New energy power generation efficiency monitoring system

Abstract

The invention discloses a new energy power generation efficiency monitoring system, and particularly relates to the technical field of new energy power generation. The data acquisition module is used for acquiring and preprocessing meteorological, radiation and equipment operation data in real time, and the data analysis and model module is used for modeling the acquired data, analyzing and evaluating the power generation efficiency and diagnosing abnormal conditions. The system can realize real-time acquisition and analysis of meteorological data, solar radiation intensity and operation state of power generation equipment, ensures data accuracy through the data preprocessing module, thereby improving reliability of subsequent analysis, and can dynamically monitor and evaluate power generation efficiency through the radiation intensity analysis module and the power generation efficiency evaluation module, thereby reducing power generation cost. And power generation and energy storage strategies are adjusted in real time through the automatic control module, and the automatic adjustment strategy ensures that the system can continuously maintain efficient power generation capacity under different meteorological conditions and operation states, so that the overall operation efficiency of the new energy power station is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of new energy power generation, and particularly relates to a new energy power generation efficiency monitoring system. BACKGROUND

[0002] With the increasing global energy demand and the intensification of environmental pollution, new energy power generation has become an important development direction in today's society. New energy power generation mainly includes solar energy, wind energy, tidal energy and other forms, among which solar power generation has been widely used due to its clean and renewable characteristics. However, new energy power generation is greatly affected by weather conditions, especially solar power generation, whose power generation efficiency is directly affected by multiple environmental factors such as weather, solar radiation intensity, wind speed, etc. In order to ensure that power generation equipment can maintain efficient operation under different weather conditions, how to effectively monitor and manage new energy power generation equipment has become a major challenge in current technology. Therefore, real-time monitoring of the operating state of power generation equipment and adjusting the power generation strategy according to environmental changes have become the key means to improve power generation efficiency.

[0003] Although the existing new energy power generation system has certain monitoring functions, it can usually only monitor a single operating parameter and cannot realize comprehensive analysis and processing of multi-dimensional data. In addition, due to the limitation of data processing capacity, the existing system is difficult to predict or intelligently respond to faults or abnormal conditions in real time. This not only affects the power generation efficiency of the system, but also may cause the equipment to fail to respond in time when a fault occurs, increasing the operation risk.

[0004] The current new energy power generation monitoring system has some deficiencies in actual application. First, the existing system usually relies on fixed parameter thresholds for monitoring and cannot flexibly adjust the equipment operating parameters according to real-time environmental changes, resulting in a decrease in system power generation efficiency under complex weather conditions. Second, although the existing system can perform basic state monitoring of power generation equipment, it lacks the ability to analyze multi-dimensional data and mine abnormal features, making it difficult to effectively predict potential faults. In addition, most existing systems have limited automatic adjustment capabilities and cannot achieve dynamic baseline adjustment, resulting in the system failing to adjust the strategy in time when environmental conditions change, affecting the stable operation of the equipment and the power generation efficiency. Therefore, it is necessary to design a monitoring system that can improve the efficiency of new energy power generation. SUMMARY

[0005] The present application aims at the deficiencies existing in the prior art, and proposes a new energy power generation efficiency monitoring system, which ensures data accuracy through preprocessing of the data acquisition module, realizes power generation efficiency evaluation and abnormal detection diagnosis through the analysis processing module, dynamically adjusts power generation equipment parameters, energy storage strategies and load distribution through the optimization control module, and relies on the system self-learning iterative optimization model and strategy, the communication maintenance module guarantees data transmission, system maintenance and data security, thereby improving the subsequent analysis reliability, improving the overall operation efficiency and equipment utilization rate of the new energy power station, preventing the identification of potential faults to reduce downtime, and ensuring the long-term optimal performance of the system through continuous optimization of the model and strategy, and reducing maintenance costs.

[0006] The technical solution for achieving the purpose of the present application is:

[0007] A new energy power generation efficiency monitoring system, comprising: a data acquisition module, an analysis processing module, an optimization control module and a communication maintenance module;

[0008] The data acquisition module comprises a meteorological data acquisition unit, a radiation intensity acquisition unit, a power generation equipment acquisition unit and a data preprocessing unit; the meteorological data acquisition unit is used to obtain real-time meteorological data from a meteorological station, the radiation intensity acquisition unit is used to obtain real-time solar radiation intensity data from a meteorological station and classify them, the power generation equipment acquisition unit is used to acquire real-time power generation equipment operation parameters, and the data preprocessing unit is used to preprocess the data collected by the above units;

