Photovoltaic power generation efficiency analysis and evaluation method

Abstract

The invention relates to a photovoltaic power generation efficiency analysis and evaluation method. The method comprises the following steps: acquiring historical operation data of a photovoltaic power station and corresponding historical meteorological data and historical power grid data; performing causal inference analysis on the historical operation data, the historical meteorological data and the historical power grid data to obtain influence factors influencing the power generation efficiency of the photovoltaic power station; performing comprehensive evaluation and weight distribution on the influence factors by combining a fuzzy analytic hierarchy process to obtain weighted influence factors; a dynamic DEA model based on time sequence analysis is constructed according to the weighted influence factors, efficiency evaluation is carried out based on the dynamic DEA model, an efficiency evaluation result is obtained, and the efficiency evaluation result comprises an efficiency change trend and real efficiency values at different time points. According to the method, through combination of causal inference, fuzzy hierarchy analysis and a dynamic DEA model, the photovoltaic power generation efficiency can be comprehensively and dynamically evaluated, a scientific basis is provided for operation and maintenance management, resource configuration is optimized, the power generation efficiency is improved, and long-term stable operation of a power station in a complex environment is ensured.

Description

Technical Field

[0001] The invention belongs to the field of computer and communication technology, and in particular relates to a photovoltaic power generation efficiency analysis and evaluation method. Background Art

[0002] With the continuous development of technology in the field of photovoltaic power generation, photovoltaic power generation efficiency evaluation is the key to improving the operating efficiency of power stations and enhancing market competitiveness. However, traditional efficiency calculation models often rely on single environmental parameters such as solar radiation and temperature to evaluate efficiency. Although these methods have certain practicality, they often ignore the interaction of multiple factors and the complex dynamic changes within the system, resulting in large errors in the evaluation results, especially under different climatic conditions or complex environments. In addition, most existing methods are based on static data analysis, which makes it difficult to capture the causes and trends of efficiency fluctuations and cannot provide forward-looking decision support for power station operation and maintenance management. Summary of the invention

[0003] Based on this, it is necessary to provide a photovoltaic power generation efficiency analysis and evaluation method for the above technical problems, so as to improve the evaluation accuracy of photovoltaic power generation efficiency and provide forward-looking decision support for the operation and maintenance management of power stations.

[0004] In a first aspect, the present application provides a photovoltaic power generation efficiency analysis and evaluation method, the method comprising: Obtain the historical operation data of the photovoltaic power station and the corresponding historical meteorological data and historical power grid data. The historical operation data includes historical power generation data, power station operation and maintenance data, and photovoltaic panel cleanliness data; Conduct causal inference analysis on historical operation data, historical meteorological data and historical power grid data to obtain the factors affecting the power generation efficiency of photovoltaic power stations; Combined with fuzzy analytic hierarchy process, the impact factors are comprehensively evaluated and weighted to obtain weighted impact factors. According to the weighted influencing factors, a dynamic DEA model based on time series analysis is constructed, and efficiency evaluation is performed based on the dynamic DEA model to obtain efficiency evaluation results. The efficiency evaluation results include efficiency change trends and real efficiency values ​​at different time points. The efficiency evaluation results are used for operation and maintenance management of photovoltaic power stations.

[0005] In one embodiment, a dynamic DEA model based on time series analysis is constructed according to weighted impact factors, including: The weighted influencing factors are divided into input indicators and output indicators. The input indicators include equipment failure rate and operation and maintenance costs, and the output indicators include power generation and power generation efficiency. The time lag relationship between input indicators and output indicators is determined through the mutual information method, and the time lag parameters are constructed; Based on the time lag parameters, the time series data of input indicators and output indicators are aligned with time lag to construct a time lag data set; The sliding window mechanism is used to dynamically divide the time-lag data set, and the window size is dynamically adjusted according to the data variation coefficient to obtain the sliding window; Based on the time-lag data set and sliding window, the objective function of the dynamic DEA model is constructed, and the efficiency value sequence at different time points is obtained by solving the objective function; Based on the efficiency value sequence, the Malmquist index is used to analyze the efficiency change and obtain the efficiency change trend, which includes comprehensive technical efficiency, pure technical efficiency and scale efficiency. Through the efficiency prediction model based on weighted influencing factors, the efficiency prediction value is generated, and the efficiency prediction value is added to the DEA evaluation as a virtual decision-making unit. The dynamic DEA model is obtained by combining the efficiency value sequence and the efficiency change trend.

[0006] In one embodiment, the objective function is: ; in, and are the input index and output index at time t, and are the input-output data with a time lag of τ, λ is the weight vector, Λ is the weight constraint set, is the time lag parameter.

[0007] In one embodiment, the Malmquist index is calculated as: ; in, represents the Malmquist index, represents the investment at time t and output The distance to the efficiency frontier, represents the investment at time t+1 and output The distance to the efficiency frontier, represents the investment at time t+1 and output The distance to the efficiency frontier at time t, represents the investment at time t and output The distance to the efficiency frontier at time t+1.

[0008] In one embodiment, historical operation data, historical meteorological data, and historical power grid data are subjected to causal inference analysis to obtain influencing factors affecting the power generation efficiency of the photovoltaic power station, including: Perform data cleaning and data alignment on historical operation data, historical meteorological data and historical power grid data. Data cleaning includes missing value filling, outlier processing and data standardization. Data alignment includes alignment by timestamp and resampling of non-uniformly sampled data. Based on the Granger causality test, the causal relationship between the variables of historical operation data, historical meteorological data and historical power grid data is identified, the significance level is set, and the direct influencing factors are screened out; A causal relationship model is constructed based on the Bayesian network, and the conditional probability distribution between variables is learned using historical operation data, historical meteorological data, and historical power grid data to identify the indirect causal relationship between direct influencing factors. According to the direct influencing factors and causal relationship model, a structural equation model is constructed to quantify the direct and indirect effects of each direct influencing factor on power generation efficiency. The maximum likelihood estimation method is used to solve the model parameters and obtain the causal effect value of each direct influencing factor. Based on the causal effect value of each direct influencing factor, a causal effect threshold is set, and the influencing factors with causal effect values ​​greater than the causal effect threshold are screened out, and the influencing factors are used as the final influencing factors affecting the power generation efficiency of the photovoltaic power station.

