An integrated identification and analysis method, system and medium for photovoltaic power generation system

Abstract

The present invention relates to an integrated identification and analysis method, system and medium for a photovoltaic power generation system, and belongs to the technical field of photovoltaic power generation equipment. The present invention sets a number of power generation efficiency ranges, and evaluates each photovoltaic power generation system based on the power generation data of each photovoltaic power generation system within a preset time, the real-time power generation data of each photovoltaic power generation system, and the power generation efficiency range through a decision tree algorithm, obtains the power generation efficiency membership of each photovoltaic power generation system, and finally identifies and analyzes the abnormal photovoltaic power generation system based on the power generation efficiency membership of each photovoltaic power generation system, obtains the abnormal photovoltaic power generation system, and marks the abnormal photovoltaic power generation system, and displays the marking information in a preset manner. The present invention can improve the recognition accuracy of abnormal power generation data by evaluating the power generation efficiency of real-time power generation data according to the power generation characteristic data under each meteorological characteristic data.

Description

Technical Field

[0001] The present invention relates to the technical field of photovoltaic power generation systems, and in particular to an integrated identification and analysis method, system and medium for photovoltaic power generation systems. Background Art

[0002] Photovoltaic power generation system (PV System) is a power generation system that converts solar energy into electrical energy, using the photovoltaic effect. Photovoltaic power generation systems are divided into independent solar photovoltaic power generation systems, grid-connected solar photovoltaic power generation systems and distributed solar photovoltaic power generation systems. Its main components are solar cells, batteries, controllers and inverters. Its characteristics are high reliability, long service life, no pollution to the environment, independent power generation and grid-connected operation. It is favored by enterprises and organizations in various countries and has broad development prospects. With the transformation of the global energy structure, distributed photovoltaic power generation systems have been widely used around the world due to their clean and renewable characteristics. These systems are deployed in different geographical locations, and their power generation performance is strongly affected by the climate and weather conditions in the region, resulting in significant non-steady-state characteristics in power generation, which poses a challenge to the stable operation and economic benefits of the power system. However, in the prior art, whether an abnormality occurs is often determined based on the working status of the equipment. However, in fact, the power generation data generated under different meteorological characteristics are inconsistent, which will lead to different power generation data and different power generation evaluation indicators. Obviously, when the real-time power generation data is lower than a single power generation data indicator, it is not enough to indicate that there is an abnormality in photovoltaic power generation. This leads to serious misjudgment when identifying the status of the photovoltaic power generation system, which will lead to excessively high maintenance costs. Summary of the invention

[0003] The present invention overcomes the deficiencies of the prior art and provides an integrated identification and analysis method, system and medium for a photovoltaic power generation system.

[0004] To achieve the above object, the technical solution adopted by the present invention is:

[0005] A first aspect of the present invention provides an integrated identification and analysis method for a photovoltaic power generation system, comprising the following steps:

[0006] The power generation data of the photovoltaic power generation system under various meteorological characteristics is obtained through big data, and a power generation data prediction model is constructed based on the power generation data of the photovoltaic power generation system under various meteorological characteristics;

[0007] Based on the power generation data prediction model, the power generation data of each photovoltaic power generation system within a preset time is predicted, and a photovoltaic power generation system integration network is constructed to obtain the real-time power generation data of each photovoltaic power generation system through the photovoltaic power generation system integration network;

[0008] Set a number of power generation efficiency ranges, and evaluate each photovoltaic power generation system based on the power generation data of each photovoltaic power generation system within a preset time, the real-time power generation data of each photovoltaic power generation system, and the power generation efficiency range through a decision tree algorithm to obtain the power generation efficiency membership of each photovoltaic power generation system;

[0009] Based on the power generation efficiency membership of each photovoltaic power generation system, the abnormal photovoltaic power generation system is identified and analyzed, the abnormal photovoltaic power generation system is obtained, and the abnormal photovoltaic power generation system is marked, and the marked information is displayed in a preset manner.

[0010] Furthermore, in this method, the power generation data of the photovoltaic power generation system under various meteorological characteristics is obtained through big data, and a power generation data prediction model is constructed based on the power generation data of the photovoltaic power generation system under various meteorological characteristics, specifically including:

[0011] The power generation data of the photovoltaic power generation system under various meteorological characteristics is obtained through big data, and the graph neural network is introduced to input the power generation data of the photovoltaic power generation system under various meteorological characteristics into the graph neural network;

[0012] Taking the meteorological characteristics as the first node and the power generation data as the second node, a directed connection description relationship is constructed. Based on the directed connection description relationship, the first node is made to point to the second node, and the first node and the second node are connected to construct a topological structure diagram;

[0013] Based on the topological structure graph, an adjacency matrix is ​​obtained, and the Jaccard similarity coefficient between the first nodes in the adjacency matrix is ​​calculated, and the first nodes whose Jaccard similarity coefficient is greater than a preset Jaccard similarity coefficient threshold are merged to obtain the merged adjacency matrix, and a power generation data prediction model is constructed based on a convolutional neural network;

[0014] The merged adjacency matrix is ​​input into the power generation data prediction model for training. When the loss function of the power generation data prediction model converges to a preset value, the model parameters of the power generation data prediction model are saved and the power generation data prediction model is output.

