Photovoltaic power station remote monitoring method and system based on Internet

Abstract

The invention relates to an internet-based photovoltaic power station remote monitoring method and system, and the method comprises the steps: obtaining a total power value inputted by a photovoltaic power station in real time, and generating a root part of a tree diagram based on the total power value, sensing binary fluctuation of each photovoltaic panel in the photovoltaic power station by utilizing a preset binary mechanism and combining with the current direction input in real time, and calibrating a tree diagram branch corresponding to each photovoltaic panel at the same time; based on the fluctuation data of the binary fluctuation, identifying the SOC value of each photovoltaic panel; and calibrating the obtained SOC values on tree diagram branches corresponding to the photovoltaic panels one by one in the tree diagram, performing data display processing on the tree diagram, and feeding back the tree diagram subjected to the data display processing to a terminal, so as to solve the problem that the monitoring of the photovoltaic power station is realized by depending on the layout of the Internet of Things in the current technical scheme. And the cost is high.

Description

Technical Field

[0001] The present invention relates to the technical field of photovoltaic power station monitoring, and in particular to an Internet-based photovoltaic power station remote monitoring method and system. Background Art

[0002] With the rapid development of renewable energy, photovoltaic power stations, as an important part of clean energy, are increasing in size and quantity. However, photovoltaic power stations are usually located in remote areas, and traditional manual inspection methods have problems such as low efficiency, high cost, and slow response. Therefore, developing an Internet-based remote monitoring system to achieve real-time, remote, and efficient monitoring of photovoltaic power stations is of great significance for improving the operating efficiency and maintenance convenience of photovoltaic power stations.

[0003] For example, the prior art solution CN109301914A - A photovoltaic microgrid energy storage control method with SOC optimization discloses a photovoltaic microgrid energy storage control method with SOC optimization, and the specific steps are as follows: constructing a photovoltaic microgrid energy storage control system; a central monitoring unit monitors the operating status of the photovoltaic microgrid; an information collector is used to collect current and voltage data of the DC bus, and the collected current and voltage data are transmitted to the central processing unit, and the central processing unit generates a control strategy by calculation and distinguishes the control layer area to control the battery and the supercapacitor; the energy controller calculates the state of charge SOC value of the battery and the supercapacitor, and compares and judges with the optimal SOC range, and the SOC optimization module adopts a fuzzy self-adjustment strategy based on the filter time constant, and finally completes the correction of the SOC value of the battery and the supercapacitor. This method enables the photovoltaic microgrid system to reach a stable state.

[0004] However, the existing technical solutions rely on the layout of the Internet of Things to realize the monitoring of photovoltaic power stations, which is similar to the need to set up Internet of Things monitoring devices on the line channels of each photovoltaic energy panel. Although it is beneficial to the subsequent SOC value calculation, the cost is high. Summary of the invention

[0005] The main purpose of the present invention is to provide an Internet-based photovoltaic power station remote monitoring method and system, aiming to solve the technical problem that the current technical solution relies on the layout of the Internet of Things to realize the monitoring of photovoltaic power stations, resulting in high costs.

[0006] To achieve the above object, the present invention provides an Internet-based photovoltaic power station remote monitoring method, comprising the following steps:

[0007] Acquire the total value of electric power input by the photovoltaic power station in real time, where the total value is the total amount of electricity obtained by each power collection unit of the photovoltaic power station;

[0008] The root of the tree diagram is generated based on the total power value, and the binary fluctuation of each photovoltaic panel in the photovoltaic power station is sensed by a preset binary mechanism combined with the current direction input in real time, and the branches of the tree diagram corresponding to each photovoltaic panel are calibrated;

[0009] Based on the fluctuation data of the binary fluctuation, identifying the SOC value of each photovoltaic panel;

[0010] In the tree diagram, each SOC value obtained is calibrated one by one on the tree diagram branch corresponding to each photovoltaic panel, and the tree diagram is processed for digital display, and the tree diagram processed for digital display is fed back to the terminal.

[0011] Furthermore, the step of using a preset binary mechanism in combination with the real-time input current direction to sense the binary fluctuation of each photovoltaic panel in the photovoltaic power station includes:

[0012] Binary mark the real-time input current, and gradually push the mark back to the photovoltaic power station end to obtain the binary fluctuation data at the root of the tree diagram;

[0013] The binary fluctuation node data when the current of each photovoltaic panel at the photovoltaic power station end is input into the main current is identified, and the binary fluctuation data of the tree branch corresponding to each photovoltaic panel is obtained.

[0014] Furthermore, based on the fluctuation data of the binary fluctuation, the step of identifying the SOC value of each photovoltaic panel comprises:

[0015] The binary fluctuation data of the tree branches corresponding to each photovoltaic panel is identified to obtain the SOC value of each photovoltaic panel.