[0009] In one embodiment, the impact factors are comprehensively evaluated and weighted by combining the fuzzy analytic hierarchy process to obtain weighted impact factors, including: Construct a hierarchical model, which includes a target layer, a criterion layer, and a solution layer. The target layer is the photovoltaic power generation efficiency, the criterion layer includes meteorological factors, equipment status, and operation and maintenance level, and the solution layer includes solar irradiance, temperature, equipment failure rate, and cleanliness; The 1-9 scaling method is used to compare the factors at the criterion level and the solution level to obtain the evaluation score results, which are then converted into triangular fuzzy numbers to construct a fuzzy judgment matrix. Based on the fuzzy judgment matrix, the fuzzy analytic hierarchy process is used to calculate the weights of the influencing factors, and the weight values ​​are obtained through defuzzification; Multiply the causal effect value of the impact factor by the corresponding weight value to obtain the weighted impact factor.

[0010] In one embodiment, the method further comprises: Based on the efficiency evaluation results, identify the time period with abnormal efficiency, and combine the contribution analysis of the influencing factors to determine the key influencing factors that cause abnormal efficiency; Optimization instructions are generated according to key influencing factors, and the optimization instructions are used to execute corresponding operation and maintenance strategies of the photovoltaic power station.

[0011] In a second aspect, the present application also provides a photovoltaic power generation efficiency analysis and evaluation system, the system comprising: A data acquisition module is used to acquire the historical operation data of the photovoltaic power station and the corresponding historical meteorological data and historical power grid data. The historical operation data includes historical power generation data, power station operation and maintenance data, and photovoltaic panel cleanliness data; The factor acquisition module is used to perform causal inference analysis on historical operation data, historical meteorological data and historical power grid data to obtain the influencing factors that affect the power generation efficiency of the photovoltaic power station; The factor processing module is used to comprehensively evaluate and assign weights to the impact factors by combining the fuzzy analytic hierarchy process to obtain the weighted impact factors; The efficiency evaluation module is used to construct a dynamic DEA model based on time series analysis according to weighted influencing factors, and to perform efficiency evaluation based on the dynamic DEA model to obtain efficiency evaluation results. The efficiency evaluation results include efficiency change trends and actual efficiency values ​​at different time points. The efficiency evaluation results are used for operation and maintenance management of photovoltaic power stations.

[0012] In a third aspect, the present application further provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of any one of the methods in the first aspect when executing the computer program.

[0013] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, which implements the steps of any one of the methods in the first aspect when the computer program is executed by a processor.

[0014] In the above-mentioned photovoltaic power generation efficiency analysis and evaluation method, firstly, by obtaining the historical operation data, historical meteorological data and historical power grid data of the photovoltaic power station, a comprehensive data basis is provided for the subsequent power generation efficiency analysis. The historical operation data includes power generation data, power station operation and maintenance data and photovoltaic panel cleanliness data, which can reflect the actual operation status of the power station. By performing causal inference analysis on these data, the influence of different factors on photovoltaic power generation efficiency can be analyzed from multiple perspectives, and then the factors affecting the power generation efficiency of the photovoltaic power station can be identified, providing a scientific basis for subsequent evaluation and optimization. Secondly, the fuzzy hierarchical analysis method is combined to comprehensively evaluate and weight these influencing factors to obtain weighted influencing factors. This step can effectively quantify the degree of influence of each influencing factor on power generation efficiency and ensure the accuracy and rationality of the evaluation results. Finally, a dynamic DEA model is constructed based on the weighted influencing factors, and the power generation efficiency of the photovoltaic power station is dynamically evaluated through time series analysis to capture the trend of photovoltaic power generation efficiency over time and obtain the efficiency evaluation results. The efficiency evaluation results not only include the efficiency change trend, but also provide the real efficiency values ​​at different time points, which provides an important reference for the operation and maintenance management of photovoltaic power stations.

[0015] Compared with the traditional photovoltaic power generation efficiency analysis method, this method can not only identify the factors affecting power generation efficiency more comprehensively through the combination of causal inference, fuzzy hierarchical analysis and dynamic DEA model, but also dynamically reflect the changing trend of efficiency, which helps operation managers to timely discover potential problems and make optimization adjustments, thereby making the operation and maintenance management of photovoltaic power stations more accurate and scientific, and effectively improving the long-term stability and power generation efficiency of the power station. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related technologies, the drawings required for use in the embodiments or the related technical descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0017] Figure 1 A flow chart of a photovoltaic power generation efficiency analysis and evaluation method provided by an exemplary embodiment of the present invention; Figure 2 A schematic diagram of the structure of a photovoltaic power generation efficiency analysis and evaluation system provided by an exemplary embodiment of the present invention. DETAILED DESCRIPTION

[0018] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0019] In one embodiment, Figure 1 As shown, a photovoltaic power generation efficiency analysis and evaluation method is provided. This embodiment is illustrated by applying the method to a terminal. It can be understood that the method can also be applied to a server, and can also be applied to a system including a terminal and a server, and is implemented through the interaction between the terminal and the server. In this embodiment, the method includes the following steps: S101: Acquire historical operation data of the photovoltaic power station and corresponding historical meteorological data and historical power grid data. The historical operation data includes historical power generation data, power station operation and maintenance data, and photovoltaic panel cleanliness data.