[0015] Furthermore, in the present method, the power generation data of each photovoltaic power generation system within a preset time is predicted based on the power generation data prediction model, specifically including:

[0016] Obtaining geographical location information of the photovoltaic power generation system, and performing data retrieval based on the geographical location information of the photovoltaic power generation system to obtain meteorological characteristic change data of the area where the photovoltaic power generation system is located within a preset time;

[0017] The meteorological characteristic change data of the area where the photovoltaic power generation system is located within the preset time is divided into several sub-periods, the meteorological characteristic data of each sub-period is counted, and the meteorological characteristic data of each sub-period is input into the power generation data prediction model for prediction, and the power generation data of each photovoltaic power generation system in each sub-period is obtained;

[0018] The power generation data of each photovoltaic power generation system in each sub-period is counted, the power generation data of each photovoltaic power generation system within a preset time is obtained, and the power generation data of each photovoltaic power generation system within the preset time is output.

[0019] Furthermore, in this method, a photovoltaic power generation system integration network is constructed, and real-time power generation data of each photovoltaic power generation system is obtained through the photovoltaic power generation system integration network, specifically:

[0020] Constructing a photovoltaic power generation system integrated network, sending each photovoltaic power generation system to the photovoltaic power generation system integrated network through a communication device, and forming a communication link through the connection between the communication device and the photovoltaic power generation system integrated network;

[0021] Testing the communication delay data of each communication link, and determining whether the communication delay data of the communication link is greater than a preset communication delay threshold;

[0022] When the communication delay data of the communication link is greater than the preset communication delay threshold, the communication device is subjected to frequency modulation processing until the communication delay data of the communication link is no greater than the preset communication delay threshold;

[0023] When the communication delay data of the communication link is not greater than a preset communication delay threshold, the photovoltaic power generation system integrated network is constructed, and the real-time power generation data of each photovoltaic power generation system is obtained through the photovoltaic power generation system integrated network.

[0024] Furthermore, in this method, several power generation efficiency ranges are set, and each photovoltaic power generation system is evaluated based on the power generation data of each photovoltaic power generation system within a preset time, the real-time power generation data of each photovoltaic power generation system, and the power generation efficiency range through a decision tree algorithm to obtain the power generation efficiency membership of each photovoltaic power generation system, specifically including:

[0025] Set several power generation efficiency ranges, introduce a decision tree algorithm, calculate the power generation efficiency of the photovoltaic power generation system based on the power generation data of each photovoltaic power generation system within a preset time and the real-time power generation data of each photovoltaic power generation system, and construct a set to be classified based on the power generation efficiency of the photovoltaic power generation system;

[0026] A root node is constructed according to the set to be classified, the root node is initialized and split based on the power generation efficiency range to generate a number of leaf nodes, and it is determined whether there are sample data of at least two power generation efficiency ranges in the leaf nodes;

[0027] When there are sample data of at least two power generation efficiency ranges in the leaf node, the leaf node is continuously split until there are no sample data of at least two power generation efficiency ranges in the leaf node;

[0028] When there are no sample data of at least two power generation efficiency ranges in the leaf node, the power generation efficiency membership corresponding to each leaf node is obtained, and the power generation efficiency membership of each photovoltaic power generation system is obtained according to the power generation efficiency membership corresponding to the leaf node.

[0029] Furthermore, in this method, based on the power generation efficiency membership of each photovoltaic power generation system, the abnormal photovoltaic power generation system is identified and analyzed, the abnormal photovoltaic power generation system is obtained, and the abnormal photovoltaic power generation system is marked, and the marking information is displayed in a preset manner, specifically:

[0030] Setting a power generation efficiency membership evaluation index, and judging whether the power generation efficiency membership of the photovoltaic power generation system is greater than the power generation efficiency membership evaluation index;

[0031] When the power generation efficiency membership of the photovoltaic power generation system is greater than the power generation efficiency membership evaluation index, the corresponding photovoltaic power generation system is regarded as an abnormal photovoltaic power generation system, and the abnormal photovoltaic power generation system is marked, and the marking information is displayed in a preset manner;

[0032] When the power generation efficiency membership of the photovoltaic power generation system is not greater than the power generation efficiency membership evaluation index, the corresponding photovoltaic power generation system is regarded as a normal photovoltaic power generation system.

[0033] A second aspect of the present invention provides an integrated identification and analysis system for a photovoltaic power generation system. The system includes a memory and a processor. The memory includes an integrated identification and analysis method program for the photovoltaic power generation system. When the integrated identification and analysis method program for the photovoltaic power generation system is executed by the processor, the following steps are implemented:

[0034] The power generation data of the photovoltaic power generation system under various meteorological characteristics is obtained through big data, and a power generation data prediction model is constructed based on the power generation data of the photovoltaic power generation system under various meteorological characteristics;

[0035] Based on the power generation data prediction model, the power generation data of each photovoltaic power generation system within a preset time is predicted, and a photovoltaic power generation system integration network is constructed to obtain the real-time power generation data of each photovoltaic power generation system through the photovoltaic power generation system integration network;

[0036] Set a number of power generation efficiency ranges, and evaluate each photovoltaic power generation system based on the power generation data of each photovoltaic power generation system within a preset time, the real-time power generation data of each photovoltaic power generation system, and the power generation efficiency range through a decision tree algorithm to obtain the power generation efficiency membership of each photovoltaic power generation system;

[0037] Based on the power generation efficiency membership of each photovoltaic power generation system, the abnormal photovoltaic power generation system is identified and analyzed, the abnormal photovoltaic power generation system is obtained, and the abnormal photovoltaic power generation system is marked, and the marked information is displayed in a preset manner.

