality evaluation. The established secondary evaluation indicators are based on the principles of easy accessibility during the daily operation of the power plant and high representativeness of the evaluation dimension. The required data does not require additional monitoring equipment and can be applied to most power plants. To address the issue of unclear analysis results, the comprehensive value of each photovoltaic power plant is calculated using the spatiotemporal range entropy weighting method. This avoids the irrationality and limitations of subjective weighting and traditional entropy methods. Furthermore, considering the dynamic changes of power plant operation indicator data in both time and space dimensions, this method can accurately evaluate the operating status of the photovoltaic power plant and identify weaknesses in the power plant's operation process. To address the issue of insufficient management methods for power plant clusters, the Dagum Gini coefficient decomposition method is adopted to assess the degree of difference between different comparative operation and maintenance areas and between power plants within different operation and maintenance areas. The power plant cluster score can be adjusted and corrected based on the Gini coefficient, which helps managers better balance the fairness and incentive effect of power plant assessment, stimulate the work enthusiasm of operation and maintenance personnel, and ultimately improve the operation and maintenance level and power generation efficiency of power plants. Attached Figure Description

[0074] The accompanying drawings, which are included to provide a further understanding of embodiments of the invention and form part of this application, do not constitute a limitation thereof. In the drawings:

[0075] Figure 1 A flowchart illustrating a method for analyzing the operation and maintenance efficiency of a photovoltaic power plant cluster, provided in an embodiment of the present invention;

[0076] Figure 2This is a schematic diagram of a photovoltaic power plant cluster operation and maintenance efficiency analysis device provided in an embodiment of the present invention. Detailed Implementation

[0077] To make the objectives, technical solutions, and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the embodiments and accompanying drawings. The illustrative embodiments and descriptions of the present invention are only used to explain the present invention and are not intended to limit the present invention.

[0078] It should be noted that the terms "comprising" or "may include" used in the various embodiments of this application indicate the presence of the claimed function, operation, or element, and do not limit the addition of one or more functions, operations, or elements. Furthermore, as used in the various embodiments of this application, the terms "comprising," "having," and their cognates are intended only to indicate a specific feature, number, step, operation, element, component, or combination of the foregoing, and should not be construed as primarily excluding the presence of one or more other features, numbers, steps, operations, elements, components, or combinations of the foregoing, or adding one or more combinations of the foregoing.

[0079] It should be understood that terms such as "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0080] Please refer to Figure 1 , Figure 1 This is a flowchart illustrating a method for analyzing the operation and maintenance efficiency of a photovoltaic power plant cluster, as provided in an embodiment of the present invention. Figure 1 As shown, the method includes:

[0081] S101 acquires data for each photovoltaic power station across four dimensions: production, operation and maintenance, faults, and environment.

[0082] In this embodiment, the data regarding the production dimension includes actual power generation during the statistical period, etc.

[0083] In terms of operation and maintenance data, the data includes the number of times that faulty equipment needs to be repaired again after maintenance within the statistical period, the number of times that faulty equipment needs to be repaired again after maintenance within the statistical period, the number of times the power plant is cleaned on time according to the cleaning plan within the statistical period, and the number of times that the power plant operation and maintenance personnel fill in the operation log on time within the statistical period.

[0084] In terms of fault data, the data includes the total number of faults of key power generation equipment such as inverters and transformer substations within the statistical period, the number of times key power generation equipment such as inverters and transformer substations suffered major and irreparable damage within the statistical period, the remaining time after deducting the time of inverter maintenance and faults within the statistical period, and the remaining time after deducting the downtime not caused by the inverter itself from the total time.

[0085] In terms of the environmental dimension, the data includes the number of minor personal injury accidents, the number of fire accidents, the number of environmental pollution or ecological damage incidents, and the number of unplanned power outage accidents or incidents within the statistical period.

[0086] S102, based on the data of each photovoltaic power station in the four dimensions of production, operation and maintenance, failure and environment, determine the analysis indicators of each photovoltaic power station in the four dimensions of production, operation and maintenance, failure and environment.

[0087] In this embodiment, the analytical indicators for the photovoltaic power station in terms of production include power generation completion rate, plant power consumption rate, and system efficiency; the analytical indicators for the photovoltaic power station in terms of operation and maintenance include fault return rate, planned cleaning completion rate, log filling completion rate, event record completeness rate, and fault handling timeliness rate; the analytical indicators for the photovoltaic power station in terms of faults include the number of equipment failures, the number of times equipment is damaged and cannot be repaired, equipment availability rate, and inverter conversion efficiency; the analytical indicators for the photovoltaic power station in terms of environment include pollution rate, number of extreme weather events, number of times ambient temperature exceeds limits, and number of times ambient humidity exceeds limits.

[0088] Specifically, the power generation completion rate is the percentage of actual power generation that meets the standard required power generation within a statistical period, indicating the degree to which the power plant's actual power generation meets the target. The standard required power generation is obtained through a power generation calculation model or is set in advance based on contractual indicators.

[0089] Plant power consumption rate is the ratio of actual power generation to plant power consumption within the statistical period.

[0090] System efficiency is the ratio of actual power generation to theoretical power generation within a statistical period. It represents the degree of rated output loss of a photovoltaic array under the combined effects of internal influencing factors such as equipment failure and external influencing factors such as power curtailment and dust accumulation.