[0009] The analysis processing module comprises a radiation intensity analysis unit, a power generation efficiency evaluation unit, an abnormal detection diagnosis unit and a data visualization unit; the radiation intensity analysis unit is used to calculate the total solar radiation intensity and the photovoltaic power generation curve according to the collected solar radiation intensity data, the power generation efficiency evaluation unit is used to calculate the current power generation efficiency of the equipment according to the real-time solar radiation data and the power generation equipment operation state, the abnormal detection diagnosis unit is used to analyze the collected data according to the machine learning algorithm to perform abnormal detection and diagnosis, and the data visualization unit is used to display the data and analysis results in the form of charts, curves and other visual forms;

[0010] The optimization control module comprises a power generation equipment control unit, a storage allocation control unit, a load management unit and a system self-learning unit; the power generation equipment control unit is used to adjust the power generation equipment operation parameters, the storage allocation control unit is used to optimize the energy storage system, the load management unit is used to distribute electric energy according to the power generation efficiency and power demand, and the system self-learning unit is used to iteratively optimize the power generation efficiency evaluation model and the equipment control strategy through historical data and real-time data;

[0011] The communication maintenance module comprises a data transmission unit, a system monitoring and maintenance unit, a user interface unit and a data storage backup unit; the data transmission unit is used for transmitting data between modules and exchanging data with external systems, the system monitoring and maintenance unit is used for monitoring the running state of the system in real time, detecting faults and timely maintenance alarm, the user interface module is used for providing a man-machine interactive interface, and the data storage backup unit is used for local or cloud storage of important data and regular backup.

[0012] Further, the data acquisition module obtains real-time meteorological data from the weather station through the meteorological data acquisition unit, including ambient temperature , local latitude , solar declination angle , solar hour angle ; the real-time solar radiation intensity data obtained from the weather station by the radiation intensity acquisition unit includes direct solar radiation intensity , heat radiation intensity , ground reflected radiation intensity ; the real-time photovoltaic power generation equipment operating parameters collected by the power generation equipment acquisition unit include current , voltage , actual power , photovoltaic module area , photovoltaic module efficiency , photovoltaic module temperature ; the data preprocessing unit is used for preprocessing the data collected by the above-mentioned units, and the sliding average filtering algorithm is used for processing the data to filter abnormal data caused by noise;

[0013] Further, the analysis processing module comprises a radiation intensity analysis unit for calculating total solar radiation intensity and photovoltaic power generation curve according to the collected solar radiation intensity data and using temperature correction method to improve the calculation accuracy of the photovoltaic power generation curve; a power generation efficiency evaluation unit for calculating the current equipment power generation efficiency according to the real-time solar radiation data and the power generation equipment operating state; an anomaly detection and diagnosis unit using isolation forest algorithm to analyze the collected data for anomaly detection and diagnosis; and a data visualization unit for displaying the system data and analysis results in the form of charts, curves and other visual forms.

[0014] Further, the optimization control module adjusts the operation parameters of the power generation equipment by the equipment control unit according to different light conditions in different equipment arrangement areas; the storage allocation control unit uses the peak clipping and valley filling and smoothing output strategy to optimize the energy storage system; the load management unit links the power generation equipment control unit and the storage allocation control unit according to the current power generation efficiency and power demand to distribute the electric energy; the system self-learning unit iteratively optimizes the power generation efficiency evaluation model and the equipment control strategy based on historical data and real-time data in an online learning manner;

[0015] Further, the communication maintenance module transmits data between modules and exchanges data with external systems through the data transmission unit 5G router; the system monitoring and maintenance unit is used for real-time monitoring of the running state of the system, detecting faults and timely maintenance alarm; the user interface module is used for providing a man-machine interactive interface; the data storage backup unit is used for local or cloud storage of important data and regular backup;

[0016] Compared with the prior art, the present application proposes a new energy power generation efficiency monitoring system, which cleans the collected data through the data preprocessing unit, ensures the high quality of the input data, improves the accuracy of analysis and decision-making, and reduces the error caused by data noise; the analysis processing module evaluates the power generation efficiency, and realizes dynamic adjustment of the power generation equipment parameters in combination with abnormal detection, thereby improving the equipment utilization rate; the machine learning algorithm is used to monitor the collected power generation equipment operation parameters in real time, and the abnormal detection diagnosis unit can find potential faults, preventively identify corresponding faults, and reduce downtime; the system self-learning unit learns from historical and real-time data, continuously optimizes the equipment control strategy and the power generation efficiency evaluation model, ensures that the system can maintain the best performance in long-term use, and reduces the maintenance cost. BRIEF DESCRIPTION OF DRAWINGS

[0017] Figure 1 The module diagram of the new energy power generation efficiency monitoring system in the application;

[0018] Figure 2 The method flowchart for calculating the total solar radiation intensity and the photovoltaic power generation curve by the analysis processing module in the application;

[0019] Figure 3 The temperature correction flowchart in the application;

[0020] Figure 4 The isolation forest algorithm flowchart in the application. DETAILED DESCRIPTION

[0021] The application will be further described in detail below in combination with the drawings and examples.

