Distributed photovoltaic power station temperature anomaly real-time monitoring method and related device

Abstract

This invention discloses a method and related device for real-time monitoring of temperature anomalies in distributed photovoltaic power plants, comprising: acquiring temperature information at various monitoring locations in the photovoltaic power plant; collecting the temperature information at various monitoring locations using Internet of Things (IoT) technology; preprocessing the temperature information to obtain preprocessed temperature information; extracting features from the preprocessed temperature information; and inputting the extracted features into a trained SVM model to determine the temperature status of the photovoltaic power plant. This method and related device can integrate IoT technology to achieve real-time monitoring of temperature anomalies.

Description

Technical Field

[0001] This invention belongs to the field of photovoltaic power generation technology, and relates to a method and related device for real-time monitoring of abnormal temperature in distributed photovoltaic power stations. Background Technology

[0002] In the current field of temperature monitoring for distributed photovoltaic (PV) power plants, several common technologies already exist. Traditional monitoring methods mainly rely on manual inspections and simple temperature sensor deployments. Manual inspections involve maintenance personnel periodically carrying temperature measuring equipment to the PV power plant site to measure the temperature of each PV module individually and record the data. While this method can directly obtain temperature information, it has significant limitations, such as low detection efficiency, high manpower and resource consumption, limited detection frequency, difficulty in achieving real-time monitoring, and the potential to miss some potential temperature anomalies.

[0003] Meanwhile, some photovoltaic power plants have adopted distributed temperature sensor network technology. These sensors are installed in key parts of photovoltaic modules, such as solar cells and backsheets, and transmit the collected temperature data to a data acquisition center via wired or wireless means. In terms of data transmission, wired transmission has the advantages of stable and reliable data, but it suffers from problems such as complex wiring, high cost, and difficult maintenance. Wireless transmission is relatively flexible, but its stability and accuracy need improvement due to factors such as transmission distance and signal interference.

[0004] In terms of data processing, some existing monitoring systems typically use a simple threshold method to identify temperature anomalies. This involves setting a fixed temperature threshold; when the monitored temperature exceeds this threshold, it is considered an anomaly and an alarm is triggered. However, this method is too simplistic and crude. The temperature of photovoltaic modules is affected by various factors, such as ambient temperature, light intensity, and module load. Relying solely on a single threshold cannot accurately distinguish between normal temperature fluctuations and genuine anomalies, easily leading to false alarms and missed alarms. This reduces the trust of maintenance personnel in the alarms, affecting the accurate assessment and timely handling of the actual operating status of the power plant.

[0005] Current shortcomings: Insufficient real-time performance: Manual inspection methods cannot achieve real-time monitoring. Even with sensor-based monitoring systems, limitations in data transmission rates, processing speeds, and system architecture often result in a time delay between the occurrence of a temperature anomaly and its detection and alarm issuance. This can lead to missed opportunities for timely intervention in some temperature anomalies, such as rapid temperature rise caused by partial short circuits, potentially resulting in more serious equipment damage or even fires and other safety incidents, severely impacting the power generation efficiency and safety of photovoltaic power plants.

[0006] Inaccuracy is a significant drawback: Firstly, as mentioned earlier, the threshold judgment method struggles to accurately identify temperature anomalies in complex and ever-changing real-world operating environments. Secondly, issues such as the accuracy of the temperature sensor itself, the suitability of its installation location, and drift during long-term operation can all lead to errors in the collected temperature data, thus affecting the accurate assessment of temperature anomalies. Inaccurate monitoring results may force maintenance personnel to take unnecessary maintenance measures, increasing maintenance costs, or may prevent timely detection and handling of actual temperature anomalies, causing irreversible damage to photovoltaic modules and reducing their lifespan and power generation performance.