[0038] A third aspect of the present invention provides a computer-readable storage medium, which includes a program for an integrated identification and analysis method for a photovoltaic power generation system. When the program for the integrated identification and analysis method for a photovoltaic power generation system is executed by a processor, any step of the integrated identification and analysis method for a photovoltaic power generation system is implemented.

[0039] The present invention solves the defects existing in the background technology and has the following beneficial effects:

[0040] The present invention obtains the real-time power generation data of each photovoltaic power generation system through a photovoltaic power generation system integrated network, thereby setting a number of power generation efficiency ranges, and evaluating each photovoltaic power generation system based on the power generation data of each photovoltaic power generation system within a preset time, the real-time power generation data of each photovoltaic power generation system, and the power generation efficiency range through a decision tree algorithm, obtaining the power generation efficiency membership of each photovoltaic power generation system, and finally identifying and analyzing the abnormal photovoltaic power generation system based on the power generation efficiency membership of each photovoltaic power generation system, obtaining the abnormal photovoltaic power generation system, and marking the abnormal photovoltaic power generation system, and displaying the marking information in a preset manner. The present invention can improve the recognition accuracy of abnormal power generation data by evaluating the power generation efficiency of real-time power generation data according to the power generation characteristic data under each meteorological characteristic data. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, drawings of other embodiments can be obtained based on these drawings without paying creative work.

[0042] Figure 1 An overall flow chart of the integrated identification and analysis method for photovoltaic power generation systems is shown;

[0043] Figure 2 A partial flow chart of an integrated identification and analysis method for a photovoltaic power generation system is shown;

[0044] Figure 3 A system block diagram of an integrated identification and analysis system for a photovoltaic power generation system is shown. DETAILED DESCRIPTION

[0045] 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.

[0046] 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.

[0047] like Figure 1 As shown, the first aspect of the present invention provides an integrated identification and analysis method for a photovoltaic power generation system, comprising the following steps:

[0048] S102: acquiring power generation data of the photovoltaic power generation system under various meteorological characteristics through big data, and constructing a power generation data prediction model based on the power generation data of the photovoltaic power generation system under various meteorological characteristics;

[0049] S104: predicting the power generation data of each photovoltaic power generation system within a preset time based on the power generation data prediction model, building a photovoltaic power generation system integration network, and obtaining real-time power generation data of each photovoltaic power generation system through the photovoltaic power generation system integration network;

[0050] S106: setting a number of power generation efficiency ranges, and evaluating each photovoltaic power generation system based on the power generation data of each photovoltaic power generation system within a preset time, the real-time power generation data of each photovoltaic power generation system, and the power generation efficiency range through a decision tree algorithm to obtain the power generation efficiency membership of each photovoltaic power generation system;

[0051] S108: Identify and analyze abnormal photovoltaic power generation systems based on the power generation efficiency membership of each photovoltaic power generation system, obtain abnormal photovoltaic power generation systems, mark the abnormal photovoltaic power generation systems, and display the marking information in a preset manner.

[0052] It should be noted that the present invention can improve the recognition accuracy of abnormal power generation data by evaluating the power generation efficiency of real-time power generation data according to the power generation characteristic data under each meteorological characteristic data.

[0053] Furthermore, in this method, the power generation data of the photovoltaic power generation system under various meteorological characteristics is obtained through big data, and a power generation data prediction model is constructed based on the power generation data of the photovoltaic power generation system under various meteorological characteristics, specifically including:

[0054] The power generation data of the photovoltaic power generation system under various meteorological characteristics is obtained through big data, and the graph neural network is introduced to input the power generation data of the photovoltaic power generation system under various meteorological characteristics into the graph neural network;

[0055] Taking the meteorological characteristics as the first node and the power generation data as the second node, a directed connection description relationship is constructed. Based on the directed connection description relationship, the first node is made to point to the second node, and the first node and the second node are connected to construct a topological structure diagram;

[0056] Based on the topological structure graph, an adjacency matrix is ​​obtained, and the Jaccard similarity coefficient between the first nodes in the adjacency matrix is ​​calculated, and the first nodes whose Jaccard similarity coefficient is greater than a preset Jaccard similarity coefficient threshold are merged to obtain the merged adjacency matrix, and a power generation data prediction model is constructed based on a convolutional neural network;

[0057] The merged adjacency matrix is ​​input into the power generation data prediction model for training. When the loss function of the power generation data prediction model converges to a preset value, the model parameters of the power generation data prediction model are saved and the power generation data prediction model is output.

[0058] It should be noted that meteorological characteristics include data such as temperature, humidity, light intensity, and solar radiation. Since the first node may have data with similar factors but different descriptions, such as Celsius temperature scale, Fahrenheit temperature scale, thermodynamic temperature scale, etc., they are actually the same factor but with different descriptions. By calculating the Jaccard similarity coefficient between the first nodes in the adjacency matrix, the first nodes with a Jaccard similarity coefficient greater than the preset Jaccard similarity coefficient threshold are merged, which can simplify the topological structure diagram, reduce the complexity of calculation, and optimize the power generation data prediction model. The power generation data includes power generation data, power generation power, and total power generation energy data within a unit time.

