Generated power prediction method and system for photovoltaic power station

Abstract

The invention relates to the technical field of photovoltaic power stations, and discloses a generation power prediction method and system for a photovoltaic power station, and the method comprises the steps: carrying out the region division of the photovoltaic power station, obtaining a plurality of data collection regions, and collecting the generation power influence data in each data collection region; outputting a data influence value corresponding to each piece of generated power influence data, and constructing a plurality of generated power influence data sequences; extracting generation power influence data of the same category from the generation power influence data sequence, constructing a generation power influence data set, and calculating a generation power influence coefficient; and obtaining the actual generation power of the current time period, calculating the product value of the generation power influence coefficient and the actual generation power, and taking the product value as the predicted generation power of the photovoltaic power station in the next time period, thereby accurately predicting the generation power of the next time period, ensuring the prediction precision and prediction efficiency, and further improving the generation efficiency of the photovoltaic power station. And powerful support is provided for optimal scheduling and stable operation of a power system.

Description

Technical Field

[0001] The present invention relates to the technical field of photovoltaic power stations, and in particular to a method and system for predicting power generation of a photovoltaic power station. Background Art

[0002] With the advancement of the global new energy strategy, photovoltaic power generation, as a clean and renewable energy, has been widely used in power systems. However, the power generation of photovoltaic power generation systems is affected by many factors, including meteorological conditions such as solar irradiance, temperature, wind speed and cloud cover, as well as factors such as component aging and equipment failure. These factors cause the photovoltaic power generation to have significant randomness, intermittency and volatility, which poses a challenge to the stability and reliability of the power system. Therefore, accurate photovoltaic power generation prediction has become an important prerequisite for the optimal scheduling and stable operation of the power system.

[0003] Traditional photovoltaic power generation prediction methods mainly include physical models and statistical models. The physical model is based on the physical characteristics of photovoltaic panels and inverters, and makes predictions by simulating changes in solar irradiance and meteorological conditions. The statistical model uses statistical analysis of historical power generation data and related meteorological data to establish a prediction model. However, these methods often find it difficult to fully and accurately capture various influencing factors and their dynamic changes, and the prediction accuracy is limited. Summary of the invention

[0004] The embodiment of the present invention provides a method and system for predicting power generation of a photovoltaic power station. The present invention can accurately predict power generation, ensure prediction accuracy and prediction efficiency, and thus improve the power generation efficiency of the photovoltaic power station.

[0005] In order to achieve the above object, the present invention provides a method for predicting power generation of a photovoltaic power station, comprising: The photovoltaic power station is divided into regions to obtain multiple data collection regions, and the power generation impact data in each data collection region is collected; Outputting the data impact value corresponding to each power generation impact data based on the pre-trained data impact value model, and constructing multiple power generation impact data sequences; Extracting power generation impact data of the same category from all power generation impact data sequences, constructing a power generation impact data set, analyzing the power generation impact data set, and calculating a power generation impact coefficient of the power generation impact data set; The actual power generation of the photovoltaic power station in the current period is obtained, and the product value of the power generation influence coefficient and the actual power generation is calculated as the predicted power generation of the photovoltaic power station in the next period.

[0006] Furthermore, when outputting the data impact value corresponding to each power generation impact data based on the pre-trained data impact value model and constructing multiple power generation impact data sequences, it includes: Calculate the data influence mean corresponding to all data influence values, extract all data influence values ​​greater than or equal to the data influence mean, and generate a first extraction mark; Extract all data influence values ​​that are smaller than the data influence mean value, sort the values, and sequentially combine them in pairs based on the sorting results to obtain multiple data influence value combinations; Calculating a data influence difference between every two data influence values ​​in the data influence value combination, determining whether the data influence difference is greater than or equal to a preset data influence difference, and if so, generating a second extraction mark for the data influence value combination; If not, deleting the next data influence value in the data influence value combination, and generating a third extraction mark for the previous data influence value; The power generation influence data sequence is constructed according to the power generation influence data corresponding to the first extraction mark, the second extraction mark and the third extraction mark.

