Photovoltaic power station operation and maintenance management method and device based on big data, equipment and medium

Abstract

The invention discloses a photovoltaic power station operation and maintenance management method and device based on big data, equipment and a medium. The method comprises the steps of obtaining an operation and maintenance data set of a target photovoltaic power station in a historical time period; constructing a photovoltaic power station operation state prediction neural network model and a photovoltaic power station knowledge graph; based on the photovoltaic power station operation state prediction neural network model, obtaining a predicted operation state of the target photovoltaic power station in a preset time period; obtaining a node actual operation state and a node prediction operation state when the target photovoltaic power station arrives at the starting time node of the preset time period, wherein the node prediction operation state belongs to the prediction operation state; and determining a target processing instruction in the knowledge graph of the photovoltaic power station according to the actual operation state of the node and the predicted operation state of the node, and controlling the target photovoltaic power station to operate according to the target processing instruction. The invention belongs to the field of photovoltaic power station operation and maintenance. According to the invention, the neural network and the knowledge graph can be combined, and intelligent operation and maintenance of the photovoltaic power station can be realized.

Description

Technical Field

[0001] The present invention relates to the field of operation and maintenance of photovoltaic power stations, and particularly to a method, device, equipment and medium for operation and maintenance management of photovoltaic power stations based on big data. Background Art

[0002] A photovoltaic power station, abbreviated as a PV power station, is a power generation facility that converts solar energy into electrical energy by using the photovoltaic effect of sunlight. The core component of a photovoltaic power station is a photovoltaic panel (also called a solar panel), which is composed of multiple photovoltaic cells, and each photovoltaic cell is made of a semiconductor material (such as silicon). The photovoltaic panel can directly convert the received sunlight into direct current.

[0003] Currently, the operation and maintenance of publicly disclosed photovoltaic power stations only collect data, monitor equipment, videos, environment, and give fault warnings for photovoltaic power stations. It is difficult to predict the future operation status of photovoltaic power stations, which means that it is even more difficult to determine the future operation and maintenance strategies of photovoltaic power stations. Therefore, there is an urgent need for a method for operation and maintenance management of photovoltaic power stations. Summary of the Invention

[0004] By providing a method, device, equipment and medium for operation and maintenance management of photovoltaic power stations based on big data, the present invention solves the technical problem that it is difficult to determine the future operation and maintenance strategies of photovoltaic power stations in the prior art, and realizes the technical effect of being able to predict the future operation status of photovoltaic power stations while arranging corresponding operation and maintenance strategies.

[0005] In a first aspect, the present invention provides a method for operation and maintenance management of a photovoltaic power station based on big data, the method comprising:

[0006] Obtain an operation and maintenance data set of a target photovoltaic power station within a historical time period. The operation and maintenance data set includes photovoltaic operation and maintenance data and processing instruction data. The photovoltaic operation and maintenance data includes: photovoltaic panel working environment data, photovoltaic panel operation data, parameter data of the photovoltaic panel, and historical fault data and repair data of the photovoltaic panel. The photovoltaic operation and maintenance data corresponds to the processing instruction data one by one;

[0007] Based on the operation and maintenance data set of the target photovoltaic power station, construct a neural network model for predicting the operation status of the photovoltaic power station and construct a knowledge graph of the photovoltaic power station;

[0008] Based on the neural network model for predicting the operation status of the photovoltaic power station, obtain the predicted operation status of the target photovoltaic power station within a preset time period;

[0009] Obtain the actual operation status and the predicted operation status of the node when the target photovoltaic power station reaches the start time node of the preset time period. The predicted operation status of the node belongs to the predicted operation status;

[0010] Determine a target processing instruction in the knowledge graph of the photovoltaic power station according to the actual operating state of the node and the predicted operating state of the node, and control the target photovoltaic power station to operate according to the target processing instruction.

