Photovoltaic power station Internet of Things intelligent management and cloud edge collaborative optimization system

Abstract

The invention relates to the technical field of photovoltaic power station management, and discloses a photovoltaic power station Internet of Things intelligent management and cloud edge collaborative optimization system. The system comprises an operation data acquisition module which is used for acquiring power station data in multiple dimensions, quantitatively identifying an abnormal operation state and generating a management early warning signal; the equipment state evaluation module is used for extracting equipment characteristics and dynamically evaluating the self-maintenance capability to obtain a state evaluation reference value; the edge processing module is used for monitoring parameters such as data traffic and predicting and analyzing edge processing efficiency to obtain an edge calculation evaluation value; the cloud edge collaboration module is used for jointly analyzing collaborative optimization efficiency and generating a regulation and control signal; the optimization parameter generation module is used for generating equipment maintenance and computing power distribution parameters; the system further comprises an authority control module and a dynamic adjustment module. According to the system, intelligent management and cloud edge collaborative optimization of the photovoltaic power station are realized, the operation efficiency and reliability of the power station are improved, and the safety and dynamic adjustment capability are enhanced.

Description

Technical Field

[0001] The present invention relates to the technical field of photovoltaic power station management, and specifically to an Internet of Things intelligent management and cloud-edge collaborative optimization system for photovoltaic power stations. Background Art

[0002] As the global energy structure shifts toward clean energy, photovoltaic power plants, as an important component of renewable energy, are expanding in scale and number. However, the operation and management of photovoltaic power plants face many challenges.

[0003] The collection and processing of power plant operating data presents challenges. Photovoltaic power plants incorporate numerous components, inverters, combiner boxes, and other equipment. During operation, these devices generate a vast amount of multi-source data, including power generation parameters, communication status parameters, and environmental meteorological factors. Traditional data collection methods often fail to comprehensively capture this data across multiple dimensions, making it difficult to accurately understand the actual operating status of the power plant. For example, if key information such as output power fluctuations, temperature anomalies, and voltage offsets within component power generation parameters cannot be effectively extracted, potential equipment failures cannot be detected promptly. Furthermore, incomplete collection of information such as signal interruption frequency, protocol compatibility, and data packet loss rate within device communication status parameters can hinder the assessment of device communication stability. Furthermore, the impact of environmental meteorological factors, such as changes in light intensity and wind speed fluctuations, on power plant operations cannot be ignored. However, traditional systems struggle to accurately collect and analyze this data in real time.

[0004] Equipment status assessment lacks scientific and dynamic nature. PV power station component attenuation characteristics, inverter conversion efficiency, and combiner box connection stability are important indicators reflecting the health of the equipment. Traditional equipment status assessment methods typically use fixed assessment criteria and are unable to dynamically adjust based on the actual operating conditions of the equipment. For example, traditional methods cannot analyze the spatial distribution of component attenuation characteristics, making it difficult to generate accurate power attenuation distribution maps and hot spot risk assessment maps, making it impossible to promptly identify component attenuation trends and hot spot risks. Furthermore, the lack of comparative analysis with healthy power station data makes it impossible to accurately assess the maintenance potential and self-maintenance capabilities of the equipment.

[0005] Insufficient edge processing and cloud-edge collaboration capabilities. In terms of data processing, traditional systems do not fully monitor the power plant's real-time data traffic, local computing load, and communication delay parameters, making it difficult to accurately predict and analyze the edge processing performance of data. For example, it is impossible to build an effective performance prediction model based on historical data, and thus it is impossible to accurately output key indicators such as data processing rate, computing power utilization, and delay fluctuation rate within the target time interval. In terms of cloud-edge collaboration, traditional systems cannot effectively combine equipment status assessment results and edge processing performance assessment results for joint analysis, making it difficult to generate reasonable edge control signals and cloud reinforcement signals based on collaborative optimization performance, resulting in the inability to optimize the allocation of power plant resources.

[0006] Imperfect permission control and dynamic adjustment mechanisms. Traditional PV power plant management systems lack real-time monitoring and effective control of equipment operating permissions, making it impossible to promptly detect violations such as unauthorized operations, posing a safety hazard. Furthermore, when adjusting resource allocation based on optimization parameters, traditional systems struggle to achieve real-time and dynamic adjustments, preventing a closed-loop optimization process and resulting in poor optimization results. Summary of the Invention

[0007] The purpose of the present invention is to provide a photovoltaic power station Internet of Things intelligent management and cloud-edge collaborative optimization system to solve the problems raised in the above background technology.

[0008] To achieve the above objectives, the present invention provides a photovoltaic power station IoT intelligent management and cloud-edge collaborative optimization system, the system comprising:

[0009] The operation data acquisition module is used to collect multi-dimensional data on the power plant's component power generation parameters, equipment communication status, and environmental meteorological factors to obtain a multi-source data set for the power plant. This module is used to quantitatively identify abnormal operating conditions of the system and generate management warning signals. The generated management warning signals trigger the edge processing module and the cloud collaboration module.

[0010] The equipment status assessment module is used to extract the characteristics of the power station's component attenuation, inverter conversion efficiency, and combiner box connection stability, dynamically evaluate the equipment's self-maintenance capabilities, and obtain a status assessment benchmark value;

[0011] The edge processing module is used to monitor the power plant's real-time data traffic, local computing load, and communication delay parameters, and to predict and analyze the edge processing efficiency of the data to obtain an edge computing evaluation value;

[0012] The cloud-edge collaboration module is used to receive the status assessment baseline value and the edge computing assessment value, conduct a joint analysis of the system's collaborative optimization efficiency, and generate edge control signals and cloud reinforcement signals;

[0013] The optimization parameter generation module is used to receive edge control signals and cloud reinforcement signals, perform multi-level optimization strategy analysis, and generate equipment maintenance parameters and computing power allocation parameters for the power station.

[0014] Preferably, the quantitative identification of the abnormal operating state of the system includes:

[0015] By extracting the output power fluctuation, temperature anomaly value and voltage offset from the power generation parameters of the power station components, the power fluctuation value, temperature anomaly value and voltage offset are obtained. The values ​​of the three are extracted and weighted for calculation to obtain the contribution of the operation anomaly.