[0059] It should be noted that, further, in this method, the power generation data of each photovoltaic power generation system within a preset time is predicted based on the power generation data prediction model, specifically including:

[0060] Obtaining geographical location information of the photovoltaic power generation system, and performing data retrieval based on the geographical location information of the photovoltaic power generation system to obtain meteorological characteristic change data of the area where the photovoltaic power generation system is located within a preset time;

[0061] The meteorological characteristic change data of the area where the photovoltaic power generation system is located within the preset time is divided into several sub-periods, the meteorological characteristic data of each sub-period is counted, and the meteorological characteristic data of each sub-period is input into the power generation data prediction model for prediction, and the power generation data of each photovoltaic power generation system in each sub-period is obtained;

[0062] The power generation data of each photovoltaic power generation system in each sub-period is counted, the power generation data of each photovoltaic power generation system within a preset time is obtained, and the power generation data of each photovoltaic power generation system within the preset time is output.

[0063] like Figure 2As shown, further, in this method, a photovoltaic power generation system integration network is constructed, and real-time power generation data of each photovoltaic power generation system is obtained through the photovoltaic power generation system integration network, specifically:

[0064] S202: constructing a photovoltaic power generation system integrated network, sending each photovoltaic power generation system to the photovoltaic power generation system integrated network through a communication device, and forming a communication link by connecting the communication device with the photovoltaic power generation system integrated network;

[0065] S204: testing the communication delay data of each communication link, and determining whether the communication delay data of the communication link is greater than a preset communication delay threshold;

[0066] S206: When the communication delay data of the communication link is greater than the preset communication delay threshold, frequency modulation processing is performed on the communication device until the communication delay data of the communication link is no greater than the preset communication delay threshold;

[0067] S208: When the communication delay data of the communication link is not greater than the preset communication delay threshold, the photovoltaic power generation system integrated network is constructed, and the real-time power generation data of each photovoltaic power generation system is obtained through the photovoltaic power generation system integrated network.

[0068] It should be noted that the frequency modulation processing includes adjusting the type of electromagnetic waves, the wavelength of electromagnetic waves, etc. This method can optimize the photovoltaic power generation system integrated network, wherein each communication device forms a communication link with the photovoltaic power generation system integrated network.

[0069] Furthermore, in this method, several power generation efficiency ranges are set, and each photovoltaic power generation system is evaluated based on the power generation data of each photovoltaic power generation system within a preset time, the real-time power generation data of each photovoltaic power generation system, and the power generation efficiency range through a decision tree algorithm to obtain the power generation efficiency membership of each photovoltaic power generation system, specifically including:

[0070] Set several power generation efficiency ranges, introduce a decision tree algorithm, calculate the power generation efficiency of the photovoltaic power generation system based on the power generation data of each photovoltaic power generation system within a preset time and the real-time power generation data of each photovoltaic power generation system, and construct a set to be classified based on the power generation efficiency of the photovoltaic power generation system;

[0071] A root node is constructed according to the set to be classified, the root node is initialized and split based on the power generation efficiency range to generate a number of leaf nodes, and it is determined whether there are sample data of at least two power generation efficiency ranges in the leaf nodes;

[0072] When there are sample data of at least two power generation efficiency ranges in the leaf node, the leaf node is continuously split until there are no sample data of at least two power generation efficiency ranges in the leaf node;

[0073] When there are no sample data of at least two power generation efficiency ranges in the leaf node, the power generation efficiency membership corresponding to each leaf node is obtained, and the power generation efficiency membership of each photovoltaic power generation system is obtained according to the power generation efficiency membership corresponding to the leaf node.

[0074] It should be noted that, the ratio between the power generation data of each photovoltaic power generation system within the preset time and the real-time power generation data of each photovoltaic power generation system can be the power generation data of each photovoltaic power generation system within the preset time as the denominator, or can be used as the denominator. Technical personnel in this field can set it according to actual needs. When the ratio between the power generation data of each photovoltaic power generation system within the preset time and the real-time power generation data of each photovoltaic power generation system is not greater than the predetermined value, it means that an abnormality has occurred in the photovoltaic power generation system. The power generation efficiency membership includes low power generation efficiency membership, high power generation membership, ultra-high power generation membership, etc.; this method can quickly evaluate massive data and achieve rapid identification.

[0075] Furthermore, in this method, based on the power generation efficiency membership of each photovoltaic power generation system, the abnormal photovoltaic power generation system is identified and analyzed, the abnormal photovoltaic power generation system is obtained, and the abnormal photovoltaic power generation system is marked, and the marking information is displayed in a preset manner, specifically:

[0076] Setting a power generation efficiency membership evaluation index, and judging whether the power generation efficiency membership of the photovoltaic power generation system is greater than the power generation efficiency membership evaluation index;

[0077] When the power generation efficiency membership of the photovoltaic power generation system is greater than the power generation efficiency membership evaluation index, the corresponding photovoltaic power generation system is regarded as an abnormal photovoltaic power generation system, and the abnormal photovoltaic power generation system is marked, and the marking information is displayed in a preset manner;

[0078] When the power generation efficiency membership of the photovoltaic power generation system is not greater than the power generation efficiency membership evaluation index, the corresponding photovoltaic power generation system is regarded as a normal photovoltaic power generation system.