[0020] Historical operation data is a key source of information for evaluating the performance of photovoltaic power stations. Among them, historical power generation data contains information on the power generation of photovoltaic power stations in different time periods in the past, including power generation efficiency and power generation, which can reflect the actual power generation capacity of the power station under different conditions. Power station operation and maintenance data can include equipment maintenance records, maintenance costs, maintenance times and other information. Through this information, we can further understand whether the power generation efficiency has been affected by equipment maintenance problems in the past operation of the power station. Photovoltaic panel cleanliness data can reflect the impact of the cleanliness of photovoltaic panels on power generation efficiency. If photovoltaic panels are not cleaned for a long time, they may be covered with dust, debris, etc., affecting their ability to absorb solar energy and thus affecting power generation efficiency. Historical meteorological data can include past weather information in the area where the photovoltaic power station is located, such as light intensity, temperature, humidity, wind speed, rainfall, etc. Indicatively, different meteorological conditions will directly affect the power generation efficiency of photovoltaic power stations. For example, light intensity directly affects the amount of solar energy obtained, and too high or too low temperature may affect the performance of photovoltaic panels. Historical power grid data can include relevant information about the access of photovoltaic power stations to the power grid, such as the voltage stability of the power grid and the loss during power transmission. This information can help us understand whether the interaction between the power station and the grid has an impact on power generation efficiency. For example, when the grid voltage is unstable, there may be certain restrictions on the output power of the photovoltaic power station.

[0021] S102: Perform causal inference analysis on historical operation data, historical meteorological data, and historical power grid data to obtain influencing factors that affect the power generation efficiency of the photovoltaic power station.

[0022] Specifically, causal inference analysis can identify the causal relationship between different data, and then determine which factors affect the power generation efficiency of photovoltaic power stations and the degree and direction of influence between different factors. For example, by analyzing the relationship between the number of equipment maintenance and power generation efficiency in historical operation data, it can be identified that when the number of equipment maintenance increases, the power generation efficiency will decrease, and the equipment maintenance situation can be judged as an influencing factor affecting the power generation efficiency. For historical meteorological data, the causal effect of light intensity on power generation efficiency can be determined by observing the power generation efficiency data under different light intensities and combining time series analysis. For example, after the light intensity reaches a certain level, the power generation efficiency may no longer increase linearly with the increase in light intensity, and may even decrease due to the increase in temperature (temperature effect of photovoltaic panels). Then, through causal inference, it can be judged that light intensity is an influencing factor, and the specific influence pattern of different light intensity ranges on power generation efficiency can be determined. This step helps to screen out the factors that really have an important impact on power generation efficiency from complex data, exclude those irrelevant or less relevant factors, and provide a more accurate basis for subsequent evaluation and decision-making.

[0023] S103: Comprehensively evaluate and weight the impact factors using the fuzzy analytic hierarchy process to obtain weighted impact factors.

[0024] Fuzzy analytic hierarchy process is a multi-criteria decision analysis method that combines analytic hierarchy process and fuzzy set theory. It can consider multiple aspects of each influencing factor to conduct a comprehensive evaluation of the influencing factors. For example, for the equipment operation and maintenance factor, not only the number of maintenance times is considered, but also multiple dimensions such as the difficulty of maintenance and the cost of maintenance are considered. Based on the fuzzy set theory, the degree of influence of each influencing factor on the power generation efficiency is quantified, and the corresponding weights are assigned through analytic hierarchy process to reflect the relative importance of different influencing factors in affecting the power generation efficiency. For example, if the equipment operation and maintenance factor is given a higher weight, and the photovoltaic panel cleanliness factor is given a relatively low weight, this means that when evaluating the power generation efficiency, the equipment operation and maintenance situation will have a greater impact on the final result than the cleanliness of the photovoltaic panel.

[0025] S104: construct a dynamic DEA model based on time series analysis according to the weighted influencing factors, and perform efficiency evaluation based on the dynamic DEA model to obtain efficiency evaluation results. The efficiency evaluation results include efficiency change trends and real efficiency values ​​at different time points. The efficiency evaluation results are used for operation and maintenance management of photovoltaic power stations.

[0026] Specifically, DEA (Data Envelopment Analysis) is a method for evaluating the efficiency of multi-input and multi-output decision-making units. By constructing a dynamic DEA model based on time series analysis by weighted influencing factors, it is possible to capture the characteristics that the power generation efficiency of photovoltaic power stations will change over time, and can better reflect the operating status and performance changes of photovoltaic power stations at different time points. For example, in different seasons and years, the power generation efficiency of photovoltaic power stations will vary due to factors such as sunshine duration, equipment aging, and maintenance. Among them, weighted influencing factors can include various types of data, such as meteorological data (light intensity, temperature, etc.), operating data (equipment operation and maintenance, photovoltaic panel cleanliness, etc.) and power grid data (voltage, power factor, etc.). Different weighted influencing factors are used as inputs and outputs at different time points to construct a dynamic input-output relationship.

[0027] Based on the dynamic DEA model, the input-output relationship at different time points can be evaluated through time series data and sliding windows to obtain efficiency evaluation results. For example, by setting a sliding window, the relative efficiency of the photovoltaic power station in different time periods can be observed, and then it can be judged whether it has achieved the optimal input-output state in different time periods, and whether the resource utilization is effective. The efficiency change trend reflects the efficiency change of the photovoltaic power station over a longer time span. By analyzing the efficiency change trend, it can be understood whether the power station is in a state of efficiency improvement, decline or relative stability. The real efficiency values ​​at different time points can be used to monitor and evaluate the operation of the power station in detail.

[0028] In the above-mentioned photovoltaic power generation efficiency analysis and evaluation method, by obtaining the historical operation data, historical meteorological data and historical power grid data of the photovoltaic power station, basic data support is provided for evaluating the power generation efficiency of the photovoltaic power station. Among them, the historical operation data includes power generation data, operation and maintenance data and cleanliness data of the photovoltaic panels, which can fully understand the operation of the photovoltaic power station. By performing causal inference analysis on these data, the relationship between various factors can be identified, and the influencing factors that have a significant impact on the power generation efficiency of the photovoltaic power station can be screened out. Through this process, it is possible to clearly identify which factors have a positive or negative impact on the efficiency of the power station, thereby providing a basis for further analysis. After obtaining the influencing factors, the fuzzy hierarchical analysis method is used to conduct a comprehensive evaluation, and the weight of each factor is reasonably allocated to obtain the weighted influencing factor. This step can effectively quantify the degree of influence of each factor on the power generation efficiency and ensure the accuracy and rationality of the evaluation results.

