Photovoltaic power generation early warning monitoring method and system based on Internet of Things technology

Abstract

The invention discloses a photovoltaic power generation early warning monitoring method and system based on the Internet of Things technology, relates to the technical field of photovoltaic power generation real-time monitoring, and is used for solving the problems of single data acquisition dimension, static state evaluation lag and lack of trend prediction in the prior art. The method specifically comprises the steps that sensor data are collected and uploaded to a distributed database through a low-power-consumption wide area network for cleaning storage; constructing a dynamic efficiency evaluation model based on a deep learning algorithm; an LSTM model is adopted to be fused with weather forecast data, and the future power generation efficiency trend is predicted; real-time monitoring and early warning linkage control is carried out; and providing a visual interaction interface. By means of the method, multi-dimensional data fusion, real-time monitoring and dynamic evaluation are achieved, and the stability and the operation and maintenance intelligent level of the photovoltaic power station are remarkably improved.

Description

Technical Field

[0001] This invention belongs to the field of real-time monitoring technology for photovoltaic power generation, specifically relating to a photovoltaic power generation early warning monitoring method and system based on Internet of Things (IoT) technology. Background Technology

[0002] With the accelerated global energy structure transformation, photovoltaic (PV) power generation, as a major clean energy source, has been deployed on a large scale. However, the power generation efficiency of PV systems is affected by multiple coupled factors, exhibiting strong nonlinear time-varying characteristics. Existing monitoring methods mainly rely on manual inspections and discrete data collection, which suffer from limitations such as a single data dimension making it difficult to cover the entire power plant's operating status, insufficient real-time status assessment, and the lack of a dynamic efficiency assessment and prediction mechanism based on multi-source heterogeneous data. This makes it impossible to provide early quantitative warnings of efficiency degradation trends and potential faults. Therefore, an intelligent monitoring and early warning platform is urgently needed to monitor and issue early warnings for power generation efficiency in real time.

[0003] Chinese invention patent CN 120729169 A discloses a real-time monitoring system for distributed photovoltaic power generation. Its features include a monitoring center equipped with a user interface and a notification module connecting the monitoring center and the user interface; a data monitoring and receiving end equipped with a data acquisition and detection module and a real-time monitoring and alarm module; a data analysis end equipped with an information analysis and diagnosis module and a data storage and historical data analysis module; a data protection end equipped with a security detection module; and a data transmission end equipped with a remote control and optimization module. This prior art suffers from the following drawbacks: limited data acquisition dimensions, lack of dynamic evaluation capabilities in the real-time monitoring and alarm module, and delayed response. These are the shortcomings of the prior art.

[0004] In view of this, it is very necessary to provide a photovoltaic power generation early warning and monitoring method and system based on Internet of Things technology to solve the above-mentioned defects in the prior art. Summary of the Invention

[0005] To address the technical problems of existing technologies, such as limited data acquisition dimensions, lack of dynamic evaluation capabilities in real-time monitoring and alarm modules, and delayed response, this invention provides a photovoltaic power generation early warning and monitoring method and system based on Internet of Things (IoT) technology to solve the aforementioned technical problems.

[0006] In a first aspect, the present invention provides a photovoltaic power generation early warning and monitoring method based on Internet of Things (IoT) technology, comprising: Step S1: Data acquisition and preprocessing step, acquiring data detected by the sensor detection unit and uploading it to the data processing center, preprocessing and storing the data detected by the sensor detection unit; The sensor detection unit includes photovoltaic module detection sensors, power plant environment detection sensors, and operating equipment detection sensors; Photovoltaic module testing sensors include voltage sensors, current sensors, and temperature sensors; The power plant environmental monitoring sensors include light intensity sensors, wind speed sensors, and humidity sensors; The operating equipment includes inverters and combiner boxes; The sensors used to detect operating equipment include current sensors and voltage sensors; Low-power wide-area network communication technology is used to collect sensor data and upload it to the data processing center. The data processing center includes a distributed database; Preprocessing sensor data includes cleaning the collected data to remove outliers, duplicates, and noisy data; The pre-processed sensor data is stored in a distributed database.