[0016] Furthermore, the step of using a preset binary mechanism in combination with the real-time input current direction to sense the binary fluctuation of each photovoltaic panel in the photovoltaic power station includes:

[0017] Recalling a preset ELC-RNN model, creating a root vector for the real-time input current, wherein a plurality of binary data storage nodes are trained on the root vector, and the binary data storage nodes are used to record and distinguish the current fluctuation characteristics of different photovoltaic panels in the photovoltaic power station;

[0018] The real-time input current data is input into the ELC-RNN model in chronological order. The model dynamically updates the binary data storage node on the root vector according to the input current data to reflect the current status of each photovoltaic panel in the photovoltaic power station in real time.

[0019] By comparing the binary data storage node updated in real time with the preset binary fluctuation pattern, the binary fluctuation of each photovoltaic panel in the photovoltaic power station is identified;

[0020] The binary fluctuation data of each identified photovoltaic panel is associated with the corresponding branch in the tree diagram, and in the subsequent steps, the SOC value is calibrated on the branch of the tree diagram corresponding to the correct photovoltaic panel.

[0021] Furthermore, the training method of the ELC-RNN model includes:

[0022] Collect historical current data of photovoltaic power plants, including current fluctuations of each photovoltaic panel at different times and under different weather conditions, as training data sets;

[0023] Preprocessing the collected historical current data, wherein the preprocessing includes data cleaning and normalization to eliminate noise and unify the data format;

[0024] Construct the ELC-RNN model, combining long short-term memory network and extreme learning machine;

[0025] The ELC-RNN model is trained using preprocessed historical current data, and the model parameters are adjusted through an iterative optimization algorithm to accurately predict and identify binary fluctuations of photovoltaic panels;

[0026] During the training process, the cross-validation method was used to evaluate the performance of the model;

[0027] After training is completed, save the parameters and structure of the ELC-RNN model.

[0028] The present invention also proposes an Internet-based photovoltaic power station remote monitoring system, comprising:

[0029] An acquisition unit is used to acquire the total value of electric power input by the photovoltaic power station in real time, wherein the total value is the total amount of electricity obtained by each power collection unit of the photovoltaic power station;

[0030] A production unit, used for generating a root of a tree diagram based on the total power value, and using a preset binary mechanism in combination with a current direction input in real time to sense binary fluctuations of each photovoltaic panel in the photovoltaic power station, and calibrating branches of the tree diagram corresponding to each photovoltaic panel;

[0031] an identification unit, configured to identify the SOC value of each photovoltaic panel based on the fluctuation data of the binary fluctuation;

[0032] The display unit is used to mark each SOC value obtained in the tree diagram on the tree diagram branches corresponding to each photovoltaic panel, perform digital display processing on the tree diagram, and feed back the digital display processed tree diagram to the terminal.

[0033] Furthermore, the production unit comprises:

[0034] The labeling module is used to binary label the real-time input current and gradually push the labeling back to the photovoltaic power station end to obtain the binary fluctuation data at the root of the tree diagram;

[0035] A production module is provided for identifying binary fluctuation node data when the current of each photovoltaic panel at the photovoltaic power station end is input into the main current, and obtaining the binary fluctuation data of the tree branch corresponding to each photovoltaic panel.

[0036] Furthermore, the identification unit includes:

[0037] The identification module is used to identify the binary fluctuation data of the tree branches corresponding to each photovoltaic panel to obtain the SOC value of each photovoltaic panel.

[0038] Furthermore, the production unit also includes:

[0039] A model module, used to call a preset ELC-RNN model, and create a root vector for the real-time input current, wherein a plurality of binary data storage nodes are trained on the root vector, and the binary data storage nodes are used to record and distinguish the current fluctuation characteristics of different photovoltaic panels in the photovoltaic power station;

[0040] The current module is used to input the real-time input current data into the ELC-RNN model in time sequence. The model dynamically updates the binary data storage node on the root vector according to the input current data to reflect the current status of each photovoltaic panel in the photovoltaic power station in real time.

[0041] An updating module, used for identifying binary fluctuations of each photovoltaic panel in the photovoltaic power station by comparing the binary data storage node updated in real time with a preset binary fluctuation pattern;

[0042] The association unit is used to associate the binary fluctuation data of each identified photovoltaic panel with the corresponding branch in the tree diagram, and in the subsequent step, mark the SOC value on the branch of the tree diagram corresponding to the correct photovoltaic panel.