[0016] By extracting the signal interruption frequency, protocol matching degree and data packet loss rate from the communication status parameters of the power station equipment, the communication interruption value, protocol matching value and data packet loss value are obtained, and they are marked as communication stability characteristic values. A communication stability threshold is set, and the characteristic value is compared and analyzed with the threshold. When the characteristic value is less than the threshold, the device is marked as an abnormal device. The ratio of the number of abnormal devices to the total number of devices in the current power station is calculated to obtain the communication abnormality rate. At the same time, the light intensity change and wind speed fluctuation values ​​in the power station environment meteorological elements are extracted and dynamic simulation calculations are performed to obtain the environmental disturbance assessment value.

[0017] The values ​​of the operation abnormality contribution, communication abnormality rate and environmental disturbance assessment value are multiplied by the corresponding weight coefficients and added together to obtain the abnormal state fusion value, which is compared with the preset abnormality threshold. If the fusion value is higher than the threshold, a management warning signal is generated.

[0018] Preferably, the dynamic evaluation of the self-maintenance capability of the equipment includes:

[0019] By analyzing the spatial distribution of the power plant's component attenuation characteristics, the corresponding power attenuation distribution map and hot spot risk assessment map are generated;

[0020] Extract the reference distribution map of component attenuation of healthy power plants from the system database, perform a topological comparison between the target power plant's power attenuation distribution map and the reference distribution map, calculate the attenuation matching degree between the two, and perform normalization processing to obtain the equipment maintenance potential index;

[0021] The hot spot occurrence frequency and power loss ratio are extracted from the hot spot risk assessment map of the power station and marked as hot spot characteristic values ​​respectively;

[0022] Extract the standard hot spot risk threshold from the system database, calculate the difference between the hot spot characteristic value and the threshold, and obtain the self-maintenance capability deviation;

[0023] The equipment maintenance potential index and the self-maintenance capability deviation are weighted and fused to obtain the condition assessment benchmark value.

[0024] Preferably, the predictive analysis of edge processing efficiency of data includes:

[0025] By extracting the monitoring data volume, control instruction volume and log storage volume from the real-time data flow of the power station, a data flow parameter set is obtained;

[0026] Extract historical processing data of similar power plants from the system database, build an efficiency prediction model based on a dynamic balance algorithm, input the flow parameter set into the model, and output the data processing rate, computing power utilization, and latency fluctuation rate within the target time interval;

[0027] The data processing rate, computing power utilization, and delay fluctuation rate are normalized to obtain the edge computing evaluation value.

[0028] Preferably, the joint analysis of the collaborative optimization effectiveness of the system includes:

[0029] Retrieve the quantified results of the abnormal state of the power station, set its correction factor, and obtain the operation impact correction value through calculation and processing;

[0030] The state assessment baseline value, edge computing assessment value, and operation impact correction value are normalized and calculated to obtain a collaborative optimization assessment value;

[0031] Set the collaborative optimization evaluation threshold. If the collaborative evaluation value is greater than or equal to the threshold, an edge control signal is generated; if it is less than the threshold, a cloud reinforcement signal is generated.

[0032] Preferably, the multi-level optimization strategy analysis includes:

[0033] If an edge control signal is captured, the device maintenance instruction is triggered. Based on the instruction, the component cleaning cycle and inverter cooling parameters of the power station are dynamically adjusted to generate equipment maintenance parameters.

[0034] If a cloud reinforcement signal is captured, the computing power allocation instruction will be triggered. Based on the instruction, the local storage capacity of the power station and the cloud computing tasks will be dynamically planned to generate computing power allocation parameters.

[0035] Preferably, the system further comprises:

[0036] The authority control module is used to monitor the power plant's equipment operation permissions in real time, extract the operator's identification, permitted operation scope, and illegal operation characteristics, and generate an authority association evaluation value;

[0037] The cloud-edge collaboration module further combines the permission association evaluation value to perform operation permission constraint analysis on the collaborative optimization performance.

[0038] Preferably, the real-time monitoring of the power plant equipment operation authority includes:

[0039] By analyzing the license data of the power plant during operation and control, the operator's permission type and historical violation records are obtained;

[0040] Match the permission type with the preset operation permission list and calculate the permission type deviation;

[0041] Calculate the difference between the frequency of unauthorized operations and the total number of operations in historical violation records to obtain the abnormal operation behavior index;

[0042] The permission type deviation degree and the operation behavior abnormality index are weighted and fused to generate the permission association evaluation value.

[0043] Preferably, the system further comprises:

[0044] The dynamic adjustment module is used to adjust the resource allocation frequency of power station operation and maintenance in real time based on the generated equipment maintenance parameters and computing power allocation parameters, and feed the adjusted parameters back to the operation data acquisition module to form a closed-loop optimization process.

[0045] Preferably, the adjustment process of the dynamic adjustment module includes:

[0046] If the equipment maintenance parameters involve adjusting the component cleaning cycle, the cleaning equipment scheduling parameters in the resource configuration will be adjusted simultaneously;

[0047] If the computing power allocation parameters involve cloud computing task optimization, the network bandwidth allocation parameters in the resource configuration will be adjusted simultaneously;

[0048] Input the adjusted parameters into the operation data acquisition module and restart the optimization and verification process.

[0049] Compared with the prior art, the present invention has the following beneficial effects:

[0050] The photovoltaic power station IoT intelligent management and cloud-edge collaborative optimization system provided by this invention uses a data acquisition module to perform multi-dimensional collection of power generation parameters of power station components, equipment communication status, and environmental meteorological factors, forming a multi-source data set. This can quantitatively identify abnormal system operating conditions and generate management warning signals, providing a basis for triggering subsequent edge processing modules and cloud-based collaborative modules. The equipment status assessment module extracts features of component attenuation, inverter conversion efficiency, and combiner box connection stability, dynamically evaluates equipment self-maintenance capabilities, and obtains a status assessment baseline value, making equipment status assessment more scientific and accurate.

[0051] The edge processing module monitors the power plant's real-time data flow, local computing load, and communication latency parameters, predicts and analyzes edge data processing efficiency, and generates edge computing evaluation values, helping to improve the efficiency and accuracy of edge data processing. The cloud-edge collaboration module receives the state assessment baseline and edge computing evaluation values, jointly analyzes the system's collaborative optimization efficiency, and generates edge control signals and cloud-side reinforcement signals, achieving the rational allocation and collaborative optimization of cloud-edge resources.