[0091] The fault return rate is the proportion of the number of times that faulty equipment needs to be repaired again after maintenance within the statistical period, out of the total number of maintenance times. It represents the accuracy and technical level of maintenance personnel in repairing power plant equipment after a fault occurs.

[0092] The planned cleaning completion rate is the proportion of times the power plant was cleaned on time according to the cleaning plan within the statistical period to the total number of planned cleaning times, indicating the timeliness of the cleaning work carried out by the power plant operation and maintenance personnel.

[0093] Log completion rate is the ratio of the number of times power plant operation and maintenance personnel fill in the operation log on time to the actual number of times they should have filled it in during the statistical period. It represents the completeness of the power plant operation and maintenance personnel's records of the daily operation of the power plant.

[0094] Event record completeness rate is the ratio of the number of times power plant operation and maintenance personnel complete the recording of critical events such as faults and power outages within the statistical period to the actual number of times critical events such as equipment faults and power outages occur. It represents the completeness of the power plant operation and maintenance personnel's records of critical events at the power plant.

[0095] The fault handling timeliness rate is the ratio of the number of times that power plant operation and maintenance personnel handle faults in a timely manner to the number of times faults occur within a statistical period, indicating the timeliness of fault handling by power plant operation and maintenance personnel.

[0096] The number of critical equipment failures is the total number of failures of key power generation equipment such as inverters and transformer substations within the statistical period, representing the normal operating capability of the power station equipment.

[0097] The number of times critical equipment is damaged beyond repair refers to the number of times critical power generation equipment such as inverters and transformer substations suffer major damage that is beyond repair within the statistical period, representing the power station's ability to ensure equipment safety.

[0098] Equipment availability is the ratio of the remaining time after deducting the time for inverter maintenance and failure within the statistical period to the remaining time after deducting the downtime not caused by the inverter itself within the total time. It represents the reliability of the power plant equipment.

[0099] Inverter conversion efficiency is the ratio of AC power generation to DC power generation of the inverter within a statistical period, representing the degree of loss of the power plant equipment itself.

[0100] The number of minor personal injury accidents refers to the number of work-related injuries suffered by operation and maintenance personnel in photovoltaic power plants within the statistical period, reflecting the power plant's ability to ensure personal safety.

[0101] The number of fire accidents refers to the number of fire accidents that occur in the photovoltaic power station within the statistical period, reflecting the fire safety management status of the power station.

[0102] The number of environmental pollution or ecological damage incidents refers to the number of times that the photovoltaic power station caused environmental pollution or ecological damage during its production and operation within the statistical period, reflecting the power station's performance in environmental protection and ecological maintenance.

[0103] The safety inspection pass rate is the ratio of the number of times a photovoltaic power station is rated as qualified during safety inspections to the total number of inspections within the statistical period. It reflects the power station's management level of the operating environment safety.

[0104] S103 uses the spatiotemporal range entropy weight method to process the analytical indicators of each photovoltaic power station in four dimensions: production, operation and maintenance, faults, and environment, and obtains the comprehensive value of each photovoltaic power station.

[0105] In this embodiment, the comprehensive value of each photovoltaic power station is calculated, including the following steps:

[0106] S1031: Obtain the initial value, global minimum value, and global maximum value of the analysis indicators for all photovoltaic power plants within the time period.

[0107] In this embodiment, the initial value of the analysis index refers to the calculated or statistical value of the analysis index for all photovoltaic power plants within a time period T. For example, assuming there are n = 3 photovoltaic power plants (A / B / C, where the subscript i represents one of the power plants or all n power plants), and in T = 2 time periods (t1, t2, where the subscript t represents one of the time periods or all T time periods), the analysis index is system efficiency j1 and the number of fires j2.

[0108] The original data can be presented in the following table:

[0109] Photovoltaic power station time System efficiency j1 Number of fires j2 A t1 85％ 2 times A t2 82％ 3 times B t1 80％ 5 times B t2 78％ 4 times C t1 75％ 6 times C t2 77％ 5 times

[0110] That is, the global maximum value of system efficiency j1 is 85%, the global minimum value is 75%, and the global maximum value of fire count j2 is 6 times, the global minimum value is 2 times.

[0111] S1032 normalizes the initial value, global minimum value, and global maximum value, and calculates the positive and negative processing results for each analysis indicator.

[0112] In this embodiment, the normalization process is divided into two categories: one is the normalization process for positive analysis indicators, and the other is the normalization process for negative analysis indicators.

[0113] Specifically, the normalization formula for the positive analysis indicator is:

[0114] Where, x ijt Let be the initial value of the j-th analysis index for the i-th photovoltaic power station within time t1, min i＝1,…,n；t＝1,…,T (x ijt Let be the global minimum value of the j-th analytical indicator for the i-th photovoltaic power station within time period T, and max be the minimum value of the j-th analytical indicator. i＝1,…,n；t＝1,…,T (x ijt ) represents the global maximum value of the j-th analysis indicator for the i-th photovoltaic power station within the time period T.

[0115] The normalization formula for the negative analysis index is:

[0116]

[0117] S1033, calculate the global mean of each analysis indicator, subtract the global maximum value from the global mean of each analysis indicator to obtain the positive range of each analysis indicator, and subtract the global mean from the global minimum value of each analysis indicator to obtain the negative range of each analysis indicator.