[0079] It should be noted that by setting a high power generation membership (such as a power generation efficiency between 80% and 90%) as a power generation efficiency membership evaluation index, this method can quickly evaluate massive data.

[0080] In addition, the method may further comprise the following steps:

[0081] Acquire service data information of photovoltaic power generation systems in a target area, construct a Bayesian network, input the service data information of photovoltaic power generation systems in the target area into the Bayesian network for training, and acquire a trained Bayesian network;

[0082] Acquiring service data information of photovoltaic power generation systems within a preset time, and inputting the service data information of photovoltaic power generation systems within the preset time into the trained Bayesian network to acquire fault information of each photovoltaic power generation system;

[0083] Acquire power generation demand information in the target area, introduce a particle swarm algorithm, acquire power generation demand time based on the power generation demand information, and determine whether the fault information of the photovoltaic power generation system is within the power generation demand time;

[0084] When the fault information of the photovoltaic power generation system is within the power generation demand time, the corresponding photovoltaic power generation system will not be used as a device for priority power generation. When the fault information of the photovoltaic power generation system is not within the power generation demand time, the corresponding photovoltaic power generation system will be used as a device for priority power generation, and the particle swarm algorithm is used to optimize the work objectives according to the priority power generation equipment and the power generation demand information in the target area.

[0085] The particle swarm algorithm is used to optimize the work objectives according to the equipment that is recommended to generate power and the power generation demand information in the target area, specifically including:

[0086] Acquire power generation data in the target area according to the power generation demand information in the target area, acquire estimated power generation data of the equipment that is preferentially recommended for power generation in each target area, and initialize the working target combination of the equipment that is preferentially recommended for power generation;

[0087] Obtaining estimated power generation data of each device with priority recommendation for power generation in the work target combination of devices with priority recommendation for power generation, and counting the estimated power generation data of each device with priority recommendation for power generation in the work target combination of devices with priority recommendation for power generation, to obtain total power generation data;

[0088] The number of iterations is set based on the particle swarm algorithm, and it is determined whether the total power generation data is greater than the power generation data in the target area. If so, a work target combination of the equipment that is preferentially recommended for power generation is output, and power generation is performed according to the work target combination of the equipment that is preferentially recommended for power generation;

[0089] When the total power generation data is not greater than the power generation data in the target area, the priority power generation equipment in the working target combination of the priority power generation equipment is readjusted until the total power generation data is greater than the power generation data in the target area.

[0090] It should be noted that this method fully considers the fault conditions in the power generation process, and optimizes the power generation equipment according to the fault conditions, making the power generation work in the target area more reasonable and enabling the photovoltaic power generation system to proceed in an orderly manner.

[0091] like Figure 3 As shown, the second aspect of the present invention provides an integrated identification and analysis system 4 for a photovoltaic power generation system, the system comprising a memory 41 and a processor 42, the memory 41 comprising an integrated identification and analysis method program for a photovoltaic power generation system, when the integrated identification and analysis method program for a photovoltaic power generation system is executed by the processor 42, the following steps are implemented:

[0092] The power generation data of the photovoltaic power generation system under various meteorological characteristics is obtained through big data, and a power generation data prediction model is constructed based on the power generation data of the photovoltaic power generation system under various meteorological characteristics;

[0093] Based on the power generation data prediction model, the power generation data of each photovoltaic power generation system within a preset time is predicted, and a photovoltaic power generation system integration network is constructed to obtain the real-time power generation data of each photovoltaic power generation system through the photovoltaic power generation system integration network;

[0094] Set a number of power generation efficiency ranges, and evaluate each photovoltaic power generation system based on the power generation data of each photovoltaic power generation system within a preset time, the real-time power generation data of each photovoltaic power generation system, and the power generation efficiency range through a decision tree algorithm to obtain the power generation efficiency membership of each photovoltaic power generation system;

[0095] Based on the power generation efficiency membership of each photovoltaic power generation system, the abnormal photovoltaic power generation system is identified and analyzed, the abnormal photovoltaic power generation system is obtained, and the abnormal photovoltaic power generation system is marked, and the marked information is displayed in a preset manner.

[0096] Furthermore, in this system, the power generation data of the photovoltaic power generation system under various meteorological characteristics is obtained through big data, and a power generation data prediction model is constructed based on the power generation data of the photovoltaic power generation system under various meteorological characteristics, specifically including:

[0097] The power generation data of the photovoltaic power generation system under various meteorological characteristics is obtained through big data, and the graph neural network is introduced to input the power generation data of the photovoltaic power generation system under various meteorological characteristics into the graph neural network;

[0098] Taking the meteorological characteristics as the first node and the power generation data as the second node, a directed connection description relationship is constructed. Based on the directed connection description relationship, the first node is made to point to the second node, and the first node and the second node are connected to construct a topological structure diagram;

[0099] Based on the topological structure graph, an adjacency matrix is ​​obtained, and the Jaccard similarity coefficient between the first nodes in the adjacency matrix is ​​calculated, and the first nodes whose Jaccard similarity coefficient is greater than a preset Jaccard similarity coefficient threshold are merged to obtain the merged adjacency matrix, and a power generation data prediction model is constructed based on a convolutional neural network;

[0100] The merged adjacency matrix is ​​input into the power generation data prediction model for training. When the loss function of the power generation data prediction model converges to a preset value, the model parameters of the power generation data prediction model are saved and the power generation data prediction model is output.

