Intelligent tracking method of solar photovoltaic panels based on power generation dynamic data
Through intelligent tracking methods based on dynamic data of power generation, photovoltaic sub-regions are divided, clustered and data analysis are performed, and the optimal tracking solution is selected, which solves the problems of low energy conversion efficiency and low monitoring efficiency of traditional photovoltaic panel tracking systems, and realizes photovoltaics Efficient tracking and fault warning of the panel.
Patent Information
- Application Number
- CN202411272103.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-11
- Publication Date
- 2024-11-15
- Estimated Expiration
- 2044-09-11
AI Technical Summary
Traditional photovoltaic panel tracking systems cannot flexibly adjust according to actual environmental characteristics and panel power generation characteristics, resulting in low energy conversion efficiency. The existing monitoring methods rely on manual inspection, which are inefficient and slow response.
Based on dynamic data of power generation, by dividing photovoltaic sub-regions, collecting environment and dynamic data, clustering and data analysis, screening out the optimal tracking scheme, and realizing intelligent tracking and fault warning of photovoltaic panels.
It improves the adaptability and efficiency of photovoltaic power generation systems in complex environments, realizes accurate tracking and fault warning of photovoltaic panels, and reduces the dependence of manual inspections.
Smart Images

Figure CN118778708B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of photovoltaic power generation, and more specifically, to a solar photovoltaic panel intelligent tracking method based on power generation dynamic data. Background Art
[0002] As the global demand for clean energy grows, solar photovoltaic power generation, as an important form of renewable energy, is becoming increasingly important. However, in practical applications, traditional photovoltaic panel tracking systems mostly rely on fixed tilt settings or simple sun position tracking mechanisms, which cannot be flexibly adjusted according to actual environmental characteristics and panel power generation characteristics, resulting in low energy conversion efficiency.
[0003] In order to solve the above problems, a variety of intelligent tracking systems have emerged in recent years, but most systems can only achieve simple angle adjustment and lack the ability to deeply mine and analyze data. There is a lack of regional characteristic analysis of different power generation areas, and a lack of precise and intelligent photovoltaic power generation tracking and analysis of photovoltaic power generation areas with different power generation characteristics. At the same time, for dynamic defects or failures of photovoltaic panels, existing monitoring methods often rely on manual inspections, which have problems such as low efficiency and slow response. Therefore, it is of great practical significance and application value to develop a method and system for intelligent tracking of solar photovoltaic panels based on dynamic power generation data and comprehensive use of multiple information technologies. Summary of the invention
[0004] The present invention overcomes the defects of the prior art and proposes a solar photovoltaic panel intelligent tracking method based on power generation dynamic data.
[0005] A first aspect of the present invention provides a solar photovoltaic panel intelligent tracking method based on power generation dynamic data, comprising:
[0006] In the photovoltaic power generation area, multiple photovoltaic sub-areas are divided based on the number distribution of photovoltaic panels;
[0007] Within a preset time period, environmental data and power generation dynamic data of each photovoltaic sub-area are collected, and data feature vectors are quantified based on the environmental data and power generation dynamic data to form environmental features and dynamic power generation features;
[0008] By presetting the clustering model, the environmental characteristics and dynamic power generation characteristics are used as clustering sample data to cluster multiple photovoltaic sub-areas. Each photovoltaic sub-area is used as a clustering unit. The clustering process performs similarity analysis based on the two data dimensions of environmental characteristics and dynamic power generation characteristics, and sets the analysis weights corresponding to the two data dimensions. After clustering, multiple photovoltaic area groups are obtained.
[0009] Mark a current photovoltaic area group, set multiple photovoltaic panel tracking schemes, divide a preset power generation cycle into multiple time periods, apply multiple photovoltaic panel tracking schemes to different time periods, collect the power generation dynamic data of all photovoltaic panels in the current photovoltaic area group based on different time periods, and analyze the changes of the power generation dynamic data based on the three dimensions of current, voltage and power generation to form a dynamic data change curve, compare the difference between the dynamic data change curve and the expected change curve, and screen out the optimal photovoltaic panel angle scheme for different time periods;
[0010] Based on the time sequence, the optimal photovoltaic panel solutions in different time periods are integrated to form a preferred tracking plan for a preset power generation cycle, and multiple preferred tracking plans are generated based on multiple photovoltaic area groups.
[0011] In this solution, the photovoltaic power generation area is divided into multiple photovoltaic sub-areas based on the number distribution of photovoltaic panels, specifically:
[0012] Obtaining the number and location information of photovoltaic panels in the photovoltaic power generation area;
[0013] The distribution of photovoltaic panels is analyzed based on the number and location information of photovoltaic panels. Based on the distribution status, the photovoltaic power generation area is divided into multiple photovoltaic sub-areas.
[0014] In the plurality of photovoltaic sub-areas, it is ensured that the difference in the number of photovoltaic panels between every two photovoltaic sub-areas is within a preset range.