[0007] Low level of intelligence: Most existing monitoring technologies lack the ability to deeply analyze and mine historical data, making it impossible to establish temperature change models based on long-term power plant operation data. This makes it difficult to predict and provide early warnings of temperature anomalies. Furthermore, the various monitoring systems are often relatively independent, lacking effective integration and linkage with other power plant equipment and systems (such as inverters and monitoring platforms). They cannot fully utilize the comprehensive data fusion and intelligent control advantages brought by IoT technology, failing to provide comprehensive, accurate, and intelligent support for the overall operation and maintenance decisions of the power plant, and thus failing to meet the needs of efficient and intelligent operation and maintenance management of modern distributed photovoltaic power plants.

[0008] Poor adaptability: Distributed photovoltaic power stations are built in a wide range of locations with varying environmental conditions (such as climate, terrain, and sunlight). Existing temperature monitoring technologies are not ideally adaptable to different environments. For example, in high-temperature and high-humidity environments, the reliability and accuracy of sensors are easily affected. In high-altitude areas, changes in factors such as air pressure may require special calibration of sensor measurement parameters, but current technical solutions do not adequately consider this, resulting in unstable performance of the monitoring system in different environments and hindering its widespread application and promotion in various types of distributed photovoltaic power stations.

[0009] In summary, existing temperature monitoring technologies for distributed photovoltaic power plants have many shortcomings in terms of real-time performance, accuracy, intelligence, and adaptability. There is an urgent need for a new real-time temperature anomaly monitoring algorithm that integrates Internet of Things (IoT) technology to solve these problems, thereby improving the operational reliability and safety of photovoltaic power plants, reducing operation and maintenance costs, and increasing power generation efficiency. Summary of the Invention

[0010] The purpose of this invention is to overcome the shortcomings of the prior art and provide a method and related device for real-time monitoring of temperature anomalies in distributed photovoltaic power plants. This method and related device can integrate Internet of Things (IoT) technology to achieve real-time monitoring of temperature anomalies.

[0011] To achieve the above objectives, this invention discloses a method for real-time monitoring of temperature anomalies in distributed photovoltaic power plants, comprising: Obtain temperature information from various monitoring locations in the photovoltaic power plant; Use Internet of Things (IoT) technology to collect temperature information from various monitoring locations; The temperature information is preprocessed to obtain preprocessed temperature information; Feature extraction is performed on the preprocessed temperature information; The extracted features are input into the trained SVM model to determine the temperature status of the photovoltaic power station.

[0012] Furthermore, in photovoltaic power plants, temperature sensors are installed in the center and edge areas of the solar panels, inside the inverter, and in the combiner box to obtain temperature information at various monitoring locations within the photovoltaic power plant.

[0013] Furthermore, temperature information from each monitoring location is collected via a LoRa wireless communication module through data acquisition nodes.

[0014] Furthermore, the process of preprocessing the temperature information to obtain preprocessed temperature information is as follows: The temperature information is cleaned using the 3σ principle and then smoothed to obtain preprocessed temperature information.

[0015] Furthermore, the extracted features include average temperature. Temperature standard deviation and rate of temperature change .

[0016] Furthermore, the SVM model is trained using a cross-validation method to obtain the trained SVM model.

[0017] Furthermore, it also includes: displaying the location of the anomaly, the abnormal temperature value, and the current temperature change trend based on the temperature status of the photovoltaic power station.

[0018] This invention discloses a real-time temperature anomaly monitoring system for distributed photovoltaic power plants, comprising: The acquisition module is used to acquire temperature information at various monitoring locations in the photovoltaic power station; The data collection module is used to collect temperature information from various monitoring locations using Internet of Things (IoT) technology. The preprocessing module is used to preprocess the temperature information to obtain preprocessed temperature information; The extraction module is used to extract features from the preprocessed temperature information; The judgment module is used to input the extracted features into the trained SVM model to determine the temperature status of the photovoltaic power station.

[0019] This invention discloses a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the steps of the method for real-time monitoring of temperature anomalies in a distributed photovoltaic power station.

[0020] The present invention discloses a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the method for real-time monitoring of temperature anomalies in a distributed photovoltaic power station.