[0011] Further, determining a target processing instruction in the knowledge graph of the photovoltaic power station according to the actual operating state of the node and the predicted operating state of the node includes:

[0012] Determine the operating parameter difference between the actual operating state of the node and the predicted operating state of the node;

[0013] When the operating parameter difference is greater than the difference threshold, in the knowledge graph of the photovoltaic power station, determine the target processing instruction according to the actual operating state of the node, and send an alarm message to the client; otherwise, in the knowledge graph of the photovoltaic power station, determine the target processing instruction according to the predicted operating state of the node.

[0014] Further, in the knowledge graph of the photovoltaic power station, determining the target processing instruction according to the predicted operating state of the node includes:

[0015] According to the predicted operating state of the node, determine the entity, association relationship and attribute corresponding to the predicted operating state of the node in the knowledge graph of the photovoltaic power station;

[0016] Determine the target processing instruction among the entity, association relationship and attribute corresponding to the predicted operating state of the node.

[0017] Further, based on the operation and maintenance data set of the target photovoltaic power station, construct a neural network model for predicting the operating state of the photovoltaic power station, including:

[0018] Combine the photovoltaic operation and maintenance data in the operation and maintenance data set with the corresponding processing instruction data to obtain data groups, and a total of several data groups are obtained;

[0019] Input several data groups into the neural network model to be trained, and obtain the predicted operating state corresponding to each data group;

[0020] Adjust the neural network parameters of the neural network model to be trained according to the predicted operating state and the actual operating state corresponding to the data group;

[0021] When the preset training requirements are met, save the latest neural network parameters, and use the neural network model to be trained corresponding to the latest neural network parameters as the neural network model for predicting the operating state of the photovoltaic power station.

[0022] Further, based on the operation and maintenance data set of the target photovoltaic power station, construct a knowledge graph of the photovoltaic power station, including:

[0023] Define the entity, association relationship and attribute of the knowledge graph of the photovoltaic power station;

[0024] Map several data in the operation and maintenance dataset to entities, association relationships, or attributes in sequence to construct a knowledge graph of a photovoltaic power station.

[0025] Furthermore, the loss function of the neural network model to be trained includes:

[0026]

[0027] Where M is the number of data groups, i is the i-th data group, P i The adjustment weight of the i-th data group, X i Is the actual operating state corresponding to the i-th data group, X i y is the predicted operating state corresponding to the i-th data group, L is the total average loss, τ is the regularization coefficient, and θ is all learnable neural network parameters in the neural network model to be trained.

[0028] Furthermore, the neural network parameters include:

[0029] Weight matrix, bias vector, parameters of the activation function, learning rate, and decay rate.

[0030] In a second aspect, the present invention provides a photovoltaic power station operation and maintenance management device based on big data. The device includes:

[0031] An acquisition module for acquiring an operation and maintenance dataset of a target photovoltaic power station within a historical time period. The operation and maintenance dataset includes photovoltaic operation and maintenance data and processing instruction data. The photovoltaic operation and maintenance data includes: photovoltaic panel working environment data, photovoltaic panel operation data, photovoltaic panel parameter data, and photovoltaic panel historical fault data and repair data. The photovoltaic operation and maintenance data corresponds to the processing instruction data one by one;

[0032] A construction module for constructing a photovoltaic power station operation state prediction neural network model and constructing a knowledge graph of the photovoltaic power station based on the operation and maintenance dataset of the target photovoltaic power station;

[0033] An operation prediction module for obtaining the predicted operation state of the target photovoltaic power station within a preset time period based on the photovoltaic power station operation state prediction neural network model;

[0034] A comparison module for obtaining the node actual operation state and the node predicted operation state of the target photovoltaic power station when reaching the start time node of the preset time period. The node predicted operation state belongs to the predicted operation state;

[0035] An operation and maintenance module for determining a target processing instruction in the knowledge graph of the photovoltaic power station according to the node actual operation state and the node predicted operation state, and controlling the target photovoltaic power station to operate with the target processing instruction.

[0036] In a third aspect, the present invention provides an electronic device, comprising:

[0037] a processor;

[0038] a memory for storing instructions executable by the processor;

[0039] wherein the processor is configured to execute to implement the big data-based photovoltaic power station operation and maintenance management method provided in the first aspect.