[0022] AsFigure 1 In one embodiment of the present application, a new energy power generation efficiency monitoring system is provided, which comprises a data acquisition module, an analysis processing module, an optimization control module, and a communication maintenance module.

[0023] The data acquisition module comprises a meteorological data acquisition unit, a radiation intensity acquisition unit, a power generation equipment acquisition unit, and a data preprocessing unit. The meteorological data acquisition unit is configured to obtain real-time meteorological data from a meteorological station. The radiation intensity acquisition unit is configured to obtain real-time solar radiation intensity data from the meteorological station and classify the data. The power generation equipment acquisition unit is configured to acquire real-time power generation equipment operating parameters. The data preprocessing unit is configured to preprocess the data acquired by the above-mentioned units.

[0024] The analysis processing module comprises a radiation intensity analysis unit, a power generation efficiency evaluation unit, an abnormality detection and diagnosis unit, and a data visualization unit. The radiation intensity analysis unit is configured to calculate total solar radiation intensity and photovoltaic power generation curves based on the acquired solar radiation intensity data. The power generation efficiency evaluation unit is configured to calculate the current power generation efficiency of the equipment based on real-time solar radiation data and the operating state of the power generation equipment. The abnormality detection and diagnosis unit is configured to perform abnormality detection and diagnosis based on machine learning algorithm analysis of the acquired data. The data visualization unit is configured to display the data and analysis results in the form of charts, curves, and other visual forms.

[0025] The optimization control module comprises a power generation equipment control unit, a storage allocation control unit, a load management unit, and a system self-learning unit. The power generation equipment control unit is configured to adjust the operating parameters of the power generation equipment. The storage allocation control unit is configured to optimize the energy storage system. The load management unit is configured to allocate power based on power generation efficiency and power demand. The system self-learning unit is configured to iteratively optimize the power generation efficiency evaluation model and equipment control strategy based on historical data and real-time data.

[0026] The communication maintenance module comprises a data transmission unit, a system monitoring and maintenance unit, a user interface unit, and a data storage and backup unit. The data transmission unit is configured to transmit data between modules and exchange data with external systems. The system monitoring and maintenance unit is configured to monitor the operating state of the system in real time, detect faults, and provide timely maintenance and alarm. The user interface module is configured to provide a human-computer interaction interface. The data storage and backup unit is configured to store important data locally or in the cloud and perform regular backups.

[0027] Further, the data acquisition module obtains real-time meteorological data from the meteorological station through the meteorological data acquisition unit, including environmental temperature , local latitude , solar declination angle , and solar hour angle . The radiation intensity acquisition unit obtains real-time solar radiation intensity data from the meteorological station, including direct solar radiation intensity , heat dissipation radiation intensity , ground reflection radiation intensity ; collecting real-time photovoltaic power generation equipment operation parameters including current , voltage , actual power , photovoltaic module area , photovoltaic module efficiency , photovoltaic module temperature ; the data preprocessing unit is used for preprocessing the data collected by the above unit, and the sliding average filtering algorithm is used for processing the data, and filtering abnormal data generated by noise;

[0028] Specifically, the data preprocessing unit is used for preprocessing the data collected by the above unit, and the sliding average filtering algorithm is used for processing the data, and filtering abnormal data generated by noise; the sliding average filtering algorithm is used for processing the collected data, the sliding average filtering algorithm is slid on the data through a fixed size window, the average value of all data points in the window is calculated and the average value is used to represent the value of the latest data point, so as to smooth the data, suppress short-term fluctuations and random noise;

[0029] Exemplarily, for the environmental temperature collected at time, the window size of the sliding average filtering algorithm is , in order to improve the speed of data calculation and reduce the consumption of calculation resources, a simple sliding average method is adopted, each data point in the window is given the same weight value 1, then the environmental temperature at the time after window processing is calculated as follows:

[0030] ,

[0031] When the value of is less than or equal to 0, the value of corresponding to it is set to 0; according to the above window processing calculation formula, it can be seen that the size of the window significantly affects the value after sliding average filtering processing, when the value of is large, the sliding average filtering algorithm can well suppress noise data and obtain very good data smoothing effect, but it will lead to data hysteresis and it is difficult to accurately reflect the change of real data; when the value of is small, the data hysteresis is small, and the change trend of real data can be quickly tracked, but the data cannot be effectively peak denoised; therefore, according to the different types of data, the value of The size of the moving average filter algorithm can effectively balance between data smoothing and hysteresis. For high-frequency data such as current and voltage data, a larger window is used for the moving average filter algorithm; for low-frequency data such as environmental temperature and radiation intensity data, a smaller window is used for the moving average filter algorithm;