[0043] Furthermore, the model module includes:

[0044] The data acquisition submodule is used to collect the historical current data of the photovoltaic power station, including the current fluctuations of each photovoltaic panel at different times and under different weather conditions, as a training data set;

[0045] A preprocessing submodule, used for preprocessing the collected historical current data, wherein the preprocessing includes data cleaning and normalization to eliminate noise and unify the data format;

[0046] Build submodules for building ELC-RNN models, combining long short-term memory networks and extreme learning machines;

[0047] The training submodule is used to train the ELC-RNN model using the preprocessed historical current data, adjust the model parameters through an iterative optimization algorithm, and accurately predict and identify the binary fluctuations of the photovoltaic panel;

[0048] The validation submodule is used to evaluate the performance of the model using the cross-validation method during the training process;

[0049] Save submodule to save the parameters and structure of the ELC-RNN model after training is completed.

[0050] The Internet-based photovoltaic power station remote monitoring method and system provided by the present invention have the following beneficial effects:

[0051] (1) Through the ELC electrical signal recognition mechanism, the fluctuation of the electrical signal can be inferred, and there is no need to deploy an IoT system at the photovoltaic power station end, thus reducing costs.

[0052] (2) By acquiring the total power value of the photovoltaic power station in real time and combining it with a binary mechanism to sense the current fluctuations of each photovoltaic panel, comprehensive, real-time, and remote monitoring of the photovoltaic power station can be achieved.

[0053] (3) The preset ELC-RNN model is used to process the real-time input current, which can dynamically update and identify the binary fluctuations of the photovoltaic panels. This data processing method based on deep learning can more effectively mine and utilize the operation data of photovoltaic power stations, providing strong support for subsequent fault prediction and optimized operation.

[0054] (4) The SOC value of each photovoltaic panel is displayed in the form of a tree diagram, so that the operation and maintenance personnel can intuitively and clearly understand the operating status of the photovoltaic power station. At the same time, the tree diagram processed by data display is fed back to the terminal, so that the operation and maintenance personnel can access the real-time operation data of the photovoltaic power station anytime and anywhere, greatly improving the convenience of operation and maintenance. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 It is a flow chart of a photovoltaic power station remote monitoring method based on the Internet in one embodiment of the present invention;

[0056] Figure 2 It is a structural block diagram of an Internet-based photovoltaic power station remote monitoring system in one embodiment of the present invention;

[0057] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0058] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0059] Reference Figure 1 , is a flow chart of a photovoltaic power station remote monitoring method based on the Internet proposed by the present invention, comprising the following steps:

[0060] S1, obtaining the total value of electric power input by the photovoltaic power station in real time, wherein the total value is the total amount of electric power obtained by each power collection unit of the photovoltaic power station;

[0061] S2, generating a root of a tree diagram based on the total power value, and using a preset binary mechanism combined with a real-time input current direction to sense binary fluctuations of each photovoltaic panel in the photovoltaic power station, and calibrating branches of the tree diagram corresponding to each photovoltaic panel;

[0062] S3, identifying the SOC value of each photovoltaic panel based on the fluctuation data of the binary fluctuation;

[0063] S4, in the tree diagram, each SOC value obtained is calibrated one by one on the tree diagram branch corresponding to each photovoltaic panel, and the tree diagram is processed for digital display, and the tree diagram processed for digital display is fed back to the terminal.

[0064] In the process of specific implementation,

[0065] In S1, the total value of power input by the photovoltaic power station is obtained in real time. The total value of power is actually the sum of the power generated by all power collection units (such as photovoltaic panels and battery packs) in the photovoltaic power station at the same time. The underlying logic of this step is that by real-time monitoring and collecting the power output of the photovoltaic power station, a comprehensive and real-time overview of the power station's operating status can be obtained. Specifically, a photovoltaic power station is usually composed of multiple power collection units, each of which generates different amounts of power according to light intensity, temperature and environmental factors. In order to accurately understand the power generation capacity of the entire power station, it is necessary to summarize the power of all power collection units to obtain a total power value. This value not only reflects the current power generation level of the power station, but also serves as the basis for subsequent data analysis, status monitoring and fault warning. The key to achieving this step lies in the use of data collection and transmission technology. Usually, a photovoltaic power station is equipped with a special data acquisition system that can read the power data of each power collection unit in real time and send this data to the system through a communication network. The system processes and analyzes the received data to obtain a real-time total value of power.

[0066] In S2, the root of the tree diagram is generated based on the total power value obtained in real time, and the binary fluctuations of each photovoltaic panel in the photovoltaic power station are sensed by using a preset binary mechanism combined with the current direction input in real time, and the branches corresponding to each photovoltaic panel are marked on the tree diagram. A tree diagram structure is constructed to intuitively represent the status and relationship of each photovoltaic panel in the photovoltaic power station. The root of the tree diagram represents the total power value of the entire photovoltaic power station, which reflects the overall power generation level of the power station. The branches of the tree diagram represent each photovoltaic panel, and their status and changes can be represented by binary fluctuations. In order to achieve this step, it is necessary to use a preset binary mechanism to sense the change in the current direction of the photovoltaic panel. This mechanism can convert the change in the current direction into a binary code, so as to facilitate data processing and analysis. When the current direction changes, the corresponding binary code will also change, and this change can be regarded as the binary fluctuation of the photovoltaic panel. At the same time, in order to intuitively display the status and changes of each photovoltaic panel on the tree diagram, they need to be calibrated. The calibration process is actually to match the photovoltaic panels with the branches of the tree diagram. In this way, when the status of the photovoltaic panels changes, the corresponding branches on the tree diagram will also change, thereby realizing real-time monitoring of the status of the photovoltaic power station.