[0040] In a fourth aspect, the present invention provides a non-transitory computer-readable storage medium, when the instructions in the storage medium are executed by the processor of the electronic device, enabling the electronic device to execute and implement the big data-based photovoltaic power station operation and maintenance management method provided in the first aspect.

[0041] One or more technical solutions provided in the present invention have at least the following technical effects or advantages:

[0042] In the loss function provided in the present invention, by adding a regularization term to the loss function, the excessive complexity of the model can be penalized, thereby avoiding the overfitting phenomenon. By minimizing the loss function, the model can better fit the data.

[0043] In the process of performing operation and maintenance on the photovoltaic power station, the present invention combines a neural network model and a knowledge graph. Through the neural network model trained with historical operation and maintenance data, the future operating state of the photovoltaic power station can be predicted. Based on the predicted data, the knowledge graph can help quickly find the most appropriate processing instructions. Based on the historical fault patterns and their corresponding solutions recorded in the knowledge graph, combined with the current or predicted state information, the fault location process can be accelerated, and targeted suggestions for maintenance can be provided, reducing the downtime and costs. And once the target processing instruction is determined, the photovoltaic power station can be automatically controlled to operate according to this instruction, reducing the need for human intervention, improving the response speed and operation consistency. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0045] Figure 1 It is a schematic flowchart of the big data-based photovoltaic power station operation and maintenance management method provided by the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0046] Embodiments of the present invention provide a method for operation and maintenance management of a photovoltaic power station based on big data, which solves the technical problem that it is difficult to determine the future operation and maintenance strategies of photovoltaic power stations in the prior art.

[0047] The technical solution of the present invention to solve the above technical problem is as follows:

[0048] A method for operation and maintenance management of a photovoltaic power station based on big data, the method includes: obtaining an operation and maintenance data set of a target photovoltaic power station in a historical time period, the operation and maintenance data set includes photovoltaic operation and maintenance data and processing instruction data, and the photovoltaic operation and maintenance data includes: photovoltaic panel working environment data, photovoltaic panel operation data, parameter data of the photovoltaic panel, historical fault data and repair data of the photovoltaic panel, and the photovoltaic operation and maintenance data corresponds to the processing instruction data one by one; based on the operation and maintenance data set of the target photovoltaic power station, constructing a neural network model for predicting the operation state of the photovoltaic power station and constructing a knowledge graph of the photovoltaic power station; based on the neural network model for predicting the operation state of the photovoltaic power station, obtaining the predicted operation state of the target photovoltaic power station in a preset time period; obtaining the actual operation state and the predicted operation state of the node when the target photovoltaic power station reaches the starting time node of the preset time period, and the predicted operation state of the node belongs to the predicted operation state;

[0049] According to the actual operation state of the node and the predicted operation state of the node, determining a target processing instruction in the knowledge graph of the photovoltaic power station, and controlling the target photovoltaic power station to operate with the target processing instruction.

[0050] To better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings of the specification and specific embodiments.

[0051] First, it should be noted that the term "and / or" appearing in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " in this article generally represents an "or" relationship between the front and rear associated objects.

[0052] The present invention provides a method for operation and maintenance management of a photovoltaic power station based on big data as shown in Figure 1 and includes steps S11 - S15:

[0053] Step S11, obtaining an operation and maintenance data set of a target photovoltaic power station in a historical time period, the operation and maintenance data set includes photovoltaic operation and maintenance data and processing instruction data, and the photovoltaic operation and maintenance data includes: photovoltaic panel working environment data, photovoltaic panel operation data, parameter data of the photovoltaic panel, historical fault data and repair data of the photovoltaic panel, and the photovoltaic operation and maintenance data corresponds to the processing instruction data one by one.