[0118] In this embodiment, the formula for calculating the positive range is: Where, μ j Let be the global mean of the j-th analytical indicator.

[0119] The formula for calculating the negative range is:

[0120] The global mean is calculated as follows:

[0121] S1034, shift the positive and negative processing results of each analysis indicator to calculate the weight of each analysis indicator.

[0122] Based on the above description, the formula for calculating the proportion of the analytical indicators using both positive and negative processing results is as follows: Where ∈ is a minimal constant, and T represents the total number of time periods.

[0123] S1035, calculate the entropy value of each analytical indicator based on the weight of each analytical indicator.

[0124] In this embodiment, the formula for calculating the entropy value of each analytical indicator is as follows:

[0125] S1036, based on the positive and negative ranges of each analytical indicator, the entropy value of each analytical indicator is corrected to calculate the correction result of the entropy value of each analytical indicator.

[0126] In this embodiment, the expression for correcting the entropy value is: Where, α + α - These are the positive range adjustment parameters and the negative range adjustment parameters, respectively.

[0127] S1037, calculate the weight of each analysis indicator based on the correction results.

[0128] In this embodiment, the formula for calculating the weight of each analysis indicator based on the correction result is as follows: Among them, H′ j H′ represents the corrected entropy value of the j-th analytical indicator, m represents the total number of analytical indicators, and H′ represents the corrected entropy value of the j-th analytical indicator. k This represents the corrected entropy value of the k-th analytical indicator.

[0129] S1038 uses a time decay function to calculate the weighted average of each analytical index of each photovoltaic power station under time decay.

[0130] In this embodiment, a dynamic time decay factor is used to improve the spatiotemporal range entropy weighting method to calculate the comprehensive value of the photovoltaic power station. It can be seen that this embodiment proposes a method that improves the spatiotemporal range entropy weighting method, thereby avoiding the irrationality and limitations of subjective weighting and traditional entropy value method. Considering the dynamic changes of the photovoltaic power station's operating index data in both time and space dimensions, it can accurately evaluate the operating status of the photovoltaic power station and trace the weak links in the power station's operation process.

[0131] First, define the time decay function: λ(t) = e -β(T-t) Where β is the decay rate parameter, T is the total number of time periods, and t is the current time period (t = 1, 2, ..., T).

[0132] For the j-th analysis index of the i-th photovoltaic power station, the formula for calculating its weighted average is:

[0133] S1039, calculate the comprehensive value of each photovoltaic power station based on the weighted average and weight of each analysis indicator.

[0134] Finally, based on the weighted average and weights calculated above, the comprehensive value of each photovoltaic power station is calculated by summing their products. Si reflects the dynamic comprehensive operation and maintenance performance of the i-th photovoltaic power station. The larger the value, the higher the photovoltaic power station's capabilities in operation and maintenance, efficiency, and other aspects.

[0135] S104 uses the Dagum Gini coefficient decomposition method to decompose the comprehensive value of each photovoltaic power station to obtain the Gini coefficient for the operation and maintenance efficiency analysis of the photovoltaic power station cluster; where multiple photovoltaic power stations constitute a photovoltaic power station cluster.

[0136] In this embodiment, the process of decomposing the comprehensive value of each photovoltaic power station to obtain the Gini coefficient for the operation and maintenance efficiency analysis of the photovoltaic power station cluster is as follows:

[0137] S1041, multiple operation and maintenance areas are divided according to the location information of each photovoltaic power station; one operation and maintenance area contains multiple photovoltaic power stations.

[0138] Specifically, the division of operation and maintenance areas can be done using conventional technical means, such as combining adjacent photovoltaic power stations or dividing according to the region to which the photovoltaic power station belongs. This embodiment does not impose specific limitations, but it should be noted that the divided operation and maintenance areas must include two or more photovoltaic power stations.

[0139] S1042, based on the comprehensive value of each photovoltaic power station and the number of photovoltaic power stations in each operation and maintenance area, calculate the first sub-Gini coefficient of each operation and maintenance area, and then weight the first sub-Gini coefficient of each operation and maintenance area according to the number of photovoltaic power stations to calculate the first difference value between each photovoltaic power station in each operation and maintenance area.

[0140] In this embodiment, the formula for calculating the first sub-Gini coefficient within the operation and maintenance area is: Where, μ a M is the average comprehensive value of all photovoltaic power stations in the a-th operation and maintenance area; as M represents the comprehensive value of the s-th photovoltaic power station in the a-th operation and maintenance area. ar Let n be the comprehensive value of the r-th photovoltaic power station in the a-th operation and maintenance area; a It represents the total number of photovoltaic power stations in the a-th operation and maintenance area.

[0141] The first difference value G between various photovoltaic power stations within the operation and maintenance area w The first sub-Gini coefficient of each operation and maintenance area is obtained by weighting the number of photovoltaic power stations.

[0142] S1043. Based on the comprehensive value of each photovoltaic power station and the number of photovoltaic power stations in each operation and maintenance area, calculate the second sub-Gini coefficient between the two operation and maintenance areas, and then calculate the second difference value between the two operation and maintenance areas by weighting the second sub-Gini coefficient between the two operation and maintenance areas according to the number of photovoltaic power stations.

