Photovoltaic power station comprehensive intelligent operation and maintenance method and system based on cloud processing

Abstract

The invention discloses a photovoltaic power station comprehensive intelligent operation and maintenance method and system based on cloud processing, and relates to the technical field of photovoltaic power station operation and maintenance management, the photovoltaic power station comprehensive intelligent operation and maintenance method based on cloud processing comprises the following steps: obtaining characteristic data of operation state data and parameter data, and storing the characteristic data in a cloud platform; evaluating the power generation performance of the photovoltaic equipment in real time by using a solar energy conversion efficiency model; formulating an optimal cleaning period of the photovoltaic equipment; and inputting a detection result into a photovoltaic equipment operation fault abnormity database for fault judgment. The power generation efficiency is evaluated in real time through the photoelectric conversion model, so that operation and maintenance personnel can know the power generation condition of the photovoltaic power station, frequent cleaning or overlong cleaning interval is avoided, the fault data discovery and recognition capability can be improved, the service life of equipment is prolonged, the operation efficiency of the equipment is improved, and the power generation efficiency is improved. And the operation and maintenance efficiency of the photovoltaic power station is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of photovoltaic power station operation and maintenance management, and in particular to a photovoltaic power station comprehensive intelligent operation and maintenance method and system based on cloud processing. Background Art

[0002] Photovoltaic power stations are facilities that use photovoltaic power generation technology to convert solar energy into electrical energy. They are composed of a large number of solar panels (photovoltaic modules), which convert solar energy into direct current through photoelectric conversion. The direct current is converted into alternating current through an inverter, and then stepped up by a transformer before being connected to the power grid or power supply equipment to achieve the transmission and utilization of electrical energy.

[0003] Intelligent operation and maintenance management is a method that uses advanced technical means and data analysis methods to improve the operation and maintenance efficiency, economic benefits and reliability of photovoltaic power stations. In the intelligent operation and maintenance management of photovoltaic power stations, power generation forecasting is a very important part. Accurate power generation forecasting can provide a reliable basis for the planning, operation management, energy market transactions and equipment maintenance of photovoltaic power stations.

[0004] However, in the prior art, since the power generation of photovoltaic power stations is affected by weather conditions, such as sunlight intensity, cloud cover, temperature, etc., it is difficult to predict the power generation of photovoltaic power stations. The assessment of photovoltaic potential focuses more on data collection and real-time monitoring, but less on data analysis and prediction, which makes it difficult to comprehensively evaluate photovoltaic potential, and further improve the accuracy and reliability of power generation prediction. The operation and maintenance efficiency and economic benefits of photovoltaic power stations are gradually reduced.

[0005] Currently, no effective solution has been proposed for the problems in the related technologies. Summary of the invention

[0006] In view of the deficiencies in the prior art, the present invention proposes a comprehensive intelligent operation and maintenance method and system for photovoltaic power stations based on cloud processing, which solves the problem mentioned in the above background technology that the power generation of existing photovoltaic power stations is affected by weather conditions, such as sunlight intensity, cloud cover, temperature, etc., and therefore it is difficult to predict the power generation of photovoltaic power stations. The assessment of photovoltaic potential focuses more on data collection and real-time monitoring, but less on data analysis and prediction, which makes it inconvenient to comprehensively evaluate photovoltaic potential, and further makes it inconvenient to improve the accuracy and reliability of power generation prediction, and the operating efficiency and economic benefits of photovoltaic power stations gradually decrease.

[0007] To achieve the above objectives, the present invention is implemented through the following technical solutions: According to one aspect of the present invention, a photovoltaic power station integrated intelligent operation and maintenance method based on cloud processing is provided, and the photovoltaic power station integrated intelligent operation and maintenance method based on cloud processing comprises the following steps: S1. Obtaining the operating status data and parameter data of the photovoltaic power station, and preprocessing the acquired operating status data and parameter data to obtain characteristic data of the operating status data and parameter data and store them in the cloud platform; S2. Use cloud processing and analysis technology to establish a solar energy conversion efficiency model for photovoltaic power plants, and use the solar energy conversion efficiency model to evaluate the power generation performance of photovoltaic equipment in real time; S3. Analyze the evaluation results of power generation performance using an analytical algorithm, determine the degree of accumulation of obstructions on the surface of the photovoltaic equipment, formulate an optimal cleaning cycle for the photovoltaic equipment, and clean it using automatic cleaning equipment; S4. Establish a photovoltaic equipment operation fault anomaly database, and perform anomaly detection on the feature data in the cloud platform through an anomaly detection algorithm, and input the detection results into the photovoltaic equipment operation fault anomaly database for fault identification; S5. Based on the historical data in the fault anomaly database and the characteristic data in the cloud platform, a fault prediction model is constructed in the cloud platform using the beamforming method and the time series analysis method, and the fault prediction model is used to predict the occurrence of the fault at the next moment; S6. Develop corresponding maintenance strategies and emergency plans based on the prediction results.

[0008] Furthermore, obtaining the operating status data and parameter data of the photovoltaic power station, and preprocessing the obtained operating status data and parameter data to obtain characteristic data of the operating status data and parameter data and store them in the cloud platform includes the following steps: S11, collecting duplicate data, missing values ​​and abnormal values ​​of the acquired operating status data and parameter data, and performing denoising, filtering and smoothing on the duplicate data, missing values ​​and abnormal values; S12, performing data verification on the operation status data and parameter data after denoising, filtering and smoothing, extracting valid data, and performing normalization processing to generate accurate operation status data and parameter data; S13, using principal component analysis to merge the generated accurate operating status data and parameter data into the same data set; S14. Extract relevant features from the fused data set to obtain feature data of the operating status data and parameter data, and store them in the cloud platform.

[0009] Furthermore, using cloud processing and analysis technology to establish a solar energy conversion efficiency model for a photovoltaic power station, and using the solar energy conversion efficiency model to evaluate the power generation performance of photovoltaic equipment in real time includes the following steps: S21. Analyze the operating status data of photovoltaic equipment using cloud processing and analysis technology, and extract features related to photovoltaic modules; S22, converting the extracted relevant features into photovoltaic module characteristics and photoelectric conversion principles, and constructing a solar energy conversion efficiency model; S23, estimating parameter values ​​in the solar energy conversion efficiency model by fitting the actually measured power generation and irradiance data with the constructed solar energy conversion efficiency model; S24. Use the established solar energy conversion efficiency model to calculate the actual power generation efficiency of the photovoltaic equipment, and compare the actual power generation efficiency with the expected efficiency to evaluate the power generation performance of the photovoltaic equipment.

[0010] Further, the evaluation results of power generation performance are analyzed by using an analysis algorithm to determine the degree of accumulation of obstructions on the surface of the photovoltaic equipment, to formulate an optimal cleaning cycle for the photovoltaic equipment, and to clean it using an automatic cleaning device, including the following steps: S31, importing the actual power generation efficiency and expected efficiency, initializing, and using the shortest path algorithm to calculate the degree of accumulation of obstructions between any two detection points on the surface of the photovoltaic device; S32, establishing a number of analysis strategies, each of which represents a correlation analysis method between the degree of accumulation of obstructions and the power generation performance of the equipment, the first N numbers represent the numbers of the selected detection points, and the last N numbers represent the corresponding power generation performance level of the photovoltaic equipment; S33, according to the preset photovoltaic equipment performance maintenance target, find the global optimal analysis strategy, add environmental impact factors and each group of local optimal analysis strategies and photovoltaic equipment operation trends to jointly influence the optimization of the analysis strategy; S34, substituting the optimized analysis strategy into Kent mapping, and comparing the analysis strategy after Kent mapping with the analysis strategy before optimization using the photovoltaic equipment power generation performance and the degree of accumulation of obstructions as evaluation criteria; S35, using the elite retention strategy and replacing the worst analysis strategy with the global suboptimal analysis strategy according to the photovoltaic equipment performance maintenance target; S36, looping through steps S33 to S35, and if the number of iterations exceeds a threshold, terminating the iterations, and obtaining the best judgment method for evaluating the power generation performance of the photovoltaic device and the degree of accumulation of obstructions; S37. According to the best judgment method, formulate the best cleaning cycle for the photovoltaic equipment, and use automatic cleaning equipment to clean it.