[0021] The present invention has the following beneficial effects: The distributed photovoltaic power station temperature anomaly real-time monitoring method and related device of the present invention, in specific operation, utilizes Internet of Things (IoT) technology to collect temperature information from various monitoring locations; preprocesses the temperature information to obtain preprocessed temperature information; extracts features from the preprocessed temperature information; inputs the extracted features into a trained SVM model to determine the temperature status of the photovoltaic power station; solves the problem of insufficient real-time performance through real-time transmission via IoT; solves the problem of poor accuracy by replacing simple thresholds with SVM models; and solves the problem of low intelligence through machine learning models. Attached Figure Description

[0022] To more clearly illustrate the technical solutions of the embodiments of this application, the drawings used in the description of the embodiments of this application will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0023] Figure 1 This is a diagram illustrating the architecture of the distributed photovoltaic power station temperature monitoring system of the present invention. Figure 2 This is a flowchart of the method of the present invention. Detailed Implementation

[0024] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0025] In the description of this invention, it should be understood that the terms "comprising" and "including" indicate the presence of the described features, integrals, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or collections thereof.

[0026] It should also be understood that the terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the invention. As used in this specification and the appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise.

[0027] It should also be further understood that the term "and / or" as used in this specification and the appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes such combinations. For example, A and / or B can represent three cases: A alone, A and B simultaneously, and B alone. Additionally, the character " / " in this invention generally indicates that the preceding and following objects have an "or" relationship.

[0028] It should be understood that although terms such as first, second, third, etc., may be used in the embodiments of the present invention to describe the preset range, these preset ranges should not be limited to these terms. These terms are only used to distinguish the preset ranges from one another. For example, without departing from the scope of the embodiments of the present invention, the first preset range may also be referred to as the second preset range, and similarly, the second preset range may also be referred to as the first preset range.

[0029] Depending on the context, the word "if" as used here can be interpreted as "when," "when," "in response to determination," or "in response to detection." Similarly, depending on the context, the phrase "if determination" or "if detection (of the stated condition or event)" can be interpreted as "when determination," "in response to determination," "when detection (of the stated condition or event)," or "in response to detection (of the stated condition or event)."

[0030] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0031] The accompanying drawings illustrate various structural schematic diagrams according to embodiments disclosed in this invention. These drawings are not to scale, and some details have been enlarged for clarity, and some details may have been omitted. The shapes of the various regions and layers shown in the drawings, as well as their relative sizes and positional relationships, are merely exemplary and may deviate from reality due to manufacturing tolerances or technical limitations. Furthermore, those skilled in the art can design regions / layers with different shapes, sizes, and relative positions as needed.

[0032] Example 1 refer to Figure 1 and Figure 2 The real-time monitoring method for abnormal temperature in a distributed photovoltaic power station according to the present invention includes the following steps: 1) System architecture and hardware deployment; 11) Temperature sensor selection and layout; In distributed photovoltaic (PV) power stations, high-precision thermistors are selected as temperature sensors, with a measurement accuracy of ±0.5℃ and a measurement range of -40℃ to 125℃, which can meet the temperature monitoring requirements of PV power stations. On the surface of the PV panels, sensors are evenly distributed in the center and edge areas of the panels, following the principle of at least one sensor per 10 square meters. Inside the inverter, 2-3 sensors are installed in key areas such as power modules and heat sinks, depending on the distribution of heat-generating elements. One to two sensors are installed in the combiner box to monitor the temperature of the line connection points.

[0033] The sensors connect to the data acquisition node wirelessly (LoRaWAN, NB-IoT, or WIFI), and each data acquisition node can connect up to 32 sensors to reduce wiring complexity and cost.

[0034] 12) Establish a data transmission network; The data acquisition nodes are equipped with LoRa wireless communication modules, which transmit the collected temperature data to the gateway device located in the power plant's central control room. The LoRa network adopts a star topology and operates at a frequency of 433MHz. In open environments, the communication distance can reach 2-5 kilometers, which can cover a typical scale of distributed photovoltaic power plants.

[0035] The gateway device connects to the data server via an Ethernet interface, uploading the received temperature data to the server for storage and processing, ensuring the stability and real-time performance of data transmission. The data transmission rate can reach over 10Mbps, meeting the requirements for transmitting large amounts of temperature data.