[0143] In this embodiment, firstly, the second sub-Gini coefficient between the two operation and maintenance areas is calculated, and its calculation formula is as follows: Where, n b It is the total number of photovoltaic power stations in the b-th operation and maintenance area, μ b It is the average comprehensive value of all photovoltaic power stations in the b-th operation and maintenance area.

[0144] The second difference value G between the two operation and maintenance regions nb The second sub-Gini coefficient between the two operation and maintenance areas is obtained by weighting the number of photovoltaic power plants.

[0145] S1044, calculate the supervariable density between two operation and maintenance areas based on the number and comprehensive value of photovoltaic power stations in each operation and maintenance area.

[0146] In this embodiment, the formula for calculating the supervariable density between the two operation and maintenance areas is: Where pa and pb represent the proportion of photovoltaic power plants in maintenance area a and maintenance area b, respectively; fa and fb represent the proportion of the comprehensive value in maintenance area a and maintenance area b, respectively; and Dab is the relative comprehensive value of maintenance area a to maintenance area b. In one embodiment, the calculation process for the supervariable density between the two maintenance areas is as follows: based on the cumulative distribution function of each of the two maintenance areas, the total analysis value of one maintenance area to the other is calculated, and the relative analysis value of one maintenance area to the other is calculated based on the total analysis value; the proportion of the comprehensive value and the proportion of the number of power plants in each of the two maintenance areas under the photovoltaic power generation cluster are calculated; and the supervariable density between the two maintenance areas is calculated based on the proportion of the comprehensive value, the proportion of the number of power plants, and the relative analysis value.

[0147] Specifically, the formula for calculating the total analytical value is as follows: Among them, F a (y), F b (x) are the cumulative distribution functions of maintenance regions a and b, respectively.

[0148] The formula for calculating the relative analysis value is: Where, d ab This represents the total analytical value of maintenance region a for maintenance region b.

[0149] S1045, based on the first difference value, the second difference value, and the supervariable density, calculate the Gini coefficient for the operation and maintenance efficiency analysis of the photovoltaic power station cluster.

[0150] In this embodiment, the Gini coefficient for analyzing the operation and maintenance efficiency of a photovoltaic power plant cluster can be calculated by summing the first difference value, the second difference value, and the supervariable density.

[0151] S105, based on the pre-configured range of the Gini coefficient, determine the analysis results of the operation and maintenance efficiency of the photovoltaic power station cluster.

[0152] In one embodiment, the range includes a first interval, a second interval, a third interval, a fourth interval, and a fifth interval whose values ​​increase sequentially.

[0153] The range of intervals is shown in Table 1 below:

[0154] Table 1

[0155] Serial Number Range of Gini coefficient for photovoltaic power plant clusters Score distribution results First section ＜0.2 Average score Second section 0.2-0.29 The scores were relatively average. Third section 0.3-0.39 The score distribution is relatively reasonable. Fourth section 0.4-0.59 The score difference is large Fifth section 0.6 The score difference is huge

[0156] Specifically, the distribution results are determined based on the range in which the Gini coefficient falls; and the analysis results of the operation and maintenance efficiency of the photovoltaic power station cluster are determined based on the corresponding distribution results.

[0157] Referring to Table 1 above, the distribution of the photovoltaic power station cluster analysis score is determined based on the range of the Gini coefficient.

[0158] Operation and maintenance recommendations are generated based on the final assessment scores, and reward and penalty management is implemented for the power plants. The final assessment scores show the overall operating status of each power plant within the statistical period, allowing for the identification of weak operational aspects. A sample score is shown in Table 2 below for reference.

[0159] Table 2

[0160] Serial Number Evaluation score range for photovoltaic power plant clusters result 1 [90,100] High performance 2 [80,90) Good, but there are 1-2 weak operation and maintenance indicators. 3 [60,80) Generally, there are many weak operation and maintenance indicators. 4 [40,60) Poor quality; power plant maintenance needs to be strengthened. 5 [0,40) Very poor, urgently needing to improve operation and maintenance methods.

[0161] In one implementation scheme, when the Gini coefficient is in the first interval, the Gini coefficient of the photovoltaic power station cluster is adjusted by increasing the incentive indicators of the month-on-month growth rate and the ranking in the same operation and maintenance area; wherein, the month-on-month growth rate is the ratio of the Gini coefficient of the photovoltaic power station in the current statistical period to that in the previous statistical period, and the ranking in the same operation and maintenance area is the ratio of the ranking of the photovoltaic power station in the Gini coefficient in its operation and maintenance area to the total number of power stations in the operation and maintenance area where the photovoltaic power station is located.

[0162] Specifically, when the scores are too evenly distributed and insufficient to achieve a good incentive effect, the evaluation score of the photovoltaic power station cluster can be adjusted by increasing the incentive indicators of the month-on-month growth rate and the ranking within the same region. The higher the value of the month-on-month growth rate, the higher the incentive amount for the power station, but it should be set within a certain range; the lower the value of the ranking within the same region, the higher the incentive amount for the power station, but the difference in the number of power stations in each region should be taken into account. This embodiment does not provide a specific explanation.

[0163] Please refer to Figure 2 , Figure 2 A schematic diagram of a photovoltaic power plant cluster operation and maintenance efficiency analysis device provided in an embodiment of the present invention is shown below. Figure 2 As shown, the device includes:

[0164] Data acquisition module 210 is used to acquire data for each photovoltaic power station in four dimensions: production, operation and maintenance, faults and environment.