[0011] Furthermore, according to the preset photovoltaic equipment performance maintenance target, the global optimal analysis strategy is found, and the optimization of the analysis strategy jointly influenced by the environmental impact factor and each group of local optimal analysis strategies and the photovoltaic equipment operation trend includes the following steps: S331, defining an objective function of the photovoltaic equipment performance maintenance target, which is used to evaluate the fitness of the analysis strategy; S332, initializing the analysis strategy population, and randomly generating parameters for each analysis strategy; S333, calculating the fitness of each analysis strategy according to the objective function, and finding the global optimal analysis strategy as the best solution; S334, randomly generating environmental impact factors for each group of optimal analysis strategies, and calculating the average parameters within each group of local optimal analysis strategies as the group population trend; S335, bringing the original analysis strategy parameters into the update formula, calculating the parameters of the new analysis strategy, and updating the parameters of each analysis strategy; S336. Repeat steps S333 to S335 until the termination condition is met.

[0012] Furthermore, substituting the optimized analysis strategy into the Kent mapping, and comparing the analysis strategy after the Kent mapping with the analysis strategy before the optimization using the photovoltaic equipment power generation performance and the degree of accumulation of obstructions as evaluation criteria, including the following steps: S341, training and iterating the analysis strategy population to obtain an optimized analysis strategy population; S342, performing data normalization processing on the optimized analysis strategy population to put it in a preset state; S343, randomly generate parameters of Kent mapping and preset a value range; S344, using the Kent mapping formula to map each optimized analysis strategy to generate a new analysis strategy individual; S345, comparing the fitness of each analysis strategy with its Kent mapping result, and retaining the analysis strategy individual with the best fitness as the Kent mapping analysis strategy; S346, compare the fitness of the Kent mapping analysis strategy with the original analysis strategy population, and retain the analysis strategy individuals with the best fitness to enter the next generation analysis strategy population; S347. Repeat steps S342 to S346 until the iteration termination condition is reached.

[0013] Furthermore, the update formula is: ; in, Represents the parameters of the new analysis strategy after optimization; represents the parameters of the original analysis strategy; m Indicates m an analysis strategy; i Indicates i Iterations; bIndicates b The parameter value of the dimension; x a parameter vector representing the analysis strategy; l 1 represents the weight of the environmental impact factor after normalization; l 2 represents growth factor δ The weight of the random weight impact factor of 1 after normalization; l 3 represents growth factor δ The weight of the random weight influence factor of 2 after normalization.

[0014] Furthermore, establishing a photovoltaic equipment operation fault anomaly database, and performing anomaly detection on the feature data in the cloud platform through an anomaly detection algorithm, and inputting the detection results into the photovoltaic equipment operation fault anomaly database for fault identification includes the following steps: S41. Establishing a database of abnormal operation failures of photovoltaic equipment; S42, inputting the performance parameter data set of the photovoltaic equipment into the cloud platform, and presetting the height of the decision tree in the anomaly detection algorithm, and initializing the random forest model; S43, using the performance parameter data of the photovoltaic equipment to construct a number of decision trees to form an initial random forest model; S44, using the performance parameters of the photovoltaic equipment in normal operation as a training set to train the initial random forest model; S45. According to the difference and accuracy of decision trees, a probability search algorithm is used to select decision trees with higher fitness from the initial forest model and combine them into a new random forest model; S46. Apply the new random forest model to the performance parameters of the photovoltaic equipment in the cloud platform, predict whether the photovoltaic equipment has a fault based on the input performance parameters, and input the prediction results into the photovoltaic equipment operation fault anomaly database to identify and record the fault.

[0015] Furthermore, based on the historical data in the fault anomaly database and the characteristic data in the cloud platform, a fault prediction model is constructed in the cloud platform using the beamforming method and the time series analysis method, and the fault prediction model is used to predict the occurrence of the fault at the next moment, including the following steps: S51, using a polynomial regression model to analyze whether there is a trend item with a longer period in the historical data and the characteristic data, if so, removing the trend item with a longer period, if not, continuing to analyze the periodic changes in the historical data and the characteristic data; S52, according to the analysis result, performing a beam forming method on the historical data after removing the trend item and the feature data in the feature data to obtain the amplitude and phase of each frequency component; S53, using a significance test to determine whether each frequency component is significant, extracting significant periodic terms, and constructing a periodic term model; S54, the residual after eliminating the trend term and the cycle term is regarded as a random change, and a residual prediction model is constructed; S55, superimposing the polynomial regression model, the periodic term model and the residual prediction model to obtain a fault prediction model; S56, predicting the historical data and characteristic data at the next moment through the fault prediction model; S57, performing corresponding weighted processing on the predicted historical data and characteristic data and the weight value to obtain a comprehensive prediction output of the fault occurrence.

[0016] According to another aspect of the present invention, a photovoltaic power station integrated intelligent operation and maintenance system based on cloud processing is also provided, and the photovoltaic power station integrated intelligent operation and maintenance system based on cloud processing includes: The data acquisition and data preprocessing module is used to obtain the operating status data and parameter data of the photovoltaic power station, and preprocess the acquired operating status data and parameter data to obtain the characteristic data of the operating status data and parameter data and store them in the cloud platform; A performance evaluation module is used to establish a solar energy conversion efficiency model of a photovoltaic power station using cloud processing and analysis technology, and to use the solar energy conversion efficiency model to evaluate the power generation performance of photovoltaic equipment in real time; The data analysis and maintenance management module is used to analyze the evaluation results of power generation performance using analytical algorithms, determine the degree of accumulation of obstructions on the surface of photovoltaic equipment, formulate the best cleaning cycle for photovoltaic equipment, and clean it using automatic cleaning equipment; The abnormal database establishment and fault identification module is used to establish a photovoltaic equipment operation fault abnormality database, and perform abnormality detection on the feature data in the cloud platform through an abnormality detection algorithm, and input the detection results into the photovoltaic equipment operation fault abnormality database for fault identification; A fault prediction model building module is used to build a fault prediction model in the cloud platform based on the historical data in the fault anomaly database and the feature data in the cloud platform using the beamforming method and the time series analysis method, and use the fault prediction model to predict the occurrence of a fault at the next moment; Formulate maintenance strategy and fault prevention management module, which is used to formulate corresponding maintenance strategy and emergency plan according to the prediction results; Among them, the data acquisition and data preprocessing module is connected with the data analysis and maintenance management module through the performance evaluation module, the data analysis and maintenance management module is connected with the fault identification module and the fault prediction model construction module through the abnormal database establishment, and the fault prediction model construction module is connected with the maintenance strategy formulation and fault prevention management module.