[0007] Furthermore, the data impact value model is pre-trained according to the following steps: Collecting historical power generation impact data of the photovoltaic power station; constructing an impact data set according to the historical power generation impact data; Sampling the impact data set according to a preset ratio to obtain a training subset and a test subset; Obtaining a pre-selected neural network model, and iteratively training the neural network model according to the training subset, evaluating the iteratively trained neural network model according to the test subset, and obtaining the data influence value model; wherein, If the evaluation value of the neural network model after the current iterative training is less than the evaluation value of the neural network model after the previous iterative training, the amplitude of the change of the neural network model in the gradient direction is reduced, and the iterative training is continued until the preset number of iterations is reached.

[0008] Furthermore, when analyzing the power generation impact data set and calculating the power generation impact coefficient of the power generation impact data set, it includes: Acquire ideal power generation impact data corresponding to the power generation impact data set; Dividing the power generation influence data set into subsets based on the ideal power generation influence data, and when the power generation influence data in the power generation influence data set is smaller than the ideal power generation influence data, dividing the power generation influence data into a first subset; When the power generation influence data in the power generation influence data set is equal to the ideal power generation influence data, the power generation influence data is divided into a second sub-data set; When the power generation impact data in the power generation impact data set is greater than the ideal power generation impact data, the power generation impact data is divided into a third sub-data set; Calculating a super-ideal power generation influence coefficient of the power generation influence data set according to the third sub-data set; Calculating a sub-ideal power generation impact coefficient of the power generation impact data set according to the first sub-data set; Counting the number of influencing data of the power generation influencing data in the first sub-data set; The power generation influence coefficient of the power generation influence data set is calculated according to the super-ideal power generation influence coefficient, the sub-ideal power generation influence coefficient and the number of influence data.

[0009] Further, when calculating the super-ideal power generation influence coefficient of the power generation influence data set according to the third sub-data set, it includes: configuring a first calculation coefficient for the ideal power generation influence data, and calculating a product value of the first calculation coefficient and the ideal power generation influence data as first super-ideal power generation influence data; configuring a second calculation coefficient for the ideal power generation influence data, and calculating a product value of the second calculation coefficient and the ideal power generation influence data as second super-ideal power generation influence data; Determine a first data range according to the first super-ideal power generation impact data and the ideal power generation impact data; determining a second data range according to the first super-ideal power generation impact data and the second super-ideal power generation impact data; determining a third data range according to the second super-ideal power generation impact data; Performing range allocation on the power generation impact data in the third sub-data set, determining a first data allocation quantity within the first data range, determining a second data allocation quantity within the second data range, and determining a third data allocation quantity within the third data range; The super-ideal power generation influence coefficient of the power generation influence data set is calculated based on the first data allocation quantity, the second data allocation quantity and the third data allocation quantity.

[0010] Further, when calculating the super-ideal power generation influence coefficient of the power generation influence data set based on the first data allocation quantity, the second data allocation quantity and the third data allocation quantity, it includes: The super-ideal power generation influence coefficient of the power generation influence data set is calculated according to the following formula: ; Where q1 is the super ideal power generation influence coefficient of the power generation influence data set, m is the number of power generation influence data in the third sub-data set, and e i is the i-th power generation influencing data, f1 is the super-ideal power generation influencing data, f2 is the first super-ideal power generation influencing data, m1 is the first data allocation quantity, m2 is the second data allocation quantity, m3 is the third data allocation quantity, and f3 is the second super-ideal power generation influencing data.

[0011] Further, when calculating the sub-ideal power generation impact coefficient of the power generation impact data set according to the first sub-data set, it includes: Determine the minimum power generation impact data from the third sub-data set, and determine the impact data clustering distance from each power generation impact data in the first sub-data set to the cluster center based on the minimum power generation impact data as the cluster center; Determine the maximum influencing data clustering distance and the minimum influencing data clustering distance from all influencing data clustering distances; A suboptimal power generation impact coefficient of the power generation impact data set is calculated according to the maximum impact data cluster distance and the minimum impact data cluster distance.