[0032] Further, the analysis processing module uses the radiation intensity analysis unit to calculate the total solar radiation intensity and the photovoltaic power generation curve according to the collected solar radiation intensity data and uses a temperature correction method to improve the calculation accuracy of the photovoltaic power generation curve; uses the power generation efficiency evaluation unit to calculate the current power generation efficiency of the equipment according to the real-time solar radiation data and the running state of the power generation equipment; uses the isolation forest algorithm in the abnormal detection and diagnosis unit to analyze the collected data to perform abnormal detection and diagnosis; and uses the data visualization unit to display the data and analysis results in the form of charts, curves and other visual forms.

[0033] Specifically, as shown in Figure 2 , the analysis processing module calculates the total solar radiation intensity and the photovoltaic power generation curve from the solar radiation intensity data collected by the radiation intensity analysis unit; the total solar radiation intensity is obtained by calculating the sum of the direct solar radiation intensity , the scattered radiation intensity and the ground reflected radiation intensity , wherein the scattered radiation intensity and the ground reflected radiation intensity can be directly obtained from the meteorological station by the radiation intensity collection unit, and the direct solar radiation intensity needs to consider the influence of the solar zenith angle on the solar radiation intensity, so the local solar zenith angle needs to be calculated according to the local latitude , the solar declination angle and the solar hour angle collected from the meteorological station by the meteorological data collection unit; the calculation method of the solar zenith angle is as follows:

[0034] ,

[0035] After calculating the solar zenith angle according to the above formula, the total solar radiation intensity is calculated according to the direct solar radiation intensity , the scattered radiation intensity and the ground reflected radiation intensity , and the calculation method of the total solar radiation intensity is as follows:

[0036] ;

[0037] The efficiency of photovoltaic power generation is directly related to the solar irradiance intensity received by the photovoltaic module, so the photovoltaic power generation curve, i.e. the theoretical output power of the photovoltaic module, is positively correlated with the total solar irradiance intensity ; in addition to the total solar irradiance intensity, the theoretical output power of the photovoltaic module is also positively correlated with the area of the photovoltaic module and the photovoltaic module efficiency ; the area of the photovoltaic module determines the amount of total solar irradiance received, and the photovoltaic module efficiency determines the loss of conversion of light energy into electrical energy; in summary, let the theoretical output power of the photovoltaic module be , the calculation method of the theoretical output power of the photovoltaic module can be obtained as follows:

[0038] ,

[0039] In consideration of the change of the photovoltaic module efficiency with the change of the ambient temperature, the temperature correction method can be used to correct the photovoltaic module efficiency ;

[0040] As shown in Figure 3 , in order to improve the accuracy of correction, the average temperature can be calculated by collecting temperature data of multiple weather stations, and the temperature value closest to the average value is selected as the reference temperature for temperature correction of the photovoltaic module efficiency ; the calculation formula of the temperature correction method is as follows:

[0041] ,

[0042] wherein represents the reference efficiency of the photovoltaic module, represents the temperature coefficient which is a negative number, represents the temperature of the photovoltaic module, represents the reference temperature;

[0043] Specifically, the power generation efficiency evaluation unit is configured to calculate the power generation efficiency of the current device according to the real-time solar radiation data and the running state of the power generation device; the power generation efficiency of the current device, i.e. the performance ratio , can be obtained by calculating the ratio between the real-time power of the device and the theoretical output power ; the calculation method of the power generation efficiency of the current device is as follows:

[0044] ;

[0045] Specifically, as Figure 4 ​As shown, the anomaly detection diagnosis unit is used to analyze the collected data according to a machine learning algorithm to perform anomaly detection and diagnosis; the isolation forest algorithm is used to model the collected historical normal data to realize unsupervised learning monitoring of abnormal data, and the core idea of the isolation forest algorithm is that the abnormal data points are easy to be isolated outlier data points; the isolation forest model realizes the monitoring of abnormal data by constructing multiple isolation trees, each tree randomly selects features and segmentation values to recursively segment data points until each point is isolated, and calculates the anomaly score of each point, which is determined by the average path length required for the data point to be isolated in the tree; for normal data points, multiple random feature selection and segmentation are required to isolate the normal data points, while for abnormal data points, due to the large difference between their feature values and normal data points, only a few random feature selection and segmentation are required to isolate them; therefore, the shorter the average path length required for a data point to be isolated, the higher the probability of its abnormality;