[0067] In S3, the SOC value of each photovoltaic panel is identified based on the aforementioned binary fluctuation data. The SOC value, i.e., the remaining capacity or state of the battery, is an important parameter reflecting the performance of the photovoltaic panel. By monitoring and analyzing the binary fluctuation data of the photovoltaic panel, the current state of the panel, especially its remaining capacity or SOC value, can be inferred. The binary fluctuation data reflects the changes in the current state of the panel, and these changes have a certain correlation with the SOC value of the panel. Therefore, by processing and analyzing these fluctuation data, the SOC value of each photovoltaic panel can be identified.

[0068] In S4, in the remote monitoring method of the photovoltaic power station, the SOC value of each photovoltaic panel is identified through step S3, and the next key step is to mark these SOC values ​​one by one on the branches of the tree diagram corresponding to each photovoltaic panel in the tree diagram. The underlying logic of this step is that through the intuitive data structure of the tree diagram, the complex photovoltaic power station status information can be displayed in a hierarchical manner, so that the operation and maintenance personnel can quickly locate each photovoltaic panel and view its current SOC value. Specifically, the root of the tree diagram represents the total power value of the entire photovoltaic power station, which provides an overview of the overall power generation level of the power station. The branches of the tree diagram are subdivided into each photovoltaic panel. By matching these branches with photovoltaic panels one by one, the SOC value of the panel can be marked on the branches. In this way, the operation and maintenance personnel can intuitively understand the current status of each photovoltaic panel by viewing the tree diagram. In order to further improve the readability and ease of use of information, it is also necessary to perform data display processing on the tree diagram. This includes optimizing the layout of the tree diagram to make it more in line with human visual habits; color coding or numerical labeling of SOC values ​​to make them easier to identify; and adding interactive functions so that operation and maintenance personnel can further explore the data by clicking or dragging. Finally, the processed tree diagram is fed back to the terminal, such as the operation and maintenance personnel's computer, mobile phone or tablet. In this way, no matter where the operation and maintenance personnel are, they can check the real-time status of the photovoltaic power station at any time, and promptly discover and deal with potential problems. The realization of this step depends on the development of modern communication technology and cloud computing technology, making data transmission and sharing more convenient and efficient.

[0069] In one embodiment, the steps of using a preset binary mechanism combined with a real-time input current direction to sense the binary fluctuation of each photovoltaic panel in the photovoltaic power station include:

[0070] Binary mark the real-time input current, and gradually push the mark back to the photovoltaic power station end to obtain the binary fluctuation data at the root of the tree diagram;

[0071] The binary fluctuation node data when the current of each photovoltaic panel at the photovoltaic power station end is input into the main current is identified, and the binary fluctuation data of the tree branch corresponding to each photovoltaic panel is obtained.

[0072] Specifically, the real-time input current data is processed, converted into binary form, and annotated. This annotation is based on the direction and size characteristics of the current, with the purpose of converting continuous current data into discrete, easy-to-process binary data. Then, these binary data will be gradually pushed back to the photovoltaic power station end, and finally the binary fluctuation data at the root of the tree diagram will be obtained. These data reflect the current state changes of the entire photovoltaic power station. Binary annotation is a data preprocessing technology that can simplify complex data into easy-to-process binary form. In the monitoring of photovoltaic power stations, this technology can help us capture and analyze current changes more effectively. By gradually pushing the annotation back to the photovoltaic power station end, we can get an overview of the current state of the entire power station, providing basic data for subsequent fault warning and performance evaluation.

[0073] In one embodiment, the steps of using a preset binary mechanism combined with a real-time input current direction to sense the binary fluctuation of each photovoltaic panel in the photovoltaic power station include:

[0074] Recalling a preset ELC-RNN model, creating a root vector for the real-time input current, wherein a plurality of binary data storage nodes are trained on the root vector, and the binary data storage nodes are used to record and distinguish the current fluctuation characteristics of different photovoltaic panels in the photovoltaic power station;

[0075] The real-time input current data is input into the ELC-RNN model in chronological order. The model dynamically updates the binary data storage node on the root vector according to the input current data to reflect the current status of each photovoltaic panel in the photovoltaic power station in real time.