[0007] Step S2: Construct a dynamic efficiency evaluation model. Based on multi-source heterogeneous operation and maintenance data, use deep learning algorithms to train and obtain the theoretical power generation efficiency prediction value, and compare it with the actual power generation efficiency to calculate the deviation value. Multi-source heterogeneous operation and maintenance data includes historical power generation data and sensor data; The deep learning algorithm uses the random forest regression algorithm to train on multi-source heterogeneous data and outputs predicted power generation efficiency values. The predicted power generation efficiency is compared with the actual output power, and the deviation between the two is calculated. The mathematical expression is as follows:

[0008] in, The theoretical power generation is predicted by the dynamic efficiency assessment model based on multi-source heterogeneous data; This refers to the grid-connected power or module output power collected in real time by the photovoltaic power plant.

[0009] Step S3: The step of constructing a time series prediction algorithm, which uses an LSTM model to predict the photovoltaic power generation efficiency for the next 24–72 hours based on historical power generation efficiency time series and real-time updated weather forecast data series; The mathematical expression for the historical power generation efficiency time series is: ,in, , where is the normalized power generation efficiency at time t; The mathematical expression for the real-time updated weather forecast data sequence is: ,in, The weather forecast data at time t includes light intensity, ambient temperature, humidity, and k-dimensional components of wind speed. At each time step t, and The concatenation results in a joint feature vector, which can be expressed mathematically as follows: The LSTM model is used to predict the photovoltaic power generation efficiency for the next H hours. The mathematical expression is as follows:

[0010] Where H = 24–72 h, The parameter matrix obtained from model training. This is the predicted value at step H.

[0011] Step S4: Real-time monitoring and early warning linkage control steps, real-time monitoring of power generation efficiency deviation value and equipment operating parameters, setting three-level early warning thresholds based on power generation efficiency deviation value, abnormality degree of equipment operating parameters and historical fault data, transmitting alarm information to operation and maintenance personnel through audible and visual alarms on the monitoring platform, and linking IoT devices to start self-healing control. The equipment operating parameters are represented in vector form, and their mathematical expressions are as follows: , and These are the lower and upper limits of the normal range for the i-th parameter, respectively. The fault risk weighting factor is calculated based on historical fault data; The three-level warning thresholds include mild warning, moderate warning, and emergency warning; Among them, when And all This triggered a mild warning. when ,but Deviation less than Triggered a moderate alert. The historical standard deviation; when or exists Deviation greater than ,or , To trigger an emergency warning based on a preset risk threshold; When the monitored data exceeds the warning threshold, the monitoring platform issues an audible and visual alarm and sends a warning message to the operation and maintenance personnel. When the monitored data exceeds the warning threshold, the data is transmitted to the IoT device to activate self-healing control. Self-healing control includes automatically activating the heat dissipation device and automatically adjusting the tracking angle of the photovoltaic panel.

[0012] Step S5: The user-visualized interaction step involves uploading real-time power generation data, operating status, efficiency analysis, and early warning information to the interactive interface to provide users with human-computer interaction functions; The human-computer interaction functions include historical data query, early warning parameter setting, remote control of IoT devices, and operation log recording.

[0013] Secondly, the technical solution of the present invention also provides a photovoltaic power generation early warning and monitoring system based on Internet of Things technology, including a data acquisition and preprocessing module, a dynamic efficiency evaluation model construction module, a time series prediction algorithm construction module, a monitoring and early warning linkage control module, and a visualization interaction module; The data acquisition and preprocessing module acquires the data detected by the sensor detection unit and uploads it to the data processing center, where it preprocesses and stores the data detected by the sensor detection unit. The sensor detection unit includes a photovoltaic module detection unit, a power plant environment detection unit, and operating equipment detection sensors; Photovoltaic module testing sensors include voltage sensors, current sensors, and temperature sensors; Sensors used in power plant environments include light intensity sensors, wind speed sensors, and humidity sensors. The operating equipment includes inverters and combiner boxes; The sensors used to detect operating equipment include current sensors and voltage sensors; Low-power wide-area network communication technology is used to collect sensor data and upload it to the data processing center. The data processing center includes a distributed database; Preprocessing sensor data includes cleaning the collected data to remove outliers, duplicates, and noisy data; The pre-processed sensor data is stored in a distributed database.