[0046] According to the collected normal data at different time points, features are constructed, in addition to directly using the original data features including environmental temperature , direct solar radiation intensity , heat dissipation radiation intensity , ground reflected radiation intensity , current , voltage , actual power , photovoltaic module temperature , in addition to the original data, features containing more device operation information are constructed to improve the effect of model anomaly detection, such as the current device power generation efficiency , temperature difference , the above original data features and constructed features are concatenated to obtain normal time point features; the normal time point features obtained after processing are input into the isolation forest model for training, and two hyperparameters, the number of trees and the expected proportion of outliers are adjusted to obtain the optimal isolation forest model; after obtaining the optimized isolation forest model through iterative optimization, the real-time data is input into the isolation forest model, and an anomaly score is output for each data point, when the anomaly score is greater than a preset threshold, an anomaly detection warning is triggered; the detailed information of the abnormal data points is recorded and a traceable report is generated to facilitate subsequent analysis and processing;

[0047] Specifically, the data visualization unit is used to display data and analysis results in visual forms such as charts and curves; by displaying collected or calculated data in the form of charts or curves, the operating efficiency of the new energy power generation efficiency monitoring system can be improved; for example, by plotting the real-time power of the power generation equipment as a real-time power curve, the fluctuation of the current power generation equipment can be monitored; the power generation efficiency of the current equipment can be displayed. The numerical values ​​are plotted as Trend charts can effectively monitor the long-term changing trends of power generation equipment efficiency;

[0048] Furthermore, the optimization control module adjusts the operating parameters of the power generation equipment by employing different adjustment strategies based on the varying sunlight conditions in the equipment's location through the power generation equipment control unit; optimizes the energy storage system by using peak shaving and valley filling and smoothing output strategies through the storage distribution control unit; distributes power by linking the power generation equipment control unit and the storage distribution control unit based on the current power generation efficiency and electricity demand through the load management unit; and iteratively optimizes the power generation efficiency evaluation model and equipment control strategies through the system self-learning unit using online learning based on historical and real-time data.

[0049] Specifically, the power generation equipment control unit is used to adjust the operating parameters of the power generation equipment. During the actual operation of the power generation equipment, considering the stability and security of the power grid to which the power generation equipment belongs, the power grid dispatch center will send corresponding instructions to the power generation equipment to dynamically adjust the output power of the power generation equipment according to the actual operation of the power grid. For example, when the electricity load is at a low point, in order to avoid the total power generation of all power generation equipment in the power grid from exceeding the load and to ensure the safety of the power grid, the power grid dispatch center will require some power generation equipment to reduce its output power. The power generation equipment control unit can actively control the output power of the power generation equipment by adjusting the operating status of the power generation equipment. Since adjusting the output power of the power generation equipment requires adjusting the photovoltaic power generation equipment, in order to improve the adjustment efficiency and reduce the number of adjustments, two different adjustment strategies are adopted considering the different regions where different power generation equipment is located. For areas with stable sunlight conditions, an absolute power limit strategy is adopted for photovoltaic power generation equipment, that is, a maximum allowable absolute value of output power is set for photovoltaic power generation equipment to ensure the constant output power of the power generation equipment. For areas with large variations in sunlight conditions, a percentage power limit strategy is adopted, that is, the actual output power of the power generation equipment is limited to a percentage of the theoretical output power.

[0050] Specifically, the storage allocation control unit is used for optimizing the energy storage system; in order to improve the charging and discharging efficiency of the energy storage system to realize the improvement of economic benefit and reliability, two strategies of peak clipping and valley filling and smooth output are adopted to optimize the energy storage system; the core idea of peak clipping and valley filling is that when the electricity price is low, the photovoltaic power generation equipment charges at the standard power to store more power; during the power consumption peak period or the electricity price peak period, the stored power is released to meet the local power demand or sold to the power grid to improve the economic benefit; smooth output refers to the problem that the output power of the photovoltaic power generation equipment suddenly drops due to the cloud cover of sunlight during the normal power generation process of the photovoltaic power generation equipment, which causes impact on the stability of the power grid; in order to reduce the impact of the sudden drop of the output power on the stability of the power grid, when the storage allocation control unit detects that the output power of the photovoltaic power generation equipment suddenly drops due to the cloud cover, the energy storage system immediately discharges to fill the gap of the sudden drop of the power, so as to keep the total output power of the photovoltaic power generation equipment smooth transition; when the cloud drifts away, the light recovers to cause the output power of the photovoltaic power generation equipment to rise, and the energy storage system charges to absorb the excess power, so as to ensure the smooth rise of the output power;

[0051] Specifically, the load management unit is used for distributing electric energy according to the power generation efficiency and power consumption demand; the load management unit links the power generation equipment control unit and the storage allocation control unit according to the power generation efficiency of the current power generation equipment and the power consumption demand to distribute electric energy; for example, when it is noon with sufficient sunlight, the photovoltaic power generation efficiency is greater than the current power grid demand at this time, the load management unit transmits the energy storage instruction to the storage allocation control unit to control the energy storage system to perform the electric energy storage operation, and transmits the power adjustment instruction to the power generation equipment control unit to adjust the real-time output power of the power generation equipment;