[0076] By comparing the binary data storage node updated in real time with the preset binary fluctuation pattern, the binary fluctuation of each photovoltaic panel in the photovoltaic power station is identified;

[0077] The binary fluctuation data of each identified photovoltaic panel is associated with the corresponding branch in the tree diagram, and in the subsequent steps, the SOC value is calibrated on the branch of the tree diagram corresponding to the correct photovoltaic panel.

[0078] Specifically,

[0079] Retrieve the preset ELC-RNN model and create the root vector for the real-time input current:

[0080] Explanation: First, we call a pre-trained ELC-RNN model. This model is specially designed to process the current data of photovoltaic power plants. It can perform deep learning and analysis on the input current data. When the real-time input current data enters the model, the model will create a root vector for it. This root vector is a multi-dimensional data representation, which contains key information about the overall current status of the photovoltaic power plant.

[0081] Underlying logic: The ELC-RNN model is a deep learning model that combines the long short-term memory (LSTM) network and the encoder-decoder architecture. It can learn complex patterns from sequence data and effectively encode and decode them. In the monitoring of photovoltaic power plants, the ELC-RNN model can capture the time series features in the current data and encode them into root vectors, providing a basis for subsequent analysis and identification.

[0082] Several binary data storage nodes are trained on the root vector to record and distinguish the current fluctuation characteristics of different photovoltaic panels in the photovoltaic power station:

[0083] Explanation: On the root vector, we train several binary data storage nodes. These storage nodes are like labels or indexes that can record and distinguish the current fluctuation characteristics of different photovoltaic panels in a photovoltaic power plant. Each storage node is associated with a specific photovoltaic panel and stores the binary representation of the current fluctuation of the panel.

[0084] Underlying logic: The design of the binary data storage node is based on the uniqueness of the current fluctuations of the photovoltaic panels. Since each photovoltaic panel has its own unique current fluctuation pattern, we can train the model to recognize these patterns and associate them with specific storage nodes. In this way, when the model receives new current data, it can quickly match this data with the storage node to identify the corresponding photovoltaic panel.

[0085] The real-time input current data is input into the ELC-RNN model in chronological order. The model dynamically updates the binary data storage node on the root vector according to the input current data:

[0086] Explanation: The real-time input current data is input into the ELC-RNN model in chronological order. The model dynamically updates the binary data storage node on the root vector based on this data. This means that as new current data is continuously input, the model will update the information in the storage node in real time to reflect the current current status of each photovoltaic panel in the photovoltaic power station.

[0087] Underlying logic: The dynamic update capability of the ELC-RNN model is based on its deep learning algorithm and the memory function of the LSTM network. The LSTM network can remember the long-term dependencies in the sequence data and update its internal state according to the new input data. In the monitoring of photovoltaic power stations, this dynamic update capability enables the model to track and reflect the current state changes of photovoltaic panels in real time.

[0088] By comparing the binary data storage nodes updated in real time with the preset binary fluctuation pattern, the binary fluctuation of each photovoltaic panel in the photovoltaic power station is identified:

[0089] Explanation: The model compares the binary data storage nodes updated in real time with the preset binary fluctuation patterns. These preset patterns are established based on the current fluctuation characteristics of photovoltaic panels under normal or fault conditions. Through comparison, the model can identify the current binary fluctuation state of each photovoltaic panel in the photovoltaic power plant.

[0090] Underlying logic: The recognition process is based on pattern matching and similarity calculation. The model calculates the similarity between the real-time updated storage node and the preset pattern, and judges the current state of the photovoltaic panel based on the similarity. If the similarity is high, it means that the photovoltaic panel is in a normal or expected state; if the similarity is low, it may indicate that the photovoltaic panel is faulty or abnormal.

[0091] The binary fluctuation data of each identified photovoltaic panel is associated with the corresponding branch in the tree diagram, and the SOC value is calibrated on the branch of the tree diagram corresponding to the correct photovoltaic panel in the subsequent steps:

[0092] Explanation: Once the model identifies the binary fluctuation status of each PV panel in the PV power plant, it will associate these status data with the corresponding branches in the tree diagram. In this way, the operation and maintenance personnel can intuitively understand the current status of each PV panel by viewing the tree diagram. In the subsequent steps, the model will also mark the identified SOC value on the tree diagram branch corresponding to the correct PV panel, so that the operation and maintenance personnel can conduct further monitoring and analysis.

[0093] Underlying logic: The implementation of this step depends on the model's accurate identification of the status of photovoltaic panels and the reasonable design of the tree diagram structure. The model uses deep learning algorithms and pattern matching technology to accurately identify the status of photovoltaic panels and match these statuses with branches in the tree diagram. The design of the tree diagram structure enables operation and maintenance personnel to easily view and analyze the overall status of the photovoltaic power station and the detailed information of each photovoltaic panel.