[0036] 2) Data acquisition and preprocessing; 21) Data acquisition frequency setting; The sensors are set to collect temperature data every 3 minutes. This ensures timely capture of temperature changes without overloading the processing due to excessive data volume. Each sensor will collect 480 data points per day, accumulating approximately 14,400 data points per month (calculated as 30 days), providing ample data samples for subsequent analysis.

[0037] 22) Data preprocessing workflow; Data cleaning: The collected data is cleaned using the 3σ principle, that is, for a temperature data sequence of a certain sensor... First, calculate its mean. and standard deviation If a certain data point satisfy If the data point is considered an outlier and is removed, then that data point is treated as an outlier. For example, if the average value of the data collected by a photovoltaic panel temperature sensor is 40℃ and the standard deviation is 2℃ over a certain period of time, and the temperature value collected at a certain moment is 48℃ (…), then… If a data point is not found to be an outlier, it is discarded to ensure the accuracy of the data.

[0038] Data smoothing: The cleaned data is smoothed using a moving average method. The window size is set to m = 5 (adjustable according to actual conditions). For the temperature value at time i... Its smoothed temperature value The calculation formula is:

[0039] For example, the temperature value at time i=10 Its smoothing value for , , , , The average of these five data points can effectively remove noise interference, making the temperature data more stable and facilitating subsequent analysis.

[0040] 3) Establish a normal temperature model; 31) Feature extraction; Several feature parameters were extracted from the preprocessed temperature data, including: Average temperature Calculate the average value of temperature data within a time window (e.g., 1 hour) to reflect the overall temperature level during that time period.

[0041] Temperature standard deviation : Measures the dispersion of temperature data within a given time window, reflecting temperature fluctuations.

[0042] Rate of temperature change The value is obtained by calculating the ratio of the temperature difference between two adjacent time points to the time interval. The formula is as follows: ,in The data acquisition time interval is 3 minutes. The temperature change rate can reflect the temperature change trend and is of great significance for judging the occurrence of temperature anomalies.

[0043] 32) Model selection and training; A normal temperature model is established using the Support Vector Machine (SVM) algorithm, and the extracted feature parameters are used as the input vector. The corresponding temperature state (normal or abnormal) is used as the output label y (normal state is marked as 1, abnormal state is marked as -1).

[0044] Collect at least two months of historical temperature data (including data under normal and abnormal conditions) as the training set to train the SVM model. Adjust the SVM kernel function (using radial basis functions). ,in, Using kernel parameters and penalty parameter C, cross-validation is employed to find the optimal combination of model parameters, enabling the model to accurately classify normal and abnormal temperatures. For example, after multiple cross-validations, the optimal combination is determined when... When C = 10, the model achieves an accuracy of over 98% on the training set, demonstrating excellent classification performance.

[0045] 4) Temperature anomaly detection and alarm; 41) Real-time monitoring and judgment; During system operation, temperature data is collected in real time and preprocessed and feature extracted to obtain the feature vector at the current moment. .Will The data is input into a pre-trained SVM model to obtain the predicted temperature state. .

[0046] like If the temperature is determined to be abnormal, it is considered to be in an abnormal state; otherwise, it is considered to be normal. To avoid false alarms due to sensor malfunctions, a threshold of N consecutive abnormality counts is set. That is, an abnormal temperature condition is only formally confirmed after N consecutive temperature anomalies, thus improving the reliability of the judgment.

[0047] 42) Alarm mechanism; Once an abnormal temperature is confirmed, the alarm system should be activated immediately. Alarm methods include: A prominent alarm window pops up on the monitoring computer in the power plant's central control room, displaying information such as the location of the anomaly (e.g., the specific photovoltaic panel number, inverter name, combiner box location, etc.), the abnormal temperature value, and the current temperature trend, so that maintenance personnel can quickly locate the problem.