[0017] The beneficial effects of the present invention are: 1. The present invention uses a photoelectric conversion model to evaluate the power generation efficiency in real time, so that the operation and maintenance personnel can understand the power generation status of the photovoltaic power station, help the operation and maintenance personnel adjust the operation strategy according to the change of power generation efficiency, and optimize the cleaning cycle of the photovoltaic equipment according to the evaluation results, avoid frequent cleaning or excessively long cleaning intervals, reduce energy consumption and cleaning costs, and increase the service life of the equipment. At the same time, through the detection of anomaly detection algorithms, it is possible to avoid erroneously marking normal data as abnormal values, thereby improving the ability to discover and identify fault data and reducing the false alarm rate. By predicting and promptly handling potential faults, it is possible to effectively avoid the decline in equipment performance, increase the service life and operating efficiency of the equipment, and thus improve the operation and maintenance efficiency of the photovoltaic power station.

[0018] 2. The present invention analyzes the evaluation results of power generation performance through an analysis algorithm, so that it can better judge the reasons for the reduction in power generation efficiency, thereby enhancing the overall power generation efficiency of the photovoltaic power station. Moreover, through the correlation analysis of the degree of accumulation of obstructions and the power generation performance of the equipment, the cleaning cycle of the photovoltaic equipment can be more accurately formulated to ensure that the equipment is in the best working condition and reduce maintenance costs. At the same time, through the cyclic execution of optimization strategies and combined with elite retention strategies, the maintenance methods can be continuously improved to ensure that the photovoltaic equipment remains efficient and stable in long-term operation, thereby improving the operating efficiency and reliability of the photovoltaic equipment, while reducing maintenance costs, and bringing long-term economic and technical benefits to the photovoltaic power station.

[0019] 3. The present invention performs anomaly detection on the characteristic data in the cloud platform through an anomaly detection algorithm, so that the real-time performance parameter data set is input into the cloud platform and analyzed through the random forest model, which can monitor the equipment status in real time, so as to more accurately identify and predict the potential failures of photovoltaic equipment, reduce false alarms and missed alarms, and thus improve the accuracy and timeliness of fault detection, optimize resource allocation, enhance the stability and reliability of photovoltaic power stations, and bring benefits to the intelligent operation and maintenance of photovoltaic power stations.

[0020] 4. The present invention uses a fault prediction model to predict possible problems before a fault occurs, providing maintenance personnel with time to take preventive measures or make corresponding preparations, thereby reducing the impact of the fault on the operation of the equipment. By predicting and promptly handling potential faults, the serious decline in equipment performance can be effectively avoided, thereby increasing the service life and operating efficiency of the equipment, and further improving the efficiency of evaluating the potential of photovoltaic equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0022] Figure 1 is a flow chart of a comprehensive intelligent operation and maintenance method of a photovoltaic power station based on cloud processing according to an embodiment of the present invention; Figure 2 It is a principle block diagram of a photovoltaic power station comprehensive intelligent operation and maintenance system based on cloud processing according to an embodiment of the present invention.

[0023] In the figure: 1. Data collection and data preprocessing module; 2. Performance evaluation module; 3. Data analysis and maintenance management module; 4. Abnormal database establishment and fault identification module; 5. Fault prediction model construction module; 6. Maintenance strategy formulation and fault prevention management module. DETAILED DESCRIPTION

[0024] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0025] In the description of the present invention, unless otherwise specified, the meaning of "plurality" is two or more. In addition, the terms "first", "second", "third", etc. are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0026] According to an embodiment of the present invention, a comprehensive intelligent operation and maintenance method and system for a photovoltaic power station based on cloud processing are provided.

[0027] The present invention is further described with reference to the accompanying drawings and specific embodiments. Figure 1 As shown, according to the photovoltaic power station integrated intelligent operation and maintenance method based on cloud processing according to an embodiment of the present invention, the photovoltaic power station integrated intelligent operation and maintenance method based on cloud processing includes the following steps: S1. Obtaining the operating status data and parameter data of the photovoltaic power station, and preprocessing the acquired operating status data and parameter data to obtain characteristic data of the operating status data and parameter data and store them in the cloud platform; Specifically, the operating status data and parameter data of the photovoltaic power station are obtained through sensors and monitoring systems (including hardware and software components. The monitoring system not only collects data provided by sensors, but also includes video monitoring equipment, communication interfaces and data processing software. It can display the operating status of the power station in real time, record historical data, and provide remote control functions).

[0028] Specifically, operating status data refers to various data of the photovoltaic power station in actual operation, such as voltage, current, power output, temperature, light intensity, wind speed and direction, environmental radiation and health status indicators.

[0029] Specifically, parameter data refers to the set parameters or configuration information of the photovoltaic power station, such as the type, capacity, layout, inclination, geographic information, climate data, building data, etc. of the photovoltaic panels.

[0030] S2. Use cloud processing and analysis technology to establish a solar energy conversion efficiency model for photovoltaic power plants, and use the solar energy conversion efficiency model to evaluate the power generation performance of photovoltaic equipment in real time; Specifically, cloud processing and analysis technology refers to the technology that uses the resources and capabilities of cloud computing to process and analyze data.

[0031] S3. Analyze the evaluation results of power generation performance using an analytical algorithm, determine the degree of accumulation of obstructions on the surface of the photovoltaic equipment, formulate an optimal cleaning cycle for the photovoltaic equipment, and clean it using automatic cleaning equipment; Specifically, obstructions include fog, rain, snow, dust, bird droppings, fallen leaves, etc.

[0032] Specifically, automatic cleaning equipment is a machine specially designed for cleaning photovoltaic panels in photovoltaic power plants. Automatic cleaning equipment includes: Intelligent control systems: Automatic cleaning equipment is usually equipped with advanced control systems that can automatically start the cleaning process according to a preset plan or based on actual needs (such as the degree of accumulation of obstructions determined by analytical algorithms).

[0033] Cleaning mechanical device: The device includes brushes, nozzles, etc., which are used to effectively remove dust, dirt and other obstructions on the surface of photovoltaic panels. Cleaning methods include dry cleaning (such as using a brush or blowing) and wet cleaning (such as using water or detergent).

[0034] Moving mechanism: Many automatic cleaning equipment are designed to move along the photovoltaic panels to achieve comprehensive and efficient cleaning. The moving mechanism can include tracks, wheels or other moving devices.

[0035] S4. Establish a photovoltaic equipment operation fault anomaly database, and perform anomaly detection on the feature data in the cloud platform through an anomaly detection algorithm, and input the detection results into the photovoltaic equipment operation fault anomaly database for fault identification; S5. Based on the historical data in the fault anomaly database and the characteristic data in the cloud platform, a fault prediction model is constructed in the cloud platform using the beamforming method and the time series analysis method, and the fault prediction model is used to predict the occurrence of the fault at the next moment; S6. Develop corresponding maintenance strategies and emergency plans based on the prediction results.

[0036] Specifically, the formulation of corresponding maintenance strategies and emergency plans includes: Fault prediction analysis: Analyze the results of fault prediction to determine the type of problem that may occur, its severity, and when it is expected to occur.

[0037] Priority setting: Different maintenance tasks are prioritized based on the severity and urgency of the prediction results. For example, the prediction results will give higher priority to faults that have a greater impact on system performance.

[0038] Resource allocation: Consider the available maintenance resources, such as personnel, equipment, materials, etc., and allocate them appropriately to cope with predicted failures.

[0039] Preventive maintenance plan: Develop a preventive maintenance plan to reduce the possibility of failures, including regular inspections, replacement of wearing parts, cleaning and other measures.

[0040] Emergency plan formulation: For sudden failures, a clear emergency plan is required, including response measures when failures occur, emergency maintenance procedures, backup system startup, etc.

[0041] Continuous monitoring and evaluation: During the implementation of maintenance strategies and emergency plans, the operating status of the PV system is continuously monitored, and plans and strategies are adjusted according to actual conditions.