[0101] Furthermore, in this system, the power generation data of each photovoltaic power generation system within a preset time is predicted based on the power generation data prediction model, specifically including:

[0102] Obtaining geographical location information of the photovoltaic power generation system, and performing data retrieval based on the geographical location information of the photovoltaic power generation system to obtain meteorological characteristic change data of the area where the photovoltaic power generation system is located within a preset time;

[0103] The meteorological characteristic change data of the area where the photovoltaic power generation system is located within the preset time is divided into several sub-periods, the meteorological characteristic data of each sub-period is counted, and the meteorological characteristic data of each sub-period is input into the power generation data prediction model for prediction, and the power generation data of each photovoltaic power generation system in each sub-period is obtained;

[0104] The power generation data of each photovoltaic power generation system in each sub-period is counted, the power generation data of each photovoltaic power generation system within a preset time is obtained, and the power generation data of each photovoltaic power generation system within the preset time is output.

[0105] Furthermore, in this system, a photovoltaic power generation system integration network is constructed, and real-time power generation data of each photovoltaic power generation system is obtained through the photovoltaic power generation system integration network, specifically:

[0106] Constructing a photovoltaic power generation system integrated network, sending each photovoltaic power generation system to the photovoltaic power generation system integrated network through a communication device, and forming a communication link through the connection between the communication device and the photovoltaic power generation system integrated network;

[0107] Testing the communication delay data of each communication link, and determining whether the communication delay data of the communication link is greater than a preset communication delay threshold;

[0108] When the communication delay data of the communication link is greater than the preset communication delay threshold, the communication device is subjected to frequency modulation processing until the communication delay data of the communication link is no greater than the preset communication delay threshold;

[0109] When the communication delay data of the communication link is not greater than a preset communication delay threshold, the photovoltaic power generation system integrated network is constructed, and the real-time power generation data of each photovoltaic power generation system is obtained through the photovoltaic power generation system integrated network.

[0110] Furthermore, in this system, several power generation efficiency ranges are set, and each photovoltaic power generation system is evaluated based on the power generation data of each photovoltaic power generation system within a preset time, the real-time power generation data of each photovoltaic power generation system, and the power generation efficiency range through a decision tree algorithm to obtain the power generation efficiency membership of each photovoltaic power generation system, specifically including:

[0111] Set several power generation efficiency ranges, introduce a decision tree algorithm, calculate the power generation efficiency of the photovoltaic power generation system based on the power generation data of each photovoltaic power generation system within a preset time and the real-time power generation data of each photovoltaic power generation system, and construct a set to be classified based on the power generation efficiency of the photovoltaic power generation system;

[0112] A root node is constructed according to the set to be classified, the root node is initialized and split based on the power generation efficiency range to generate a number of leaf nodes, and it is determined whether there are sample data of at least two power generation efficiency ranges in the leaf nodes;

[0113] When there are sample data of at least two power generation efficiency ranges in the leaf node, the leaf node is continuously split until there are no sample data of at least two power generation efficiency ranges in the leaf node;

[0114] When there are no sample data of at least two power generation efficiency ranges in the leaf node, the power generation efficiency membership corresponding to each leaf node is obtained, and the power generation efficiency membership of each photovoltaic power generation system is obtained according to the power generation efficiency membership corresponding to the leaf node.

[0115] Furthermore, in this system, based on the power generation efficiency membership of each photovoltaic power generation system, the abnormal photovoltaic power generation system is identified and analyzed, the abnormal photovoltaic power generation system is obtained, and the abnormal photovoltaic power generation system is marked, and the marking information is displayed in a preset manner, specifically:

[0116] Setting a power generation efficiency membership evaluation index, and judging whether the power generation efficiency membership of the photovoltaic power generation system is greater than the power generation efficiency membership evaluation index;

[0117] When the power generation efficiency membership of the photovoltaic power generation system is greater than the power generation efficiency membership evaluation index, the corresponding photovoltaic power generation system is regarded as an abnormal photovoltaic power generation system, and the abnormal photovoltaic power generation system is marked, and the marking information is displayed in a preset manner;

[0118] When the power generation efficiency membership of the photovoltaic power generation system is not greater than the power generation efficiency membership evaluation index, the corresponding photovoltaic power generation system is regarded as a normal photovoltaic power generation system.

[0119] A third aspect of the present invention provides a computer-readable storage medium, which includes a program for an integrated identification and analysis method for a photovoltaic power generation system. When the program for the integrated identification and analysis method for a photovoltaic power generation system is executed by a processor, any step of the integrated identification and analysis method for a photovoltaic power generation system is implemented.

[0120] 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.

[0121] 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.

[0122] 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.

[0123] 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.

[0124] 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 of 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.