[0029] Finally, based on these weighted influencing factors, a dynamic DEA model based on time series analysis can be constructed. By considering the factors of time change, this dynamic DEA model can truly reflect the operating status of the power station at different time points, and then dynamically evaluate the efficiency changes of the photovoltaic power station, and provide real efficiency values ​​for each time point to obtain efficiency evaluation results. According to the efficiency evaluation results, the operation and maintenance strategy can be optimized, the power generation plan can be adjusted, and the equipment management level can be improved, thereby improving the overall power generation efficiency of the photovoltaic power station and ensuring good benefits in long-term operation.

[0030] Compared with traditional power generation efficiency analysis methods, this method can not only more comprehensively identify factors affecting power generation efficiency, but also dynamically reflect the changing trend of efficiency through the combination of causal inference, fuzzy hierarchical analysis and dynamic DEA model. Through scientific weight allocation of influencing factors and time series analysis, this method optimizes the operation and maintenance management strategy of photovoltaic power stations, improves the evaluation accuracy of power generation efficiency, and provides strong support for the long-term stable operation of power stations. In addition, by combining advanced causal inference technology and dynamic DEA model, this method can effectively cope with complex meteorological and power grid conditions, ensure the efficient operation of photovoltaic power stations in a variety of environments, and provide a scientific basis for fault prevention and performance optimization of photovoltaic power stations.

[0031] In one exemplary embodiment, a dynamic DEA model based on time series analysis is constructed according to weighted impact factors, including: The weighted influencing factors are divided into input indicators and output indicators. The input indicators include equipment failure rate and operation and maintenance costs, and the output indicators include power generation and power generation efficiency. The time lag relationship between input indicators and output indicators is determined through the mutual information method, and the time lag parameters are constructed; Based on the time lag parameters, the time series data of input indicators and output indicators are aligned with time lag to construct a time lag data set; The sliding window mechanism is used to dynamically divide the time-lag data set, and the window size is dynamically adjusted according to the data variation coefficient to obtain the sliding window; Based on the time-lag data set and sliding window, the objective function of the dynamic DEA model is constructed, and the efficiency value sequence at different time points is obtained by solving the objective function; Based on the efficiency value sequence, the Malmquist index is used to analyze the efficiency change and obtain the efficiency change trend, which includes comprehensive technical efficiency, pure technical efficiency and scale efficiency. Through the efficiency prediction model based on weighted influencing factors, the efficiency prediction value is generated, and the efficiency prediction value is added to the DEA evaluation as a virtual decision-making unit. The dynamic DEA model is obtained by combining the efficiency value sequence and the efficiency change trend.

[0032] The mutual information method is a statistical method used to measure the correlation and dependence between two variables. It can determine whether there is a time delay relationship between input indicators and output indicators, and then construct a time lag parameter. For example, the failure of equipment may not immediately lead to a decrease in power generation and power generation efficiency, and there may be a certain time delay. Through the mutual information method, the length of this delay, that is, the time lag relationship, can be determined. The time lag parameter can reflect the time difference between the change of input indicators and the change of output indicators, which helps to more accurately understand and analyze the dynamic relationship between various factors in photovoltaic power stations and avoid the errors that may be caused by simple simultaneity analysis. And considering the time lag relationship between input indicators and output indicators, the time series data is adjusted according to the time lag parameter to make the input indicators and output indicators consistent in time, and obtain a time lag data set.

[0033] The sliding window mechanism is a method of dividing time series data into multiple subsequences. It can perform local analysis on data in different time periods and observe the input-output relationship within different time ranges, so as to better capture the dynamic characteristics of the data. The coefficient of variation of the data reflects the degree of discreteness of the data. By dynamically adjusting the window size according to the coefficient of variation of the data, the window division can be made more stable and representative. Based on the time-lag data set and the sliding window, an objective function is constructed to calculate the efficiency value of each time window. The objective function is solved by mathematical optimization methods to obtain the efficiency value sequence at different time points. These efficiency value sequences reflect the relative efficiency of the photovoltaic power station in different time windows and provide data support for subsequent analysis. The Malmquist index is a tool for analyzing changes in production efficiency. By taking the efficiency value sequence at different time points as input, the efficiency change trend can be obtained. Among them, the comprehensive technical efficiency can reflect the overall technical efficiency of the entire photovoltaic power station, the pure technical efficiency can reflect the impact of the main technical factors on efficiency, and the scale efficiency measures the impact of changes in scale on efficiency, which can reflect the scale economy effect of the power station, that is, whether there is an increase or decrease in efficiency due to changes in scale.

[0034] Indicatively, an efficiency prediction model can be constructed based on deep learning models such as multi-layer perceptrons or long short-term memory networks, combined with weighted influencing factors, to generate efficiency prediction values. By adding the efficiency prediction value as a virtual decision-making unit to the DEA evaluation, the power generation situation in the future can be considered, making the DEA model more forward-looking. Through this process, the final dynamic DEA model fully considers the time factor, the dynamic changes of data, the time lag relationship between input and output, and future predictions, and can conduct a comprehensive and dynamic analysis of the efficiency evaluation and management of photovoltaic power stations, further improving the operating efficiency of power stations and the scientific nature of decision-making.

[0035] In one exemplary embodiment, the objective function is: ; in, and are the input index and output index at time t, and are the input-output data with a time lag of τ, λ is the weight vector, Λ is the weight constraint set, is the time lag parameter.