[0042] Communication mechanism: Establish an effective communication mechanism to ensure that all relevant personnel can quickly receive information and take appropriate actions when necessary.

[0043] Recording and feedback: Keep detailed records of maintenance activities and fault response processes, and provide feedback and optimization based on actual conditions.

[0044] Preferably, obtaining the operating status data and parameter data of the photovoltaic power station, preprocessing the obtained operating status data and parameter data, obtaining characteristic data of the operating status data and parameter data and storing them in the cloud platform includes the following steps: S11, collecting duplicate data, missing values ​​and abnormal values ​​of the acquired operating status data and parameter data, and performing denoising, filtering and smoothing on the duplicate data, missing values ​​and abnormal values; S12, performing data verification on the operation status data and parameter data after denoising, filtering and smoothing, extracting valid data, and performing normalization processing to generate accurate operation status data and parameter data; S13, using principal component analysis to merge the generated accurate operating status data and parameter data into the same data set; Specifically, principal component analysis (PCA) is a commonly used data analysis technique, especially in feature extraction and dimensionality reduction. First, the data needs to be standardized to ensure that the importance of each feature in the analysis is consistent. Then the covariance matrix of the data is calculated, and the eigenvalues ​​and eigenvectors are extracted to determine the principal components. Finally, a certain number of principal components are selected as needed for data dimensionality reduction and feature representation. In this way, key information in photovoltaic power plant data can be effectively extracted and utilized.

[0045] S14. Extract relevant features from the fused data set to obtain feature data of the operating status data and parameter data, and store them in the cloud platform.

[0046] Specifically, the relevant features include electrical characteristic data (such as voltage, current, power, power generation, etc., which are data that directly reflect the power generation performance of photovoltaic panels), environmental characteristic data (such as temperature, light intensity, wind speed, humidity, etc., which help understand the impact of the external environment on the performance of photovoltaic panels), equipment status data (including equipment operating time, on / off status, fault records, maintenance history, etc.), performance degradation data (the degradation of photovoltaic panel performance during long-term operation, such as the trend of declining efficiency, the occurrence of hot spot effects, etc.) and obstruction accumulation data (data on the accumulation of obstructions (such as dust and leaves) collected through image recognition or other sensors).

[0047] Preferably, using cloud processing and analysis technology to establish a solar energy conversion efficiency model for a photovoltaic power station, and using the solar energy conversion efficiency model to evaluate the power generation performance of photovoltaic equipment in real time includes the following steps: S21. Analyze the operating status data of photovoltaic equipment using cloud processing and analysis technology, and extract features related to photovoltaic modules; S22, converting the extracted relevant features into photovoltaic module characteristics and photoelectric conversion principles, and constructing a solar energy conversion efficiency model; S23, estimating parameter values ​​in the solar energy conversion efficiency model by fitting the actually measured power generation and irradiance data with the constructed solar energy conversion efficiency model; Specifically, the actual measured power generation and irradiance data refer to the numerical data of power generation and irradiance obtained by actually measuring photovoltaic cells or photovoltaic power stations in reality. By fitting the actual measured power generation and irradiance data with the constructed photoelectric conversion model, the parameter values ​​in the model can be estimated. The fitting process will try to adjust the parameters in the model so that the power generation calculated by the model is close to the actual measured power generation.

[0048] S24. Use the established solar energy conversion efficiency model to calculate the actual power generation efficiency of the photovoltaic equipment, and compare the actual power generation efficiency with the expected efficiency to evaluate the power generation performance of the photovoltaic equipment.

[0049] Specifically, the solar energy conversion efficiency model is a device that converts light energy into electrical energy. Its working principle is based on the photoelectric voltage effect and the photoelectric current effect. The photoelectric conversion model includes a single diode model (Single DiodeModel), also known as an equivalent circuit model. The photoelectric conversion model is based on circuit theory and semiconductor physics principles, and abstracts photovoltaic cells into a combination of a current source, a voltage source, and two diode equivalent circuits.

[0050] Preferably, using an analysis algorithm to analyze the evaluation results of power generation performance, determining the degree of accumulation of obstructions on the surface of the photovoltaic device, formulating the optimal cleaning cycle of the photovoltaic device, and using an automatic cleaning device to clean it includes the following steps: S31, importing the actual power generation efficiency and expected efficiency, initializing, and using the shortest path algorithm to calculate the degree of accumulation of obstructions between any two detection points on the surface of the photovoltaic device; Specifically, the shortest path algorithm is the Floyd-Warshall algorithm, which is a classic algorithm for searching for the shortest path between any two points in a weighted graph. It uses the idea of ​​dynamic programming to gradually improve the path to obtain the shortest path length, splits the path through intermediate nodes, and compares and selects the better indirect path.

[0051] Specifically, the surface of the photovoltaic panel is divided into multiple detection points, each of which represents a specific position on the photovoltaic panel. These detection points can be physical measurement points or virtual points defined by image analysis software. The shortest path refers to the shortest distance path from one detection point to another on the surface of the photovoltaic panel, and the accumulation of obstructions on this path is the lowest.

[0052] S32, establishing a number of analysis strategies, each analysis strategy (i.e., each coyote in the improved coyote optimization algorithm) represents a correlation analysis method between the degree of accumulation of obstructions and the power generation performance of the equipment, the first N numbers represent the numbers of the selected detection points, and the last N numbers represent the corresponding power generation performance level of the photovoltaic equipment; Specifically, the numbers of the selected detection points refer to the obstruction detection points set at specific positions on the surface of the photovoltaic panel. These detection points will be used to collect data on the degree of obstruction accumulation in order to evaluate and predict the degree of obstruction accumulation.

[0053] S33, according to the preset photovoltaic equipment performance maintenance target, find the global optimal analysis strategy, add environmental impact factors and each group of local optimal analysis strategies and photovoltaic equipment operation trends to jointly influence the optimization of the analysis strategy; S34, substituting the optimized analysis strategy into Kent mapping, and comparing the analysis strategy after Kent mapping with the analysis strategy before optimization using the photovoltaic equipment power generation performance and the degree of accumulation of obstructions as evaluation criteria; Specifically, the Kent map is a chaotic map, and when the value is 0.5, it is a symmetric chaotic map.

[0054] S35, using the elite retention strategy and replacing the worst analysis strategy with the global suboptimal analysis strategy according to the photovoltaic equipment performance maintenance target; Specifically, the elite retention strategy itself is to replace the worst solution with the optimal solution, so as to avoid the algorithm eliminating excellent solutions during the optimization process and achieve the purpose of retaining the genes of excellent solutions. Therefore, the elite selection strategy is adjusted to name the suboptimal wolf before the entire population grows as Beta wolf, and use Beta wolf to replace the wolf with the worst social adaptability in the grown wolf pack, thereby improving the search efficiency while retaining the genes of excellent solutions in the population.

[0055] S36, looping through steps S33 to S35, and if the number of iterations exceeds a threshold, terminating the iterations, and obtaining the best judgment method for evaluating the power generation performance of the photovoltaic device and the degree of accumulation of obstructions; Specifically, the best judgment method is an algorithm or decision-making process. In the present invention, the best judgment method refers to an analysis result that can accurately and efficiently determine the degree of influence of the accumulation of obstructions (such as dust, dirt, etc.) on power generation performance.

[0056] Specifically, setting the threshold is a process that requires comprehensive consideration of multiple factors and needs to be optimized through multiple experiments and iterations. The threshold is based on algorithm performance evaluation indicators, such as error rate, accuracy, recall rate, or a problem-specific indicator. By adjusting these indicators to set one or more thresholds, the best judgment method can be obtained in practical applications.