[0012] Further, when calculating the sub-ideal power generation impact coefficient of the power generation impact data set according to the maximum impact data cluster distance and the minimum impact data cluster distance, it includes: The suboptimal power generation impact coefficient of the power generation impact data set is calculated according to the following formula: ; Among them, q2 is the suboptimal power generation coefficient of the power generation data set, n is the number of clustering distances affecting the data, Δy j is the weight corresponding to the jth influencing data clustering distance, y i is the clustering distance of the i-th influencing data, y min is the minimum influencing data clustering distance, y max is the maximum influencing data clustering distance.

[0013] Further, when calculating the power generation influence coefficient of the power generation influence data set according to the super-ideal power generation influence coefficient, the sub-ideal power generation influence coefficient and the number of influence data, it includes: A third calculation coefficient is configured for the super-ideal power generation influence coefficient, and a fourth calculation coefficient is configured for the sub-ideal power generation influence coefficient; The power generation influence coefficient of the power generation influence data set is calculated according to the following formula: ; Wherein, h is the power generation influence coefficient of the power generation influence data set, k1 is the third calculation coefficient, k2 is the fourth calculation coefficient, and t is the optimization number of the power generation influence coefficient; Determine the optimal number t of the power generation influence coefficient according to the number of influence data r; Counting the number w of power generation impact data in the first sub-data set; Presetting a first preset optimization number, a second preset optimization number, and a third preset optimization number; When r<w+m, the first preset optimization number is selected as the optimization number t of the power generation influence coefficient; When r=w+m, the second preset optimization number is selected as the optimization number t of the power generation influence coefficient; When r>w+m, the third preset optimization number is selected as the optimization number t of the power generation influence coefficient.

[0014] In order to achieve the above object, the present invention also provides a power generation prediction system for a photovoltaic power station, comprising: The data collection module is used to divide the photovoltaic power station into regions, obtain multiple data collection regions, and collect the power generation impact data in each data collection region; A sequence construction module, used for outputting a data impact value corresponding to each power generation impact data based on a pre-trained data impact value model, and constructing a plurality of power generation impact data sequences; A coefficient calculation module is used to extract power generation impact data of the same category from all power generation impact data sequences, construct a power generation impact data set, analyze the power generation impact data set, and calculate the power generation impact coefficient of the power generation impact data set; The power prediction module is used to obtain the actual power generation of the photovoltaic power station in the current period, and calculate the product value of the power generation influence coefficient and the actual power generation as the predicted power generation of the photovoltaic power station in the next period.

[0015] Compared with the prior art, the present invention has the following beneficial effects: The present invention discloses a power generation prediction method and system for a photovoltaic power station. The photovoltaic power station is divided into regions to obtain multiple data collection regions, and the power generation impact data in each data collection region are collected; the data impact value corresponding to each power generation impact data is output to construct multiple power generation impact data sequences; the power generation impact data of the same category are respectively extracted from the power generation impact data sequences to construct a power generation impact data set, and the power generation impact coefficient is calculated; the actual power generation power in the current time period is obtained, and the product value of the power generation impact coefficient and the actual power generation power is calculated as the predicted power generation power of the photovoltaic power station in the next time period. The power generation power in the next time period can be accurately predicted, and the prediction accuracy and prediction efficiency are guaranteed, thereby improving the power generation efficiency of the photovoltaic power station, and providing strong support for the optimized scheduling and stable operation of the power system. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present invention. Moreover, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings: Figure 1 A schematic diagram of a flow chart of a method for predicting power generation of a photovoltaic power station in an embodiment of the present invention is shown; Figure 2 The schematic diagram of the structure of the power generation prediction system for a photovoltaic power station in an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0017] The specific implementation of the present invention is further described in detail below in conjunction with the accompanying drawings and examples. The following examples are used to illustrate the present invention, but are not intended to limit the scope of the present invention.

[0018] In the description of the present application, it should be understood that the terms "center", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present application.

[0019] The terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, unless otherwise specified, "plurality" means two or more.

[0020] In the description of this application, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0021] The following is a description of preferred embodiments of the present invention with reference to the accompanying drawings.

[0022] like Figure 1 As shown, an embodiment of the present invention discloses a method for predicting power generation of a photovoltaic power station, comprising: S110: Divide the photovoltaic power station into regions to obtain multiple data collection regions, and collect power generation impact data in each data collection region; In this embodiment, the photovoltaic power station can be divided according to its area, and the number of divisions is 20, so as to ensure uniform division.