[0052] Specifically, the system self-learning unit is used for iteratively optimizing the power generation efficiency evaluation model and the equipment control strategy through historical data and real-time data; in order to ensure the accuracy of the isolation forest model in the anomaly detection and diagnosis unit, an online learning mechanism is established, and the isolation forest model is retrained regularly using newly collected data, so that the model can adapt to the aging of the equipment and the change of the environment, and at the same time, due to the increase of the training data, the model can capture the long-term mode change of the data, further improving the prediction and diagnosis accuracy of the isolation forest model;

[0053] Further, the communication maintenance module transmits data between modules and exchanges data with external systems through the data transmission unit 5G router; the system monitoring and maintenance unit is used for monitoring the running state of the system in real time, detecting faults and timely repairing and alarming; the user interface module is used for providing a man-machine interactive interface; the data storage and backup unit is used for storing important data locally or in the cloud and performing regular backup;

[0054] Specifically, the data transmission unit is used for transmitting data between modules and exchanging data with external systems; based on 5G communication technology, a 5G industrial router is used to provide a high-speed and stable data transmission link between modules, and the collected real-time data can be transmitted to the analysis processing module for analysis faster, so that the new energy power generation efficiency monitoring system can make accurate decisions;

[0055] Specifically, the system monitoring and maintenance unit is used for real-time monitoring of the running state of the system, fault detection and timely maintenance alarm; when the system monitoring and maintenance unit detects that the monitoring system is abnormal or the power generation equipment fails, it immediately sends an alarm information to the system operation and maintenance personnel through SMS or email; in addition, the system monitoring and maintenance unit provides a remote log viewing function to facilitate troubleshooting without the system operation and maintenance personnel being on site;

[0056] Specifically, the user interface module is used to provide a human-computer interaction interface; the user interface module provides two different human-computer interaction interfaces, including a Web end and an App end, which can facilitate the staff to view the system; in addition, the user interface module sets up a multi-level role permission management to assign different permissions to different roles;

[0057] Specifically, the data storage and backup unit is used for local or cloud storage of important data and regular backup; the data storage and backup unit uses a MySQL database for data storage management to improve data management efficiency; incremental backup is performed according to the data collected by the system running every day, and the backup data is stored in the cloud to ensure data security;

[0058] Compared with the prior art, the present application proposes a new energy power generation efficiency monitoring system, which cleans the collected data through the data preprocessing unit to ensure the high quality of the input data, improves the accuracy of analysis and decision-making, and reduces errors caused by data noise; the analysis processing module evaluates the power generation efficiency, and realizes dynamic adjustment of the power generation equipment parameters in combination with abnormal detection, thereby improving the equipment utilization rate; the machine learning algorithm is used to monitor the running parameters of the power generation equipment in real time, and the abnormal detection diagnosis unit can find potential faults to preventively identify corresponding faults and reduce downtime; the system self-learning unit learns from historical and real-time data to continuously optimize the equipment control strategy and power generation efficiency evaluation model, so that the system can maintain optimal performance in long-term use and reduce maintenance costs.

[0059] The above merely describes the preferred embodiments of the present application, and the protection scope of the present application is not limited to the above-described embodiments. Any technical solution falling within the concept of the present application shall fall within the protection scope of the present application. It should be noted that, for ordinary skilled persons in the art, some improvements and refinements without departing from the principles of the present application shall also be considered as falling within the protection scope of the present application.