[0036] Specifically, the input indicators It may include various factors such as equipment failure rate, operation and maintenance costs, etc. It includes power generation, power generation efficiency, etc. and is the input-output data with a time lag of τ, which indicates that there is a time delay between input and output. For example, equipment failure may not affect power generation immediately, but may take effect after τ time. λ is a weight vector, which is used to weight different input and output indicators. Reasonable weighting can more accurately reflect the importance of each indicator in efficiency evaluation. Λ is a set of weight constraints, which limits the value range and conditions of the weight vector λ to ensure that the weight value is reasonable and stable, such as requiring the weight to be non-negative or the sum of the weights to be 1. Under the above constraints, solving the objective function makes The minimum value is reached. It is the efficiency value of the decision-making unit at time t, which is used for subsequent work such as efficiency evaluation and analysis, and helps to understand the operating efficiency of the system at different times.

[0037] In one exemplary embodiment, the Malmquist index is calculated as: ; in, represents the Malmquist index, represents the investment at time t and output The distance to the efficiency frontier, represents the investment at time t+1 and output The distance to the efficiency frontier, represents the investment at time t+1 and output The distance to the efficiency frontier at time t, represents the investment at time t and output The distance to the efficiency frontier at time t+1.

[0038] Indicatively, the efficiency frontier in the above formula can be understood as the optimal output boundary that can be achieved under given inputs. The efficiency frontier distance reflects the gap between the current input-output combination and the optimal state. The formula is obtained by calculating the product of the ratio of the input-output combination at different times to the efficiency frontier distance at different times and taking the square root. The index can reflect the changes in production efficiency from time t to time t+1, including the comprehensive impact of multiple factors such as technological progress and changes in technical efficiency on production efficiency. It helps to gain a deeper understanding of the dynamic evolution of efficiency in the production process and provide a scientific basis for the reasons for efficiency improvement or decline in photovoltaic power station decision-making.

[0039] In one exemplary embodiment, historical operation data, historical meteorological data, and historical power grid data are subjected to causal inference analysis to obtain influencing factors affecting the power generation efficiency of the photovoltaic power station, including: Perform data cleaning and data alignment on historical operation data, historical meteorological data and historical power grid data. Data cleaning includes missing value filling, outlier processing and data standardization. Data alignment includes alignment by timestamp and resampling of non-uniformly sampled data. Based on the Granger causality test, the causal relationship between the variables of historical operation data, historical meteorological data and historical power grid data is identified, the significance level is set, and the direct influencing factors are screened out; A causal relationship model is constructed based on the Bayesian network, and the conditional probability distribution between variables is learned using historical operation data, historical meteorological data, and historical power grid data to identify the indirect causal relationship between direct influencing factors. According to the direct influencing factors and causal relationship model, a structural equation model is constructed to quantify the direct and indirect effects of each direct influencing factor on power generation efficiency. The maximum likelihood estimation method is used to solve the model parameters and obtain the causal effect value of each direct influencing factor. Based on the causal effect value of each direct influencing factor, a causal effect threshold is set, and the influencing factors with causal effect values ​​greater than the causal effect threshold are screened out, and the influencing factors are used as the final influencing factors affecting the power generation efficiency of the photovoltaic power station.

[0040] Indicatively, missing values ​​can be supplemented by filling in the mean, median, or model-based prediction to ensure data integrity. And outliers in the data can be identified and processed by statistical methods or specific algorithms, such as using box plots to determine and process outliers, to avoid adverse effects on subsequent analysis. Finally, data normalization is performed by using methods such as Z-score standardization or Min-Max standardization to eliminate the impact of dimensions and make the data comparable. In addition, in order to ensure the consistency and comparability of the data, various types of data can be aligned according to timestamps and resampled into uniform time interval data by resampling non-uniformly sampled data.

[0041] Granger causality test is a statistical method that can determine the causal relationship between two variables by testing whether the lagged value of one variable can significantly affect the current value of another variable. By setting a significance level, if the lagged value of the test result is less than the significance level, it is considered that there is a Granger causal relationship between the two variables, thereby screening out factors that directly affect the power generation efficiency of photovoltaic power plants. In addition, Bayesian network is a probabilistic graphical model that can intuitively represent the causal relationship and conditional probability distribution between variables. By using historical operation data, historical meteorological data, and historical power grid data to learn the conditional probability distribution between variables, indirect causal relationships between direct influencing factors can be identified.

[0042] Structural equation modeling is a comprehensive statistical analysis method that can simultaneously consider the direct and indirect relationships between multiple variables. Therefore, a structural equation model can be constructed based on direct influencing factors and causal relationship models. By using the maximum likelihood estimation method to solve the model parameters, the direct and indirect effects of each direct influencing factor on power generation efficiency can be quantified, and the causal effect value of each direct influencing factor can be obtained. For example, the direct impact of light intensity on power generation and the indirect impact through other intermediate variables can be calculated through the structural equation model. By setting a causal effect threshold, the influencing factors with causal effect values ​​greater than the causal effect threshold are screened out, and these influencing factors are used as the final influencing factors that affect the power generation efficiency of photovoltaic power stations. Then, those factors that have a significant impact on power generation efficiency can be highlighted, providing key variable basis for subsequent power generation efficiency analysis and optimization.

[0043] In one exemplary embodiment, the impact factors are comprehensively evaluated and weighted by combining the fuzzy analytic hierarchy process to obtain weighted impact factors, including: Construct a hierarchical model, which includes a target layer, a criterion layer, and a solution layer. The target layer is the photovoltaic power generation efficiency, the criterion layer includes meteorological factors, equipment status, and operation and maintenance level, and the solution layer includes solar irradiance, temperature, equipment failure rate, and cleanliness; The 1-9 scaling method is used to compare the factors at the criterion level and the solution level to obtain the evaluation score results, which are then converted into triangular fuzzy numbers to construct a fuzzy judgment matrix. Based on the fuzzy judgment matrix, the fuzzy analytic hierarchy process is used to calculate the weights of the influencing factors, and the weight values ​​are obtained through defuzzification; Multiply the causal effect value of the impact factor by the corresponding weight value to obtain the weighted impact factor.