[0057] S37. According to the best judgment method, the best cleaning cycle of the photovoltaic equipment is formulated, and the photovoltaic equipment is cleaned using automatic cleaning equipment.

[0058] Specifically, according to the best judgment method, the optimal cleaning cycle for photovoltaic equipment includes: Analyze the evaluation results: Use the evaluation results obtained by the best judgment method to analyze the accumulation of obstructions on the surface of photovoltaic equipment and their impact on power generation performance. This includes identifying the types of obstructions, the speed of accumulation, and the specific impact on photovoltaic panel performance.

[0059] Determine the performance threshold: According to the design parameters and operating requirements of the photovoltaic equipment, a threshold for power generation performance is set. When the performance of the photovoltaic panel drops below this threshold, it indicates that cleaning is required.

[0060] Predict accumulation trends: Use best judgment methods to predict the accumulation trend of obstructions and estimate the time required to reach the performance threshold. This time interval is an important reference for the cleaning cycle.

[0061] Consider environmental factors: The cleaning cycle of photovoltaic equipment also needs to consider environmental factors, such as seasonal changes, local climate conditions, air pollution levels, etc., which will affect the accumulation rate of obstructions.

[0062] Develop a cleaning plan: Based on the above information, develop a cleaning plan that includes cleaning cycles, cleaning methods (such as manual or automatic), cleaning times (such as daytime or nighttime), etc.

[0063] Specifically, the analysis algorithm is to improve the coyote optimization algorithm. The growth of coyotes is the main way to obtain new solutions when the traditional coyote optimization algorithm is optimized. The coyote optimization algorithm divides the entire coyote population into groups for growth. During the growth process, the growth of coyotes in the group is guided by the group alpha wolf and the group cultural trend cult, which greatly limits the population diversity of COA coyotes and the information exchange within the population. The global traversal of coyotes during the growth process is low. At the same time, due to the low birth rate and low population diversity of COA coyotes, the exploration ability of the algorithm is poor and it is easy to fall into the local optimum. The present invention mainly improves the growth mode of coyotes in the coyote optimization algorithm (that is, the update formula in the present invention).

[0064] Preferably, according to the preset photovoltaic equipment performance maintenance target, finding the global optimal analysis strategy, adding environmental impact factors and each group of local optimal analysis strategies and photovoltaic equipment operation trends to jointly influence the optimization of the analysis strategy includes the following steps: S331, defining an objective function of the photovoltaic equipment performance maintenance target, which is used to evaluate the fitness of the analysis strategy; Specifically, the performance maintenance objectives of photovoltaic equipment are mainly to ensure the optimal operating state of the equipment, improve power generation efficiency, reduce failure rate, extend equipment life, and ensure safe and reliable power output. In order to achieve the performance maintenance objectives of photovoltaic equipment, an objective function is defined to evaluate and optimize the maintenance strategy of photovoltaic equipment. When defining the objective function, the following aspects need to be considered: Power generation efficiency: The objective function should consider the difference between the actual power generation efficiency of the photovoltaic equipment and the theoretical or expected efficiency. The closer the efficiency is to the theoretical maximum, the better.

[0065] Operational stability: includes the frequency and severity of equipment failures. The goal is to reduce the number and impact of failures.

[0066] Operation and maintenance costs: Consider the cost of maintenance activities such as cleaning, repairs, replacement of parts, etc. The goal is to minimize these costs while ensuring the performance of the equipment.

[0067] Equipment life: Consider the impact of maintenance strategies on equipment life. The ideal strategy should extend the effective service life of the equipment.

[0068] Full performance: Ensure that the operation and maintenance activities of photovoltaic equipment meet safety standards.

[0069] Environmental factors: Consider the impact of environmental changes on the performance of photovoltaic equipment, such as temperature, humidity, dust, etc.

[0070] S332, initializing the analysis strategy population (i.e., the coyote population), and randomly generating parameters for each analysis strategy (i.e., to improve the position of coyotes in the coyote optimization algorithm); S333, calculating the fitness of each analysis strategy according to the objective function, and finding the global optimal analysis strategy as the best solution; S334, randomly generating environmental impact factors for each group of optimal analysis strategies, and calculating the average parameters within each group of local optimal analysis strategies as the group population trend; Specifically, the environmental impact factor is a parameter used to simulate the impact of randomness in the natural environment on the development of coyote populations. In nature, the growth of organisms and the development of populations are not only determined by the characteristics of the organisms themselves, but also affected by environmental factors such as food supply, climate change, predator pressure, etc. The introduction of environmental impact factors in the algorithm is to imitate this natural phenomenon and increase the practical applicability and effectiveness of the algorithm.

[0071] S335, bringing the original analysis strategy parameters into the update formula, calculating the parameters of the new analysis strategy, and updating the parameters of each analysis strategy; Specifically, the updated formula constructs a new growth method for coyotes.

[0072] S336. Repeat steps S333 to S335 until the termination condition is met.

[0073] Preferably, substituting the optimized analysis strategy into Kent mapping, and comparing the analysis strategy after Kent mapping with the analysis strategy before optimization using the photovoltaic equipment power generation performance and the degree of accumulation of obstructions as evaluation criteria comprises the following steps: S341, training and iterating the analysis strategy population to obtain an optimized analysis strategy population; S342, performing data normalization processing on the optimized analysis strategy population to put it in a preset state; Specifically, normalization: Normalization is to unify the dimensions of the data to make different data comparable. Normalizing the prediction results helps to eliminate the impact of the data dimensions and facilitates subsequent weighted processing and summation calculations.

[0074] S343, randomly generate parameters of Kent mapping, and preset the value range (0, 1); S344, using the Kent mapping formula to map each optimized analysis strategy to generate a new analysis strategy individual; Specifically, each optimized analysis strategy is each grown-up coyote.

[0075] S345, comparing the fitness of each analysis strategy with its Kent mapping result, and retaining the analysis strategy individual with the best fitness as the Kent mapping analysis strategy; S346, compare the fitness of the Kent mapping analysis strategy with the original analysis strategy population, and retain the analysis strategy individuals with the best fitness to enter the next generation analysis strategy population; S347. Repeat steps S342 to S346 until the iteration termination condition is reached.

[0076] Preferably, the update formula is: ; in, Represents the parameters of the new analysis strategy after optimization; represents the parameters of the original analysis strategy; m Indicates m an analysis strategy; i Indicates i Iterations; b Indicates b The parameter value of the dimension; xa parameter vector representing the analysis strategy; l 1 represents the weight of the environmental impact factor after normalization; l 2 represents growth factor δ The weight of the random weight impact factor of 1 after normalization; l 3 represents growth factor δ The weight of the random weight influence factor of 2 after normalization.

[0077] Preferably, establishing a photovoltaic equipment operation fault anomaly database, performing anomaly detection on the feature data in the cloud platform through an anomaly detection algorithm, and inputting the detection results into the photovoltaic equipment operation fault anomaly database for fault identification includes the following steps: S41. Establishing a database of abnormal operation failures of photovoltaic equipment; S42, inputting the performance parameter data set of the photovoltaic equipment into the cloud platform, and presetting the height of the decision tree in the anomaly detection algorithm, and initializing the random forest model; S43, using the performance parameter data of the photovoltaic equipment to construct a number of decision trees to form an initial random forest model; S44, using the performance parameters of the photovoltaic equipment in normal operation as a training set to train the initial random forest model; S45. According to the difference and accuracy of decision trees, a probability search algorithm is used to select decision trees with higher fitness from the initial forest model and combine them into a new random forest model; Specifically, the precision value of each decision tree is calculated by the leave-one-out method, and the difference value between decision trees is calculated using the statistical method.