[0054] A photovoltaic power station, abbreviated as PV power station, is a power generation facility that converts solar energy into electrical energy using the photovoltaic effect of sunlight. The core component of a photovoltaic power station is the photovoltaic panel (also known as a solar panel), which is composed of multiple photovoltaic cells, and each photovoltaic cell is made of semiconductor materials (such as silicon). The photovoltaic panel can directly convert the received sunlight into direct current electricity.

[0055] The historical time period refers to a certain time period in the past when the photovoltaic equipment was operating. The length of the historical time period can be customized, such as several months or several years.

[0056] Photovoltaic operation and maintenance data refers to the data related to the daily operation and maintenance of the target photovoltaic power station; processing instruction data refers to the specific measures or commands taken for a certain operation and maintenance event. The processing instructions can be issued by staff or by an automated control system. It can be understood that the processing instructions can include processing measures for faulty equipment, maintaining the current operating state, or adjusting the operating parameters of a certain equipment when a photovoltaic equipment is operating normally, etc.

[0057] The working environment data of the photovoltaic panel includes environmental factors such as temperature, humidity, wind speed, and sunlight intensity. The working environment data of the photovoltaic panel will affect the working efficiency of the photovoltaic panel. The operating data of the photovoltaic panel involves the actual output performance of the photovoltaic panel. The operating data of the photovoltaic panel includes voltage, current, and power, etc. The parameter data of the photovoltaic panel refers to the technical specifications and set values of the photovoltaic panel. The historical fault data and repair data of the photovoltaic panel include historical fault conditions and their corresponding repair actions.

[0058] Step S12: Based on the operation and maintenance data set of the target photovoltaic power station, construct a neural network model for predicting the operation state of the photovoltaic power station and construct a knowledge graph of the photovoltaic power station.

[0059]

Construct a neural network model for predicting the operation state of the photovoltaic power station

[0060] Combine the photovoltaic operation and maintenance data in the operation and maintenance data set with the corresponding processing instruction data to obtain data groups, and a total of several data groups are obtained; input the several data groups into the neural network model to be trained, and obtain the predicted operation state corresponding to each data group; adjust the neural network parameters of the neural network model to be trained according to the predicted operation state and the actual operation state corresponding to the data group; when the preset training requirements are met, save the latest neural network parameters, and use the neural network model to be trained corresponding to the latest neural network parameters as the neural network model for predicting the operation state of the photovoltaic power station.

[0061] It should be noted that the photovoltaic operation and maintenance data at each moment corresponds one-to-one with the processing instruction data. Even if the fault phenomena of photovoltaic devices are the same, the processing instructions may be different under different environments or parameters. Therefore, it is necessary to perform corresponding matching on the photovoltaic operation and maintenance data and the processing instruction data at each moment. After matching, the data group at that moment can be obtained. What the neural network model to be trained predicts is the operating state of the photovoltaic power station after being processed with the corresponding processing instruction data under the photovoltaic operation and maintenance data. The actual operating state of the photovoltaic power station processed with the processing instruction data is compared with the predicted operating state to obtain the difference, and the neural network parameters of the neural network model to be trained are adjusted with the difference.

[0062] The loss function of the neural network model to be trained provided by the present invention includes:

[0063]

[0064] where M is the number of data groups, i is the i-th data group, P o is the adjustment weight of the i-th data group, X o is the actual operating state corresponding to the i-th data group, X oy is the predicted operating state corresponding to the i-th data group, L is the total average loss, τ is the regularization coefficient, and θ is all the learnable neural network parameters in the neural network model to be trained. The learnable neural network parameters may include: weight matrix, bias vector, parameters of the activation function, learning rate, and decay rate.

[0065] In the loss function provided by the present invention, by adding a regularization term to the loss function, the excessive complexity of the model can be penalized, thereby avoiding the overfitting phenomenon. By minimizing the loss function, the model can better fit the data.

[0066]

Constructing the Knowledge Graph of Photovoltaic Power Station

[0067] Define the entities, association relationships, and attributes of the knowledge graph of the photovoltaic power station; map several data in the operation and maintenance dataset to the entities, association relationships, or attributes in turn to construct the knowledge graph of the photovoltaic power station.