[0165] The indicator calculation module 220 is used to determine the analytical indicators of each photovoltaic power station in the four dimensions of production, operation and maintenance, failure and environment based on the data of each photovoltaic power station in the four dimensions of production, operation and maintenance, failure and environment.

[0166] The comprehensive value calculation module 230 is used to process the analysis indicators of each photovoltaic power station in four dimensions: production, operation and maintenance, fault and environment using the spatiotemporal range entropy weight method to obtain the comprehensive value of each photovoltaic power station.

[0167] The coefficient decomposition module 240 is used to decompose the comprehensive value of each photovoltaic power station using the Dagum Gini coefficient decomposition method to obtain the Gini coefficient for the operation and maintenance efficiency analysis of the photovoltaic power station cluster; where multiple photovoltaic power stations constitute a photovoltaic power station cluster.

[0168] The efficiency analysis module 250 is used to determine the analysis results of the operation and maintenance efficiency of the photovoltaic power station cluster based on the pre-configured range of the Gini coefficient.

[0169] In the apparatus provided in this embodiment, the present invention addresses the problem of the lack of effective dimensions in current power plant analysis. Based on a comprehensive consideration of various factors affecting the power generation level of a power plant, it divides the evaluation into four dimensions: production operation quality evaluation, operation and maintenance management quality evaluation, equipment operation quality evaluation, and operating environment quality evaluation. The established secondary evaluation indicators are based on the principles of easy accessibility during the daily operation of the power plant and high representativeness of each evaluation dimension. The required data does not require additional monitoring equipment and can be applied to most power plants. To address the problem of unclear analysis results, the spatiotemporal range entropy weighting method is used to calculate the comprehensive value of each photovoltaic power plant, avoiding the irrationality and limitations of subjective weighting and traditional entropy methods. Considering the dynamic changes of power plant operation indicator data in both time and space dimensions, it can accurately evaluate the operating status of photovoltaic power plants and trace the weak links in the power plant operation process. To address the issue of insufficient management methods for power plant clusters, the Dagum Gini coefficient decomposition method is adopted to assess the degree of difference between different comparative operation and maintenance areas and between power plants within different operation and maintenance areas. The power plant cluster score can be adjusted and corrected based on the Gini coefficient, which helps managers better balance the fairness and incentive effect of power plant assessment, stimulate the work enthusiasm of operation and maintenance personnel, and ultimately improve the operation and maintenance level and power generation efficiency of power plants.

[0170] In some embodiments, the analytical indicators for the photovoltaic power plant in terms of production include power generation completion rate, plant power consumption rate, and system efficiency; the analytical indicators for the photovoltaic power plant in terms of operation and maintenance include fault return rate, planned cleaning completion rate, log filling completion rate, event record completeness rate, and fault handling timeliness rate; the analytical indicators for the photovoltaic power plant in terms of faults include the number of equipment failures, the number of times equipment is damaged and cannot be repaired, equipment availability rate, and inverter conversion efficiency; the analytical indicators for the photovoltaic power plant in terms of the environment include the number of minor personal injury accidents, the number of fire accidents, the number of pollution and damage incidents, and the number of power outages.

[0171] In some embodiments, the comprehensive value calculation module 230 is specifically used for: obtaining the initial value, global minimum value, and global maximum value of the analysis indicators of all photovoltaic power plants within a time period; normalizing the initial value, global minimum value, and global maximum value to calculate the positive and negative processing results for each analysis indicator; calculating the global mean of each analysis indicator; subtracting the global maximum value from the global mean to obtain the positive range of each analysis indicator; and subtracting the global mean from the global minimum value to obtain the negative range of each analysis indicator; and performing analysis on each analysis... The positive and negative processing results of the indicators are shifted to calculate the weight of each analytical indicator; based on the weight of each analytical indicator, the entropy value of each analytical indicator is calculated; the entropy value of each analytical indicator is corrected according to the positive and negative ranges of each analytical indicator to calculate the corrected entropy value of each analytical indicator; the weight of each analytical indicator is calculated based on the corrected result; the weighted average value of each analytical indicator of each photovoltaic power station under time decay is calculated using a time decay function; and the comprehensive value of each photovoltaic power station is calculated based on the weighted average value and weight of each analytical indicator.

[0172] In one embodiment, the coefficient decomposition module 240 is specifically used for: dividing multiple operation and maintenance areas according to the location information of each photovoltaic power station; wherein, one operation and maintenance area contains multiple photovoltaic power stations; calculating the first sub-Gini coefficient of each operation and maintenance area based on the comprehensive value of each photovoltaic power station and the number of photovoltaic power stations in each operation and maintenance area, and weighting the first sub-Gini coefficient of each operation and maintenance area according to the number of photovoltaic power stations to calculate the first difference value between each photovoltaic power station in each operation and maintenance area; calculating the second sub-Gini coefficient between two operation and maintenance areas based on the comprehensive value of each photovoltaic power station and the number of photovoltaic power stations in each operation and maintenance area, and weighting the second sub-Gini coefficient between two operation and maintenance areas according to the number of photovoltaic power stations to calculate the second difference value between two operation and maintenance areas; calculating the supervariable density between two operation and maintenance areas based on the number of photovoltaic power stations and the comprehensive value in each operation and maintenance area; and calculating the Gini coefficient for photovoltaic power station cluster operation and maintenance efficiency analysis based on the first difference value, the second difference value, and the supervariable density.