[0015] In this solution, the environmental data and power generation dynamic data of each photovoltaic sub-area are collected within a preset time period, and data feature vectors are quantized based on the environmental data and power generation dynamic data to form environmental features and dynamic power generation features, specifically:
[0016] Collect environmental data and power generation dynamic data of each photovoltaic sub-area within a preset time period;
[0017] The environmental data include temperature, light intensity, and light time parameters, and the power generation dynamic data include current, voltage, and power generation parameters;
[0018] Environmental data and power generation dynamic data are vectorized based on different parameter dimensions to form environmental characteristics and dynamic power generation characteristics.
[0019] In this scheme, the clustering model is preset, and the environmental characteristics and dynamic power generation characteristics are used as clustering sample data to cluster multiple photovoltaic sub-areas. Each photovoltaic sub-area is used as a clustering unit. The clustering process is based on the two data dimensions of environmental characteristics and dynamic power generation characteristics. Similarity analysis is performed, and the analysis weights corresponding to the two data dimensions are set. After clustering, multiple photovoltaic area groups are obtained, specifically:
[0020] Construct a clustering model based on Dbscan and set the radiation radius of the sample points;
[0021] The environmental characteristics and dynamic power generation characteristics of each photovoltaic sub-area are imported into cluster grouping and used as cluster sample data, and each photovoltaic sub-area is used as a clustering unit for clustering;
[0022] In the clustering process, similarity analysis is performed based on the two data dimensions of environmental characteristics and dynamic power generation characteristics of each photovoltaic sub-region. The similarity analysis process is to calculate the sample distance of environmental characteristics and dynamic power generation characteristics between two photovoltaic sub-regions. The distance calculation is based on the standard Euclidean distance, and two distance values are obtained. Two similarities are obtained based on the two distance values, and the analysis weights corresponding to the two data dimensions are set. The two similarities are weighted averaged according to the analysis weights, and the similarity between the two photovoltaic sub-regions is obtained;
[0023] Clustering is performed based on the similarity between clustered sample data, and multiple photovoltaic region groups are finally formed.
[0024] In this scheme, a current photovoltaic area group is marked, multiple photovoltaic panel tracking schemes are set, multiple time periods are divided in a preset power generation cycle, and multiple photovoltaic panel tracking schemes are applied to different time periods respectively. Based on different time periods, the power generation dynamic data of all photovoltaic panels in the current photovoltaic area group are collected and the power generation dynamic data is analyzed based on the three dimensions of current, voltage, and power generation to form a dynamic data change curve. The dynamic data change curve is compared with the expected change curve, and the optimal photovoltaic panel angle scheme for different time periods is selected, specifically:
[0025] Mark a photovoltaic region group as the current photovoltaic region group;
[0026] Set multiple photovoltaic panel tracking schemes based on the type and quantity of photovoltaic panels in the current photovoltaic area group;
[0027] Divide a preset power generation cycle into multiple time periods, and apply multiple sets of photovoltaic panel tracking solutions to the photovoltaic area group in each time period;
[0028] Taking a time period as the analysis unit, the power generation dynamic data of all photovoltaic panels in the current photovoltaic area group is collected and the linear change analysis of the power generation dynamic data is performed based on the three dimensions of current, voltage and power generation to form a dynamic data change curve;
[0029] The dynamic data change curves include three change curves of current, voltage and power generation;
[0030] The dynamic data change curve is compared with the expected change curve. The comparison process is based on the linear growth rate of the change curve and the difference analysis of the average value. Three difference values are obtained based on the change curves of the three dimensions of current, voltage and power generation. The three difference values are averaged to obtain the change difference degree.
[0031] According to the variation difference of each photovoltaic panel tracking scheme, the optimal photovoltaic panel tracking scheme within a time period is selected and marked as the optimal photovoltaic panel angle scheme;
[0032] Based on multiple time periods, the optimal photovoltaic panel angle solutions for different time periods are screened out.
[0033] In this solution, the optimal photovoltaic panel solutions in different time periods are integrated based on the time sequence to form a preferred tracking solution for a preset power generation cycle, and multiple preferred tracking solutions are generated based on multiple photovoltaic area groups, specifically:
[0034] Based on the time sequence, the optimal photovoltaic panel solutions in different time periods are integrated to form a preferred tracking plan for a preset power generation cycle, and the preferred tracking plan is applied to the current photovoltaic area group;
[0035] A plurality of preferred tracking schemes are generated based on the plurality of photovoltaic region groups, and the plurality of preferred tracking schemes are applied to different photovoltaic region groups in the next preset power generation cycle.