[0014] The dynamic efficiency evaluation model construction module, based on multi-source heterogeneous operation and maintenance data, uses deep learning algorithms to train and obtain theoretical power generation efficiency prediction values, and compares them with actual power generation efficiency to calculate the deviation value. The time series prediction algorithm construction module uses an LSTM model to predict the photovoltaic power generation efficiency for the next 24–72 hours based on historical power generation efficiency time series and real-time updated meteorological forecast data series. The monitoring and early warning linkage control module monitors the power generation efficiency deviation value and equipment operating parameters in real time. Based on the power generation efficiency deviation value, the degree of abnormality of equipment operating parameters and historical fault data, it sets three-level early warning thresholds. The alarm information is transmitted to the operation and maintenance personnel through the audible and visual alarm of the monitoring platform, and the IoT devices are linked to start the self-healing control. The visualization and interaction module uploads real-time power generation data, operating status, efficiency analysis and early warning information to the interactive interface, providing users with functions such as historical data query, early warning parameter setting, remote control of IoT devices and operation log recording. The human-computer interaction functions include historical data query, early warning parameter setting, remote control of IoT devices, and operation log recording.

[0015] The beneficial effects of this invention are that it provides a photovoltaic power generation early warning and monitoring method and system based on Internet of Things technology. By fusing multi-source heterogeneous data, it solves the problem of single data collection dimension in existing technologies, constructs a dynamic efficiency evaluation model and time series prediction algorithm, realizes real-time monitoring and dynamic evaluation of photovoltaic power generation efficiency, and changes the traditional passive mode of lagging manual response through multi-level early warning linkage and equipment self-healing control.

[0016] Furthermore, the design principle of this invention is reliable, the structure is simple, and it has a very wide range of application prospects. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is a flowchart of a photovoltaic power generation early warning and monitoring method based on Internet of Things (IoT) technology provided by the present invention.

[0019] Figure 2 This is a schematic diagram of a photovoltaic power generation early warning and monitoring system based on Internet of Things technology provided by the present invention. Detailed Implementation

[0020] To enable those skilled in the art to better understand the technical solutions of this invention, the technical solutions of the embodiments of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this invention, and not all embodiments. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of this invention.

[0021] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used herein in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention.

[0022] Example 1: like Figure 1 As shown, this embodiment of the invention provides a photovoltaic power generation early warning and monitoring method based on Internet of Things (IoT) technology, comprising the following steps: Step S1: Data acquisition and preprocessing step, acquiring data detected by the sensor detection unit and uploading it to the data processing center, preprocessing and storing the data detected by the sensor detection unit; The sensor detection unit includes photovoltaic module detection sensors, power plant environment detection sensors, and operating equipment detection sensors; Photovoltaic module testing sensors include voltage sensors, current sensors, and temperature sensors, which are used to collect real-time data on the operating voltage, current, and temperature of photovoltaic modules. Preferably, the photovoltaic module sensor data is collected every ten minutes.

[0023] The power plant environmental monitoring sensors include light intensity sensors, wind speed sensors, and humidity sensors, which are used to acquire real-time environmental parameters. Preferably, sensor data in the power plant environment is collected every 1 hour.

[0024] The operating equipment includes inverters and combiner boxes; Operating equipment detection sensors include current sensors and voltage sensors, used to monitor the operating status and output power parameters of the equipment; Preferably, sensor data from the operating equipment is collected every 1 hour.

[0025] Low-power wide-area network communication technology is used to collect sensor data and upload it to the data processing center. Preferably, NB-IoT (Narrowband Internet of Things) or LoRa (Long Range Radio) is used to stably and efficiently transmit the large amount of data collected by the sensors to the data processing center.

[0026] The data processing center includes a distributed database; Preprocessing sensor data includes cleaning the collected data to remove outliers, duplicates, and noisy data; The pre-processed sensor data is stored in a distributed database.

[0027] Preferably, the latest collected data is analyzed every hour to update the parameters of the dynamic efficiency evaluation model and predict the power generation efficiency trend for the next 24 hours.

[0028] Step S2: Construct a dynamic efficiency evaluation model. Based on multi-source heterogeneous operation and maintenance data, use deep learning algorithms to train and obtain the theoretical power generation efficiency prediction value, and compare it with the actual power generation efficiency to calculate the deviation value. Multi-source heterogeneous operation and maintenance data includes historical power generation data and sensor data; The deep learning algorithm uses the random forest regression algorithm to train on multi-source heterogeneous data and outputs predicted power generation efficiency values. The predicted power generation efficiency is compared with the actual output power, and the deviation between the two is calculated. The mathematical expression is as follows:

[0029] in, The theoretical power generation is predicted by the dynamic efficiency assessment model based on multi-source heterogeneous data; This refers to the grid-connected power or module output power collected in real time by the photovoltaic power plant.