[0125] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art who is familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. An integrated identification and analysis method for a photovoltaic power generation system, characterized in that: The following steps are involved: Acquire power generation data of the photovoltaic power generation system under various meteorological characteristics through big data, and build a power generation data prediction model based on the power generation data of the photovoltaic power generation system under various meteorological characteristics; Predicting the power generation data of each photovoltaic power generation system within a preset time based on the power generation data prediction model, building a photovoltaic power generation system integration network, and obtaining the real-time power generation data of each photovoltaic power generation system through the photovoltaic power generation system integration network; Setting a number of power generation efficiency ranges, and evaluating each photovoltaic power generation system by a decision tree algorithm based on the power generation data of each photovoltaic power generation system within the preset time, the real-time power generation data of each photovoltaic power generation system, and the power generation efficiency range, to obtain the power generation efficiency membership of each photovoltaic power generation system; Based on the power generation efficiency membership of each photovoltaic power generation system, an abnormal photovoltaic power generation system is identified and analyzed, the abnormal photovoltaic power generation system is obtained, and the abnormal photovoltaic power generation system is marked, and the marking information is displayed in a preset manner; The power generation data of the photovoltaic power generation system under various meteorological characteristics is obtained through big data, and a power generation data prediction model is constructed based on the power generation data of the photovoltaic power generation system under various meteorological characteristics, specifically including: The power generation data of the photovoltaic power generation system under various meteorological characteristics is obtained through big data, and the graph neural network is introduced to input the power generation data of the photovoltaic power generation system under various meteorological characteristics into the graph neural network; Taking the meteorological characteristics as the first node and the power generation data as the second node, a directed connection description relationship is constructed, based on the directed connection description relationship, the first node is made to point to the second node, and the first node and the second node are connected to construct a topological structure diagram; Based on the topological structure diagram, an adjacency matrix is ​​obtained, and the Jaccard similarity coefficient between the first nodes in the adjacency matrix is ​​calculated, and the first nodes whose Jaccard similarity coefficient is greater than a preset Jaccard similarity coefficient threshold are merged to obtain a merged adjacency matrix, and a power generation data prediction model is constructed based on a convolutional neural network; Inputting the merged adjacency matrix into the power generation data prediction model for training, and when the loss function of the power generation data prediction model converges to a preset value, saving the model parameters of the power generation data prediction model, and outputting the power generation data prediction model; A number of power generation efficiency ranges are set, and each photovoltaic power generation system is evaluated based on the power generation data of each photovoltaic power generation system within the preset time, the real-time power generation data of each photovoltaic power generation system, and the power generation efficiency range through a decision tree algorithm to obtain the power generation efficiency membership of each photovoltaic power generation system, specifically including: Setting a number of power generation efficiency ranges, introducing a decision tree algorithm, calculating the power generation efficiency of the photovoltaic power generation system based on the power generation data of each photovoltaic power generation system within the preset time and the real-time power generation data of each photovoltaic power generation system, and constructing a set to be classified based on the power generation efficiency of the photovoltaic power generation system; Constructing a root node according to the set to be classified, performing initialization splitting on the root node based on the power generation efficiency range to generate a plurality of leaf nodes, and determining whether there are sample data of at least two power generation efficiency ranges in the leaf nodes; When there are sample data of at least two power generation efficiency ranges in the leaf node, the leaf node is continuously split until there are no sample data of at least two power generation efficiency ranges in the leaf node; When there are no sample data of at least two power generation efficiency ranges in the leaf node, the power generation efficiency membership corresponding to each leaf node is obtained, and the power generation efficiency membership of each photovoltaic power generation system is obtained according to the power generation efficiency membership corresponding to the leaf node.

2. The integrated identification and analysis method of a photovoltaic power generation system according to claim 1, characterized in that: Predicting the power generation data of each photovoltaic power generation system within a preset time based on the power generation data prediction model specifically includes: Obtaining geographical location information of the photovoltaic power generation system, and performing data retrieval based on the geographical location information of the photovoltaic power generation system to obtain meteorological characteristic change data of the area where the photovoltaic power generation system is located within a preset time; Divide the meteorological characteristic change data of the area where the photovoltaic power generation system is located within a preset time into several sub-periods, count the meteorological characteristic data of each sub-period, and input the meteorological characteristic data of each sub-period into a power generation data prediction model for prediction, and obtain the power generation data of each photovoltaic power generation system in each sub-period; The power generation data of each photovoltaic power generation system in each sub-period is counted, the power generation data of each photovoltaic power generation system within a preset time is obtained, and the power generation data of each photovoltaic power generation system within the preset time is output.

3. The integrated identification and analysis method of a photovoltaic power generation system according to claim 1, characterized in that: Constructing a photovoltaic power generation system integrated network, and obtaining real-time power generation data of each photovoltaic power generation system through the photovoltaic power generation system integrated network, specifically: Constructing a photovoltaic power generation system integrated network, sending each photovoltaic power generation system to the photovoltaic power generation system integrated network through a communication device, and forming a communication link through the connection between the communication device and the photovoltaic power generation system integrated network; Testing the communication delay data of each communication link, and determining whether the communication delay data of the communication link is greater than a preset communication delay threshold; When the communication delay data of the communication link is greater than the preset communication delay threshold, frequency modulation processing is performed on the communication device until the communication delay data of the communication link is no greater than the preset communication delay threshold; When the communication delay data of the communication link is not greater than the preset communication delay threshold, the photovoltaic power generation system integrated network is constructed, and the real-time power generation data of each photovoltaic power generation system is obtained through the photovoltaic power generation system integrated network.