[0023] In this embodiment, the power generation influencing data includes radiation intensity, sunshine time, ambient temperature, etc.

[0024] S120: outputting a data impact value corresponding to each power generation impact data based on a pre-trained data impact value model, and constructing a plurality of power generation impact data sequences; In some embodiments of the present application, when outputting the data impact value corresponding to each power generation impact data based on the pre-trained data impact value model and constructing multiple power generation impact data sequences, it includes: Calculate the data influence mean corresponding to all data influence values, extract all data influence values ​​greater than or equal to the data influence mean, and generate a first extraction mark; Extract all data influence values ​​that are smaller than the data influence mean value, sort the values, and sequentially combine them in pairs based on the sorting results to obtain multiple data influence value combinations; Calculating a data influence difference between every two data influence values ​​in the data influence value combination, determining whether the data influence difference is greater than or equal to a preset data influence difference, and if so, generating a second extraction mark for the data influence value combination; If not, deleting the next data influence value in the data influence value combination, and generating a third extraction mark for the previous data influence value; The power generation influence data sequence is constructed according to the power generation influence data corresponding to the first extraction mark, the second extraction mark and the third extraction mark.

[0025] In this embodiment, the preset data impact difference is preferably 2.

[0026] In this embodiment, the latter data influence value refers to a smaller data influence value in the data influence value combination, and the former data influence value refers to a larger data influence value in the data influence value combination.

[0027] The beneficial effect of the above technical solution is: the present invention constructs a power generation influence data sequence according to the power generation influence data corresponding to the first extraction mark, the second extraction mark and the third extraction mark, thereby ensuring the comprehensiveness of the construction of the power generation influence data sequence and laying the foundation for the power generation prediction of the photovoltaic power station.

[0028] In some embodiments of the present application, the data influence value model is pre-trained according to the following steps: Collecting historical power generation impact data of the photovoltaic power station; constructing an impact data set according to the historical power generation impact data; Sampling the impact data set according to a preset ratio to obtain a training subset and a test subset; Obtaining a pre-selected neural network model, and iteratively training the neural network model according to the training subset, evaluating the iteratively trained neural network model according to the test subset, and obtaining the data influence value model; wherein, If the evaluation value of the neural network model after the current iterative training is less than the evaluation value of the neural network model after the previous iterative training, the amplitude of the change of the neural network model in the gradient direction is reduced, and the iterative training is continued until the preset number of iterations is reached.

[0029] In this embodiment, the preset ratio may be 1:2 or 3:7, etc.

[0030] The beneficial effect of the above technical solution is that the present invention can accurately output the data influence value corresponding to each power generation influence data by pre-training the data influence value model.

[0031] S130: extracting power generation impact data of the same category from all power generation impact data sequences, constructing a power generation impact data set, analyzing the power generation impact data set, and calculating a power generation impact coefficient of the power generation impact data set; In some embodiments of the present application, when analyzing the power generation impact data set and calculating the power generation impact coefficient of the power generation impact data set, the method includes: Acquire ideal power generation impact data corresponding to the power generation impact data set; Dividing the power generation influence data set into subsets based on the ideal power generation influence data, and when the power generation influence data in the power generation influence data set is smaller than the ideal power generation influence data, dividing the power generation influence data into a first subset; When the power generation influence data in the power generation influence data set is equal to the ideal power generation influence data, the power generation influence data is divided into a second sub-data set; When the power generation impact data in the power generation impact data set is greater than the ideal power generation impact data, the power generation impact data is divided into a third sub-data set; Calculating a super-ideal power generation influence coefficient of the power generation influence data set according to the third sub-data set; Calculating a sub-ideal power generation impact coefficient of the power generation impact data set according to the first sub-data set; Counting the number of influencing data of the power generation influencing data in the first sub-data set; The power generation influence coefficient of the power generation influence data set is calculated according to the super-ideal power generation influence coefficient, the sub-ideal power generation influence coefficient and the number of influence data.