[0044] Specifically, the target layer is the photovoltaic power generation efficiency, which is the object of the final analysis. The criterion layer is a classification of factors affecting photovoltaic power generation efficiency from a macro perspective, and is the intermediate layer connecting the target layer and the solution layer. The solution layer includes specific factors such as solar irradiance, temperature, equipment failure rate, and cleanliness. The hierarchical model decomposes complex problems into multiple levels, which is convenient for systematic analysis and evaluation. The 1-9 scale method is a quantitative method of subjective judgment, which can compare the factors of the criterion layer and the solution layer in pairs to evaluate their relative importance. Based on fuzzy theory, the evaluation score results are converted into triangular fuzzy numbers, which can better deal with the uncertainty and ambiguity in the evaluation. Based on triangular fuzzy numbers, the fuzzy judgment matrix of the criterion layer and the solution layer is constructed, which can represent the fuzzy relationship of the relative importance of different factors. Based on the fuzzy judgment matrix, the relevant calculation steps of the fuzzy hierarchy analysis method are used to calculate the weights of the influencing factors, such as multiplication and addition of fuzzy numbers, and the defuzzification operation can be performed through the centroid method to convert the obtained fuzzy weights into clear weight values. Finally, the causal effect value of the influencing factor is multiplied by the corresponding weight value to obtain the weighted influencing factor. Among them, the causal effect value reflects the actual impact of the influencing factor on photovoltaic power generation efficiency, and the weight value reflects the relative importance of the influencing factor in the comprehensive evaluation. By combining the two, the final weighted influencing factor takes into account both the actual influence of the factor and its importance in the overall evaluation, providing a more scientific and reasonable quantitative basis for the subsequent construction of a dynamic DEA model based on time series analysis.

[0045] In one exemplary embodiment, the method further comprises: Based on the efficiency evaluation results, identify the time period with abnormal efficiency, and combine the contribution analysis of the influencing factors to determine the key influencing factors that cause abnormal efficiency; Optimization instructions are generated according to key influencing factors, and the optimization instructions are used to execute corresponding operation and maintenance strategies of the photovoltaic power station.

[0046] Indicatively, the efficiency evaluation results obtained based on the dynamic DEA model include the efficiency change trend and the actual efficiency values ​​at different time points. These data can be compared with reference standards such as the preset efficiency range or historical average efficiency under normal conditions, so as to identify the time period of abnormal efficiency. For example, if the power generation efficiency value in a certain period of time is significantly lower than the historical average level of the same period, or the efficiency change trend shows a sudden and sharp decline, the time period can be determined as an efficiency abnormality time period, and combined with the contribution of various influencing factors such as solar irradiance and equipment failure rate obtained in the previous analysis, the contribution can be analyzed. Among them, the contribution can be measured by the direct and indirect effects of various direct influencing factors on power generation efficiency obtained by the structural equation model. By analyzing which changes in influencing factors contribute more to the decline in efficiency during the efficiency abnormality time period, for example, in a certain efficiency abnormality time period, it is found that the equipment failure rate suddenly increases, and through the contribution analysis, it is known that the equipment failure rate contributes more to the decline in power generation efficiency. The equipment failure rate is the key influencing factor causing the efficiency abnormality. And by generating corresponding optimization instructions to instruct the execution of the corresponding operation and maintenance strategy of the photovoltaic power station, the key problems that lead to efficiency abnormalities can be targeted to improve the power generation efficiency of the photovoltaic power station and restore it to normal or better operating state, thereby ensuring the stable and efficient operation of the photovoltaic power station and improving energy utilization efficiency and economic benefits.

[0047] Based on the same inventive concept, Figure 2 As shown, the embodiment of the present application also provides a photovoltaic power generation efficiency analysis and evaluation system 200, which includes: The data acquisition module 201 is used to acquire the historical operation data of the photovoltaic power station and the corresponding historical meteorological data and historical power grid data. The historical operation data includes historical power generation data, power station operation and maintenance data, and photovoltaic panel cleanliness data; The factor acquisition module 202 is used to perform causal inference analysis on historical operation data, historical meteorological data and historical power grid data to obtain influencing factors that affect the power generation efficiency of the photovoltaic power station; The factor processing module 203 is used to comprehensively evaluate and assign weights to the impact factors in combination with the fuzzy hierarchical analysis method to obtain weighted impact factors; The efficiency evaluation module 204 is used to construct a dynamic DEA model based on time series analysis according to weighted influencing factors, and to perform efficiency evaluation based on the dynamic DEA model to obtain efficiency evaluation results. The efficiency evaluation results include efficiency change trends and actual efficiency values ​​at different time points. The efficiency evaluation results are used for operation and maintenance management of photovoltaic power stations.

[0048] The system is divided into four main modules. The data acquisition module 201 can obtain the historical operation data of the photovoltaic power station and the corresponding historical meteorological data and historical power grid data. The historical operation data covers the historical power generation data, power station operation and maintenance data and photovoltaic panel cleanliness data. The accurate data acquisition of this module provides a comprehensive and reliable information basis for subsequent analysis work, ensuring that the analysis process of the entire system has solid data support. The factor acquisition module 202 performs causal inference analysis on the data provided by the data acquisition module 201, and can accurately obtain the influencing factors that affect the power generation efficiency of the photovoltaic power station, and then clarify which factors play a key role in the power generation efficiency among many factors, which points out the direction for subsequent research and optimization. The factor processing module 203 combines the fuzzy hierarchical analysis method to comprehensively evaluate and weight the influencing factors obtained by the factor acquisition module. Through this scientific processing method, the factor processing module 203 can quantify the importance of different influencing factors and obtain weighted influencing factors, thereby providing strong support for building a reasonable evaluation model. The efficiency evaluation module 204 can construct a dynamic DEA model based on time series analysis according to the weighted influencing factors, and perform efficiency evaluation based on this model, and finally obtain an efficiency evaluation result including the efficiency change trend and the real efficiency value at different time points. This efficiency evaluation result will be used for the operation and maintenance management of photovoltaic power stations, providing a key basis for the scientific operation and maintenance of power stations.