[0173] In some embodiments, the supervariable density between two operation and maintenance areas is calculated based on the number of photovoltaic power plants and the comprehensive value of each operation and maintenance area. Specifically, this involves: calculating the total analysis value of one operation and maintenance area relative to the other based on the cumulative distribution function of each of the two operation and maintenance areas; calculating the relative analysis value of one operation and maintenance area relative to the other based on the total analysis value; calculating the comprehensive value ratio and power plant number ratio of each of the two operation and maintenance areas under the photovoltaic power generation cluster; and calculating the supervariable density between the two operation and maintenance areas based on the comprehensive value ratio, power plant number ratio, and relative analysis value.

[0174] It should be noted that the photovoltaic power plant cluster operation and maintenance efficiency analysis device in this application embodiment is a technical solution based on the same inventive concept as the photovoltaic power plant cluster operation and maintenance efficiency analysis method described above. Through the detailed description of the photovoltaic power plant cluster operation and maintenance efficiency analysis method provided in the above embodiment, those skilled in the art can clearly understand the implementation process of each module of the photovoltaic power plant cluster operation and maintenance efficiency analysis device in this embodiment. Therefore, for the sake of brevity, it will not be described again here.

[0175] This invention also provides an electronic device, which includes a processor, a memory, a communication interface, and at least one communication bus for connecting the processor, the memory, and the communication interface. The memory includes, but is not limited to, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (PROM), or portable read-only memory (CD-ROM), and is used for related instructions and data.

[0176] The communication interface is used to receive and send data. The processor can be one or more CPUs; if it is a single-core CPU, it can be a multi-core CPU. The processor in the electronic device reads one or more programs stored in the memory and performs the following operations: acquires data for each photovoltaic power station in four dimensions: production, operation and maintenance, faults, and environment; determines the analytical indicators for each photovoltaic power station in these four dimensions based on the data; processes the analytical indicators for each photovoltaic power station using the spatiotemporal range entropy weight method to obtain the comprehensive value for each photovoltaic power station; decomposes the comprehensive value for each photovoltaic power station using the Dagum Gini coefficient decomposition method to obtain the Gini coefficient for analyzing the operation and maintenance efficiency of the photovoltaic power station cluster; multiple photovoltaic power stations constitute a photovoltaic power station cluster; and determines the analysis results of the photovoltaic power station cluster's operation and maintenance efficiency based on the pre-configured range of the Gini coefficient.

[0177] It should be noted that the specific implementation of each operation can be described above. Figure 1 The corresponding description of the method embodiments shown indicates that the electronic device can be used to execute a photovoltaic power plant cluster operation and maintenance efficiency analysis method according to the above method embodiments of this application, which will not be described in detail here.

[0178] This invention also provides a computer-readable storage medium, which is a memory device in a computer device used to store programs and data. It is understood that the computer-readable storage medium here can include both the built-in storage medium in the computer device and extended storage media supported by the computer device. The computer-readable storage medium provides storage space that stores the terminal's operating system. Furthermore, the storage space also stores one or more instructions suitable for loading and execution by a processor. These instructions can be one or more computer programs (including program code). It should be noted that the computer-readable storage medium here can be high-speed RAM or non-volatile memory, such as at least one disk storage device. The processor can load and execute one or more instructions stored in the computer-readable storage medium to implement the corresponding steps of the photovoltaic power plant cluster operation and maintenance efficiency analysis method in the above embodiments. Those skilled in the art should understand that the embodiments of this invention can be provided as methods, systems, or computer program products. Therefore, this invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0179] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for analyzing the operation and maintenance efficiency of a photovoltaic power plant cluster, characterized in that, The methods include: Acquire data for each photovoltaic power station across four dimensions: production, operation and maintenance, faults, and environment. Based on the data of each photovoltaic power station in four dimensions—production, operation and maintenance, failure, and environment—analysis indicators for each photovoltaic power station in these four dimensions are determined. The spatiotemporal range entropy weight method is used to process the analytical indicators of each photovoltaic power station in four dimensions: production, operation and maintenance, failure and environment, to obtain the comprehensive value of each photovoltaic power station; The comprehensive value of each photovoltaic power station is decomposed using the Dagum Gini coefficient decomposition method to obtain the Gini coefficient for the operation and maintenance efficiency analysis of the photovoltaic power station cluster; where multiple photovoltaic power stations constitute a photovoltaic power station cluster. The analysis results of the operation and maintenance efficiency of the photovoltaic power plant cluster are determined based on the pre-configured range of the Gini coefficient.

2. The method for analyzing the operation and maintenance efficiency of a photovoltaic power station cluster according to claim 1, characterized in that, The analytical indicators for the photovoltaic power plant in terms of production include power generation completion rate, plant power consumption rate, and system efficiency. The operational and maintenance indicators for the photovoltaic power plant include fault return rate, planned cleaning completion rate, log reporting completion rate, event recording completeness rate, and fault handling timeliness rate. The analysis indicators for the photovoltaic power plant in terms of fault dimension include the number of equipment failures, the number of times the equipment is damaged and cannot be repaired, the equipment availability rate, and the inverter conversion efficiency. The environmental analysis indicators for the photovoltaic power station include the number of minor personal injury accidents, the number of fire accidents, the number of pollution and damage incidents, and the number of power outages.