[0068] Constructing the knowledge graph (KG) of the photovoltaic power station involves defining entities, relationships, and attributes.

[0069] A knowledge graph is a structured semantic network used to represent the complex relationships between different entities in the real world and the characteristics of each entity.

[0070] Entity: Represents an actual object or concept in a knowledge graph. For example, photovoltaic panels, inverters, transformers, weather conditions, etc. are all entities in a photovoltaic power station.

[0071] Associative relationship: Describes the logical connections that exist between entities, such as connection, location, monitoring, influence, etc. For example, there is a "connection" relationship between photovoltaic panels and inverters; weather conditions have an "influence" on photovoltaic panels.

[0072] Attribute: The characteristics or states of an entity itself, such as size, efficiency, temperature, power output, etc. For a photovoltaic panel, its material type, maximum output power, installation angle, etc. are all attributes.

[0073] The specific process can be as follows: Identify all key components in the photovoltaic power station as entities, such as photovoltaic panels, brackets, cables, inverters, transformers, monitoring systems, etc. Determine the interaction methods between entities (i.e., the changes in the photovoltaic power station after real-time instructions), and set specific attributes for each entity, such as the model, rated power, and tilt angle of the photovoltaic panel; the maximum input voltage and conversion efficiency of the inverter, etc.

[0074] Map the working environment data of the photovoltaic panel to the attributes of the corresponding photovoltaic panel entity. Map the operating data of the photovoltaic panel to the relevant attributes of the photovoltaic panel entity as well. Map the parameter data of the photovoltaic panel to the technical specification attributes of the photovoltaic panel entity. For historical fault data and repair data, new entities (such as fault events) and associative relationships (such as caused or repaired) can be created, and specific information such as time, cause, and solution can be mapped to the attributes of these new entities. By integrating the entities, associative relationships, and attributes defined above, a complete knowledge graph of the photovoltaic power station is formed.

[0075] Step S13: Based on the neural network model for predicting the operating state of the photovoltaic power station, obtain the predicted operating state of the target photovoltaic power station within a preset time period.

[0076] The preset time period refers to a period of time in the future. The real-time operation and maintenance data set of the photovoltaic power station can be obtained and input into the neural network model for predicting the operating state of the photovoltaic power station to obtain the predicted operating state of the target photovoltaic power station within the preset time period. For the accuracy of prediction, the duration of the preset time period can be set to several hours in the future.

[0077] Step S14: Obtain the actual operating state of the node and the predicted operating state of the node when the target photovoltaic power station reaches the start time node of the preset time period. The predicted operating state of the node belongs to the predicted operating state.

[0078] When reaching the start time node of the preset time period, directly obtain the actual operating status of the target photovoltaic power station at the start time node, and obtain the predicted operating status of the target photovoltaic power station at the start time node when reaching the preset time period.

[0079] Step S15, determine the target processing instruction in the photovoltaic power station knowledge graph according to the actual node operating status and the predicted node operating status, and control the target photovoltaic power station to operate with the target processing instruction.

[0080] Compare the actual node operating status and the predicted node operating status (that is, compare the operating parameters of each photovoltaic device in the target photovoltaic power station).

[0081] Specifically include:

[0082] Determine the operating parameter difference between the actual node operating status and the predicted node operating status; when the operating parameter difference is greater than the difference threshold, in the photovoltaic power station knowledge graph, determine the target processing instruction according to the actual node operating status, and send an alarm message to the client; otherwise, in the photovoltaic power station knowledge graph, determine the target processing instruction according to the predicted node operating status.

[0083] When the operating parameter difference is greater than the difference threshold, it indicates that the predicted operating status of the nodes of the target photovoltaic power station at the start time node is inaccurate. The reason for the inaccurate prediction may be that the operating parameters of each photovoltaic device in the target photovoltaic power station have changed greatly in a short period of time, which may mean that a concentrated fault event has occurred. Therefore, the alarm message can be sent to the client for relevant staff to check and verify.