[0032] In some embodiments of the present application, when calculating the super-ideal power generation influence coefficient of the power generation influence data set according to the third sub-data set, it includes: configuring a first calculation coefficient for the ideal power generation influence data, and calculating a product value of the first calculation coefficient and the ideal power generation influence data as first super-ideal power generation influence data; configuring a second calculation coefficient for the ideal power generation influence data, and calculating a product value of the second calculation coefficient and the ideal power generation influence data as second super-ideal power generation influence data; Determine a first data range according to the first super-ideal power generation impact data and the ideal power generation impact data; determining a second data range according to the first super-ideal power generation impact data and the second super-ideal power generation impact data; determining a third data range according to the second super-ideal power generation impact data; Performing range allocation on the power generation impact data in the third sub-data set, determining a first data allocation quantity within the first data range, determining a second data allocation quantity within the second data range, and determining a third data allocation quantity within the third data range; The super-ideal power generation influence coefficient of the power generation influence data set is calculated based on the first data allocation quantity, the second data allocation quantity and the third data allocation quantity.

[0033] In this embodiment, the first calculation coefficient is 1.1, and the second calculation coefficient is 1.2.

[0034] In this embodiment, the third data range is [second super-ideal power generation impact data, +∞].

[0035] The beneficial effect of the above technical solution is: the present invention calculates the super-ideal power generation influence coefficient of the power generation influence data set based on the first data allocation quantity, the second data allocation quantity and the third data allocation quantity, thereby ensuring the calculation accuracy of the super-ideal power generation influence coefficient and providing a basis for the calculation of the power generation influence coefficient.

[0036] In some embodiments of the present application, when calculating the super-ideal power generation influence coefficient of the power generation influence data set based on the first data allocation quantity, the second data allocation quantity and the third data allocation quantity, it includes: The super-ideal power generation influence coefficient of the power generation influence data set is calculated according to the following formula: ; Where q1 is the super ideal power generation influence coefficient of the power generation influence data set, m is the number of power generation influence data in the third sub-data set, and e i is the i-th power generation influencing data, f1 is the super-ideal power generation influencing data, f2 is the first super-ideal power generation influencing data, m1 is the first data allocation quantity, m2 is the second data allocation quantity, m3 is the third data allocation quantity, and f3 is the second super-ideal power generation influencing data.

[0037] In some embodiments of the present application, when calculating the sub-ideal power generation impact coefficient of the power generation impact data set according to the first sub-data set, it includes: Determine the minimum power generation impact data from the third sub-data set, and determine the impact data clustering distance from each power generation impact data in the first sub-data set to the cluster center based on the minimum power generation impact data as the cluster center; Determine the maximum influencing data clustering distance and the minimum influencing data clustering distance from all influencing data clustering distances; A suboptimal power generation impact coefficient of the power generation impact data set is calculated according to the maximum impact data cluster distance and the minimum impact data cluster distance.

[0038] In this embodiment, the method for determining the clustering distance is not repeated here.

[0039] The beneficial effect of the above technical solution is: the present invention calculates the sub-ideal power generation influence coefficient of the power generation influence data set according to the maximum influence data clustering distance and the minimum influence data clustering distance, while also ensuring the calculation accuracy of the sub-ideal power generation influence coefficient, providing a basis for the calculation of the power generation influence coefficient.

[0040] In some embodiments of the present application, when calculating the sub-ideal power generation impact coefficient of the power generation impact data set according to the maximum impact data cluster distance and the minimum impact data cluster distance, it includes: The suboptimal power generation impact coefficient of the power generation impact data set is calculated according to the following formula: ; Among them, q2 is the suboptimal power generation coefficient of the power generation data set, n is the number of clustering distances affecting the data, Δy j is the weight corresponding to the jth influencing data clustering distance, y i is the clustering distance of the i-th influencing data, y min is the minimum influencing data clustering distance, y max is the maximum influencing data clustering distance.