[0036] The second aspect of the present invention further provides a solar photovoltaic panel intelligent tracking system based on power generation dynamic data, the system comprising: a memory, a processor, the memory comprising a solar photovoltaic panel intelligent tracking program based on power generation dynamic data, the solar photovoltaic panel intelligent tracking program based on power generation dynamic data when executed by the processor implements the following steps:
[0037] In the photovoltaic power generation area, multiple photovoltaic sub-areas are divided based on the number distribution of photovoltaic panels;
[0038] Within a preset time period, environmental data and power generation dynamic data of each photovoltaic sub-area are collected, and data feature vectors are quantified based on the environmental data and power generation dynamic data to form environmental features and dynamic power generation features;
[0039] By presetting the clustering model, the environmental characteristics and dynamic power generation characteristics are used as clustering sample data to cluster multiple photovoltaic sub-areas. Each photovoltaic sub-area is used as a clustering unit. The clustering process performs similarity analysis based on the two data dimensions of environmental characteristics and dynamic power generation characteristics, and sets the analysis weights corresponding to the two data dimensions. After clustering, multiple photovoltaic area groups are obtained.
[0040] Mark a current photovoltaic area group, set multiple photovoltaic panel tracking schemes, divide a preset power generation cycle into multiple time periods, apply multiple photovoltaic panel tracking schemes to different time periods, collect the power generation dynamic data of all photovoltaic panels in the current photovoltaic area group based on different time periods, and analyze the changes of the power generation dynamic data based on the three dimensions of current, voltage and power generation to form a dynamic data change curve, compare the difference between the dynamic data change curve and the expected change curve, and screen out the optimal photovoltaic panel angle scheme for different time periods;
[0041] Based on the time sequence, the optimal photovoltaic panel solutions in different time periods are integrated to form a preferred tracking plan for a preset power generation cycle, and multiple preferred tracking plans are generated based on multiple photovoltaic area groups.
[0042] The third aspect of the present invention also provides a computer-readable storage medium, which includes a solar photovoltaic panel intelligent tracking program based on power generation dynamic data. When the solar photovoltaic panel intelligent tracking program based on power generation dynamic data is executed by a processor, the steps of the solar photovoltaic panel intelligent tracking method based on power generation dynamic data as described in any of the above items are implemented.
[0043] The present invention discloses a solar photovoltaic panel intelligent tracking method based on power generation dynamic data. By dividing a photovoltaic power generation area into multiple photovoltaic sub-areas, clustering is performed based on a preset clustering model using the environmental characteristics and dynamic power generation characteristics of the sub-areas as clustering sample data to obtain multiple photovoltaic areas. For the photovoltaic areas, multiple time periods are divided in a preset power generation cycle, and multiple sets of photovoltaic panel tracking schemes are applied to different time periods respectively. Based on different time periods, the dynamic data change curve is compared with the expected change curve, and the optimal photovoltaic panel angle schemes for different time periods are screened and combined to form a preferred tracking scheme. Through the present invention, it is possible to effectively perform regional feature analysis on photovoltaic power generation sites and realize photovoltaic optimization tracking in different areas, thereby improving the adaptability of photovoltaic power generation systems in complex environments and photovoltaic power generation efficiency. BRIEF DESCRIPTION OF THE DRAWINGS
[0044] Figure 1 A flow chart of a solar photovoltaic panel intelligent tracking method based on power generation dynamic data of the present invention is shown;
[0045] Figure 2 A block diagram of a solar photovoltaic panel intelligent tracking system based on power generation dynamic data of the present invention is shown. DETAILED DESCRIPTION
[0046] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.
[0047] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.
[0048] Example 1
[0049] Figure 1 A flow chart of a solar photovoltaic panel intelligent tracking method based on power generation dynamic data of the present invention is shown.
[0050] like Figure 1 As shown, the first aspect of the present invention provides a solar photovoltaic panel intelligent tracking method based on power generation dynamic data, comprising:
[0051] S102, in the photovoltaic power generation area, dividing a plurality of photovoltaic sub-areas based on the number distribution of photovoltaic panels;
[0052] S104, collecting environmental data and power generation dynamic data of each photovoltaic sub-area within a preset time period, and quantizing data features based on the environmental data and the power generation dynamic data to form environmental features and dynamic power generation features;
[0053] S106, by using a preset clustering model, taking environmental characteristics and dynamic power generation characteristics as clustering sample data, clustering and grouping multiple photovoltaic sub-areas, taking each photovoltaic sub-area as a clustering unit, and performing similarity analysis based on the two data dimensions of environmental characteristics and dynamic power generation characteristics in the clustering process, and setting analysis weights corresponding to the two data dimensions, and obtaining multiple photovoltaic area groups after clustering is completed;
[0054] S108, marking a current photovoltaic area group, setting multiple photovoltaic panel tracking schemes, dividing a preset power generation cycle into multiple time periods, applying the multiple photovoltaic panel tracking schemes to different time periods respectively, collecting power generation dynamic data of all photovoltaic panels in the current photovoltaic area group based on different time periods, and performing change analysis on the power generation dynamic data based on three dimensions of current, voltage, and power generation to form a dynamic data change curve, performing a difference comparison between the dynamic data change curve and the expected change curve, and screening out the optimal photovoltaic panel angle schemes for different time periods;
[0055] S110, based on the time sequence, the optimal photovoltaic panel solutions in different time periods are integrated to form a preferred tracking solution for a preset power generation cycle, and multiple preferred tracking solutions are generated based on multiple photovoltaic area groups.