Claims

1. A new energy power generation efficiency monitoring system, characterized in that, It includes a data acquisition module, an analysis and processing module, an optimization and control module, and a communication and maintenance module; The data acquisition module includes a meteorological data acquisition unit, a radiation intensity acquisition unit, a power generation equipment acquisition unit, and a data preprocessing unit. The meteorological data acquisition unit is used to acquire real-time meteorological data from the meteorological station, the radiation intensity acquisition unit is used to acquire real-time solar radiation intensity data from the meteorological station and classify it, the power generation equipment acquisition unit is used to acquire real-time power generation equipment operating parameters, and the data preprocessing unit is used to preprocess the data acquired by the above units. The analysis and processing module includes a radiation intensity analysis unit, a power generation efficiency evaluation unit, an anomaly detection and diagnosis unit, and a data visualization unit. The radiation intensity analysis unit is used to calculate the total solar radiation intensity and photovoltaic power generation curve based on the collected solar radiation intensity data. The power generation efficiency evaluation unit is used to calculate the current power generation efficiency of the equipment based on real-time solar radiation data and the operating status of the power generation equipment. The anomaly detection and diagnosis unit is used to perform anomaly detection and diagnosis based on the collected data analyzed by machine learning algorithms. The data visualization unit is used to display the data and analysis results in the form of charts, curves and other visualizations. The optimization control module includes a power generation equipment control unit, a storage allocation control unit, a load management unit, and a system self-learning unit. The power generation equipment control unit is used to adjust the operating parameters of the power generation equipment, the storage allocation control unit is used to optimize the energy storage system, the load management unit is used to allocate power according to power generation efficiency and power demand, and the system self-learning unit is used to iteratively optimize the power generation efficiency evaluation model and equipment control strategy through historical data and real-time data. The communication maintenance module includes a data transmission unit, a system monitoring and maintenance unit, a user interface unit, and a data storage and backup unit. The data transmission unit is used to transmit data between modules and exchange data with external systems. The system monitoring and maintenance unit is used to monitor the system's operating status in real time, detect faults, and repair alarms in a timely manner. The user interface module is used to provide a human-machine interaction interface. The data storage and backup unit is used to store important data locally or in the cloud and perform regular backups.

2. The new energy power generation efficiency monitoring system as described in claim 1, characterized in that, The preprocessing of the data collected by the above-mentioned units includes: The moving average filtering algorithm is used to process the data and filter out abnormal data caused by noise. The moving average filtering algorithm slides a fixed-size window across the data, calculates the average value of all data points within the window, and uses this average value to represent the value of the latest data point. Adaptively adjusting the window size according to the data type can effectively achieve a balance between data smoothing and lag. For high-frequency data, the moving average filtering algorithm uses a larger window; for low-frequency data, the moving average filtering algorithm uses a smaller window.

3. The new energy power generation efficiency monitoring system as described in claim 1, characterized in that, The radiation intensity analysis unit is used to calculate the total solar radiation intensity and photovoltaic power generation curve based on the collected solar radiation intensity data, including: The total solar radiation intensity is obtained by calculating the sum of direct solar radiation intensity, diffuse radiation intensity, and ground reflected radiation intensity. The diffuse radiation intensity and ground reflected radiation intensity are obtained directly from the meteorological station by the radiation intensity acquisition unit, while the direct solar radiation intensity needs to take into account the influence of the solar zenith angle on the solar radiation intensity. Based on the local latitude collected by the meteorological data acquisition unit from the meteorological station Solar declination angle Solar hour angle To calculate the local solar zenith angle Its value is equal to the local latitude. Solar declination angle The product of the sine and the local latitude Solar declination angle Solar hour angle The sum of the products of cosines; Based on direct solar radiation intensity Heat dissipation and radiation intensity Ground reflected radiation intensity Calculate the total solar radiation intensity Its value is the intensity of direct solar radiation. With the zenith angle of the sun The product of heat dissipation and radiation intensity Ground reflected radiation intensity The sum of; The efficiency of photovoltaic (PV) power generation is directly related to the intensity of solar radiation received by the PV module; that is, the PV power generation curve, which represents the theoretical output power of the PV module versus the total solar radiation intensity. There is a positive correlation; the area of ​​photovoltaic modules The efficiency of a photovoltaic module is determined by the amount of total solar radiation received. The losses that determine the conversion of light energy into electrical energy; the theoretical output power of photovoltaic modules. Total solar radiation intensity Area of ​​photovoltaic modules Photovoltaic module efficiency The product of the three; Considering the changes in ambient temperature, a temperature correction method is used to adjust the efficiency of photovoltaic modules. Correction: The average temperature is calculated by collecting temperature data from multiple weather stations, and the temperature value closest to this average is selected as the reference temperature for photovoltaic module efficiency. Temperature correction.

4. The new energy power generation efficiency monitoring system as described in claim 1, characterized in that, The power generation efficiency evaluation unit is used to calculate the current power generation efficiency of the equipment based on real-time solar radiation data and the operating status of the power generation equipment, including: The power generation efficiency, i.e., performance ratio of the current equipment The real-time power of the device can be calculated. and theoretical output power The ratio between them indicates the real-time power of the device. The theoretical output power is obtained by collecting real-time operating status data of the power generation equipment through the power generation equipment acquisition unit. The radiation intensity is calculated using the radiation intensity analysis unit.