3. The method for analyzing the operation and maintenance efficiency of a photovoltaic power station cluster according to claim 1, characterized in that, The spatiotemporal range entropy weight method is used to process the analytical indicators of photovoltaic power plants in four dimensions: production, operation and maintenance, failure, and environment, to obtain the comprehensive value of the photovoltaic power plant, specifically: Obtain the initial values, global minimum values, and global maximum values ​​of the analysis indicators for all photovoltaic power plants within a time period; The initial value, global minimum value, and global maximum value are normalized to calculate the positive and negative results for each analysis indicator. Calculate the global mean of each analysis indicator, subtract the global maximum value from the global mean to obtain the positive range of each analysis indicator, and subtract the global mean from the global minimum value to obtain the negative range of each analysis indicator. The positive and negative results of each analytical indicator are shifted to calculate the weight of each analytical indicator. Based on the weight of each analytical indicator, the entropy value of each analytical indicator is calculated. The entropy value of each analytical indicator is corrected based on its positive and negative ranges to calculate the corrected entropy value of each analytical indicator. The weight of each analytical indicator is calculated based on the correction results; The weighted average of each analytical index of each photovoltaic power station under time decay is calculated using the time decay function; The comprehensive value of each photovoltaic power station is calculated based on the weighted average and weight of each analytical indicator.

4. The method for analyzing the operation and maintenance efficiency of a photovoltaic power station cluster according to claim 1, characterized in that, The Dagum Gini coefficient decomposition method is used to decompose the comprehensive value of photovoltaic power plants, resulting in the Gini coefficient for analyzing the operation and maintenance efficiency of photovoltaic power plant clusters. Specifically: Multiple operation and maintenance areas are divided based on the location information of each photovoltaic power station; one operation and maintenance area contains multiple photovoltaic power stations. Based on the comprehensive value of each photovoltaic power station and the number of photovoltaic power stations in each operation and maintenance area, the first sub-Gini coefficient of each operation and maintenance area is calculated, and the first sub-Gini coefficient of each operation and maintenance area is weighted and averaged according to the number of photovoltaic power stations to calculate the first difference value between each photovoltaic power station in each operation and maintenance area. Based on the comprehensive value of each photovoltaic power station and the number of photovoltaic power stations in each operation and maintenance area, the second sub-Gini coefficient between the two operation and maintenance areas is calculated, and the second sub-Gini coefficient between the two operation and maintenance areas is weighted and averaged according to the number of photovoltaic power stations to calculate the second difference value between the two operation and maintenance areas. The super-variable density between two operation and maintenance areas is calculated based on the number and comprehensive value of photovoltaic power stations in each operation and maintenance area. The Gini coefficient for analyzing the operation and maintenance efficiency of photovoltaic power plant clusters is calculated based on the first difference value, the second difference value, and the supervariable density.

5. The method for analyzing the operation and maintenance efficiency of a photovoltaic power station cluster according to claim 4, characterized in that, Based on the number and overall value of photovoltaic power plants in each operation and maintenance area, the supervariable density between the two operation and maintenance areas is calculated as follows: Based on the cumulative distribution function of each of the two operation and maintenance regions, the total analysis value of one operation and maintenance region relative to the other operation and maintenance region is calculated, and the relative analysis value of one operation and maintenance region relative to the other operation and maintenance region is calculated based on the total analysis value. Calculate the percentage of the comprehensive value and the percentage of the number of power plants in each of the two operation and maintenance regions under the photovoltaic power generation cluster; The supervariable density between the two operation and maintenance areas is calculated based on the comprehensive value ratio, the power station number ratio, and the relative analysis value.

6. The method for analyzing the operation and maintenance efficiency of a photovoltaic power station cluster according to claim 1, characterized in that, The range of intervals includes a first interval, a second interval, a third interval, a fourth interval, and a fifth interval whose values ​​increase sequentially. Based on the pre-configured range of the Gini coefficient, the analysis results of the operation and maintenance efficiency of the photovoltaic power station cluster are determined. Specifically, the distribution results are determined based on the range of the Gini coefficient, and the analysis results of the operation and maintenance efficiency of the photovoltaic power station cluster are determined based on the corresponding distribution results.

7. The method for analyzing the operation and maintenance efficiency of a photovoltaic power station cluster according to claim 6, characterized in that, When the Gini coefficient is in the first interval, the Gini coefficient of the photovoltaic power station cluster is adjusted by increasing the incentive indicators of the month-on-month growth rate and the ranking of the same operation and maintenance area. Among them, the month-on-month growth rate is the ratio of the Gini coefficient of the photovoltaic power station in the current statistical period to that in the previous statistical period, and the ranking in the same operation and maintenance area is the ratio of the Gini coefficient ranking of the photovoltaic power station in its operation and maintenance area to the total number of power stations in the operation and maintenance area of ​​the photovoltaic power station.