[0094] In one embodiment, the training method of the ELC-RNN model includes:

[0095] Collect historical current data of photovoltaic power plants, including current fluctuations of each photovoltaic panel at different times and under different weather conditions, as training data sets;

[0096] Preprocessing the collected historical current data, wherein the preprocessing includes data cleaning and normalization to eliminate noise and unify the data format;

[0097] Construct the ELC-RNN model, combining long short-term memory network and extreme learning machine;

[0098] The ELC-RNN model is trained using preprocessed historical current data, and the model parameters are adjusted through an iterative optimization algorithm to accurately predict and identify binary fluctuations of photovoltaic panels;

[0099] During the training process, the cross-validation method was used to evaluate the performance of the model;

[0100] After training is completed, save the parameters and structure of the ELC-RNN model.

[0101] Specifically,

[0102] Collect historical current data of photovoltaic power plants: This step is the basis of model training. It is necessary to collect the current fluctuations of each photovoltaic panel in the photovoltaic power plant at different times (such as day, month, year) and different weather conditions (such as sunny, cloudy, rainy, etc.). These data will be used as training data sets for subsequent training of the ELC-RNN model. Preprocess the collected historical current data: Preprocessing is a key step before data analysis and modeling, which includes data cleaning and normalization. The purpose of data cleaning is to eliminate noise and outliers in the data to ensure the accuracy and reliability of the data. Normalization is to unify the data into the same format and range so that the model can process and learn more effectively. Build the ELC-RNN model: The ELC-RNN model is a deep learning model that combines the long short-term memory (LSTM) network and the extreme learning machine (ELM). The LSTM network can handle long-term dependencies in sequence data and is suitable for time series analysis of photovoltaic power plant current data. ELM is a fast and effective single hidden layer feedforward neural network suitable for classification and regression tasks of large-scale data. Combining LSTM and ELM can fully utilize the advantages of both and improve the prediction and recognition capabilities of the model. Use the preprocessed historical current data to train the ELC-RNN model: Training is the process of model learning. The model parameters are adjusted through iterative optimization algorithms (such as gradient descent) so that the model can accurately predict and identify the binary fluctuations of photovoltaic panels. During the training process, the model learns the features and patterns in the current data and associates them with the binary fluctuations of photovoltaic panels. During the training process, the cross-validation method is used to evaluate the performance of the model: Cross-validation is a method for evaluating model performance. It divides the data set into a training set and a validation set, and uses the training set to train the model, and then uses the validation set to test the performance of the model. Through cross-validation, the performance of the model on different data subsets can be evaluated to ensure the generalization ability and stability of the model. After training, save the parameters and structure of the ELC-RNN model: After training, the parameters and structure of the ELC-RNN model need to be saved for use in subsequent photovoltaic power station monitoring and analysis. The saved model can be loaded into the monitoring system to predict and identify the real-time input current data, thereby realizing real-time monitoring of the photovoltaic power station status and fault warning.

[0103] Reference Figure 2 The present invention proposes an Internet-based photovoltaic power station remote monitoring system, comprising:

[0104] An acquisition unit is used to acquire the total value of electric power input by the photovoltaic power station in real time, wherein the total value is the total amount of electricity obtained by each power collection unit of the photovoltaic power station;

[0105] A production unit, used for generating a root of a tree diagram based on the total power value, and using a preset binary mechanism in combination with a current direction input in real time to sense binary fluctuations of each photovoltaic panel in the photovoltaic power station, and calibrating branches of the tree diagram corresponding to each photovoltaic panel;

[0106] an identification unit, configured to identify the SOC value of each photovoltaic panel based on the fluctuation data of the binary fluctuation;

[0107] The display unit is used to mark each SOC value obtained in the tree diagram on the tree diagram branches corresponding to each photovoltaic panel, perform digital display processing on the tree diagram, and feed back the digital display processed tree diagram to the terminal.

[0108] The production units include:

[0109] The labeling module is used to binary label the real-time input current and gradually push the labeling back to the photovoltaic power station end to obtain the binary fluctuation data at the root of the tree diagram;

[0110] A production module is provided for identifying binary fluctuation node data when the current of each photovoltaic panel at the photovoltaic power station end is input into the main current, and obtaining the binary fluctuation data of the tree branch corresponding to each photovoltaic panel.

[0111] The identification unit includes:

[0112] The identification module is used to identify the binary fluctuation data of the tree branches corresponding to each photovoltaic panel to obtain the SOC value of each photovoltaic panel.

[0113] The production unit also includes:

[0114] A model module, used to call a preset ELC-RNN model, and create a root vector for the real-time input current, wherein a plurality of binary data storage nodes are trained on the root vector, and the binary data storage nodes are used to record and distinguish the current fluctuation characteristics of different photovoltaic panels in the photovoltaic power station;

[0115] The current module is used to input the real-time input current data into the ELC-RNN model in time sequence. The model dynamically updates the binary data storage node on the root vector according to the input current data to reflect the current status of each photovoltaic panel in the photovoltaic power station in real time.