5. The new energy power generation efficiency monitoring system as described in claim 1, characterized in that, The anomaly detection and diagnosis unit is used to perform anomaly detection and diagnosis based on the analysis of collected data using machine learning algorithms, including: The Isolation Forest algorithm is used to model the collected historical normal data to achieve unsupervised learning monitoring of abnormal data. The core idea of ​​the Isolation Forest algorithm is that abnormal data points are outliers that are easily isolated. The Isolation Forest model monitors abnormal data by constructing multiple isolation trees. Each tree randomly selects features and split values ​​to recursively split data points until every point is isolated, and calculates an anomaly score for each point. This anomaly score is determined by the average path length required for the data point to be isolated in the tree. For normal data points, multiple random feature selections and splits are required to isolate them, while for abnormal data points, due to the large difference between their feature values ​​and those of normal data points, only a few random feature selections and splits are needed to isolate them. Therefore, for a data point, the shorter the average path length required to isolate it, the higher its probability of being an anomaly. Features were constructed based on normal data collected at different time points, in addition to directly using raw data features including ambient temperature. direct solar radiation intensity Heat dissipation and radiation intensity Ground reflected radiation intensity Current ,Voltage Actual power Photovoltaic module temperature In addition, features containing more equipment operation information are constructed based on the original data. The original data features and the constructed features are concatenated to obtain features at normal time points. The processed features at normal time points are then input into the isolated forest model for training, and the number of hyperparameter trees is adjusted. and outlier expected ratio Adjustments are made to obtain the optimal isolated forest model; after obtaining the optimized isolated forest model through iterative optimization, the real-time data is processed and input into the isolated forest model, and an anomaly score is output for each data point. When the anomaly score is greater than the preset threshold, an anomaly detection warning is triggered; the detailed information of the abnormal data points is recorded and a traceable report is generated for subsequent analysis and processing.

6. The new energy power generation efficiency monitoring system as described in claim 1, characterized in that, The power generation equipment control unit is used to adjust the operating parameters of the power generation equipment, including: The power generation equipment control unit actively controls the output power of the power generation equipment by adjusting its operating status. Considering the different regions where the power generation equipment is located, two different adjustment strategies are adopted: For areas with stable sunlight conditions, an absolute power limit strategy is implemented for photovoltaic power generation equipment, that is, a maximum allowable absolute value of output power is set for the photovoltaic power generation equipment to ensure that the output power of the power generation equipment is constant; For areas with large variations in sunlight conditions, a power percentage limit strategy is adopted, that is, the actual output power of the power generation equipment is limited to a percentage of the theoretical output power.

7. The new energy power generation efficiency monitoring system as described in claim 1, characterized in that, The storage allocation control unit is used for optimization of the energy storage system, including: The energy storage system is optimized by adopting two major strategies: peak shaving and valley filling, and smooth output. The core idea of ​​peak shaving and valley filling is that when electricity prices are low, photovoltaic power generation equipment is charged at standard power to store more electricity; during peak electricity consumption periods or peak electricity prices, the stored electricity is released to meet local electricity demand or sold to the grid to improve economic efficiency. Smooth output refers to the phenomenon where, during normal power generation of photovoltaic (PV) equipment, the output power of the PV equipment suddenly drops due to cloud cover blocking sunlight, impacting grid stability. When the energy storage and distribution control unit detects this sudden drop in output power, the energy storage system immediately discharges to fill the power gap, maintaining a smooth transition in the total output power of the PV equipment. When the clouds disperse and sunlight returns, causing the output power of the PV equipment to recover, the energy storage system charges to absorb excess power, ensuring a smooth recovery of output power.

8. The new energy power generation efficiency monitoring system as described in claim 1, characterized in that, The load management unit is used to allocate electrical energy according to power generation efficiency and electricity demand, including: The load management unit coordinates the power generation equipment control unit and the storage distribution control unit to distribute electrical energy based on the current power generation efficiency and electricity demand of the power generation equipment. When the solar radiation is strong at noon, the photovoltaic power generation efficiency is greater than the current grid demand. The load management unit transmits energy storage instructions to the storage distribution control unit to control the energy storage system to perform energy storage operations and transmits power regulation instructions to the power generation equipment control unit to adjust the real-time output power of the power generation equipment.

9. A new energy power generation efficiency monitoring system as described in claim 1, characterized in that, The system self-learning unit is used to iteratively optimize the power generation efficiency assessment model and equipment control strategy using historical and real-time data, including: An online learning mechanism is established to periodically train the isolated forest model in the anomaly detection unit based on the collected data. Each training session retrains the isolated forest model using historical and real-time data, and re-optimizes the number of trees. and outlier expected ratio Two model hyperparameters are used to adapt the model to changes in the environment and the aging of the equipment.

10. A new energy power generation efficiency monitoring system as described in claim 1, characterized in that, The data storage and backup unit is used for storing important data locally or in the cloud and performing regular backups, including: The data storage and backup unit uses a MySQL database for data storage management to improve data management efficiency; it performs incremental backups based on the data collected daily during system operation and stores the backup data in the cloud to ensure data security.

Images