[0048] At the same time, SMS alarms are sent to the mobile phones of maintenance personnel, containing key abnormal information, so that maintenance personnel can be informed of abnormal temperatures in a timely manner even when they are not in the central control room, and take appropriate measures to deal with them in a timely manner, such as on-site inspection of equipment and adjustment of operating parameters, to prevent equipment damage and reduced power generation efficiency caused by abnormal temperatures.

[0049] 5) System performance evaluation and optimization; 51) Setting evaluation indicators; The performance of the monitoring system should be evaluated regularly using the following indicators: Accuracy: Defined as the ratio of the number of correctly identified temperature states (including normal and abnormal) to the total number of judgments, reflecting the overall accuracy of the system. The calculation formula is: ,in, True cases (the number of times an actual anomaly is correctly identified as an anomaly). True negative examples (the number of times a data point is actually normal and correctly identified as normal). False positives (the number of times a data is actually normal but is mistakenly identified as abnormal). These are false negatives (the number of times an actual anomaly was not detected).

[0050] False Alarm Rate: The ratio of false positives to the total number of judgments, reflecting the false alarm rate of the system. The formula is: A lower false alarm rate can reduce unnecessary workload for maintenance personnel and improve system usability.

[0051] 52) Optimization measures; Based on the performance evaluation results, the system should be optimized accordingly. If the accuracy is low, it may be necessary to readjust the parameters of the SVM model, increase the diversity and quantity of training data, or improve the feature extraction method to enhance the model's classification ability. If the false positive rate is high, further investigation should be conducted to check for problems in the data preprocessing stage, such as whether the data cleaning threshold is set reasonably, or to optimize the alarm mechanism, such as appropriately adjusting the threshold N for consecutive anomalies to balance the system's accuracy and reliability.

[0052] In addition, as the operation of the photovoltaic power station and environmental conditions change, the normal temperature model should be updated regularly (e.g., quarterly) to adapt to new temperature change patterns, ensure that the system always maintains good performance, accurately and timely monitor temperature anomalies, and guarantee the safe and stable operation of the distributed photovoltaic power station.

[0053] In actual operation testing at a 10MW photovoltaic power station, the system achieved an accuracy rate of 98.7% and a false alarm rate of 0.5%, with an average response time of 28 seconds. Specifically, during a continuous monitoring period of 3 months, it successfully identified 12 real temperature anomaly events with only 1 false alarm, verifying the high efficiency and reliability of the invention.

[0054] Example 2 The distributed photovoltaic power station temperature anomaly real-time monitoring system of the present invention includes: The acquisition module is used to acquire temperature information at various monitoring locations in the photovoltaic power station; The data collection module is used to collect temperature information from various monitoring locations using Internet of Things (IoT) technology. The preprocessing module is used to preprocess the temperature information to obtain preprocessed temperature information; The extraction module is used to extract features from the preprocessed temperature information; The judgment module is used to input the extracted features into the trained SVM model to determine the temperature status of the photovoltaic power station.

[0055] The module division in this embodiment is illustrative and represents only one logical functional division. In actual implementation, other division methods may be used. Furthermore, the functional modules in each embodiment of this application can be integrated into a single processor, exist as separate physical entities, or be integrated into a single module. The integrated modules described above can be implemented in hardware or as software functional modules.

[0056] Example 3 A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the steps of a method for real-time monitoring of temperature anomalies in a distributed photovoltaic power station. For example, the method includes: acquiring temperature information at various monitoring locations within the photovoltaic power station; collecting the temperature information from each monitoring location using Internet of Things (IoT) technology; preprocessing the temperature information to obtain preprocessed temperature information; extracting features from the preprocessed temperature information; and inputting the extracted features into a trained SVM model to determine the temperature status of the photovoltaic power station. The memory may include main memory, such as high-speed random access memory (RAM), or non-volatile memory, such as at least one disk storage device. The processor, network interface, and memory are interconnected via an internal bus, which can be an industry-standard architecture bus, a peripheral component interconnection standard bus, or an extended industry-standard architecture bus. The bus can be categorized as an address bus, data bus, or control bus. The memory stores the program, specifically program code, which includes computer operation instructions. The memory may include main memory and non-volatile memory, and provides instructions and data to the processor.