[0049] Through the coordinated work of these four modules, the system can realize the accurate evaluation of the power generation efficiency of photovoltaic power stations, which helps operation and maintenance managers to optimize the management of photovoltaic power stations under different environments and operating conditions, thereby improving power generation efficiency and overall performance, and ensuring the long-term stable and efficient operation of photovoltaic power stations.

[0050] Furthermore, the efficiency evaluation module 204 includes a model building subunit for: The weighted influencing factors are divided into input indicators and output indicators. The input indicators include equipment failure rate and operation and maintenance costs, and the output indicators include power generation and power generation efficiency. The time lag relationship between input indicators and output indicators is determined through the mutual information method, and the time lag parameters are constructed; Based on the time lag parameters, the time series data of input indicators and output indicators are aligned with time lag to construct a time lag data set; The sliding window mechanism is used to dynamically divide the time-lag data set, and the window size is dynamically adjusted according to the data variation coefficient to obtain the sliding window; Based on the time-lag data set and sliding window, the objective function of the dynamic DEA model is constructed, and the efficiency value sequence at different time points is obtained by solving the objective function; Based on the efficiency value sequence, the Malmquist index is used to analyze the efficiency change and obtain the efficiency change trend, which includes comprehensive technical efficiency, pure technical efficiency and scale efficiency. Through the efficiency prediction model based on weighted influencing factors, the efficiency prediction value is generated, and the efficiency prediction value is added to the DEA evaluation as a virtual decision-making unit. The dynamic DEA model is obtained by combining the efficiency value sequence and the efficiency change trend.

[0051] Exemplarily, the objective function is: ; in, and are the input index and output index at time t, and are the input-output data with a time lag of τ, λ is the weight vector, Λ is the weight constraint set, is the time lag parameter.

[0052] Exemplarily, the calculation formula of the Malmquist index is: ; in, represents the Malmquist index, represents the investment at time t and output The distance to the efficiency frontier, represents the investment at time t+1 and output The distance to the efficiency frontier, represents the investment at time t+1 and output The distance to the efficiency frontier at time t, represents the investment at time t and output The distance to the efficiency frontier at time t+1.

[0053] Furthermore, the factor acquisition module 202 includes: A data preprocessing subunit is used to clean and align historical operation data, historical meteorological data and historical power grid data. Data cleaning includes missing value filling, outlier processing and data standardization. Data alignment includes alignment by timestamp and resampling of non-uniformly sampled data. Factor screening subunit, used to: Based on the Granger causality test, the causal relationship between the variables of historical operation data, historical meteorological data and historical power grid data is identified, the significance level is set, and the direct influencing factors are screened out; A causal relationship model is constructed based on the Bayesian network, and the conditional probability distribution between variables is learned using historical operation data, historical meteorological data, and historical power grid data to identify the indirect causal relationship between direct influencing factors. According to the direct influencing factors and causal relationship model, a structural equation model is constructed to quantify the direct and indirect effects of each direct influencing factor on power generation efficiency. The maximum likelihood estimation method is used to solve the model parameters and obtain the causal effect value of each direct influencing factor. Based on the causal effect value of each direct influencing factor, a causal effect threshold is set, and the influencing factors with causal effect values ​​greater than the causal effect threshold are screened out, and the influencing factors are used as the final influencing factors affecting the power generation efficiency of the photovoltaic power station.

[0054] Furthermore, the factor processing module 203 includes: The hierarchical model construction subunit is used to construct the hierarchical model. The hierarchical model includes a target layer, a criterion layer and a solution layer. The target layer is the photovoltaic power generation efficiency. The criterion layer includes meteorological factors, equipment status, and operation and maintenance level. The solution layer includes solar irradiance, temperature, equipment failure rate, and cleanliness. The fuzzy evaluation subunit is used to compare the factors at the criterion layer and the solution layer using the 1-9 scaling method to obtain the evaluation score results, and convert the evaluation score results into triangular fuzzy numbers to construct a fuzzy judgment matrix; it is used to calculate the weights of the influencing factors based on the fuzzy judgment matrix using the fuzzy hierarchical analysis method, and obtain the weight values ​​through defuzzification; The weighting subunit is used to multiply the causal effect value of the impact factor by the corresponding weight value to obtain the weighted impact factor.

[0055] Furthermore, the system also includes an operation and maintenance implementation module, which is used to: Based on the efficiency evaluation results, identify the time period with abnormal efficiency, and combine the contribution analysis of the influencing factors to determine the key influencing factors that cause abnormal efficiency; Optimization instructions are generated according to key influencing factors, and the optimization instructions are used to execute corresponding operation and maintenance strategies of the photovoltaic power station.

[0056] In an exemplary embodiment, the present invention further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of a photovoltaic power generation efficiency analysis and evaluation method of the present application are implemented. A multi-core processor is preferred to improve the parallel processing capability of the system. Memory: Provides sufficient temporary storage space to support the operation of the program and the processing of data. The memory capacity should be large enough to accommodate a large amount of supply information and computing tasks.

[0057] In an exemplary embodiment, the present invention further provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, the steps of a photovoltaic power generation efficiency analysis and evaluation method of the present application are implemented. The computer-readable storage medium may include: a read-only memory (ROM), a random access memory (RAM), a solid state drive (SSD), or an optical disk, etc. Among them, the random access memory may include a resistance random access memory (ReRAM) and a dynamic random access memory (DRAM).

[0058] The above-mentioned embodiments only express several implementation methods of the embodiments of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the patent of the embodiments of the present application. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the embodiments of the present application, and these all belong to the protection scope of the embodiments of the present application.

Claims

1. A photovoltaic power generation efficiency analysis and evaluation method, characterized in that: The method comprises: Obtain the historical operation data of the photovoltaic power station and the corresponding historical meteorological data and historical power grid data. The historical operation data includes historical power generation data, power station operation and maintenance data, and photovoltaic panel cleanliness data; Performing causal inference analysis on the historical operation data, the historical meteorological data and the historical power grid data to obtain influencing factors affecting the power generation efficiency of the photovoltaic power station; Combining the fuzzy analytic hierarchy process, the impact factors are comprehensively evaluated and weighted to obtain weighted impact factors; A dynamic DEA model based on time series analysis is constructed according to the weighted influencing factors, and efficiency evaluation is performed based on the dynamic DEA model to obtain efficiency evaluation results, wherein the efficiency evaluation results include efficiency change trends and real efficiency values ​​at different time points, and the efficiency evaluation results are used for operation and maintenance management of the photovoltaic power station.