[0116] An updating module, used for identifying binary fluctuations of each photovoltaic panel in the photovoltaic power station by comparing the binary data storage node updated in real time with a preset binary fluctuation pattern;

[0117] The association unit is used to associate the binary fluctuation data of each identified photovoltaic panel with the corresponding branch in the tree diagram, and in the subsequent step, mark the SOC value on the branch of the tree diagram corresponding to the correct photovoltaic panel.

[0118] The model modules include:

[0119] The data acquisition submodule is used to collect the historical current data of the photovoltaic power station, including the current fluctuations of each photovoltaic panel at different times and under different weather conditions, as a training data set;

[0120] A preprocessing submodule, used for preprocessing the collected historical current data, wherein the preprocessing includes data cleaning and normalization to eliminate noise and unify the data format;

[0121] Build submodules for building ELC-RNN models, combining long short-term memory networks and extreme learning machines;

[0122] The training submodule is used to train the ELC-RNN model using the preprocessed historical current data, adjust the model parameters through an iterative optimization algorithm, and accurately predict and identify the binary fluctuations of the photovoltaic panel;

[0123] The validation submodule is used to evaluate the performance of the model using the cross-validation method during the training process;

[0124] Save submodules to save the parameters and structure of the ELC-RNN model after training is completed

[0125] In summary, the total value of electric power input by the photovoltaic power station is obtained in real time, the root of the tree diagram is generated based on the total value of electric power, and the binary fluctuation of each photovoltaic panel in the photovoltaic power station is sensed by a preset binary mechanism combined with the current direction of the real-time input, and the tree diagram branches corresponding to each photovoltaic panel are calibrated at the same time; based on the fluctuation data of the binary fluctuation, the SOC value of each photovoltaic panel is identified; in the tree diagram, each SOC value obtained is calibrated one by one on the tree diagram branch corresponding to each photovoltaic panel, and the tree diagram is processed for digital display, and the tree diagram processed for digital display is fed back to the terminal, so as to solve the technical problem that the current technical solution relies on the layout of the Internet of Things to realize the monitoring of photovoltaic power stations, resulting in high costs.

[0126] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, device, article or method including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, device, article or method. In the absence of further restrictions, an element defined by the sentence "includes a ..." does not exclude the presence of other identical elements in the process, device, article or method including the element.

[0127] The above description is only a preferred embodiment of the present invention, and does not limit the patent scope of the present invention. Any effective structure or effective process transformation made by using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A photovoltaic power station remote monitoring method based on the Internet, characterized in that: The following steps are involved: Acquire the total value of electric power input by the photovoltaic power station in real time, where the total value is the total amount of electricity obtained by each power collection unit of the photovoltaic power station; The root of the tree diagram is generated based on the total power value, and the binary fluctuation of each photovoltaic panel in the photovoltaic power station is sensed by a preset binary mechanism combined with the current direction input in real time, and the branches of the tree diagram corresponding to each photovoltaic panel are calibrated; Based on the fluctuation data of the binary fluctuation, identifying the SOC value of each photovoltaic panel; In the tree diagram, each SOC value obtained is calibrated one by one on the tree diagram branch corresponding to each photovoltaic panel, and the tree diagram is processed for digital display, and the tree diagram processed for digital display is fed back to the terminal.

2. The method for remote monitoring of a photovoltaic power station based on the Internet according to claim 1, characterized in that: The steps of using a preset binary mechanism combined with a real-time input current direction to sense binary fluctuations of each photovoltaic panel in a photovoltaic power station include: Binary mark the real-time input current, and gradually push the mark back to the photovoltaic power station end to obtain the binary fluctuation data at the root of the tree diagram; The binary fluctuation node data when the current of each photovoltaic panel at the photovoltaic power station end is input into the main current is identified, and the binary fluctuation data of the tree branch corresponding to each photovoltaic panel is obtained.

3. The method for remote monitoring of a photovoltaic power station based on the Internet according to claim 2, characterized in that: The step of identifying the SOC value of each photovoltaic panel based on the fluctuation data of the binary fluctuation comprises: The binary fluctuation data of the tree branches corresponding to each photovoltaic panel is identified to obtain the SOC value of each photovoltaic panel.