[0057] Example 4 A computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of a real-time temperature anomaly monitoring method for a distributed photovoltaic power station. For example, the method includes: acquiring temperature information at various monitoring locations within the photovoltaic power station; collecting the temperature information from each monitoring location using Internet of Things (IoT) technology; preprocessing the temperature information to obtain preprocessed temperature information; extracting features from the preprocessed temperature information; and inputting the extracted features into a trained SVM model to determine the temperature state of the photovoltaic power station. Specifically, the computer-readable storage medium includes, but is not limited to, volatile memory and / or non-volatile memory. The volatile memory may include random access memory (RAM) and / or cache memory, etc. The non-volatile memory may include read-only memory (ROM), hard disk, flash memory, optical disk, magnetic disk, etc.

[0058] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0059] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0060] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0061] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0062] Other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and disclosure of the invention. This application is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of the invention are indicated by the following claims.

[0063] It should be understood that the present invention is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the invention is limited only by the appended claims.

[0064] The above description is merely a preferred embodiment of the present invention and does not constitute any limitation on the present invention. Any simple modifications, alterations, or equivalent structural changes made to the above embodiments based on the technical essence of the present invention shall still fall within the protection scope of the present invention.

Claims

1. A method for real-time monitoring of temperature anomalies in a distributed photovoltaic power station, characterized in that, include: Obtain temperature information from various monitoring locations in the photovoltaic power plant; Use Internet of Things (IoT) technology to collect temperature information from various monitoring locations; The temperature information is preprocessed to obtain preprocessed temperature information; Feature extraction is performed on the preprocessed temperature information; The extracted features are input into the trained SVM model to determine the temperature status of the photovoltaic power station.

2. The method for real-time monitoring of temperature anomalies in a distributed photovoltaic power station according to claim 1, characterized in that, In photovoltaic power plants, temperature sensors are installed in the center and edge areas of the solar panels, inside the inverter, and in the combiner box to obtain temperature information at various monitoring locations in the photovoltaic power plant.

3. The method for real-time monitoring of temperature anomalies in a distributed photovoltaic power station according to claim 1, characterized in that, Temperature information from each monitoring location is collected via a LoRa wireless communication module through a data acquisition node.

4. The method for real-time monitoring of temperature anomalies in a distributed photovoltaic power station according to claim 1, characterized in that, The process of preprocessing the temperature information to obtain the preprocessed temperature information is as follows: The temperature information is cleaned using the 3σ principle and then smoothed to obtain preprocessed temperature information.

5. The method for real-time monitoring of temperature anomalies in a distributed photovoltaic power station according to claim 1, characterized in that, The extracted features include average temperature. Temperature standard deviation and rate of temperature change .

6. The method for real-time monitoring of temperature anomalies in a distributed photovoltaic power station according to claim 1, characterized in that, The SVM model is trained using a cross-validation method to obtain the trained SVM model.

7. The method for real-time monitoring of temperature anomalies in a distributed photovoltaic power station according to claim 1, characterized in that, Also includes: Based on the temperature status of the photovoltaic power station, the system displays the location of the anomaly, the abnormal temperature value, and the current temperature change trend.

8. A real-time temperature anomaly monitoring system for a distributed photovoltaic power station, characterized in that, include: The acquisition module is used to acquire temperature information at various monitoring locations in the photovoltaic power station; The data collection module is used to collect temperature information from various monitoring locations using Internet of Things (IoT) technology. The preprocessing module is used to preprocess the temperature information to obtain preprocessed temperature information; The extraction module is used to extract features from the preprocessed temperature information; The judgment module is used to input the extracted features into the trained SVM model to determine the temperature status of the photovoltaic power station.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method for real-time monitoring of temperature anomalies in a distributed photovoltaic power station as described in any one of claims 1-7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the method for real-time monitoring of temperature anomalies in a distributed photovoltaic power station as described in any one of claims 1-7.

Images