[0030] Step S3: The step of constructing a time series prediction algorithm, which uses an LSTM model to predict the photovoltaic power generation efficiency for the next 24–72 hours based on historical power generation efficiency time series and real-time updated weather forecast data series; The mathematical expression for the historical power generation efficiency time series is: ,in, , where is the normalized power generation efficiency at time t; The mathematical expression for the real-time updated weather forecast data sequence is: ,in, The weather forecast data at time t includes light intensity, ambient temperature, humidity, and k-dimensional components of wind speed. At each time step t, and The concatenation results in a joint feature vector, which can be expressed mathematically as follows: The LSTM model is used to predict the photovoltaic power generation efficiency for the next H hours. The mathematical expression is as follows:

[0031] Where H = 24–72 h, The parameter matrix obtained from model training. This is the predicted value at step H; Preferably, real-time updated weather forecast data includes future light intensity and temperature change trends.

[0032] Step S4: Real-time monitoring and early warning linkage control steps, real-time monitoring of power generation efficiency deviation value and equipment operating parameters, setting three-level early warning thresholds based on power generation efficiency deviation value, abnormality degree of equipment operating parameters and historical fault data, transmitting alarm information to operation and maintenance personnel through audible and visual alarms on the monitoring platform, and linking IoT devices to start self-healing control. The equipment operating parameters are represented in vector form, and their mathematical expressions are as follows: , and These are the lower and upper limits of the normal range for the i-th parameter, respectively. The fault risk weighting factor is calculated based on historical fault data; The three-level warning thresholds include mild warning, moderate warning, and emergency warning; Among them, when And all This triggered a mild warning. when ,but Deviation less than Triggered a moderate alert. The historical standard deviation; when or exists Deviation greater than ,or , To trigger an emergency warning based on a preset risk threshold; When the monitored data exceeds the warning threshold, the monitoring platform issues an audible and visual alarm and sends a warning message to the operation and maintenance personnel. When the monitored data exceeds the warning threshold, the data is transmitted to the IoT device to activate self-healing control. Self-healing control includes automatically activating the heat dissipation device and automatically adjusting the tracking angle of the photovoltaic panel.

[0033] Step S5: The user-visualized interaction step involves uploading real-time power generation data, operating status, efficiency analysis, and early warning information to the interactive interface to provide users with human-computer interaction functions; The human-computer interaction functions include historical data query, early warning parameter setting, remote control of IoT devices, and operation log recording.

[0034] Example 2: like Figure 2 As shown, this embodiment also provides a photovoltaic power generation early warning and monitoring system based on Internet of Things technology, including a data acquisition and preprocessing module 1, a dynamic efficiency evaluation model construction module 2, a time series prediction algorithm construction module 3, a monitoring and early warning linkage control module 4, and a visualization interaction module 5; Data acquisition and preprocessing module 1 acquires data detected by the sensor detection unit and uploads it to the data processing center, and preprocesses and stores the data detected by the sensor detection unit. The sensor detection unit includes a photovoltaic module detection unit, a power plant environment detection unit, and operating equipment detection sensors; the photovoltaic module detection sensors include voltage sensors, current sensors, and temperature sensors. Sensors used in power plant environments include light intensity sensors, wind speed sensors, and humidity sensors. The operating equipment includes inverters and combiner boxes; Operating equipment detection sensors include operating status sensors and voltage sensors; Low-power wide-area network communication technology is used to collect sensor data and upload it to the data processing center. The data processing center includes a distributed database; Preprocessing sensor data includes cleaning the collected data to remove outliers, duplicates, and noisy data; The pre-processed sensor data is stored in a distributed database.

[0035] Module 2 for constructing a dynamic efficiency evaluation model uses deep learning algorithms to train theoretical power generation efficiency predictions based on multi-source heterogeneous operation and maintenance data, and compares them with actual power generation efficiency to calculate the deviation value. The time series prediction algorithm construction module 3 uses an LSTM model to predict the photovoltaic power generation efficiency for the next 24–72 hours based on historical power generation efficiency time series and real-time updated meteorological forecast data series. The monitoring and early warning linkage control module 4 monitors the power generation efficiency deviation value and equipment operating parameters in real time. Based on the power generation efficiency deviation value, the degree of abnormality of equipment operating parameters and historical fault data, it sets three-level early warning thresholds. The alarm information is transmitted to the operation and maintenance personnel through the audible and visual alarm of the monitoring platform, and the self-healing control of the Internet of Things devices is activated. The visualization and interaction module 5 uploads real-time power generation data, operating status, efficiency analysis and early warning information to the interactive interface, providing users with functions such as historical data query, early warning parameter setting, remote control of IoT devices and operation log recording. The human-computer interaction functions include historical data query, early warning parameter setting, remote control of IoT devices, and operation log recording.