[0052] The optimization parameter generation module performs multi-level optimization strategy analysis based on edge control signals and cloud reinforcement signals, generating equipment maintenance parameters and computing power allocation parameters, making power plant equipment maintenance and computing power allocation more reasonable and efficient. The permission management module monitors power plant equipment operation permissions in real time and generates permission association evaluation values. The cloud-edge collaboration module combines these evaluation values ​​to perform operation permission constraint analysis, enhancing the security and reliability of the system.

[0053] The dynamic adjustment module adjusts the frequency of power plant operation and maintenance resource allocation in real time based on generated equipment maintenance parameters and computing power allocation parameters. This adjustment is then fed back to the operational data acquisition module, forming a closed-loop optimization process that further enhances the system's optimization effectiveness and adaptability. Specifically, when equipment maintenance parameters involve adjusting component cleaning cycles, cleaning equipment scheduling parameters are adjusted simultaneously; when computing power allocation parameters involve optimizing cloud computing tasks, network bandwidth allocation parameters are adjusted simultaneously to ensure precise resource allocation.

[0054] Through the collaborative work of multiple modules, the system realizes comprehensive and intelligent management of photovoltaic power stations, improves the stability and reliability of power station operation, optimizes resource allocation, improves the power generation efficiency and economic benefits of the power station, and at the same time enhances the system's security and dynamic adjustment capabilities, providing an effective solution for the intelligent management of photovoltaic power stations. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 This is a working principle diagram of the photovoltaic power station IoT intelligent management and cloud-edge collaborative optimization system according to the present invention;

[0056] Figure 2 Flowchart for dynamic evaluation of equipment self-maintenance capability;

[0057] Figure 3 A flowchart for edge processing performance prediction analysis;

[0058] Figure 4 A flowchart for real-time monitoring of equipment operation permissions;

[0059] Figure 5 Flowchart for closed-loop optimization of the dynamic adjustment module. DETAILED DESCRIPTION

[0060] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0061] See also Figure 1-Figure 5 The present invention provides a photovoltaic power station IoT intelligent management and cloud-edge collaborative optimization system, which includes: an operation data acquisition module, an equipment status assessment module, an edge processing module, a cloud-edge collaboration module, and an optimization parameter generation module. The specific implementation steps are as follows:

[0062] The operation data acquisition module collects the power generation parameters of the power station's components, the communication status of the equipment, and the environmental meteorological factors in multiple dimensions to obtain a multi-source data set for the power station. By extracting the output power fluctuation, temperature anomaly value, and voltage offset in the component power generation parameters, the power fluctuation value, temperature anomaly value, and voltage offset are obtained. The values ​​of the three are extracted and weighted for calculation and processing to obtain the contribution of operation anomaly. The signal interruption frequency, protocol matching degree, and data packet loss rate in the equipment communication status parameters are extracted to obtain the communication interruption value, protocol matching value, and data packet loss value, which are marked as communication stability characteristic values, and the communication stability threshold is set. The characteristic value is compared with the threshold. A comparative analysis is performed. When the characteristic value is less than the threshold, the device is marked as an abnormal device. The ratio of the number of abnormal devices to the total number of devices in the current power station is counted to obtain the communication abnormality rate. At the same time, the light intensity changes and wind speed fluctuations in the power station's environmental meteorological elements are extracted, and dynamic simulation calculations are performed to obtain the environmental disturbance assessment value. The values ​​of the operation abnormality contribution, communication abnormality rate, and environmental disturbance assessment value are multiplied by the corresponding weight coefficients and added together to obtain the abnormal state fusion value, which is compared with the preset abnormality threshold. If the fusion value is higher than the threshold, a management warning signal is generated, and the edge processing module and the cloud collaboration module are triggered based on the generated management warning signal.

[0063] The equipment status assessment module extracts the characteristics of the power station's component attenuation, inverter conversion efficiency, and combiner box connection stability, dynamically evaluates the equipment's self-maintenance capabilities, and obtains a status assessment benchmark value.

[0064] The edge processing module monitors the power station's real-time data traffic, local computing load, and communication delay parameters, and predicts and analyzes the edge processing efficiency of the data to obtain an edge computing evaluation value.

[0065] The cloud-edge collaboration module receives the status assessment benchmark value and the edge computing assessment value, conducts a joint analysis of the system's collaborative optimization efficiency, and generates edge control signals and cloud reinforcement signals.

[0066] The optimization parameter generation module receives edge control signals and cloud reinforcement signals, performs multi-level optimization strategy analysis, and generates equipment maintenance parameters and computing power allocation parameters for the power station.

[0067] Example 1: In this embodiment, the operation data acquisition module quantitatively identifies the abnormal operating status of the system, which is specifically achieved by collecting and analyzing multi-dimensional data of the power station. For the power generation parameters of the components of the power station, the module will extract the output power fluctuations, temperature anomalies and voltage offsets. The output power fluctuation here refers to the amplitude of the change in the output power of the component within a certain time range. For example, within a certain time period, the power fluctuates from one value to another, and the magnitude and frequency of the fluctuation need to be recorded; the temperature anomaly value is compared with the temperature range when the component is operating normally. The temperature value outside this range is an abnormal value. For example, the normal temperature is between 25°C and 50°C, so the temperature above 50°C or below 25°C needs to be extracted; the voltage offset refers to the degree of deviation between the output voltage of the component and the rated voltage. For example, if the rated voltage is 30V, the difference between the actual output voltage and 30V is the voltage offset. After extracting these three values, the module performs a weighted calculation on them. The weighted calculation here requires setting different weight coefficients based on the degree of influence of these three parameters on the operating status of the component. For example, power fluctuations may have a greater impact on the operating status, so the weight is set higher. The weights of temperature anomalies and voltage offsets are relatively low. The three values ​​are then multiplied by their respective weight coefficients and added together to obtain the contribution of the operating anomaly.

[0068] For device communication status parameters, the module extracts signal interruption frequency, protocol compatibility, and packet loss rate. Signal interruption frequency refers to the number of times a device's communication signal is interrupted within a certain period, such as several interruptions within an hour. Protocol compatibility refers to the degree to which the protocol used by the device complies with the system's specified protocol, typically expressed as a percentage; for example, a 90% compatibility indicates close compliance. Packet loss rate refers to the ratio of the number of data packets lost during data transmission to the total number of data packets. After extracting these three values, they are marked as communication stability feature values. A communication stability threshold is also set based on the communication status during normal system operation. These feature values ​​are then compared with the threshold value for analysis. If a feature value falls below the threshold, it indicates that the device's communication status is abnormal and the device is marked as abnormal. The module then calculates the ratio of the number of abnormal devices to the total number of devices in the power plant. For example, if there are 100 devices in the power plant and 5 are marked as abnormal, the ratio is 5%, which is the communication anomaly rate.