[0084] When the operating parameter difference is less than or equal to the difference threshold, it indicates that the target photovoltaic power station is operating in the expected operating status.

[0085]

Determine the target processing instruction based on the predicted node operating status

[0086] In the photovoltaic power station knowledge graph, determine the target processing instruction according to the predicted node operating status, including: according to the predicted node operating status, determine the entity, association relationship and attribute corresponding to the predicted node operating status in the photovoltaic power station knowledge graph; determine the target processing instruction from the entity, association relationship and attribute corresponding to the predicted node operating status.

[0087]

Determine the target processing instruction based on the actual node operating status

[0088] In the knowledge graph of a photovoltaic power station, according to the actual operating status of nodes, determine target processing instructions, including: according to the actual operating status of nodes, determine the entities, association relationships, and attributes corresponding to the actual operating status of nodes in the knowledge graph of the photovoltaic power station; determine the target processing instructions from the entities, association relationships, and attributes corresponding to the actual operating status of nodes.

[0089] In summary, the present invention provides a method for operation and maintenance management of a photovoltaic power station based on big data. The method includes: obtaining an operation and maintenance data set of a target photovoltaic power station in a historical time period. The operation and maintenance data set includes photovoltaic operation and maintenance data and processing instruction data. The photovoltaic operation and maintenance data includes: photovoltaic panel working environment data, photovoltaic panel operation data, parameter data of photovoltaic panels, and historical fault data and repair data of photovoltaic panels. The photovoltaic operation and maintenance data corresponds one-to-one with the processing instruction data. Based on the operation and maintenance data set of the target photovoltaic power station, construct a neural network model for predicting the operation status of the photovoltaic power station and construct a knowledge graph of the photovoltaic power station. Based on the neural network model for predicting the operation status of the photovoltaic power station, obtain the predicted operation status of the target photovoltaic power station in a preset time period. Obtain the actual operation status of a node and the predicted operation status of the node when the target photovoltaic power station reaches the start time node of the preset time period. The predicted operation status of the node belongs to the predicted operation status. According to the actual operation status of the node and the predicted operation status of the node, determine the target processing instructions in the knowledge graph of the photovoltaic power station, and control the target photovoltaic power station to operate according to the target processing instructions.

[0090] In the loss function provided by the present invention, by adding a regularization term to the loss function, the excessive complexity of the model can be punished, thereby avoiding the overfitting phenomenon. By minimizing the loss function, the model can better fit the data.

[0091] In the process of operation and maintenance of a photovoltaic power station, the present invention combines a neural network model and a knowledge graph. Through the neural network model trained with historical operation and maintenance data, the future operation status of the photovoltaic power station can be predicted. Based on the predicted data, the knowledge graph can help quickly find the most suitable processing instructions. Based on the historical fault patterns and their corresponding solutions recorded in the knowledge graph, combined with the current or predicted status information, the fault location process can be accelerated, and targeted suggestions for maintenance can be provided, reducing downtime and costs. And once the target processing instructions are determined, the photovoltaic power station can be automatically controlled to operate according to the instructions, reducing the need for human intervention, improving the response speed and operation consistency.

[0092] Based on the same inventive concept, the present invention provides an operation and maintenance management device for a photovoltaic power station based on big data. The device includes:

[0093] An acquisition module for acquiring an operation and maintenance data set of a target photovoltaic power station within a historical time period. The operation and maintenance data set includes photovoltaic operation and maintenance data and processing instruction data. The photovoltaic operation and maintenance data includes: photovoltaic panel working environment data, photovoltaic panel operation data, parameter data of photovoltaic panels, historical fault data and repair data of photovoltaic panels. The photovoltaic operation and maintenance data corresponds one-to-one with the processing instruction data;

[0094] A construction module for constructing a neural network model for predicting the operation state of a photovoltaic power station and constructing a knowledge graph of the photovoltaic power station based on the operation and maintenance data set of the target photovoltaic power station;

[0095] An operation prediction module for obtaining the predicted operation state of the target photovoltaic power station within a preset time period based on the neural network model for predicting the operation state of the photovoltaic power station;

[0096] A comparison module for obtaining the actual operation state and the predicted operation state of a node when the target photovoltaic power station reaches the start time node of the preset time period. The predicted operation state of the node belongs to the predicted operation state;

[0097] An operation and maintenance module for determining a target processing instruction in the knowledge graph of the photovoltaic power station according to the actual operation state and the predicted operation state of the node, and controlling the target photovoltaic power station to operate with the target processing instruction.