[0036] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. The methods disclosed in the embodiments are described simply because they correspond to the systems disclosed in the embodiments; relevant details can be found in the method section.

[0037] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0038] In the embodiments provided by this invention, it should be understood that the disclosed systems, methods, and approaches can be implemented in other ways. For example, the system embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between systems or units may be electrical, mechanical, or other forms.

[0039] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0040] In addition, the functional modules in the various embodiments of the present invention can be integrated into one processing unit, or each module can exist physically separately, or two or more modules can be integrated into one unit.

[0041] Similarly, in the various embodiments of the present invention, each processing unit can be integrated into a functional module, or each processing unit can exist physically, or two or more processing units can be integrated into a functional module.

[0042] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein can be implemented directly by hardware, a software module executed by a processor, or a combination of both. The software module can be located in random access memory (RAM), main memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art.

[0043] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0044] The above-disclosed embodiments are merely preferred embodiments of the present invention, but the present invention is not limited thereto. Any non-creative variations that can be conceived by those skilled in the art, as well as any improvements and modifications made without departing from the principles of the present invention, should fall within the protection scope of the present invention.

Claims

1. A photovoltaic power generation early warning and monitoring method based on Internet of Things (IoT) technology, characterized in that, Includes the following steps: Step S1: Data acquisition and preprocessing step, acquiring data detected by the sensor detection unit and uploading it to the data processing center, preprocessing and storing the data detected by the sensor detection unit; Step S2: Construct a dynamic efficiency evaluation model. Based on multi-source heterogeneous operation and maintenance data, use deep learning algorithms to train and obtain the theoretical power generation efficiency prediction value, and compare it with the actual power generation efficiency to calculate the deviation value. Step S3: The step of constructing a time series prediction algorithm, which uses an LSTM model to predict the photovoltaic power generation efficiency for the next 24–72 hours based on historical power generation efficiency time series and real-time updated weather forecast data series; Step S4: Real-time monitoring and early warning linkage control steps, real-time monitoring of power generation efficiency deviation value and equipment operating parameters, setting three-level early warning thresholds based on power generation efficiency deviation value, abnormality degree of equipment operating parameters and historical fault data, transmitting alarm information to operation and maintenance personnel through audible and visual alarms on the monitoring platform, and linking IoT devices to start self-healing control. Step S5: The user-visualized interaction step involves uploading real-time power generation data, operating status, efficiency analysis, and early warning information to the interactive interface, providing users with human-computer interaction functions.

2. The photovoltaic power generation early warning and monitoring method based on Internet of Things technology according to claim 1, characterized in that, The sensor detection unit includes photovoltaic module detection sensors, power plant environment detection sensors, and operating equipment detection sensors; Photovoltaic module testing sensors include voltage sensors, current sensors, and temperature sensors; Sensors used in power plant environments include light intensity sensors, wind speed sensors, and humidity sensors. The operating equipment includes inverters and combiner boxes; The sensors used to detect operating equipment include current sensors and voltage sensors; Low-power wide-area network communication technology is used to collect sensor data and upload it to the data processing center. The data processing center includes a distributed database.

3. The photovoltaic power generation early warning and monitoring method based on Internet of Things technology according to claim 2, characterized in that, Preprocessing sensor data includes cleaning the collected data to remove outliers, duplicates, and noisy data; The pre-processed sensor data is stored in a distributed database.

4. The photovoltaic power generation early warning and monitoring method based on Internet of Things technology according to claim 1, characterized in that, The multi-source heterogeneous operation and maintenance data includes historical power generation data and sensor data; The deep learning algorithm uses the random forest regression algorithm to train on multi-source heterogeneous data and output predicted values ​​of power generation efficiency.