[0069] The module also extracts light intensity variations and wind speed fluctuations from the power station's environmental meteorological elements. Light intensity variations refer to the change in light intensity at different time points, such as the process from strong to weak and then strong again from morning to afternoon. Wind speed fluctuations refer to the magnitude of wind speed changes over a period of time, such as the wind speed fluctuating from 5m / s to 10m / s and then back to 5m / s. After extracting these values, dynamic simulation calculations are performed. This dynamic simulation builds a model based on the changing patterns of light intensity and wind speed to simulate their impact on power station operations, thereby deriving an environmental disturbance assessment value.

[0070] The module multiplies the three values ​​of operation anomaly contribution, communication anomaly rate and environmental disturbance assessment value by the corresponding weight coefficients and adds them together to obtain the abnormal state fusion value. The weight coefficients here are also set according to the degree of influence of these three parameters on the abnormal operation state of the system. For example, the weight of operation anomaly contribution may be set to 0.4, the weight of communication anomaly rate is set to 0.3, and the weight of environmental disturbance assessment value is set to 0.3. After obtaining the abnormal state fusion value, it is compared with the preset abnormal threshold. This preset abnormal threshold is a standard value set according to the state of the system during normal operation. If the fusion value is higher than the threshold, it means that the system has an abnormal operation state. At this time, a management warning signal is generated, which triggers the edge processing module and the cloud collaboration module to start working.

[0071] Throughout the entire process, the module must accurately collect every piece of data. For example, when collecting component power generation parameters, it is necessary to ensure the accuracy and stability of the sensor to ensure that the collected power fluctuations, temperature anomalies, and voltage offsets are real and reliable data. When collecting device communication status parameters, it is necessary to ensure the correct parsing of the communication protocol and the stability of data transmission to avoid problems such as statistical errors in signal interruption frequency, inaccurate calculation of protocol matching, or deviation in data packet loss rate measurement. When collecting environmental meteorological elements, it is necessary to select appropriate meteorological sensors and install them in appropriate locations to ensure that the collected light intensity changes and wind speed fluctuations can truly reflect the environmental conditions around the power station. At the same time, when performing various calculations, it is necessary to strictly follow the set algorithms and weight coefficients to ensure that the obtained operation anomaly contribution, communication anomaly rate, environmental disturbance assessment value, and abnormal state fusion value are accurate, so that it can correctly judge whether the system has an abnormal operation state and generate management warning signals in a timely manner, providing a reliable basis for subsequent edge processing and cloud collaboration.

[0072] Example 2: In this example, the equipment status assessment module dynamically evaluates the self-maintenance capability of the equipment, which is specifically achieved through multi-dimensional feature extraction and data analysis. The module performs spatial distribution analysis on the attenuation characteristics of the power station components. Here, it is necessary to obtain the location information of the components in the power station and the power generation parameters of each component. For example, the output power, temperature and other data of each component are collected by sensors, and then these data are mapped to the spatial coordinate system according to the physical position of the component to generate a power attenuation distribution map. When generating the power attenuation distribution map, it is necessary to consider factors such as the installation direction and inclination of the component, because these factors will affect the light intensity received by the component, and thus affect its attenuation degree. At the same time, the module will also generate a hot spot risk assessment map. A hot spot refers to the phenomenon that the temperature of some battery cells rises abnormally during the operation of the component due to the obstruction of some battery cells or other reasons. When generating a hot spot risk assessment map, it is necessary to analyze the temperature distribution data of the component to determine which areas are prone to hot spots, as well as the possibility and severity of the occurrence of hot spots.

[0073] The module extracts a reference distribution of component attenuation for healthy power plants from the system database. Healthy power plants must be representative, typically those in good operating condition and without obvious faults. The target power plant's power attenuation distribution map is then topologically compared with the reference distribution map. This topological comparison involves comparing the shape, trend, and attenuation differences between the two distribution maps. For example, the module examines whether the target power plant's power attenuation exhibits a similar pattern to the reference distribution map, or whether any areas exhibit significantly higher attenuation than the reference distribution map. By calculating the attenuation matching between the two, the module measures the difference in component attenuation between the target power plant and the healthy power plant. The attenuation matching calculation method considers multiple factors, such as the difference in attenuation between regions and the similarity of the distribution shapes. After calculating the attenuation matching, it is normalized and converted to a value within a specific range (e.g., between 0 and 1) to generate the equipment maintenance potential index. The equipment maintenance potential index reflects the potential for the target power plant's components to be restored to a healthy state through maintenance.

[0074] To obtain the component attenuation characteristics, it is necessary to first use distributed sensors to collect the output power, operating temperature and operating time data of each component at different time periods, and combine the standard power parameters of the components when they leave the factory to calculate the power attenuation rate change curve over time. At the same time, use infrared imaging equipment to scan the component surface, identify the hot spot area and record its position and area ratio to comprehensively form the component attenuation characteristics; the inverter conversion efficiency is obtained by installing high-precision power sensors on the input and output sides of the inverter respectively, collecting the input power and output power in real time, and calculating the ratio of the two to obtain the instantaneous conversion efficiency. Then, combined with the efficiency data under different load rates, a characteristic curve of efficiency change with load is generated; to obtain the connection stability of the junction box, it is necessary to monitor the current and voltage fluctuation values ​​of each branch of the junction box and the connection point temperature. By analyzing the sudden change frequency of current and voltage and the number of abnormal temperature increases, combined with the characteristic parameters corresponding to loose connections in historical fault data, the connection stability is judged.

[0075] The module extracts the hot spot frequency and power loss ratio from the power plant's hot spot risk assessment map, marking them as hot spot characteristic values. The hot spot frequency refers to the number of hot spot occurrences within a certain period, such as the number of hot spots in a month. The power loss ratio refers to the extent of module power loss caused by hot spots, typically expressed as the ratio of lost power to normal power. These two characteristic values ​​provide a direct reflection of the impact of hot spots on module operation.