[0041] In some embodiments of the present application, when calculating the power generation influence coefficient of the power generation influence data set according to the super-ideal power generation influence coefficient, the sub-ideal power generation influence coefficient and the number of influence data, it includes: A third calculation coefficient is configured for the super-ideal power generation influence coefficient, and a fourth calculation coefficient is configured for the sub-ideal power generation influence coefficient; The power generation influence coefficient of the power generation influence data set is calculated according to the following formula: ; Wherein, h is the power generation influence coefficient of the power generation influence data set, k1 is the third calculation coefficient, k2 is the fourth calculation coefficient, and t is the optimization number of the power generation influence coefficient; Determine the optimal number t of the power generation influence coefficient according to the number of influence data r; Counting the number w of power generation impact data in the first sub-data set; Presetting a first preset optimization number, a second preset optimization number, and a third preset optimization number; When r<w+m, the first preset optimization number is selected as the optimization number t of the power generation influence coefficient; When r=w+m, the second preset optimization number is selected as the optimization number t of the power generation influence coefficient; When r>w+m, the third preset optimization number is selected as the optimization number t of the power generation influence coefficient.

[0042] In this embodiment, the third configuration coefficient is preferably 0.6, and the fourth configuration coefficient is preferably 0.4.

[0043] In this embodiment, the first preset optimization number is preferably 0.85, the second preset optimization number is preferably 1.15, and the third preset optimization number is preferably 1.25.

[0044] The beneficial effect of the above technical solution is: the present invention can dynamically adjust the power generation influence coefficient by selecting different preset optimization numbers, thereby ensuring the calculation accuracy of the power generation influence coefficient, and calculating the power generation influence coefficient of the power generation influence data set according to the super-ideal power generation influence coefficient, the sub-ideal power generation influence coefficient and the number of influencing data, thereby avoiding the calculation errors existing in manual participation and providing an accurate prediction basis for the power generation prediction of photovoltaic power stations.

[0045] S140: Acquire the actual power generation of the photovoltaic power station in the current period, and calculate the product value of the power generation influence coefficient and the actual power generation as the predicted power generation of the photovoltaic power station in the next period.

[0046] The beneficial effect of the above technical solution is that the present invention can accurately predict the power generation in the next period, ensure the prediction accuracy and prediction efficiency, thereby improving the power generation efficiency of photovoltaic power stations, and providing strong support for the optimized scheduling and stable operation of the power system.

[0047] In order to further explain the technical idea of ​​the present invention, the technical solution of the present invention is now described in combination with specific application scenarios.

[0048] Correspondingly, such as Figure 2 As shown, the present application also provides a power generation prediction system for a photovoltaic power station, comprising: The data collection module is used to divide the photovoltaic power station into regions, obtain multiple data collection regions, and collect the power generation impact data in each data collection region; A sequence construction module, used for outputting a data impact value corresponding to each power generation impact data based on a pre-trained data impact value model, and constructing a plurality of power generation impact data sequences; A coefficient calculation module is used to extract power generation impact data of the same category from all power generation impact data sequences, construct a power generation impact data set, analyze the power generation impact data set, and calculate the power generation impact coefficient of the power generation impact data set; The power prediction module is used to obtain the actual power generation of the photovoltaic power station in the current period, and calculate the product value of the power generation influence coefficient and the actual power generation as the predicted power generation of the photovoltaic power station in the next period.

[0049] In the description of the above embodiments, specific features, structures, materials or characteristics may be combined in a suitable manner in any one or more embodiments or examples.

[0050] Although the present invention has been described above with reference to the embodiments, various modifications may be made thereto and parts thereof may be replaced with equivalents without departing from the scope of the present invention. In particular, as long as there is no structural conflict, the various features in the embodiments disclosed by the present invention may be used in combination with each other in any manner, and the fact that these combinations are not fully described in this specification is only for the sake of omitting space and saving resources.

[0051] Those skilled in the art can understand that the above are only preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions recorded in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for predicting power generation of a photovoltaic power station, characterized in that: include: The photovoltaic power station is divided into regions to obtain multiple data collection regions, and the power generation impact data in each data collection region is collected; Outputting the data impact value corresponding to each power generation impact data based on the pre-trained data impact value model, and constructing multiple power generation impact data sequences; Extracting power generation impact data of the same category from all power generation impact data sequences, constructing a power generation impact data set, analyzing the power generation impact data set, and calculating a power generation impact coefficient of the power generation impact data set; The actual power generation of the photovoltaic power station in the current period is obtained, and the product value of the power generation influence coefficient and the actual power generation is calculated as the predicted power generation of the photovoltaic power station in the next period.