[0056] The expected change curve is an idealized data change curve, which is used for data change comparison.
[0057] According to an embodiment of the present invention, in the photovoltaic power generation area, a plurality of photovoltaic sub-areas are divided based on the number distribution of photovoltaic panels, specifically:
[0058] Obtaining the number and location information of photovoltaic panels in the photovoltaic power generation area;
[0059] The distribution of photovoltaic panels is analyzed based on the number and location information of photovoltaic panels. Based on the distribution status, the photovoltaic power generation area is divided into multiple photovoltaic sub-areas.
[0060] In the plurality of photovoltaic sub-areas, it is ensured that the difference in the number of photovoltaic panels between every two photovoltaic sub-areas is within a preset range.
[0061] It should be noted that in a photovoltaic power generation area, there are often multiple photovoltaic panels, and the environment and lighting where the photovoltaic panels and related equipment are located have certain differences. Therefore, the present invention divides the area into multiple sub-areas, each of which contains a certain number of photovoltaic devices, which is the minimum analysis unit. The sub-areas are then clustered based on relevant feature data to form corresponding area groups.
[0062] According to an embodiment of the present invention, the environmental data and power generation dynamic data of each photovoltaic sub-area are collected within a preset time period, and data feature vectorization is performed based on the environmental data and the power generation dynamic data to form environmental features and dynamic power generation features, specifically:
[0063] Collect environmental data and power generation dynamic data of each photovoltaic sub-area within a preset time period;
[0064] The environmental data include temperature, light intensity, and light time parameters, and the power generation dynamic data include current, voltage, and power generation parameters;
[0065] Environmental data and power generation dynamic data are vectorized based on different parameter dimensions to form environmental characteristics and dynamic power generation characteristics.
[0066] It should be noted that the preset time period is a relatively long period, during which corresponding photovoltaic data is collected for power generation and environmental characteristics analysis. In the environmental characteristics and dynamic power generation characteristics, corresponding feature vectors are included. The feature vectors include multiple dimensions, and the value of each dimension corresponds to the corresponding parameter value, such as temperature, light intensity, and light time parameters. A multi-dimensional feature vector is formed based on multiple parameter values.
[0067] According to an embodiment of the present invention, a clustering model is preset, and environmental characteristics and dynamic power generation characteristics are used as clustering sample data to cluster multiple photovoltaic sub-areas, and each photovoltaic sub-area is used as a clustering unit. The clustering process performs similarity analysis based on the two data dimensions of environmental characteristics and dynamic power generation characteristics, and sets the analysis weights corresponding to the two data dimensions. After clustering, multiple photovoltaic area groups are obtained, specifically:
[0068] Construct a clustering model based on Dbscan and set the radiation radius of the sample points;
[0069] The environmental characteristics and dynamic power generation characteristics of each photovoltaic sub-area are imported into cluster grouping and used as cluster sample data, and each photovoltaic sub-area is used as a clustering unit for clustering;
[0070] In the clustering process, similarity analysis is performed based on the two data dimensions of environmental characteristics and dynamic power generation characteristics of each photovoltaic sub-region. The similarity analysis process is to calculate the sample distance of environmental characteristics and dynamic power generation characteristics between two photovoltaic sub-regions. The distance calculation is based on the standard Euclidean distance, and two distance values are obtained. Two similarities are obtained based on the two distance values, and the analysis weights corresponding to the two data dimensions are set. The two similarities are weighted averaged according to the analysis weights, and the similarity between the two photovoltaic sub-regions is obtained;
[0071] Clustering is performed based on the similarity between clustered sample data, and multiple photovoltaic region groups are finally formed.
[0072] It should be noted that the preset clustering model adopts the Dbscan algorithm, which is specifically a density-based spatial clustering algorithm. When calculating the spatial distance between two data, two data dimensions, environmental characteristics and dynamic power generation characteristics, are introduced for analysis, and the similarity is reflected by the distance value. The smaller the distance value, the greater the similarity between the two sets of data. At the same time, the preset weight is set to judge the comprehensive similarity. The distance value is inversely proportional to the similarity.
[0073] It is worth mentioning that in the process of clustering areas of the present invention, preset analysis weights are introduced, and the similarity of the two dimensions of environmental characteristics and dynamic power generation characteristics is calculated and the similarity is calculated according to the weight ratio. Based on the actual photovoltaic power generation situation, the system can dynamically adjust the preset analysis weights to dynamically adjust the clustering data focused on by the clustering area. For example, in a certain photovoltaic power generation area, its dynamic power generation characteristics vary greatly, and the environmental characteristics of each area are relatively consistent. At this time, similar clustering analysis can be performed by increasing the analysis weight of the dynamic power generation characteristics to obtain the expected clustering results, which can realize precise tracking scheme evaluation and optimization screening combination in the subsequent period.