[0076] The module extracts a standard hot spot risk threshold from the system database. This threshold, determined based on industry standards or extensive historical data, measures the acceptable range of hot spot risk. The hot spot characteristic value is then subtracted from the threshold to calculate the self-maintenance capability deviation. For example, if the standard threshold for hot spot frequency is two occurrences per month, and the target power plant's hot spot frequency is five per month, the difference is three. This difference is then converted into the self-maintenance capability deviation using a specific calculation method. The self-maintenance capability deviation reflects the degree to which the target power plant's components' hot spot self-maintenance capability deviates from the standard requirements.

[0077] The module performs a weighted fusion of the values ​​of the equipment maintenance potential index and the self-maintenance capability deviation to derive a baseline value for condition assessment. Weighted fusion requires setting weights based on the degree to which these two parameters affect the equipment's self-maintenance capability. For example, a weight of 0.6 is set for the equipment maintenance potential index, and a weight of 0.4 is set for the self-maintenance capability deviation. This weighted fusion comprehensively considers the impact of component degradation and hot spot risk on the equipment's self-maintenance capability, resulting in an assessment baseline that comprehensively reflects the equipment's condition.

[0078] Throughout the entire evaluation process, data collection and processing must be highly accurate. For example, when collecting component power generation parameters and temperature data, it is necessary to ensure the accuracy and reliability of the sensors to avoid inaccurate data due to sensor failure. When extracting reference distribution maps of healthy power plants, it is necessary to ensure the authenticity and timeliness of the data in the database and update the data of healthy power plants in a timely manner. When performing topological comparisons and numerical calculations, scientific and reasonable algorithms need to be used to ensure the accuracy of the calculation results. In addition, the assessment of hot spot risks also needs to consider the influence of environmental factors such as light intensity and temperature, as these factors can affect the occurrence and development of hot spots.

[0079] Example 3: In this embodiment, the edge processing module predicts and analyzes the edge processing efficiency of data, which is specifically achieved through data collection, model construction and numerical calculation. The module extracts the amount of monitoring data, control instructions and log storage in the real-time data flow of the power station. The amount of monitoring data refers to the total amount of data collected and transmitted in real time by various sensors during the operation of the power station, such as the output voltage, current, temperature and other data of the photovoltaic components transmitted per unit time; the amount of control instructions refers to the number of control instructions issued by the system to the power station equipment, such as the start and stop instructions for the inverter, the switching instructions for the junction box, etc.; the log storage capacity is the storage capacity of the operation log data recorded by the system, including the storage size of information such as equipment operating status, fault records, and operation logs. These three types of data constitute the data flow parameter set. The module needs to ensure the integrity and accuracy of the data during the extraction process to avoid data loss due to network transmission failure or storage device abnormality.

[0080] The module extracts historical processing data from similar power plants in the system database. Similar power plants are selected based on factors such as installed capacity, equipment model, and geographic location. For example, historical data from power plants with similar installed capacity to the target power plant, using the same inverter and component types, and located in a similar climate region are selected. An efficiency prediction model is constructed based on a dynamic balancing algorithm. The core of this model is to establish mapping rules by analyzing the correlation between data flow parameters and processing efficiency indicators in historical data. The dynamic balancing algorithm considers the dynamic changes in computing power allocation, storage resource scheduling, and communication bandwidth usage during data processing to ensure that the model can adapt to different data flow scenarios.

[0081] After inputting the data flow parameter set into the model, the data processing rate, computing power utilization, and latency fluctuation within the target time interval are output. The data processing rate refers to the amount of data processed by the model per unit time, measured in bytes per second (B / s). The computing power utilization is the ratio of the computing power actually used during model execution to the total available computing power, expressed as a percentage. The latency fluctuation measures the degree of fluctuation in data processing latency and is calculated as the ratio of the standard deviation of the latency values ​​to the average latency value within the target time interval.

[0082] To achieve unified quantitative analysis of each indicator, the module needs to normalize the output value to obtain the edge computing evaluation value. The normalization process uses the linear transformation method, and the formula is as follows:

[0083]

[0084] Where E represents the edge computing evaluation value; n is the number of indicators, where n = 3, corresponding to data processing rate, computing power utilization, and delay fluctuation rate; w i is the weight coefficient of the i-th indicator. Each weight is set according to the degree of influence of the indicator on the edge processing performance. For example, the data processing rate weight w1 = 0.4, the computing power utilization weight w2 = 0.3, and the delay volatility weight w3 = 0.3; x i is the original value of the i-th indicator, such as the original value of the data processing rate is in B / s, the original value of the computing power utilization is a percentage, and the original value of the delay volatility is a dimensionless value; x min and x max are the minimum and maximum values ​​of the ith indicator, respectively, obtained through historical data statistics of similar power plants, such as the minimum value of the data processing rate x min1 =1000B / s, maximum value x max1 =10000B / s, the minimum value of computing power utilization x min2 =20%, maximum value x max2 =80%, the minimum value of the delayed volatility x min3 =0.1, maximum value x max3 =0.5.

[0085] During the model building process, the applicability of the dynamic balance algorithm needs to be verified. For example, by comparing actual processing performance over different historical time periods with the model's predictions, algorithm parameters such as the computing power allocation coefficient and storage scheduling threshold can be adjusted to improve the model's prediction accuracy. Furthermore, redundancy mechanisms must be implemented in the data collection process, such as using dual sensors to collect key data. When the difference between the two sensor data exceeds a preset threshold, a data verification process is triggered to ensure the accuracy and reliability of the data input to the model.

[0086] The target time interval should be set based on the plant's operational characteristics. For example, short-term forecasts (within an hour) can use a minute-by-minute data update frequency, while long-term forecasts (within a day) can use an hourly data update frequency. When calculating data processing rates, it's important to prioritize different types of data. For example, control command data should be prioritized over monitoring data. Different processing queues and resource allocation strategies can be set within the model.

[0087] When normalizing, it is important to pay attention to the physical meaning of the indicator. For example, the delay volatility is an inverse indicator. The smaller the value, the more stable the processing delay. Therefore, it needs to be inverted before normalization, that is, To ensure that all indicators are positively correlated with edge computing evaluation values ​​after normalization.

[0088] Throughout the forecasting and analysis process, the module regularly updates the system database with historical data on similar power plants, automatically synchronizing new data weekly, for example, to adapt to the impact of factors such as equipment upgrades and environmental changes on edge processing performance. Furthermore, a model error feedback mechanism is established. When the deviation between actual processing performance and the predicted value exceeds 15%, the model reconstruction process is automatically triggered, re-extracting historical data and optimizing algorithm parameters to ensure that the edge computing evaluation value accurately reflects the current edge processing performance.