5. The photovoltaic power generation early warning and monitoring method based on Internet of Things technology according to claim 4, characterized in that, The predicted power generation efficiency is compared with the actual output power, and the deviation between the two is calculated. The mathematical expression is as follows: in, The theoretical power generation is predicted by the dynamic efficiency assessment model based on multi-source heterogeneous data; This refers to the grid-connected power or module output power collected in real time by the photovoltaic power plant.

6. The photovoltaic power generation early warning and monitoring method based on Internet of Things technology according to claim 1, characterized in that, The mathematical expression for the historical power generation efficiency time series is: ,in, , where is the normalized power generation efficiency at time t; The mathematical expression for the real-time updated weather forecast data sequence is: ,in, The weather forecast data at time t includes light intensity, ambient temperature, humidity, and k-dimensional components of wind speed. At each time step t, and The concatenation results in a joint feature vector, which can be expressed mathematically as follows: The LSTM model is used to predict the photovoltaic power generation efficiency for the next H hours. The mathematical expression is as follows: Where H = 24–72 h, The parameter matrix obtained from model training. This is the predicted value at step H.

7. The photovoltaic power generation early warning and monitoring method based on Internet of Things technology according to claim 1, characterized in that, The equipment operating parameters are represented in vector form, and the mathematical expression is: , and These are the lower and upper limits of the normal range for the i-th parameter, respectively. The fault risk weighting factor is calculated based on historical fault data; The three-level warning thresholds include mild warning, moderate warning, and emergency warning; Among them, when And all This triggered a mild warning. when ,but Deviation less than Triggered a moderate alert. The historical standard deviation; when or exists Deviation greater than ,or , An emergency warning is triggered based on a preset risk threshold.

8. The photovoltaic power generation early warning and monitoring method based on Internet of Things technology according to claim 1, characterized in that, When the monitored data exceeds the warning threshold, the monitoring platform issues an audible and visual alarm and sends a warning message to the operation and maintenance personnel. When the monitored data exceeds the warning threshold, the data is transmitted to the IoT device to activate self-healing control. Self-healing control includes automatically activating the heat dissipation device and automatically adjusting the tracking angle of the photovoltaic panel.

9. A photovoltaic power generation early warning and monitoring system based on Internet of Things (IoT) technology, characterized in that, It includes a data acquisition and preprocessing module, a dynamic efficiency evaluation model construction module, a time series prediction algorithm construction module, a monitoring and early warning linkage control module, and a visualization and interaction module; The data acquisition and preprocessing module acquires the data detected by the sensor detection unit and uploads it to the data processing center, and preprocesses and stores the data detected by the sensor detection unit. The dynamic efficiency evaluation model construction module uses deep learning algorithms to train and obtain theoretical power generation efficiency prediction values ​​based on multi-source heterogeneous operation and maintenance data, and compares them with actual power generation efficiency to calculate the deviation value. The time series prediction algorithm construction module uses an LSTM model to predict the photovoltaic power generation efficiency for the next 24–72 hours based on historical power generation efficiency time series and real-time updated meteorological forecast data series. The monitoring and early warning linkage control module monitors the power generation efficiency deviation value and equipment operating parameters in real time. Based on the power generation efficiency deviation value, the degree of abnormality of equipment operating parameters and historical fault data, it sets a three-level early warning threshold. The alarm information is transmitted to the operation and maintenance personnel through the audible and visual alarm of the monitoring platform, and the self-healing control of the Internet of Things device is activated. The visualization interaction module uploads real-time power generation data, operating status, efficiency analysis, and early warning information to the interactive interface, providing users with functions such as historical data query, early warning parameter setting, remote control of IoT devices, and operation log recording.

10. A photovoltaic power generation early warning and monitoring system based on Internet of Things technology according to claim 9, characterized in that, The sensor detection unit includes a photovoltaic module detection unit, a power plant environment detection unit, and operation detection sensors; Photovoltaic module testing sensors include voltage sensors, current sensors, and temperature sensors; Sensors used in power plant environments include light intensity sensors, wind speed sensors, and humidity sensors. The operating equipment includes inverters and combiner boxes; The sensors used to detect operating equipment include current sensors and voltage sensors; Low-power wide-area network communication technology is used to collect sensor data and upload it to the data processing center. The data processing center includes a distributed database; Preprocessing sensor data includes cleaning the collected data to remove outliers, duplicates, and noisy data; The pre-processed sensor data is stored in a distributed database; The human-computer interaction functions include historical data query, early warning parameter setting, remote control of IoT devices, and operation log recording.

Images