4. The integrated identification and analysis method of a photovoltaic power generation system according to claim 1, characterized in that: Based on the power generation efficiency membership of each photovoltaic power generation system, the abnormal photovoltaic power generation system is identified and analyzed, the abnormal photovoltaic power generation system is obtained, and the abnormal photovoltaic power generation system is marked, and the marking information is displayed in a preset manner, specifically: Setting a power generation efficiency membership evaluation index, and determining whether the power generation efficiency membership of the photovoltaic power generation system is greater than the power generation efficiency membership evaluation index; When the power generation efficiency membership of the photovoltaic power generation system is greater than the power generation efficiency membership evaluation index, the corresponding photovoltaic power generation system is regarded as an abnormal photovoltaic power generation system, and the abnormal photovoltaic power generation system is marked, and the marking information is displayed in a preset manner; When the power generation efficiency membership of the photovoltaic power generation system is not greater than the power generation efficiency membership evaluation index, the corresponding photovoltaic power generation system is regarded as a normal photovoltaic power generation system.

5. An integrated identification and analysis system for photovoltaic power generation system, characterized in that: The system includes a memory and a processor, wherein the memory includes an integrated identification and analysis method program for a photovoltaic power generation system, and when the integrated identification and analysis method program for a photovoltaic power generation system is executed by the processor, the following steps are implemented: Acquire power generation data of the photovoltaic power generation system under various meteorological characteristics through big data, and build a power generation data prediction model based on the power generation data of the photovoltaic power generation system under various meteorological characteristics; Predicting the power generation data of each photovoltaic power generation system within a preset time based on the power generation data prediction model, building a photovoltaic power generation system integration network, and obtaining the real-time power generation data of each photovoltaic power generation system through the photovoltaic power generation system integration network; Setting a number of power generation efficiency ranges, and evaluating each photovoltaic power generation system by a decision tree algorithm based on the power generation data of each photovoltaic power generation system within the preset time, the real-time power generation data of each photovoltaic power generation system, and the power generation efficiency range, to obtain the power generation efficiency membership of each photovoltaic power generation system; Based on the power generation efficiency membership of each photovoltaic power generation system, an abnormal photovoltaic power generation system is identified and analyzed, the abnormal photovoltaic power generation system is obtained, and the abnormal photovoltaic power generation system is marked, and the marking information is displayed in a preset manner; The power generation data of the photovoltaic power generation system under various meteorological characteristics is obtained through big data, and a power generation data prediction model is constructed based on the power generation data of the photovoltaic power generation system under various meteorological characteristics, specifically including: The power generation data of the photovoltaic power generation system under various meteorological characteristics is obtained through big data, and the graph neural network is introduced to input the power generation data of the photovoltaic power generation system under various meteorological characteristics into the graph neural network; Taking the meteorological characteristics as the first node and the power generation data as the second node, a directed connection description relationship is constructed, based on the directed connection description relationship, the first node is made to point to the second node, and the first node and the second node are connected to construct a topological structure diagram; Based on the topological structure diagram, an adjacency matrix is ​​obtained, and the Jaccard similarity coefficient between the first nodes in the adjacency matrix is ​​calculated, and the first nodes whose Jaccard similarity coefficient is greater than a preset Jaccard similarity coefficient threshold are merged to obtain a merged adjacency matrix, and a power generation data prediction model is constructed based on a convolutional neural network; Inputting the merged adjacency matrix into the power generation data prediction model for training, and when the loss function of the power generation data prediction model converges to a preset value, saving the model parameters of the power generation data prediction model, and outputting the power generation data prediction model; A number of power generation efficiency ranges are set, and each photovoltaic power generation system is evaluated based on the power generation data of each photovoltaic power generation system within the preset time, the real-time power generation data of each photovoltaic power generation system, and the power generation efficiency range through a decision tree algorithm to obtain the power generation efficiency membership of each photovoltaic power generation system, specifically including: Setting a number of power generation efficiency ranges, introducing a decision tree algorithm, calculating the power generation efficiency of the photovoltaic power generation system based on the power generation data of each photovoltaic power generation system within the preset time and the real-time power generation data of each photovoltaic power generation system, and constructing a set to be classified based on the power generation efficiency of the photovoltaic power generation system; Constructing a root node according to the set to be classified, performing initialization splitting on the root node based on the power generation efficiency range to generate a plurality of leaf nodes, and determining whether there are sample data of at least two power generation efficiency ranges in the leaf nodes; When there are sample data of at least two power generation efficiency ranges in the leaf node, the leaf node is continuously split until there are no sample data of at least two power generation efficiency ranges in the leaf node; When there are no sample data of at least two power generation efficiency ranges in the leaf node, the power generation efficiency membership corresponding to each leaf node is obtained, and the power generation efficiency membership of each photovoltaic power generation system is obtained according to the power generation efficiency membership corresponding to the leaf node.

6. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes an integrated identification and analysis method program for a photovoltaic power generation system. When the integrated identification and analysis method program for a photovoltaic power generation system is executed by a processor, the steps of the integrated identification and analysis method for a photovoltaic power generation system as described in any one of claims 1 to 4 are implemented.

Images