[0089] Example 4: In this example, the cloud-edge collaboration module performs a joint analysis of the system's collaborative optimization effectiveness, specifically through data retrieval, numerical calculation, and signal generation. The module retrieves the abnormal state quantification results of the power plant. These results come from the operation data acquisition module's analysis of component power generation parameters, equipment communication status, and environmental meteorological factors. These results include data such as the operational anomaly contribution, communication anomaly rate, and environmental disturbance assessment value. For example, within a certain time period, a power plant's operational anomaly contribution is 0.6, the communication anomaly rate is 15%, and the environmental disturbance assessment value is 0.4. These data constitute the abnormal state quantification results. The module sets a correction factor for this result. The value of the correction factor is based on the type of abnormal state and the scope of impact. For example, if the abnormality is primarily caused by environmental factors, the correction factor is set to 0.8; if it is caused by equipment failure, the correction factor is set to 1.2. The operational impact correction value is calculated by multiplying each parameter in the abnormal state quantification result by the correction factor and taking a weighted sum. For example, operational impact correction value = 0.6 × 1.2 + 0.15 × 1 + 0.4 × 0.8 (this is only an example calculation logic, not an actual formula).

[0090] The module normalizes the values ​​of the condition assessment baseline, edge computing assessment value, and operational impact correction value. The condition assessment baseline value is generated by the equipment condition assessment module and reflects the equipment's self-maintenance capability. For example, the condition assessment baseline value for a power plant is 0.75. The edge computing assessment value comes from the edge processing module's predictive analysis of data processing efficiency. For example, at a certain moment, the edge computing assessment value is 0.8. Normalization converts these values ​​into a uniform range for easier comparison and analysis. For example, using a normalization range of 0-1, if the condition assessment baseline value is 0.75, the edge computing assessment value is 0.8, and the operational impact correction value is 0.9, the values ​​are maintained within this range. If the original value of a parameter is 1.2, it is scaled to between 0 and 1 through a linear transformation. This processing yields a collaborative optimization assessment value, which comprehensively reflects the system's collaborative optimization level under the influence of equipment conditions, edge computing efficiency, and abnormalities. In the above example, the collaborative optimization assessment value might be (0.75 + 0.8 + 0.9) ÷ 3 = 0.817 (this is just example calculation logic, not an actual formula).

[0091] The module sets a collaborative optimization evaluation threshold, which is determined based on the collaborative optimization level during normal system operation (e.g., 0.75). If the collaborative evaluation value is greater than or equal to the threshold, it indicates that the current system collaborative optimization performance is good and can be directly controlled by the edge processing module, generating an edge control signal. If it is less than the threshold, it indicates that the cloud needs stronger computing and resource support, generating a cloud reinforcement signal.

[0092] For example, on a weekday morning, the operation data acquisition module detected significant fluctuations in module output power, with an operational anomaly contribution of 0.65. The device communication status saw an increase in signal interruption frequency, with a communication anomaly rate of 18%. Furthermore, the ambient weather factor, light intensity, fluctuated dramatically, with an environmental disturbance assessment value of 0.5. The cloud-edge collaboration module retrieved these anomaly status quantification results and, considering that the anomaly was primarily caused by environmental factors (light intensity fluctuations), set a correction factor of 0.8. When calculating the operational impact correction value, assuming equal weighting for each parameter, the operational impact correction value = (0.65 + 0.18 + 0.5) × 0.8 = 1.064 × 0.8 = 0.8512 (this is just example calculation logic, not an actual formula). Simultaneously, the device status assessment module generated a status assessment baseline value of 0.7, and the edge processing module generated an edge computing assessment value of 0.72. Normalizing these three values, assuming they are all within the range of 0-1, yields a collaborative optimization assessment value of (0.7 + 0.72 + 0.8512) ÷ 3 ≈ 0.757. Since 0.757 is greater than the preset threshold 0.75, the module generates an edge control signal, triggering the edge processing module to adjust the data processing strategy.

[0093] For example, during a rainy day, the power generation parameters of power plant components are abnormal, with an operational anomaly contribution of 0.8. Due to the weather, device communications experience significant packet loss, resulting in a communication anomaly rate of 25% and an environmental disturbance assessment value of 0.6. The cloud-edge collaboration module sets a correction factor of 1.1 (accounting for both the device failure and the environmental impact). The operational impact correction value = (0.8 + 0.25 + 0.6) × 1.1 = 1.65 × 1.1 = 1.815, which after normalization is 0.9075 (assuming the original range is 0-2). The state assessment baseline value is 0.6, the edge computing assessment value is 0.65, and the collaborative optimization assessment value = (0.6 + 0.65 + 0.9075) ÷ 3 ≈ 0.719. Because 0.719 is less than the threshold of 0.75, the module generates a cloud reinforcement signal, requesting additional cloud computing resources to optimize the scheduling of edge processing module tasks.

[0094] Throughout the joint analysis process, data accuracy and real-time availability are crucial. The module must ensure that the retrieved abnormal state quantification results, state assessment baseline values, and edge computing assessment values ​​are all the latest data, for example, updated every 10 minutes. The setting of correction factors needs to be combined with historical data and expert experience, and regularly optimized and adjusted. For example, the correction factor values ​​for various types of anomalies should be re-evaluated monthly based on the power plant's operating conditions. The collaborative optimization assessment thresholds also need to be dynamically adjusted based on factors such as season and equipment operating status. For example, during high temperatures in the summer, the thresholds can be appropriately lowered to trigger the control mechanism in advance.

[0095] The module also needs to have a data verification function. When a certain type of retrieved data is missing or abnormal, it automatically triggers the data re-collection process. For example, if the status assessment baseline value has not been updated for more than 30 minutes, a data request instruction is sent to the equipment status assessment module to ensure the accuracy of the joint analysis. Through this process, the cloud-edge collaboration module can accurately judge the effectiveness of collaborative optimization based on the actual operating status of the system, generate corresponding control signals, and achieve reasonable allocation of cloud-edge resources and optimization of system performance.