[0098] Based on the same inventive concept, the present invention also provides an electronic device as shown, including:

[0099] A processor;

[0100] A memory for storing instructions executable by the processor;

[0101] Wherein, the processor is configured to execute to implement the photovoltaic power station operation and maintenance management method based on big data as provided above.

[0102] Based on the same inventive concept, the present invention also provides a non-transitory computer-readable storage medium. When the instructions in the storage medium are executed by the processor of the electronic device, the electronic device can be enabled to execute and implement the photovoltaic power station operation and maintenance management method based on big data as provided above.

[0103] Since the electronic device introduced in this embodiment is the electronic device adopted for implementing the information processing method in the embodiment of the present invention, based on the information processing method introduced in the embodiment of the present invention, those skilled in the art can understand the specific implementation manners and various forms of changes of the electronic device in this embodiment. Therefore, the specific implementation of how this electronic device implements the method in the embodiment of the present invention will not be described in detail here. As long as the electronic device adopted by those skilled in the art to implement the information processing method in the embodiment of the present invention belongs to the scope protected by the present invention.

[0104] Those skilled in the art will understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0105] The present invention is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to embodiments of the present invention. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, as well as the combination of flows and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices generate means for implementing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0106] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including instruction means that implement the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0107] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0108] Although the preferred embodiments of the present invention have been described, those skilled in the art can make additional changes and modifications once they know the basic creative concepts. Therefore, the appended claims are intended to be construed to include the preferred embodiments as well as all changes and modifications that fall within the scope of the present invention.

[0109] Obviously, those skilled in the art can make various modifications and variations to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention is also intended to include these modifications and variations.

Claims

1. A method for operation and maintenance management of a photovoltaic power station based on big data, characterized in that, The method includes: Obtain the operation and maintenance data set of the target photovoltaic power station in the historical time period. The operation and maintenance data set includes photovoltaic operation and maintenance data and processing instruction data. The photovoltaic operation and maintenance data includes: photovoltaic panel working environment data, photovoltaic panel operation data, parameter data of the photovoltaic panel, historical fault data and repair data of the photovoltaic panel. The photovoltaic operation and maintenance data corresponds to the processing instruction data one by one; Based on the operation and maintenance data set of the target photovoltaic power station, construct a photovoltaic power station operation status prediction neural network model and construct a photovoltaic power station knowledge graph; Based on the photovoltaic power station operation status prediction neural network model, obtain the predicted operation status of the target photovoltaic power station within a preset time period; Obtain the actual operation status and the predicted operation status of the node when the target photovoltaic power station reaches the starting time node of the preset time period. The predicted operation status of the node belongs to the predicted operation status; According to the actual operation status of the node and the predicted operation status of the node, determine the target processing instruction in the photovoltaic power station knowledge graph, and control the target photovoltaic power station to operate with the target processing instruction.

2. The method for photovoltaic power station operation and maintenance management based on big data according to claim 1, characterized in that According to the actual operation status of the node and the predicted operation status of the node, determining the target processing instruction in the photovoltaic power station knowledge graph includes: Determine the operation parameter difference between the actual operation status of the node and the predicted operation status of the node; When the operation parameter difference is greater than the difference threshold, in the photovoltaic power station knowledge graph, determine the target processing instruction according to the actual operation status of the node, and send an alarm message to the client; otherwise, in the photovoltaic power station knowledge graph, determine the target processing instruction according to the predicted operation status of the node.