[0074] According to an embodiment of the present invention, a current photovoltaic area group is marked, multiple photovoltaic panel tracking schemes are set, multiple time periods are divided in a preset power generation cycle, and multiple photovoltaic panel tracking schemes are applied to different time periods respectively. Based on different time periods, the power generation dynamic data of all photovoltaic panels in the current photovoltaic area group are collected and the power generation dynamic data is analyzed based on the three dimensions of current, voltage, and power generation to form a dynamic data change curve. The dynamic data change curve is compared with the expected change curve, and the optimal photovoltaic panel angle scheme for different time periods is screened out, specifically:
[0075] Mark a photovoltaic region group as the current photovoltaic region group;
[0076] Set multiple photovoltaic panel tracking schemes based on the type and quantity of photovoltaic panels in the current photovoltaic area group;
[0077] Divide a preset power generation cycle into multiple time periods, and apply multiple sets of photovoltaic panel tracking solutions to the photovoltaic area group in each time period;
[0078] Taking a time period as the analysis unit, the power generation dynamic data of all photovoltaic panels in the current photovoltaic area group is collected and the linear change analysis of the power generation dynamic data is performed based on the three dimensions of current, voltage and power generation to form a dynamic data change curve;
[0079] The dynamic data change curves include three change curves of current, voltage and power generation;
[0080] The dynamic data change curve is compared with the expected change curve. The comparison process is based on the linear growth rate of the change curve and the difference analysis of the average value. Three difference values are obtained based on the change curves of the three dimensions of current, voltage and power generation. The three difference values are averaged to obtain the change difference degree.
[0081] According to the variation difference of each photovoltaic panel tracking scheme, the optimal photovoltaic panel tracking scheme within a time period is selected and marked as the optimal photovoltaic panel angle scheme;
[0082] Based on multiple time periods, the optimal photovoltaic panel angle solutions for different time periods are screened out.
[0083] It should be noted that the multiple sets of photovoltaic panel tracking schemes are specifically preset schemes, which can be tracking according to light intensity, setting different angles according to power generation efficiency, and setting different angles according to panel temperature. Different schemes have different power generation efficiency results, and each has its own advantages under complex environmental conditions and in different time periods. Therefore, the present invention clusters the corresponding power generation areas, and further divides the areas that meet the expected similarities into a group. Taking the regional group as a unit, multiple preset schemes are evaluated for discovery efficiency in multiple time periods. The optimal schemes corresponding to different time periods are screened out through the evaluation results. Based on the multiple optimal schemes and the time period parameters, the schemes are integrated to form the optimal integrated scheme for a power generation cycle, thereby improving the efficient, precise control and intelligent tracking control of multiple photovoltaic panel areas in complex environments. The method divides a preset power generation cycle into multiple time periods, and applies multiple photovoltaic panel tracking solutions to the photovoltaic regional group in each time period. Specifically, for different time periods, multiple solutions are applied to different panels in the photovoltaic regional group, and after the end of the time period, the corresponding power dynamic data is collected to analyze the change curve, and compared with the expected curve to screen out the preferred tracking solution for the time period. Since the photovoltaic panels in the regional group have similar environmental and power generation characteristics, the preferred solution for the time period can be applied to all photovoltaic panels in the regional group after it is selected.
[0084] In a time period, within the current photovoltaic area group, each set of photovoltaic panel tracking solutions is applied to different panels within the group, and each set of photovoltaic panel tracking solutions obtains a corresponding independent dynamic data change curve.
[0085] According to an embodiment of the present invention, the optimal photovoltaic panel solutions in different time periods are integrated based on the time sequence to form a preferred tracking solution for a preset power generation cycle, and multiple preferred tracking solutions are generated based on multiple photovoltaic area groups, specifically:
[0086] Based on the time sequence, the optimal photovoltaic panel solutions in different time periods are integrated to form a preferred tracking plan for a preset power generation cycle, and the preferred tracking plan is applied to the current photovoltaic area group;
[0087] A plurality of preferred tracking schemes are generated based on the plurality of photovoltaic region groups, and the plurality of preferred tracking schemes are applied to different photovoltaic region groups in the next preset power generation cycle.