[0096] Example 5: In this example, the optimization parameter generation module performs multi-level optimization strategy analysis, and the system involves the collaborative work of the permission control module and the dynamic adjustment module. When the optimization parameter generation module captures the edge control signal or the cloud reinforcement signal, it will execute different optimization strategies to generate corresponding parameters.

[0097] When the module captures an edge control signal, generated by the cloud-edge collaboration module when the collaborative optimization evaluation value is greater than or equal to a preset threshold, it triggers a device maintenance command. For example, in a photovoltaic power plant, if the edge control signal is triggered by the need to adjust the module cleaning cycle, the module will dynamically adjust the module cleaning cycle according to the command. This adjustment takes into account factors such as the degree of module contamination and local climatic conditions. For example, in dusty areas, where module surfaces are prone to dust accumulation, the cleaning cycle may need to be shortened from 30 days to 20 days; in rainy regions, the cleaning cycle may be extended to 40 days. Simultaneously, the inverter's cooling parameters are dynamically adjusted. Inverters generate heat during operation, and poor heat dissipation can affect conversion efficiency. The module adjusts the cooling fan speed and start / stop times based on the inverter's real-time temperature data. For example, when the inverter temperature reaches 60°C, the cooling fan runs at full speed to ensure the inverter operates within the appropriate temperature range. This generates device maintenance parameters.

[0098] If the module captures a cloud reinforcement signal, which is generated by the cloud-edge collaborative module when the collaborative optimization evaluation value is less than the preset threshold, the computing power allocation instruction is triggered. The module dynamically plans the local storage capacity and cloud computing tasks of the power station based on the instruction. For example, when the local storage capacity of the power station is about to reach the upper limit, the module will upload some non-real-time data to the cloud storage to free up local storage space; at the same time, it will optimize the scheduling of cloud computing tasks and assign tasks with larger computational workloads to more powerful computing resources on the cloud to improve computing efficiency. For example, when making long-term power generation forecasts for power stations, it is necessary to process a large amount of historical data and complex algorithm models. This task is assigned to cloud computing, while the edge side focuses on the collection and processing of real-time data, thereby generating computing power allocation parameters.

[0099] The system also includes a permission management module, which monitors the power plant's equipment operation permissions in real time. It extracts the operator's identification, permitted operation scope, and characteristics of illegal operations to generate a permission association assessment. Specifically, the permission management module analyzes the power plant's license data during operation management to obtain the operator's permission type and historical violation records. For example, the operator might be an operation and maintenance personnel, whose permission types might include module maintenance and inverter commissioning. Historical violation records include whether there have been unauthorized operations or erroneous operations. The permission type is matched against a pre-set operation permission list, and the permission type deviation is calculated. The pre-set operation permission list specifies the operation permissions for different positions. For example, a module maintenance personnel can only perform operations such as cleaning and replacing components and cannot modify inverter parameters. If the operator's permission type exceeds the scope of the permission list, a permission type deviation is generated. The difference between the frequency of unauthorized operations and the total number of operations in the historical violation records is calculated to obtain the operation behavior anomaly index. For example, if an operation and maintenance personnel performs 100 operations in a month, including 5 unauthorized operations, with a difference rate of 5%, the operation behavior anomaly index is calculated. The permission type deviation degree and the operation behavior abnormality index are weighted and fused to generate a permission association evaluation value, which is used to reflect the permission compliance of the operating subject.

[0100] The cloud-edge collaboration module further combines the permission association evaluation value to analyze the operation permission constraints of collaborative optimization effectiveness. For example, when generating an edge control signal or cloud reinforcement signal, the cloud-edge collaboration module checks whether the operator's permissions meet the requirements for executing the corresponding control or reinforcement operation. If the operator's permissions are insufficient, the operation is rejected and a warning of insufficient permissions is issued to ensure the security and compliance of system operations.

[0101] The system also includes a dynamic adjustment module, which adjusts the frequency of resource allocation for power plant operations and maintenance in real time based on generated equipment maintenance parameters and computing power allocation parameters. These adjusted parameters are then fed back to the operational data acquisition module, forming a closed-loop optimization process. The dynamic adjustment module operates as follows: If an equipment maintenance parameter involves adjusting component cleaning cycles, such as shortening the cleaning cycle from 30 days to 20 days, the cleaning equipment scheduling parameters in the resource allocation are adjusted simultaneously to increase the frequency and number of cleaning equipment dispatches to ensure timely cleaning of components. If the computing power allocation parameters involve optimizing cloud computing tasks, such as allocating some computing tasks to the cloud, the network bandwidth allocation parameters in the resource allocation are adjusted simultaneously to allocate more network bandwidth for cloud data transmission to ensure speed and stability. The adjusted parameters are then fed into the operational data acquisition module, which recollects power plant operational data based on the new parameters to verify the optimization results. If the optimization results are not as expected, the optimization process is restarted, adjusting the equipment maintenance parameters and computing power allocation parameters until satisfactory optimization results are achieved.

[0102] Throughout the entire process, data exchange and collaboration between modules must be accurate. The optimization parameter generation module must fully consider the plant's actual operating conditions and permission control requirements when generating equipment maintenance parameters and computing power allocation parameters. The permission control module must accurately monitor operational permissions in real time to ensure system operational security. The dynamic adjustment module must promptly adjust resource allocation based on optimization parameters and feed back the adjustment results to the operation data acquisition module to form an effective closed-loop optimization loop, thereby achieving intelligent management of the PV plant and cloud-edge collaborative optimization.

[0103] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus.

[0104] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A photovoltaic power station Internet of Things intelligent management and cloud-edge collaborative optimization system, characterized by: include: The operation data acquisition module is used to collect multi-dimensional data on the power plant's component power generation parameters, equipment communication status, and environmental meteorological factors to obtain a multi-source data set for the power plant. This module is used to quantitatively identify abnormal operating conditions of the system and generate management warning signals. The generated management warning signals trigger the edge processing module and the cloud collaboration module. The equipment status assessment module is used to extract the characteristics of the power station's component attenuation, inverter conversion efficiency, and combiner box connection stability, dynamically evaluate the equipment's self-maintenance capabilities, and obtain a status assessment benchmark value; The edge processing module is used to monitor the power plant's real-time data traffic, local computing load, and communication delay parameters, and to predict and analyze the edge processing efficiency of the data to obtain an edge computing evaluation value; The cloud-edge collaboration module is used to receive the status assessment baseline value and the edge computing assessment value, conduct a joint analysis of the system's collaborative optimization efficiency, and generate edge control signals and cloud reinforcement signals; The optimization parameter generation module is used to receive edge control signals and cloud reinforcement signals, perform multi-level optimization strategy analysis, and generate equipment maintenance parameters and computing power allocation parameters for the power station.