2. The method for predicting power generation of a photovoltaic power station according to claim 1, characterized in that: When outputting the data impact value corresponding to each power generation impact data based on the pre-trained data impact value model and constructing multiple power generation impact data sequences, it includes: Calculate the data influence mean corresponding to all data influence values, extract all data influence values ​​greater than or equal to the data influence mean, and generate a first extraction mark; Extract all data influence values ​​that are smaller than the data influence mean value, sort the values, and sequentially combine them in pairs based on the sorting results to obtain multiple data influence value combinations; Calculating a data influence difference between every two data influence values ​​in the data influence value combination, determining whether the data influence difference is greater than or equal to a preset data influence difference, and if so, generating a second extraction mark for the data influence value combination; If not, deleting the next data influence value in the data influence value combination, and generating a third extraction mark for the previous data influence value; The power generation influence data sequence is constructed according to the power generation influence data corresponding to the first extraction mark, the second extraction mark and the third extraction mark.

3. The method for predicting power generation of a photovoltaic power station according to claim 2, characterized in that: The data impact value model is pre-trained according to the following steps: Collecting historical power generation impact data of the photovoltaic power station; constructing an impact data set according to the historical power generation impact data; Sampling the impact data set according to a preset ratio to obtain a training subset and a test subset; Obtaining a pre-selected neural network model, and iteratively training the neural network model according to the training subset, evaluating the iteratively trained neural network model according to the test subset, and obtaining the data influence value model; wherein, If the evaluation value of the neural network model after the current iterative training is less than the evaluation value of the neural network model after the previous iterative training, the amplitude of the change of the neural network model in the gradient direction is reduced, and the iterative training is continued until the preset number of iterations is reached.

4. The method for predicting power generation of a photovoltaic power station according to claim 1, characterized in that: When analyzing the power generation impact data set and calculating the power generation impact coefficient of the power generation impact data set, it includes: Acquire ideal power generation impact data corresponding to the power generation impact data set; Dividing the power generation influence data set into subsets based on the ideal power generation influence data, and when the power generation influence data in the power generation influence data set is smaller than the ideal power generation influence data, dividing the power generation influence data into a first subset; When the power generation influence data in the power generation influence data set is equal to the ideal power generation influence data, the power generation influence data is divided into a second sub-data set; When the power generation impact data in the power generation impact data set is greater than the ideal power generation impact data, the power generation impact data is divided into a third sub-data set; Calculating a super-ideal power generation influence coefficient of the power generation influence data set according to the third sub-data set; Calculating a sub-ideal power generation impact coefficient of the power generation impact data set according to the first sub-data set; Counting the number of influencing data of the power generation influencing data in the first sub-data set; The power generation influence coefficient of the power generation influence data set is calculated according to the super-ideal power generation influence coefficient, the sub-ideal power generation influence coefficient and the number of influence data.

5. The method for predicting power generation of a photovoltaic power station according to claim 4, characterized in that: When calculating the super-ideal power generation influence coefficient of the power generation influence data set according to the third sub-data set, it includes: configuring a first calculation coefficient for the ideal power generation influence data, and calculating a product value of the first calculation coefficient and the ideal power generation influence data as first super-ideal power generation influence data; configuring a second calculation coefficient for the ideal power generation influence data, and calculating a product value of the second calculation coefficient and the ideal power generation influence data as second super-ideal power generation influence data; Determine a first data range according to the first super-ideal power generation impact data and the ideal power generation impact data; determining a second data range according to the first super-ideal power generation impact data and the second super-ideal power generation impact data; determining a third data range according to the second super-ideal power generation impact data; Performing range allocation on the power generation impact data in the third sub-data set, determining a first data allocation quantity within the first data range, determining a second data allocation quantity within the second data range, and determining a third data allocation quantity within the third data range; The super-ideal power generation influence coefficient of the power generation influence data set is calculated based on the first data allocation quantity, the second data allocation quantity and the third data allocation quantity.