[0088] According to an embodiment of the present invention, it also includes:
[0089] In the current photovoltaic area group, select a photovoltaic panel and mark it as the current photovoltaic panel;
[0090] In a preset power generation cycle, the power generation dynamic data of the current photovoltaic panel is collected and the data is serialized based on the time dimension to form first time series data;
[0091] In a preset power generation cycle, the power generation dynamic data of the current photovoltaic area group is serialized based on the time dimension to form second time series data;
[0092] Build an ARIMA-based forecasting model;
[0093] Serialize the historical dynamic power generation data of the photovoltaic power generation area to form historical time series data;
[0094] Import the historical time series data into the forecasting model, generate the corresponding autocorrelation graph and partial autocorrelation graph through the historical time series, and determine the p, d and q parameters of the forecasting model;
[0095] p represents the autoregressive order of the time series, d represents the difference order of the time series, and q represents the moving average order of the time series;
[0096] After the parameters are determined, the prediction model is trained through historical time series data, the model accuracy is evaluated based on the root mean square error, and the prediction model is optimized;
[0097] Importing the first time series data and the second time series data into the prediction model for prediction, setting the prediction period, and obtaining the first prediction result data and the second prediction result data;
[0098] Generating individual change curves based on current, voltage, and power generation according to the first prediction result data;
[0099] Generate an overall change curve based on current, voltage, and power generation according to the second prediction result data;
[0100] Through the individual change curve and the overall change curve, analyze whether the individual change trend deviates from the overall change trend of the photovoltaic area group. The analysis is based on the difference of the linear change rate and the preset difference range. If the analysis determines that the individual change trend deviates from the overall change trend, the current photovoltaic panel is marked as a warning device;
[0101] The photovoltaic panels of all photovoltaic area groups are analyzed and it is determined whether the current number of warning devices is greater than the warning threshold. If so, a photovoltaic equipment maintenance plan is generated based on the warning devices and the photovoltaic area groups in which they are located.
[0102] It should be noted that the prediction result data is specifically predicted dynamic power generation data, including current, voltage, power generation and other data.
[0103] Through the method of the present invention, the changing trend of the power generation characteristics of the photovoltaic panel can be effectively explored, and the power generation quality can be predicted by using a specific prediction model (such as the ARIMA model combined with time series source data), and the difference of a certain panel in the preset regional group can be evaluated based on the prediction result, that is, the overall power generation characteristic difference within the individual power generation characteristic regional group, so as to effectively realize the fault early warning evaluation based on the power generation change characteristics, and have a certain foresight and prediction ability in fault analysis. Compared with the comparison based on the acquisition of real-time numerical values in the traditional technology, the method of the present invention effectively improves the accuracy of fault and maintenance analysis, and reasonably evaluates the abnormal working changes of the photovoltaic panel through the prediction data, so as to realize the setting of the maintenance plan for the photovoltaic panel in advance, and greatly improve the precision quality control and operation process optimization of photovoltaic power generation.
[0104] Example 2
[0105] Figure 2 A block diagram of a solar photovoltaic panel intelligent tracking system based on power generation dynamic data of the present invention is shown.
[0106] The second aspect of the present invention further provides a solar photovoltaic panel intelligent tracking system 2 based on power generation dynamic data, the system comprising: a memory 21, a processor 22, the memory 21 comprising a solar photovoltaic panel intelligent tracking program based on power generation dynamic data, the solar photovoltaic panel intelligent tracking program based on power generation dynamic data when executed by the processor 22 implements the following steps:
[0107] In the photovoltaic power generation area, multiple photovoltaic sub-areas are divided based on the number distribution of photovoltaic panels;
[0108] Within a preset time period, environmental data and power generation dynamic data of each photovoltaic sub-area are collected, and data feature vectors are quantified based on the environmental data and power generation dynamic data to form environmental features and dynamic power generation features;
[0109] By presetting the clustering model, the environmental characteristics and dynamic power generation characteristics are used as clustering sample data to cluster multiple photovoltaic sub-areas. Each photovoltaic sub-area is used as a clustering unit. The clustering process performs similarity analysis based on the two data dimensions of environmental characteristics and dynamic power generation characteristics, and sets the analysis weights corresponding to the two data dimensions. After clustering, multiple photovoltaic area groups are obtained.
[0110] Mark a current photovoltaic area group, set multiple photovoltaic panel tracking schemes, divide a preset power generation cycle into multiple time periods, apply multiple photovoltaic panel tracking schemes to different time periods, collect the power generation dynamic data of all photovoltaic panels in the current photovoltaic area group based on different time periods, and analyze the changes of the power generation dynamic data based on the three dimensions of current, voltage and power generation to form a dynamic data change curve, compare the difference between the dynamic data change curve and the expected change curve, and screen out the optimal photovoltaic panel angle scheme for different time periods;
[0111] Based on the time sequence, the optimal photovoltaic panel solutions in different time periods are integrated to form a preferred tracking plan for a preset power generation cycle, and multiple preferred tracking plans are generated based on multiple photovoltaic area groups.
[0112] According to Embodiment 2 of the present invention, the solar photovoltaic panel intelligent tracking system based on power generation dynamic data implements all steps of the solar photovoltaic panel intelligent tracking method based on power generation dynamic data in Embodiment 1 above during operation.