2. The photovoltaic power station IoT intelligent management and cloud-edge collaborative optimization system according to claim 1 is characterized in that: The quantitative identification of the abnormal operating state of the system includes: By extracting the output power fluctuation, temperature anomaly value and voltage offset from the power generation parameters of the power station components, the power fluctuation value, temperature anomaly value and voltage offset are obtained. The values ​​of the three are extracted and weighted for calculation to obtain the contribution of the operation anomaly. By extracting the signal interruption frequency, protocol matching degree and data packet loss rate from the communication status parameters of the power station equipment, the communication interruption value, protocol matching value and data packet loss value are obtained, and they are marked as communication stability characteristic values. A communication stability threshold is set, and the characteristic value is compared and analyzed with the threshold. When the characteristic value is less than the threshold, the device is marked as an abnormal device. The ratio of the number of abnormal devices to the total number of devices in the current power station is calculated to obtain the communication abnormality rate. At the same time, the light intensity change and wind speed fluctuation values ​​in the power station environment meteorological elements are extracted and dynamic simulation calculations are performed to obtain the environmental disturbance assessment value. The values ​​of the operation abnormality contribution, communication abnormality rate and environmental disturbance assessment value are multiplied by the corresponding weight coefficients and added together to obtain the abnormal state fusion value, which is compared with the preset abnormality threshold. If the fusion value is higher than the threshold, a management warning signal is generated.

3. The photovoltaic power station IoT intelligent management and cloud-edge collaborative optimization system according to claim 1 is characterized in that: The dynamic evaluation of the self-maintenance capability of the equipment includes: By analyzing the spatial distribution of the power plant's component attenuation characteristics, the corresponding power attenuation distribution map and hot spot risk assessment map are generated; Extract the reference distribution map of component attenuation of healthy power plants from the system database, perform a topological comparison between the target power plant's power attenuation distribution map and the reference distribution map, calculate the attenuation matching degree between the two, and perform normalization processing to obtain the equipment maintenance potential index; The hot spot occurrence frequency and power loss ratio are extracted from the hot spot risk assessment map of the power station and marked as hot spot characteristic values ​​respectively; Extract the standard hot spot risk threshold from the system database, calculate the difference between the hot spot characteristic value and the threshold, and obtain the self-maintenance capability deviation; The equipment maintenance potential index and the self-maintenance capability deviation are weighted and fused to obtain the condition assessment benchmark value.

4. The photovoltaic power station IoT intelligent management and cloud-edge collaborative optimization system according to claim 1 is characterized in that: The predictive analysis of edge processing efficiency of data includes: By extracting the monitoring data volume, control instruction volume and log storage volume from the real-time data flow of the power station, a data flow parameter set is obtained; Extract historical processing data of similar power plants from the system database, build an efficiency prediction model based on a dynamic balance algorithm, input the flow parameter set into the model, and output the data processing rate, computing power utilization, and latency fluctuation rate within the target time interval; The data processing rate, computing power utilization, and delay fluctuation rate are normalized to obtain the edge computing evaluation value.

5. The photovoltaic power station IoT intelligent management and cloud-edge collaborative optimization system according to claim 1 is characterized in that: The joint analysis of the system's collaborative optimization effectiveness includes: Retrieve the quantified results of the abnormal state of the power station, set its correction factor, and obtain the operation impact correction value through calculation and processing; The state assessment baseline value, edge computing assessment value, and operation impact correction value are normalized and calculated to obtain a collaborative optimization assessment value; Set the collaborative optimization evaluation threshold. If the collaborative evaluation value is greater than or equal to the threshold, an edge control signal is generated; if it is less than the threshold, a cloud reinforcement signal is generated.

6. The photovoltaic power station IoT intelligent management and cloud-edge collaborative optimization system according to claim 1 is characterized in that: The multi-level optimization strategy analysis includes: If an edge control signal is captured, the device maintenance instruction is triggered. Based on the instruction, the component cleaning cycle and inverter cooling parameters of the power station are dynamically adjusted to generate equipment maintenance parameters. If a cloud reinforcement signal is captured, the computing power allocation instruction will be triggered. Based on the instruction, the local storage capacity of the power station and the cloud computing tasks will be dynamically planned to generate computing power allocation parameters.

7. The photovoltaic power station IoT intelligent management and cloud-edge collaborative optimization system according to claim 1 is characterized in that: Also includes: The authority control module is used to monitor the power plant's equipment operation permissions in real time, extract the operator's identification, permitted operation scope, and illegal operation characteristics, and generate an authority association evaluation value; The cloud-edge collaboration module further combines the permission association evaluation value to perform operation permission constraint analysis on the collaborative optimization performance.

8. The photovoltaic power station IoT intelligent management and cloud-edge collaborative optimization system according to claim 7 is characterized in that: The real-time monitoring of the power plant's equipment operation authority includes: By analyzing the license data of the power plant during operation and control, the operator's permission type and historical violation records are obtained; Match the permission type with the preset operation permission list and calculate the permission type deviation; Calculate the difference between the frequency of unauthorized operations and the total number of operations in historical violation records to obtain the abnormal operation behavior index; The permission type deviation degree and the operation behavior abnormality index are weighted and fused to generate the permission association evaluation value.

9. The photovoltaic power station IoT intelligent management and cloud-edge collaborative optimization system according to claim 1, characterized in that: Also includes: The dynamic adjustment module is used to adjust the resource allocation frequency of power station operation and maintenance in real time based on the generated equipment maintenance parameters and computing power allocation parameters, and feed the adjusted parameters back to the operation data acquisition module to form a closed-loop optimization process.

10. The photovoltaic power station IoT intelligent management and cloud-edge collaborative optimization system according to claim 9, characterized in that: The adjustment process of the dynamic adjustment module includes: If the equipment maintenance parameters involve adjusting the component cleaning cycle, the cleaning equipment scheduling parameters in the resource configuration will be adjusted simultaneously; If the computing power allocation parameters involve cloud computing task optimization, the network bandwidth allocation parameters in the resource configuration will be adjusted simultaneously; Input the adjusted parameters into the operation data acquisition module and restart the optimization and verification process.

Images