6. The method for predicting power generation of a photovoltaic power station according to claim 5, characterized in that: When calculating the super-ideal power generation influence coefficient of the power generation influence data set based on the first data allocation quantity, the second data allocation quantity and the third data allocation quantity, it includes: The super-ideal power generation influence coefficient of the power generation influence data set is calculated according to the following formula: ； Where q1 is the super ideal power generation influence coefficient of the power generation influence data set, m is the number of power generation influence data in the third sub-data set, and e i is the i-th power generation influencing data, f1 is the super-ideal power generation influencing data, f2 is the first super-ideal power generation influencing data, m1 is the first data allocation quantity, m2 is the second data allocation quantity, m3 is the third data allocation quantity, and f3 is the second super-ideal power generation influencing data.

7. The method for predicting power generation of a photovoltaic power station according to claim 6, characterized in that: When calculating the sub-ideal power generation impact coefficient of the power generation impact data set according to the first sub-data set, it includes: Determine the minimum power generation impact data from the third sub-data set, and determine the impact data clustering distance from each power generation impact data in the first sub-data set to the cluster center based on the minimum power generation impact data as the cluster center; Determine the maximum influencing data clustering distance and the minimum influencing data clustering distance from all influencing data clustering distances; A suboptimal power generation impact coefficient of the power generation impact data set is calculated according to the maximum impact data cluster distance and the minimum impact data cluster distance.

8. The method for predicting power generation of a photovoltaic power station according to claim 7, characterized in that: When calculating the sub-ideal power generation impact coefficient of the power generation impact data set according to the maximum impact data cluster distance and the minimum impact data cluster distance, it includes: The suboptimal power generation impact coefficient of the power generation impact data set is calculated according to the following formula: ； Among them, q2 is the suboptimal power generation coefficient of the power generation data set, n is the number of clustering distances affecting the data, Δy j is the weight corresponding to the jth influencing data clustering distance, y i is the clustering distance of the i-th influencing data, y min is the minimum influencing data clustering distance, y max is the maximum influencing data clustering distance.

9. The method for predicting power generation of a photovoltaic power station according to claim 8, characterized in that: When calculating the power generation influence coefficient of the power generation influence data set according to the super-ideal power generation influence coefficient, the sub-ideal power generation influence coefficient and the number of influence data, it includes: A third calculation coefficient is configured for the super-ideal power generation influence coefficient, and a fourth calculation coefficient is configured for the sub-ideal power generation influence coefficient; The power generation influence coefficient of the power generation influence data set is calculated according to the following formula: ； Wherein, h is the power generation influence coefficient of the power generation influence data set, k1 is the third calculation coefficient, k2 is the fourth calculation coefficient, and t is the optimization number of the power generation influence coefficient; Determine the optimal number t of the power generation influence coefficient according to the number of influence data r; Counting the number w of power generation impact data in the first sub-data set; Presetting a first preset optimization number, a second preset optimization number, and a third preset optimization number; When r<w+m, the first preset optimization number is selected as the optimization number t of the power generation influence coefficient; When r=w+m, the second preset optimization number is selected as the optimization number t of the power generation influence coefficient; When r>w+m, the third preset optimization number is selected as the optimization number t of the power generation influence coefficient.

10. A power generation prediction system for a photovoltaic power station, applied to the power generation prediction method for a photovoltaic power station as claimed in any one of claims 1 to 9, characterized in that: include: The data collection module is used to divide the photovoltaic power station into regions, obtain multiple data collection regions, and collect the power generation impact data in each data collection region; A sequence construction module, used for outputting a data impact value corresponding to each power generation impact data based on a pre-trained data impact value model, and constructing a plurality of power generation impact data sequences; A coefficient calculation module is used to extract power generation impact data of the same category from all power generation impact data sequences, construct a power generation impact data set, analyze the power generation impact data set, and calculate the power generation impact coefficient of the power generation impact data set; The power prediction module is used to obtain the actual power generation of the photovoltaic power station in the current period, and calculate the product value of the power generation influence coefficient and the actual power generation as the predicted power generation of the photovoltaic power station in the next period.

Images