2. The method according to claim 1, characterized in that The step of constructing a dynamic DEA model based on time series analysis according to the weighted impact factors includes: Dividing the weighted influencing factors into input indicators and output indicators, the input indicators include equipment failure rate and operation and maintenance cost, and the output indicators include power generation and power generation efficiency; Determine the time lag relationship between the input indicator and the output indicator through the mutual information method, and construct the time lag parameter; Based on the time lag parameter, align the time series data of the input indicator and the output indicator with a time lag to construct a time lag data set; The time-lag data set is dynamically divided by using a sliding window mechanism, and the window size is dynamically adjusted according to the coefficient of variation of the data to obtain a sliding window; Based on the time-lag data set and the sliding window, construct an objective function of a dynamic DEA model, and obtain efficiency value sequences at different time points by solving the objective function; Based on the efficiency value sequence, the Malmquist index is used to perform efficiency change analysis to obtain the efficiency change trend, wherein the efficiency change trend includes comprehensive technical efficiency, pure technical efficiency and scale efficiency; The efficiency prediction model based on the weighted influencing factors is used to generate efficiency prediction values, and the efficiency prediction values ​​are added to the DEA evaluation as virtual decision units, and the dynamic DEA model is obtained by combining the efficiency value sequence and the efficiency change trend.

3. The method according to claim 2, characterized in that The objective function is: ； in, and are the input index and the output index at time t respectively, and are the input-output data with a time lag of τ, λ is the weight vector, Λ is the weight constraint set, is the time lag parameter.

4. The method according to claim 2, characterized in that: The calculation formula of the Malmquist index is: ； in, represents the Malmquist index, represents the investment at time t and output The distance to the efficiency frontier, represents the investment at time t+1 and output The distance to the efficiency frontier, represents the investment at time t+1 and output The distance to the efficiency frontier at time t, represents the investment at time t and output The distance to the efficiency frontier at time t+1.

5. The method according to claim 1, characterized in that The causal inference analysis of the historical operation data, the historical meteorological data and the historical power grid data to obtain the influencing factors affecting the power generation efficiency of the photovoltaic power station includes: Performing data cleaning and data alignment on the historical operation data, the historical meteorological data and the historical power grid data, wherein the data cleaning includes missing value filling, outlier processing and data standardization, and the data alignment includes alignment by timestamp and resampling of non-uniformly sampled data; Based on the Granger causality test, the causal relationship between the variables of the historical operation data, the historical meteorological data and the historical power grid data is identified, the significance level is set, and the direct influencing factors are screened out; Building a causal relationship model based on a Bayesian network, using the historical operation data, the historical meteorological data and the historical power grid data to learn the conditional probability distribution between the variables, and identifying the indirect causal relationship between the direct influencing factors; According to the direct influencing factors and the causal relationship model, a structural equation model is constructed to quantify the direct and indirect effects of each of the direct influencing factors on power generation efficiency, and the model parameters are solved using the maximum likelihood estimation method to obtain the causal effect value of each of the direct influencing factors; Based on the causal effect value of each of the direct influencing factors, a causal effect threshold is set, and the influencing factors whose causal effect values ​​are greater than the causal effect threshold are screened out, and the influencing factors are used as the final influencing factors affecting the power generation efficiency of the photovoltaic power station.

6. The method according to claim 5, characterized in that The influencing factors are comprehensively evaluated and weighted by combining the fuzzy hierarchical analysis method to obtain weighted influencing factors, including: Constructing a hierarchical model, the hierarchical model includes a target layer, a criterion layer and a solution layer, the target layer is photovoltaic power generation efficiency, the criterion layer includes meteorological factors, equipment status, and operation and maintenance level, and the solution layer includes solar irradiance, temperature, equipment failure rate, and cleanliness; The factors of the criterion layer and the solution layer are compared using a 1-9 scaling method to obtain an evaluation score result, and the evaluation score result is converted into a triangular fuzzy number to construct a fuzzy judgment matrix; Based on the fuzzy judgment matrix, the weights of the influencing factors are calculated using the fuzzy analytic hierarchy process, and the weight values ​​are obtained by defuzzification; The causal effect value of the influencing factor is multiplied by the corresponding weight value to obtain the weighted influencing factor.

7. The method according to claim 1, characterized in that The method further comprises: Based on the efficiency evaluation results, identify the efficiency abnormality time period, and combine the contribution analysis of the influencing factors to determine the key influencing factors that cause the efficiency abnormality; An optimization instruction is generated according to the key influencing factors, and the optimization instruction is used to execute a corresponding operation and maintenance strategy of the photovoltaic power station.

8. A photovoltaic power generation efficiency analysis and evaluation system, characterized in that: The system comprises: A data acquisition module is used to acquire the historical operation data of the photovoltaic power station and the corresponding historical meteorological data and historical power grid data. The historical operation data includes historical power generation data, power station operation and maintenance data, and photovoltaic panel cleanliness data; A factor acquisition module, used to perform causal inference analysis on the historical operation data, the historical meteorological data and the historical power grid data to obtain influencing factors affecting the power generation efficiency of the photovoltaic power station; A factor processing module is used to comprehensively evaluate and weight the impact factors in combination with the fuzzy analytic hierarchy process to obtain weighted impact factors; The efficiency evaluation module is used to construct a dynamic DEA model based on time series analysis according to the weighted influencing factors, and to perform efficiency evaluation based on the dynamic DEA model to obtain efficiency evaluation results, wherein the efficiency evaluation results include efficiency change trends and actual efficiency values ​​at different time points, and the efficiency evaluation results are used for operation and maintenance management of the photovoltaic power station.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

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

Images