[0113] In the present invention, a solar photovoltaic panel intelligent tracking system based on power generation dynamic data also includes:
[0114] Photovoltaic panel module: specifically, photovoltaic panels and panel adjustment devices;
[0115] Data monitoring module: obtain power generation monitoring data and environmental data through various monitoring sensors;
[0116] Data processing module: used to store and process the collected data;
[0117] Network transmission module: Data transmission between photovoltaic equipment and network terminals through the Internet of Things.
[0118] Example 3
[0119] The third aspect of the present invention also provides a computer-readable storage medium, which includes a solar photovoltaic panel intelligent tracking program based on power generation dynamic data. When the solar photovoltaic panel intelligent tracking program based on power generation dynamic data is executed by a processor, the steps of the solar photovoltaic panel intelligent tracking method based on power generation dynamic data as described in any one of the above-mentioned Embodiment 1 are implemented.
[0120] The present invention discloses a solar photovoltaic panel intelligent tracking method based on power generation dynamic data. By dividing a photovoltaic power generation area into multiple photovoltaic sub-areas, clustering is performed based on a preset clustering model using the environmental characteristics and dynamic power generation characteristics of the sub-areas as clustering sample data to obtain multiple photovoltaic areas. For the photovoltaic areas, multiple time periods are divided in a preset power generation cycle, and multiple sets of photovoltaic panel tracking schemes are applied to different time periods respectively. Based on different time periods, the dynamic data change curve is compared with the expected change curve, and the optimal photovoltaic panel angle schemes for different time periods are screened and combined to form a preferred tracking scheme. Through the present invention, it is possible to effectively perform regional feature analysis on photovoltaic power generation sites and realize photovoltaic optimization tracking in different areas, thereby improving the adaptability of photovoltaic power generation systems in complex environments and photovoltaic power generation efficiency.
[0121] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.
[0122] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.
[0123] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.
[0124] A person of ordinary skill in the art can understand that: all or part of the steps of implementing the above method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above method embodiment; and the aforementioned storage medium includes: a mobile storage device, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes.
[0125] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention can be essentially or partly reflected in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, magnetic disks or optical disks.
[0126] The above description is only a specific implementation mode of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.
Claims
1. A solar photovoltaic panel intelligent tracking method based on power generation dynamic data, characterized in that: include: In the photovoltaic power generation area, multiple photovoltaic sub-areas are divided based on the number distribution of photovoltaic panels; Within a preset time period, environmental data and power generation dynamic data of each photovoltaic sub-area are collected, and data feature vectors are quantified based on the environmental data and power generation dynamic data to form environmental features and dynamic power generation features; By presetting the clustering model, the environmental characteristics and dynamic power generation characteristics are used as clustering sample data to cluster multiple photovoltaic sub-areas. Each photovoltaic sub-area is used as a clustering unit. The clustering process performs similarity analysis based on the two data dimensions of environmental characteristics and dynamic power generation characteristics, and sets the analysis weights corresponding to the two data dimensions. After clustering, multiple photovoltaic area groups are obtained. Mark a current photovoltaic area group, set multiple photovoltaic panel tracking schemes, divide a preset power generation cycle into multiple time periods, apply multiple photovoltaic panel tracking schemes to different time periods, collect the power generation dynamic data of all photovoltaic panels in the current photovoltaic area group based on different time periods, and analyze the changes of the power generation dynamic data based on the three dimensions of current, voltage and power generation to form a dynamic data change curve, compare the difference between the dynamic data change curve and the expected change curve, and screen out the optimal photovoltaic panel angle scheme for different time periods; Based on the time sequence, the optimal photovoltaic panel solutions in different time periods are integrated to form a preferred tracking plan for a preset power generation cycle, and multiple preferred tracking plans are generated based on multiple photovoltaic area groups.
2. According to claim 1, a solar photovoltaic panel intelligent tracking method based on power generation dynamic data is characterized in that: In the photovoltaic power generation area, a plurality of photovoltaic sub-areas are divided based on the number distribution of photovoltaic panels, specifically: Obtaining the number and location information of photovoltaic panels in the photovoltaic power generation area; The distribution of photovoltaic panels is analyzed based on the number and location information of photovoltaic panels. Based on the distribution status, the photovoltaic power generation area is divided into multiple photovoltaic sub-areas. In the plurality of photovoltaic sub-areas, it is ensured that the difference in the number of photovoltaic panels between every two photovoltaic sub-areas is within a preset range.
3. A solar photovoltaic panel intelligent tracking method based on power generation dynamic data according to claim 2, characterized in that: In a preset time period, the environmental data and power generation dynamic data of each photovoltaic sub-area are collected, and data feature vectors are quantized based on the environmental data and the power generation dynamic data to form environmental features and dynamic power generation features, specifically: Collect environmental data and power generation dynamic data of each photovoltaic sub-area within a preset time period; The environmental data include temperature, light intensity, and light time parameters, and the power generation dynamic data include current, voltage, and power generation parameters; Environmental data and power generation dynamic data are vectorized based on different parameter dimensions to form environmental characteristics and dynamic power generation characteristics.