[0078] Specifically, the statistical method is Q-statistic, which is a statistical method for calculating the difference between two classifiers. In the present invention, Q-statistic is used to evaluate the degree of difference in the classification results between each two decision trees. By calculating the Q value between the decision trees, the difference between the decision trees can be obtained, and the decision tree with greater difference can be selected accordingly, thereby improving the generalization ability of the random forest.

[0079] Specifically, the probability search algorithm is a simulated annealing algorithm, which is a heuristic optimization algorithm that gradually optimizes the objective function value by simulating the cooling process during solid annealing. In the present invention, the simulated annealing algorithm is used to find the optimal decision tree combination, which comes from an initial random forest model. The fitness value of each decision tree combination is calculated based on the difference and accuracy of the decision trees. The combination with large difference and high accuracy has a larger fitness value. The simulated annealing algorithm searches for the decision tree combination with the largest fitness value in the solution space.

[0080] Specifically, according to the differences and precision of decision trees, a probability search algorithm is used to select decision trees with higher fitness from the initial forest model, and the combination into a new random forest model includes the following steps: S451, initializing the probability search algorithm, setting the initial temperature and initial solution; S452, repeating steps S563 to S566 according to the set initial temperature; S453, randomly perturbing the set initial solution (i.e., the current decision tree combination) to generate a new solution (new decision tree combination); S454, calculating the difference between the fitness value of the new solution and the fitness value of the initial solution; S455. If the fitness value of the new solution is higher than that of the initial solution (i.e., the difference is less than 0), the new solution is accepted as the initial solution. Otherwise, the acceptance probability of the new solution is calculated according to the Metropolis rule. If the acceptance probability is greater than the random number, the new solution is accepted as the initial solution. Otherwise, the initial solution is retained. S456, if the set termination condition is met, the initial solution is output as the optimal solution. The termination condition is that the new solution is not accepted in several consecutive Metropolis chains or reaches the end temperature. Otherwise, the temperature is decayed by the decay function and then the process returns to step S452; Specifically, the Metropolis rule is an acceptance-rejection criterion used in Monte Carlo simulation. The basic idea of ​​this rule is: if the new state has lower energy (or higher probability) than the current state, then accept the new state; otherwise, accept the new state with a probability that is the negative exponent of the energy difference (or probability ratio) between the new state and the current state.

[0081] S457, repeating steps S453 to S456, selecting a number of decision trees that meet the preset fitness values ​​from the initial forest model, and combining them into a new random forest model.

[0082] S46. Apply the new random forest model to the performance parameters of the photovoltaic equipment in the cloud platform, predict whether the photovoltaic equipment has a fault based on the input performance parameters, and input the prediction results into the photovoltaic equipment operation fault anomaly database to identify and record the fault.

[0083] Specifically, the anomaly detection algorithm is a data anomaly detection algorithm based on SA-iForest (subspace isolation forest), which is an improved data anomaly detection algorithm based on the isolation forest (iForest) algorithm.

[0084] Specifically, the Isolation Forest (iForest) algorithm may cause the performance of the algorithm to degrade when processing high-dimensional data. Therefore, the Subspace-based Isolation Forest (SA-iForest) algorithm is proposed. SA-iForest does not perform data segmentation on all features each time, but randomly selects a feature subspace and selects features in the subspace for segmentation. This can reduce the complexity of the algorithm on the one hand, and improve the accuracy of anomaly detection on the other hand.

[0085] Preferably, based on the historical data in the fault anomaly database and the characteristic data in the cloud platform, a fault prediction model is constructed in the cloud platform using a beamforming method and a time series analysis method, and the fault prediction model is used to predict the occurrence of a fault at the next moment, including the following steps: S51, using a polynomial regression model to analyze whether there is a trend item with a longer period in the historical data and the characteristic data, if so, removing the trend item with a longer period, if not, continuing to analyze the periodic changes in the historical data and the characteristic data; S52, according to the analysis result, performing a beam forming method on the historical data after removing the trend item and the feature data in the feature data to obtain the amplitude and phase of each frequency component; Specifically, the amplitude represents the amount of change of historical data or characteristic data at a certain frequency, and the phase represents the time lag characteristic of the change of historical data or characteristic data.

[0086] S53, using a significance test to determine whether each frequency component is significant, extracting significant periodic terms, and constructing a periodic term model; S54, the residual after eliminating the trend term and the cycle term is regarded as a random change, and a residual prediction model is constructed; S55, superimposing the polynomial regression model, the periodic term model and the residual prediction model to obtain a fault prediction model; S56, predicting the historical data and characteristic data at the next moment through the fault prediction model; S57, performing corresponding weighted processing on the predicted historical data and characteristic data and the weight value to obtain a comprehensive prediction output of the fault occurrence.

[0087] Specifically, using information gain to calculate the weight values ​​of historical data and feature data includes: Collect sample data sets of historical data and feature data; Calculate the information entropy of the target variable in the sample data set to measure the uncertainty of the target variable; Specifically, the target variable refers to a variable used to determine whether the photovoltaic power station operation and maintenance system is faulty.

[0088] For each feature, calculate the information gain between it and the target variable; The information gain value is used as the weight value of the feature and the weight value is normalized; Analyze the normalized weight values ​​to understand the importance of historical data and feature data.

[0089] Specifically, significance test: significance test is a statistical method used to test whether there is a significant difference between the observed data and a hypothesis. In time series analysis, significance test is often used to determine whether the cyclical components in the data are statistically significant. The results of significance test are usually expressed as p-values. The smaller the p-value, the more significant the difference between the observed data and the hypothesis.

[0090] Specifically, the periodic term model: The periodic term model is mainly used to describe the periodic components in time series data. In the prediction of photovoltaic power station failures, the periodic term model can help capture the periodic changes of failures on different time scales such as within a day and a week. Methods for constructing periodic term models include Fourier analysis, periodic regression, etc.

[0091] Specifically, eliminate trend terms and periodic terms: In time series analysis, data can usually be decomposed into trend terms, periodic terms, and random changes (residuals). By eliminating trend terms and periodic terms, the regular components in the data can be removed, so that random changes can be better focused. Methods for eliminating trend terms and periodic terms include differencing, filtering, etc.

[0092] Specifically, residual prediction model: The residual prediction model is used to describe the random changes (residuals) in time series data. After eliminating the trend term and the cycle term, the residual is regarded as a random change, and its fluctuation at the next moment can be estimated by constructing a residual prediction model. Commonly used residual prediction models include the autoregressive moving average model (ARIMA), the exponential smoothing model (ETS), etc.