3. The method for photovoltaic power station operation and maintenance management based on big data according to claim 1, characterized in that, In the photovoltaic power station knowledge graph, determining the target processing instruction according to the predicted operation status of the node includes: According to the predicted operation status of the node, determine the entity, association relationship and attribute corresponding to the predicted operation status of the node in the photovoltaic power station knowledge graph; Determine the target processing instruction from the entity, association relationship and attribute corresponding to the predicted operation status of the node.

4. The method for operation and maintenance management of a photovoltaic power station based on big data according to claim 1, wherein Based on the operation and maintenance data set of the target photovoltaic power station, constructing a photovoltaic power station operation status prediction neural network model includes: Combine the photovoltaic operation and maintenance data in the operation and maintenance data set with the corresponding processing instruction data to obtain data groups, and a total of several data groups are obtained; Input several data groups into the neural network model to be trained, and obtain the predicted operation status corresponding to each data group; Adjust the neural network parameters of the neural network model to be trained according to the predicted operation status and the actual operation status corresponding to the data group; When the preset training requirements are met, save the latest neural network parameters, and use the neural network model to be trained corresponding to the latest neural network parameters as the photovoltaic power station operation status prediction neural network model.

5. The method for operation and maintenance management of a photovoltaic power station based on big data according to claim 1, wherein Based on the operation and maintenance data set of the target photovoltaic power station, constructing a photovoltaic power station knowledge graph includes: Define the entity, association relationship and attribute of the photovoltaic power station knowledge graph; Map several data in the operation and maintenance data set to the entity, association relationship or attribute in turn to construct the photovoltaic power station knowledge graph.

6. The method for operation and maintenance management of a photovoltaic power station based on big data according to claim 4, wherein, The loss function of the neural network model to be trained includes: where M is the number of data groups, i is the i-th data group, P i is the adjustment weight of the i-th data group, X i is the actual operating state corresponding to the i-th data group, is the predicted operating state corresponding to the i-th data group, L is the total average loss, τ is the regularization coefficient, and θ is all learnable neural network parameters in the neural network model to be trained.

7. The method for photovoltaic power station operation and maintenance management based on big data according to claim 6, wherein The neural network parameters include: The weight matrix, the bias vector, the parameters of the activation function, the learning rate, and the decay rate.

8. A photovoltaic power station operation and maintenance management device based on big data, characterized in that The device includes: An acquisition module, configured to acquire an operation and maintenance data set of a target photovoltaic power station in a historical time period. The operation and maintenance data set includes photovoltaic operation and maintenance data and processing instruction data. The photovoltaic operation and maintenance data includes: photovoltaic panel working environment data, photovoltaic panel operation data, photovoltaic panel parameter data, photovoltaic panel historical fault data and repair data, and the photovoltaic operation and maintenance data corresponds to the processing instruction data one by one; A construction module, configured to construct a photovoltaic power station operation status prediction neural network model and construct a photovoltaic power station knowledge graph based on the operation and maintenance data set of the target photovoltaic power station; An operation prediction module, configured to obtain the predicted operation status of the target photovoltaic power station in a preset time period based on the photovoltaic power station operation status prediction neural network model; A comparison module, configured to obtain the actual operation status and the predicted operation status of the node when the target photovoltaic power station reaches the start time node of the preset time period, and the predicted operation status of the node belongs to the predicted operation status; An operation and maintenance module, configured to determine a target processing instruction in the photovoltaic power station knowledge graph according to the actual operation status of the node and the predicted operation status of the node, and control the target photovoltaic power station to operate with the target processing instruction.

9. An electronic device, characterized in that, Includes: A processor; A memory for storing executable instructions of the processor; Wherein, the processor is configured to execute to implement the big data-based photovoltaic power station operation and maintenance management method according to any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium, characterized in that, When the instructions in the storage medium are executed by the processor of the electronic device, the electronic device can execute to implement the big data-based photovoltaic power station operation and maintenance management method according to any one of claims 1 to 7.

Images