8. A photovoltaic power plant cluster operation and maintenance efficiency analysis device, characterized in that, The device includes: The data acquisition module is used to acquire data for each photovoltaic power station in four dimensions: production, operation and maintenance, faults, and environment. The indicator calculation module is used to determine the analytical indicators for each photovoltaic power station in the four dimensions of production, operation and maintenance, failure and environment based on the data of each photovoltaic power station in the four dimensions of production, operation and maintenance, failure and environment. The comprehensive value calculation module is used to process the analysis indicators of each photovoltaic power station in four dimensions: production, operation and maintenance, failure and environment, using the spatiotemporal range entropy weight method to obtain the comprehensive value of each photovoltaic power station. The coefficient decomposition module is used to decompose the comprehensive value of each photovoltaic power station using the Dagum Gini coefficient decomposition method to obtain the Gini coefficient for the operation and maintenance efficiency analysis of the photovoltaic power station cluster; where multiple photovoltaic power stations constitute a photovoltaic power station cluster. The efficiency analysis module is used to determine the analysis results of the operation and maintenance efficiency of photovoltaic power plant clusters based on the pre-configured range of the Gini coefficient.

9. The photovoltaic power plant cluster operation and maintenance efficiency analysis device according to claim 8, characterized in that, The analytical indicators for the photovoltaic power plant in terms of production include power generation completion rate, plant power consumption rate, and system efficiency. The operational and maintenance indicators for the photovoltaic power plant include fault return rate, planned cleaning completion rate, log reporting completion rate, event recording completeness rate, and fault handling timeliness rate. The analysis indicators for the photovoltaic power plant in terms of fault dimension include the number of equipment failures, the number of times the equipment is damaged and cannot be repaired, the equipment availability rate, and the inverter conversion efficiency. The environmental analysis indicators for the photovoltaic power station include the number of minor personal injury accidents, the number of fire accidents, the number of pollution and damage incidents, and the number of power outages.

10. The photovoltaic power plant cluster operation and maintenance efficiency analysis device according to claim 8, characterized in that, The comprehensive value calculation module is specifically used for: Obtain the initial values, global minimum values, and global maximum values ​​of the analysis indicators for all photovoltaic power plants within a time period; The initial value, global minimum value, and global maximum value are normalized to calculate the positive and negative results for each analysis indicator. Calculate the global mean of each analytical indicator. Subtract the global maximum value from the global mean to obtain the positive range of each analytical indicator. Subtract the global mean from the global minimum value to obtain the negative range of each analytical indicator. The positive and negative results of each analytical indicator are shifted to calculate the weight of each analytical indicator. Based on the weight of each analytical indicator, the entropy value of each analytical indicator is calculated. The entropy value of each analytical indicator is corrected based on its positive and negative ranges to calculate the corrected entropy value of each analytical indicator. The weight of each analytical indicator is calculated based on the correction results; The weighted average of each analytical index of each photovoltaic power station under time decay is calculated using the time decay function; The comprehensive value of each photovoltaic power station is calculated based on the weighted average and weight of each analytical indicator.

11. The photovoltaic power plant cluster operation and maintenance efficiency analysis device according to claim 8, characterized in that, The coefficient decomposition module is specifically used for: Multiple operation and maintenance areas are divided based on the location information of each photovoltaic power station; one operation and maintenance area contains multiple photovoltaic power stations. Based on the comprehensive value of each photovoltaic power station and the number of photovoltaic power stations in each operation and maintenance area, the first sub-Gini coefficient of each operation and maintenance area is calculated, and the first sub-Gini coefficient of each operation and maintenance area is weighted and averaged according to the number of photovoltaic power stations to calculate the first difference value between each photovoltaic power station in each operation and maintenance area. Based on the comprehensive value of each photovoltaic power station and the number of photovoltaic power stations in each operation and maintenance area, the second sub-Gini coefficient between the two operation and maintenance areas is calculated, and the second sub-Gini coefficient between the two operation and maintenance areas is weighted and averaged according to the number of photovoltaic power stations to calculate the second difference value between the two operation and maintenance areas. The super-variable density between two operation and maintenance areas is calculated based on the number and comprehensive value of photovoltaic power stations in each operation and maintenance area. The Gini coefficient for analyzing the operation and maintenance efficiency of photovoltaic power plant clusters is calculated based on the first difference value, the second difference value, and the supervariable density.

12. The photovoltaic power plant cluster operation and maintenance efficiency analysis device according to claim 11, characterized in that, Based on the number and overall value of photovoltaic power plants in each operation and maintenance area, the supervariable density between the two operation and maintenance areas is calculated as follows: Based on the cumulative distribution function of each of the two operation and maintenance regions, the total analysis value of one operation and maintenance region relative to the other operation and maintenance region is calculated, and the relative analysis value of one operation and maintenance region relative to the other operation and maintenance region is calculated based on the total analysis value. Calculate the percentage of the comprehensive value and the percentage of the number of power plants in each of the two operation and maintenance regions under the photovoltaic power generation cluster; The supervariable density between the two operation and maintenance areas is calculated based on the comprehensive value ratio, the power station number ratio, and the relative analysis value.

13. An electronic device, characterized in that, The electronic device includes a processor, a memory, and a computer program stored in the memory and executable by the processor, wherein when the computer program is executed by the processor, it implements the steps of the photovoltaic power plant cluster operation and maintenance efficiency analysis method as described in any one of claims 1 to 7.

14. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, wherein when the computer program is executed by a processor, it implements the steps of a photovoltaic power plant cluster operation and maintenance efficiency analysis method as described in any one of claims 1 to 7.

Images