[0093] According to another embodiment of the present invention, Figure 2As shown, a photovoltaic power station integrated intelligent operation and maintenance system based on cloud processing is also provided, and the photovoltaic power station integrated intelligent operation and maintenance system based on cloud processing includes: The data acquisition and data preprocessing module 1 is used to obtain the operating status data and parameter data of the photovoltaic power station, and preprocess the obtained operating status data and parameter data to obtain the characteristic data of the operating status data and parameter data and store them in the cloud platform; Performance evaluation module 2, used to establish a solar energy conversion efficiency model of a photovoltaic power station using cloud processing and analysis technology, and to use the solar energy conversion efficiency model to evaluate the power generation performance of photovoltaic equipment in real time; Data analysis and maintenance management module 3 is used to analyze the evaluation results of power generation performance using an analysis algorithm, determine the degree of accumulation of obstructions on the surface of the photovoltaic equipment, formulate the best cleaning cycle for the photovoltaic equipment, and clean it using automatic cleaning equipment; The abnormality database establishment and fault identification module 4 is used to establish a photovoltaic equipment operation fault abnormality database, and perform abnormality detection on the feature data in the cloud platform through an abnormality detection algorithm, and input the detection results into the photovoltaic equipment operation fault abnormality database for fault identification; The fault prediction model building module 5 is used to build a fault prediction model in the cloud platform based on the historical data in the fault anomaly database and the feature data in the cloud platform by using the beam forming method and the time series analysis method, and use the fault prediction model to predict the occurrence of the fault at the next moment; The maintenance strategy and fault prevention management module 6 is used to formulate corresponding maintenance strategies and emergency plans according to the prediction results; Among them, the data acquisition and data preprocessing module 1 is connected with the data analysis and maintenance management module 3 through the performance evaluation module 2, the data analysis and maintenance management module 3 is connected with the fault identification module 4 and the fault prediction model construction module 5 through the abnormal database establishment, and the fault prediction model construction module 5 is connected with the maintenance strategy formulation and fault prevention management module 6.

[0094] In summary, with the help of the above technical scheme of the present invention, the present invention analyzes the evaluation results of power generation performance through an analysis algorithm, so that the reasons for the reduction of power generation efficiency can be better judged, thereby enhancing the overall power generation efficiency of the photovoltaic power station, and through the correlation analysis of the degree of accumulation of obstructions and the power generation performance of the equipment, the cleaning cycle of the photovoltaic equipment can be more accurately formulated to ensure that the equipment is in the best working state and reduce maintenance costs. At the same time, by cyclically executing the optimization strategy and combining the elite retention strategy, the maintenance method can be continuously improved to ensure that the photovoltaic equipment remains efficient and stable in long-term operation, thereby improving the operating efficiency and reliability of the photovoltaic equipment, while reducing maintenance costs, and bringing long-term economic and technical benefits to the photovoltaic power station. The present invention performs anomaly detection on the feature data in the cloud platform through an anomaly detection algorithm, so that the real-time performance parameter data set is input into the cloud platform, and analyzed through a random forest model, the equipment status can be monitored in real time, so that the potential faults of the photovoltaic equipment can be more accurately identified and predicted, and false alarms and missed alarms can be reduced, thereby improving the accuracy and timeliness of fault detection, optimizing resource allocation, enhancing the stability and reliability of the photovoltaic power station, and bringing benefits to the intelligent operation and maintenance of the photovoltaic power station. The present invention uses a fault prediction model to predict possible problems in advance before a fault occurs, providing maintenance personnel with time to take preventive measures or make corresponding preparations, thereby reducing the impact of the fault on the operation of the equipment. By predicting and promptly handling potential faults, the serious decline in equipment performance can be effectively avoided, thereby increasing the service life and operating efficiency of the equipment, and further improving the efficiency of evaluating the potential of photovoltaic equipment.

[0095] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A comprehensive intelligent operation and maintenance method for photovoltaic power stations based on cloud processing, characterized in that: The photovoltaic power station integrated intelligent operation and maintenance method based on cloud processing includes the following steps: S1. Obtaining the operating status data and parameter data of the photovoltaic power station, and preprocessing the acquired operating status data and parameter data to obtain characteristic data of the operating status data and parameter data and store them in the cloud platform; S2. Use cloud processing and analysis technology to establish a solar energy conversion efficiency model for photovoltaic power plants, and use the solar energy conversion efficiency model to evaluate the power generation performance of photovoltaic equipment in real time; S3. Analyze the evaluation results of power generation performance using an analytical algorithm, determine the degree of accumulation of obstructions on the surface of the photovoltaic equipment, formulate an optimal cleaning cycle for the photovoltaic equipment, and clean it using automatic cleaning equipment; S4. Establish a photovoltaic equipment operation fault anomaly database, and perform anomaly detection on the feature data in the cloud platform through an anomaly detection algorithm, and input the detection results into the photovoltaic equipment operation fault anomaly database for fault identification; S5. Based on the historical data in the fault anomaly database and the characteristic data in the cloud platform, a fault prediction model is constructed in the cloud platform using the beamforming method and the time series analysis method, and the fault prediction model is used to predict the occurrence of the fault at the next moment; S6. Develop corresponding maintenance strategies and emergency plans based on the prediction results.

2. According to claim 1, a photovoltaic power station comprehensive intelligent operation and maintenance method based on cloud processing is characterized in that: The step of obtaining the operating status data and parameter data of the photovoltaic power station, preprocessing the obtained operating status data and parameter data, obtaining characteristic data of the operating status data and parameter data and storing them in the cloud platform includes the following steps: S11, collecting duplicate data, missing values ​​and abnormal values ​​of the acquired operating status data and parameter data, and performing denoising, filtering and smoothing on the duplicate data, missing values ​​and abnormal values; S12, performing data verification on the operation status data and parameter data after denoising, filtering and smoothing, extracting valid data, and performing normalization processing to generate accurate operation status data and parameter data; S13, using principal component analysis to merge the generated accurate operating status data and parameter data into the same data set; S14. Extract relevant features from the fused data set to obtain feature data of the operating status data and parameter data, and store them in the cloud platform.

3. The photovoltaic power station integrated intelligent operation and maintenance method based on cloud processing according to claim 1 is characterized in that: The method of using cloud processing and analysis technology to establish a solar energy conversion efficiency model for a photovoltaic power station and using the solar energy conversion efficiency model to evaluate the power generation performance of photovoltaic equipment in real time includes the following steps: S21. Analyze the operating status data of photovoltaic equipment using cloud processing and analysis technology, and extract features related to photovoltaic modules; S22, converting the extracted relevant features into photovoltaic module characteristics and photoelectric conversion principles, and constructing a solar energy conversion efficiency model; S23, estimating parameter values ​​in the solar energy conversion efficiency model by fitting the actually measured power generation and irradiance data with the constructed solar energy conversion efficiency model; S24. Use the established solar energy conversion efficiency model to calculate the actual power generation efficiency of the photovoltaic equipment, and compare the actual power generation efficiency with the expected efficiency to evaluate the power generation performance of the photovoltaic equipment.

4. A photovoltaic power station integrated intelligent operation and maintenance method based on cloud processing according to claim 3, characterized in that: The method of analyzing the evaluation results of power generation performance by using an analysis algorithm, determining the degree of accumulation of obstructions on the surface of the photovoltaic equipment, formulating the optimal cleaning cycle of the photovoltaic equipment, and cleaning the photovoltaic equipment by using an automatic cleaning device includes the following steps: S31, importing the actual power generation efficiency and expected efficiency, initializing, and using the shortest path algorithm to calculate the degree of accumulation of obstructions between any two detection points on the surface of the photovoltaic device; S32, establishing a number of analysis strategies, each of which represents a correlation analysis method between the degree of accumulation of obstructions and the power generation performance of the equipment, the first N numbers represent the numbers of the selected detection points, and the last N numbers represent the corresponding power generation performance level of the photovoltaic equipment; S33, according to the preset photovoltaic equipment performance maintenance target, find the global optimal analysis strategy, add environmental impact factors and each group of local optimal analysis strategies and photovoltaic equipment operation trends to jointly influence the optimization of the analysis strategy; S34, substituting the optimized analysis strategy into Kent mapping, and comparing the analysis strategy after Kent mapping with the analysis strategy before optimization using the photovoltaic equipment power generation performance and the degree of accumulation of obstructions as evaluation criteria; S35, using the elite retention strategy and replacing the worst analysis strategy with the global suboptimal analysis strategy according to the photovoltaic equipment performance maintenance target; S36, looping through steps S33 to S35, and if the number of iterations exceeds a threshold, terminating the iterations, and obtaining the best judgment method for evaluating the power generation performance of the photovoltaic device and the degree of accumulation of obstructions; S37. According to the best judgment method, formulate the best cleaning cycle for the photovoltaic equipment, and use automatic cleaning equipment to clean it.