4. The solar photovoltaic panel intelligent tracking method based on power generation dynamic data according to claim 3 is characterized in that: The clustering model is preset, and the environmental characteristics and dynamic power generation characteristics are used as clustering sample data to cluster multiple photovoltaic sub-areas. Each photovoltaic sub-area is used as a clustering unit. The clustering process performs similarity analysis based on the two data dimensions of environmental characteristics and dynamic power generation characteristics, and sets the analysis weights corresponding to the two data dimensions. After clustering, multiple photovoltaic area groups are obtained, which are specifically: Construct a clustering model based on Dbscan and set the radiation radius of the sample points; The environmental characteristics and dynamic power generation characteristics of each photovoltaic sub-area are imported into cluster grouping and used as cluster sample data, and each photovoltaic sub-area is used as a clustering unit for clustering; In the clustering process, similarity analysis is performed based on the two data dimensions of environmental characteristics and dynamic power generation characteristics of each photovoltaic sub-region. The similarity analysis process is to calculate the sample distance of environmental characteristics and dynamic power generation characteristics between two photovoltaic sub-regions. The distance calculation is based on the standard Euclidean distance, and two distance values are obtained. Two similarities are obtained based on the two distance values, and the analysis weights corresponding to the two data dimensions are set. The two similarities are weighted averaged according to the analysis weights, and the similarity between the two photovoltaic sub-regions is obtained; Clustering is performed based on the similarity between clustered sample data, and multiple photovoltaic region groups are finally formed.
5. The solar photovoltaic panel intelligent tracking method based on power generation dynamic data according to claim 4 is characterized in that: The method marks a current photovoltaic area group, sets multiple photovoltaic panel tracking schemes, divides a preset power generation cycle into multiple time periods, applies multiple photovoltaic panel tracking schemes to different time periods, collects power generation dynamic data of all photovoltaic panels in the current photovoltaic area group based on different time periods, and performs change analysis on the power generation dynamic data based on three dimensions of current, voltage, and power generation to form a dynamic data change curve, compares the difference between the dynamic data change curve and the expected change curve, and selects the optimal photovoltaic panel angle scheme for different time periods, specifically: Mark a photovoltaic region group as the current photovoltaic region group; Set multiple photovoltaic panel tracking schemes based on the type and quantity of photovoltaic panels in the current photovoltaic area group; Divide a preset power generation cycle into multiple time periods, and apply multiple sets of photovoltaic panel tracking solutions to the photovoltaic area group in each time period; Taking a time period as the analysis unit, the power generation dynamic data of all photovoltaic panels in the current photovoltaic area group is collected and the linear change analysis of the power generation dynamic data is performed based on the three dimensions of current, voltage and power generation to form a dynamic data change curve; The dynamic data change curves include three change curves of current, voltage and power generation; The dynamic data change curve is compared with the expected change curve. The comparison process is based on the linear growth rate of the change curve and the difference analysis of the average value. Three difference values are obtained based on the change curves of the three dimensions of current, voltage and power generation. The three difference values are averaged to obtain the change difference degree. According to the variation difference of each photovoltaic panel tracking scheme, the optimal photovoltaic panel tracking scheme within a time period is selected and marked as the optimal photovoltaic panel angle scheme; Based on multiple time periods, the optimal photovoltaic panel angle solutions for different time periods are screened out.
6. A solar photovoltaic panel intelligent tracking method based on power generation dynamic data according to claim 5, characterized in that: Based on the time sequence, the optimal photovoltaic panel solutions in different time periods are integrated to form a preferred tracking solution for a preset power generation cycle, and multiple preferred tracking solutions are generated based on multiple photovoltaic area groups, specifically: Based on the time sequence, the optimal photovoltaic panel solutions in different time periods are integrated to form a preferred tracking plan for a preset power generation cycle, and the preferred tracking plan is applied to the current photovoltaic area group; A plurality of preferred tracking schemes are generated based on the plurality of photovoltaic region groups, and the plurality of preferred tracking schemes are applied to different photovoltaic region groups in the next preset power generation cycle.
7. A solar photovoltaic panel intelligent tracking system based on power generation dynamic data, characterized in that: The system includes: a memory and a processor, wherein the memory includes a solar photovoltaic panel intelligent tracking program based on power generation dynamic data, and when the solar photovoltaic panel intelligent tracking program based on power generation dynamic data is executed by the processor, all steps of a solar photovoltaic panel intelligent tracking method based on power generation dynamic data as described in claim 1 above are implemented.
8. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a solar photovoltaic panel intelligent tracking program based on power generation dynamic data. When the solar photovoltaic panel intelligent tracking program based on power generation dynamic data is executed by a processor, the steps of the solar photovoltaic panel intelligent tracking method based on power generation dynamic data as described in any one of claims 1 to 6 are implemented.