4. The method for remote monitoring of a photovoltaic power station based on the Internet according to claim 1, characterized in that: The steps of using a preset binary mechanism combined with a real-time input current direction to sense binary fluctuations of each photovoltaic panel in a photovoltaic power station include: Recalling a preset ELC-RNN model, creating a root vector for the real-time input current, wherein a plurality of binary data storage nodes are trained on the root vector, and the binary data storage nodes are used to record and distinguish the current fluctuation characteristics of different photovoltaic panels in the photovoltaic power station; The real-time input current data is input into the ELC-RNN model in chronological order. The model dynamically updates the binary data storage node on the root vector according to the input current data to reflect the current status of each photovoltaic panel in the photovoltaic power station in real time. By comparing the binary data storage node updated in real time with the preset binary fluctuation pattern, the binary fluctuation of each photovoltaic panel in the photovoltaic power station is identified; The binary fluctuation data of each identified photovoltaic panel is associated with the corresponding branch in the tree diagram, and in the subsequent steps, the SOC value is calibrated on the branch of the tree diagram corresponding to the correct photovoltaic panel.

5. The method for remote monitoring of a photovoltaic power station based on the Internet according to claim 4, characterized in that: The training method of the ELC-RNN model includes: Collect historical current data of photovoltaic power plants, including current fluctuations of each photovoltaic panel at different times and under different weather conditions, as training data sets; Preprocessing the collected historical current data, wherein the preprocessing includes data cleaning and normalization to eliminate noise and unify the data format; Construct the ELC-RNN model, combining long short-term memory network and extreme learning machine; The ELC-RNN model is trained using preprocessed historical current data, and the model parameters are adjusted through an iterative optimization algorithm to accurately predict and identify binary fluctuations of photovoltaic panels; During the training process, the cross-validation method was used to evaluate the performance of the model; After training is completed, save the parameters and structure of the ELC-RNN model.

6. A photovoltaic power station remote monitoring system based on the Internet, characterized in that: include: An acquisition unit is used to acquire the total value of electric power input by the photovoltaic power station in real time, wherein the total value is the total amount of electricity obtained by each power collection unit of the photovoltaic power station; A production unit, used for generating a root of a tree diagram based on the total power value, and using a preset binary mechanism in combination with a current direction input in real time to sense binary fluctuations of each photovoltaic panel in the photovoltaic power station, and calibrating branches of the tree diagram corresponding to each photovoltaic panel; an identification unit, configured to identify the SOC value of each photovoltaic panel based on the fluctuation data of the binary fluctuation; The display unit is used to mark each SOC value obtained in the tree diagram on the tree diagram branches corresponding to each photovoltaic panel, perform digital display processing on the tree diagram, and feed back the digital display processed tree diagram to the terminal.

7. The Internet-based photovoltaic power station remote monitoring system according to claim 6, characterized in that: Production units include: The labeling module is used to binary label the real-time input current and gradually push the labeling back to the photovoltaic power station end to obtain the binary fluctuation data at the root of the tree diagram; A production module is provided for identifying binary fluctuation node data when the current of each photovoltaic panel at the photovoltaic power station end is input into the main current, and obtaining the binary fluctuation data of the tree branch corresponding to each photovoltaic panel.

8. The Internet-based photovoltaic power station remote monitoring system according to claim 7, characterized in that: The identification unit includes: The identification module is used to identify the binary fluctuation data of the tree branches corresponding to each photovoltaic panel to obtain the SOC value of each photovoltaic panel.

9. The Internet-based photovoltaic power station remote monitoring system according to claim 6, characterized in that: The production unit also includes: A model module, used to call a preset ELC-RNN model, and create a root vector for the real-time input current, wherein a plurality of binary data storage nodes are trained on the root vector, and the binary data storage nodes are used to record and distinguish the current fluctuation characteristics of different photovoltaic panels in the photovoltaic power station; The current module is used to input the real-time input current data into the ELC-RNN model in time sequence. The model dynamically updates the binary data storage node on the root vector according to the input current data to reflect the current status of each photovoltaic panel in the photovoltaic power station in real time. An updating module, used for identifying binary fluctuations of each photovoltaic panel in the photovoltaic power station by comparing the binary data storage node updated in real time with a preset binary fluctuation pattern; The association unit is used to associate the binary fluctuation data of each identified photovoltaic panel with the corresponding branch in the tree diagram, and in the subsequent step, mark the SOC value on the branch of the tree diagram corresponding to the correct photovoltaic panel.

10. The Internet-based photovoltaic power station remote monitoring system according to claim 9, characterized in that: The model modules include: The data acquisition submodule is used to collect the historical current data of the photovoltaic power station, including the current fluctuations of each photovoltaic panel at different times and under different weather conditions, as a training data set; A preprocessing submodule, used for preprocessing the collected historical current data, wherein the preprocessing includes data cleaning and normalization to eliminate noise and unify the data format; Build submodules for building ELC-RNN models, combining long short-term memory networks and extreme learning machines; The training submodule is used to train the ELC-RNN model using the preprocessed historical current data, adjust the model parameters through an iterative optimization algorithm, and accurately predict and identify the binary fluctuations of the photovoltaic panel; The validation submodule is used to evaluate the performance of the model using the cross-validation method during the training process; Save submodule to save the parameters and structure of the ELC-RNN model after training is completed.

Images