5. A photovoltaic power station integrated intelligent operation and maintenance method based on cloud processing according to claim 4, characterized in that: The method of finding the global optimal analysis strategy according to the preset photovoltaic equipment performance maintenance target, adding environmental impact factors and each group of local optimal analysis strategies and photovoltaic equipment operation trends to jointly influence the optimization of the analysis strategy includes the following steps: S331, defining an objective function of the photovoltaic equipment performance maintenance target, which is used to evaluate the fitness of the analysis strategy; S332, initializing the analysis strategy population, and randomly generating parameters for each analysis strategy; S333, calculating the fitness of each analysis strategy according to the objective function, and finding the global optimal analysis strategy as the best solution; S334, randomly generating environmental impact factors for each group of optimal analysis strategies, and calculating the average parameters within each group of local optimal analysis strategies as the group population trend; S335, bringing the original analysis strategy parameters into the update formula, calculating the parameters of the new analysis strategy, and updating the parameters of each analysis strategy; S336. Repeat steps S333 to S335 until the termination condition is met.

6. A photovoltaic power station integrated intelligent operation and maintenance method based on cloud processing according to claim 5, characterized in that: Substituting the optimized analysis strategy into the Kent mapping, and comparing the analysis strategy after the Kent mapping with the analysis strategy before the optimization using the photovoltaic equipment power generation performance and the degree of accumulation of obstructions as evaluation criteria, comprises the following steps: S341, training and iterating the analysis strategy population to obtain an optimized analysis strategy population; S342, performing data normalization processing on the optimized analysis strategy population to put it in a preset state; S343, randomly generate parameters of Kent mapping and preset a value range; S344, using the Kent mapping formula to map each optimized analysis strategy to generate a new analysis strategy individual; S345, comparing the fitness of each analysis strategy with its Kent mapping result, and retaining the analysis strategy individual with the best fitness as the Kent mapping analysis strategy; S346, compare the fitness of the Kent mapping analysis strategy with the original analysis strategy population, and retain the analysis strategy individuals with the best fitness to enter the next generation analysis strategy population; S347. Repeat steps S342 to S346 until the iteration termination condition is reached.

7. A photovoltaic power station integrated intelligent operation and maintenance method based on cloud processing according to claim 6, characterized in that: The update formula is: ； in, Represents the parameters of the new analysis strategy after optimization; represents the parameters of the original analysis strategy; m Indicates m an analysis strategy; i Indicates i Iterations; b Indicates b The parameter value of the dimension; x a parameter vector representing the analysis strategy; l 1 represents the weight of the environmental impact factor after normalization; l 2 represents growth factor δ The weight of the random weight impact factor of 1 after normalization; l 3 represents growth factor δ The weight of the random weight influence factor of 2 after normalization.

8. The photovoltaic power station integrated intelligent operation and maintenance method based on cloud processing according to claim 1, characterized in that: The step of establishing a photovoltaic equipment operation fault anomaly database, performing anomaly detection on feature data in the cloud platform using an anomaly detection algorithm, and inputting the detection results into the photovoltaic equipment operation fault anomaly database for fault identification includes the following steps: S41. Establishing a database of abnormal operation failures of photovoltaic equipment; S42, inputting the performance parameter data set of the photovoltaic equipment into the cloud platform, and presetting the height of the decision tree in the anomaly detection algorithm, and initializing the random forest model; S43, using the performance parameter data of the photovoltaic equipment to construct a number of decision trees to form an initial random forest model; S44, using the performance parameters of the photovoltaic equipment in normal operation as a training set to train the initial random forest model; S45. According to the difference and accuracy of decision trees, a probability search algorithm is used to select decision trees with higher fitness from the initial forest model and combine them into a new random forest model; S46. Apply the new random forest model to the performance parameters of the photovoltaic equipment in the cloud platform, predict whether the photovoltaic equipment has a fault based on the input performance parameters, and input the prediction results into the photovoltaic equipment operation fault anomaly database to identify and record the fault.

9. A photovoltaic power station integrated intelligent operation and maintenance method based on cloud processing according to claim 8, characterized in that: The method of constructing a fault prediction model in the cloud platform based on the historical data in the fault anomaly database and the characteristic data in the cloud platform by using the beamforming method and the time series analysis method, and predicting the occurrence of a fault at the next moment by using the fault prediction model includes the following steps: S51, using a polynomial regression model to analyze whether there is a trend item with a longer period in the historical data and the characteristic data, if so, removing the trend item with a longer period, if not, continuing to analyze the periodic changes in the historical data and the characteristic data; S52, according to the analysis result, performing a beam forming method on the historical data after removing the trend item and the feature data in the feature data to obtain the amplitude and phase of each frequency component; S53, using a significance test to determine whether each frequency component is significant, extracting significant periodic terms, and constructing a periodic term model; S54, the residual after eliminating the trend term and the cycle term is regarded as a random change, and a residual prediction model is constructed; S55, superimposing the polynomial regression model, the periodic term model and the residual prediction model to obtain a fault prediction model; S56, predicting the historical data and characteristic data at the next moment through the fault prediction model; S57, performing corresponding weighted processing on the predicted historical data and characteristic data and the weight value to obtain a comprehensive prediction output of the fault occurrence.

10. A photovoltaic power station integrated intelligent operation and maintenance system based on cloud processing, used to implement the photovoltaic power station integrated intelligent operation and maintenance method based on cloud processing according to any one of claims 1 to 9, characterized in that: The cloud-based integrated intelligent operation and maintenance system for photovoltaic power plants includes: The data acquisition and data preprocessing module is used to obtain the operating status data and parameter data of the photovoltaic power station, and preprocess the acquired operating status data and parameter data to obtain the characteristic data of the operating status data and parameter data and store them in the cloud platform; A performance evaluation module is used to establish a solar energy conversion efficiency model of a photovoltaic power station using cloud processing and analysis technology, and to use the solar energy conversion efficiency model to evaluate the power generation performance of photovoltaic equipment in real time; The data analysis and maintenance management module is used to analyze the evaluation results of power generation performance using analytical algorithms, determine the degree of accumulation of obstructions on the surface of photovoltaic equipment, formulate the best cleaning cycle for photovoltaic equipment, and clean it using automatic cleaning equipment; The abnormal database establishment and fault identification module is used to establish a photovoltaic equipment operation fault abnormality database, and perform abnormality detection on the feature data in the cloud platform through an abnormality detection algorithm, and input the detection results into the photovoltaic equipment operation fault abnormality database for fault identification; A fault prediction model building module is used to build a fault prediction model in the cloud platform based on the historical data in the fault anomaly database and the feature data in the cloud platform using the beamforming method and the time series analysis method, and use the fault prediction model to predict the occurrence of a fault at the next moment; Formulate maintenance strategy and fault prevention management module, which is used to formulate corresponding maintenance strategy and emergency plan according to the prediction results; Among them, the data acquisition and data preprocessing module is connected with the data analysis and maintenance management module through the performance evaluation module, the data analysis and maintenance management module is connected with the fault identification module and the fault prediction model construction module through the abnormal database establishment, and the fault prediction model construction module is connected with the maintenance strategy formulation and fault prevention management module.

Images