Power equipment meteorological monitoring and early warning system based on artificial intelligence

Abstract

The invention provides a power equipment meteorological monitoring and early warning system based on artificial intelligence. The power equipment meteorological monitoring and early warning system based on artificial intelligence comprises a data acquisition module, a data preprocessing module, a spatio-temporal feature fusion module and a meteorological disaster prediction model, the meteorological disaster prediction model adopts a deep reinforcement learning framework, inputs a multi-dimensional spatio-temporal feature matrix, and carries out meteorological disaster prediction on the multi-dimensional spatio-temporal feature matrix. And outputting meteorological disaster risk levels and key parameter predicted values in a future preset time period, including a wind speed, precipitation, temperature anomaly and tropical cyclone path probability, a dynamic early warning threshold generation module, an early warning decision module and a model optimization module. The power equipment meteorological monitoring and early warning system based on artificial intelligence provided by the invention has the advantages that the data interpolation precision of a complex terrain region can be improved, high-precision prediction of a typhoon path, short-time strong wind and an icing risk can be realized, and the early warning accuracy and defense response efficiency of a power system to meteorological disasters can be comprehensively improved.

Description

Technical Field

[0001] The present invention relates to the field of electric power technology, and in particular to an artificial intelligence-based meteorological monitoring and early warning system for electric power equipment. Background Art

[0002] As renewable energy power systems expand, meteorological disasters pose an increasingly severe threat to power transmission and transformation equipment, wind farms, and photovoltaic power plants. Traditional meteorological monitoring systems, which often rely on data from a single meteorological station, suffer from low spatial coverage and difficulty integrating heterogeneous data from multiple sources. This makes it difficult to timely capture the evolving characteristics of disasters, such as localized severe convection and sudden typhoon path changes.

[0003] Existing technologies often use spatial kriging to interpolate meteorological data, but this method fails to fully account for the spatiotemporal coupling of meteorological elements, leading to high interpolation errors in complex terrain such as mountainous and coastal areas. Disaster prediction models are often based on statistical methods or single deep learning architectures, lacking the constraints of physical laws. This can easily lead to misjudgments such as wind speed prediction errors exceeding 5 m / s in extreme weather conditions. Furthermore, warning thresholds for power equipment often use fixed standards, failing to account for dynamic factors such as equipment aging and grid load fluctuations, resulting in a high false alarm rate. Regarding defense strategies, existing systems often provide general emergency plans, failing to generate targeted response plans based on the geographical distribution and operating status of equipment. Furthermore, existing models generally lack online learning capabilities and are unable to adapt to shifting weather patterns caused by climate change. While some research has attempted to integrate the complementary characteristics of wind and solar resources, dynamic optimization models that minimize grid fluctuations have not been established, resulting in inefficient renewable energy absorption.

[0004] Therefore, it is necessary to provide an artificial intelligence-based meteorological monitoring and early warning system for power equipment to solve the above technical problems. Summary of the Invention

[0005] The technical problem solved by the present invention is to provide an artificial intelligence-based meteorological monitoring and early warning system for power equipment that can improve the data interpolation accuracy in complex terrain areas, achieve high-precision predictions of typhoon paths, short-term strong winds and icing risks, and comprehensively improve the early warning accuracy and defense response efficiency of the power system in response to meteorological disasters.

[0006] To solve the above technical problems, the present invention provides an artificial intelligence-based meteorological monitoring and early warning system for electric power equipment, comprising: a data acquisition module, the data acquisition module being used to acquire multi-source meteorological data and electric power equipment operation data in real time;

[0007] A data preprocessing module, connected to the data acquisition module, for performing quality control, missing value interpolation, and time-space consistency correction on the original data to generate a standardized meteorological data set;

[0008] A spatiotemporal feature fusion module, which extracts spatial correlation features and time series dependencies of meteorological data based on convolutional neural networks and graph attention networks, integrates the geographical distribution information of power equipment, and constructs a multidimensional spatiotemporal feature matrix;

[0009] A meteorological disaster prediction model, which uses a deep reinforcement learning framework to input the multidimensional spatiotemporal feature matrix and outputs meteorological disaster risk levels and predicted values of key parameters within a preset future time period, including wind speed, precipitation, temperature anomalies, and tropical cyclone path probabilities;

[0010] A dynamic warning threshold generation module, which adaptively calculates meteorological risk thresholds for different power equipment types, regional locations, and operating stages based on historical disaster data and equipment disaster resistance indicators;

[0011] An early warning decision module compares the prediction results with dynamic thresholds, generates graded early warning signals and defense strategy recommendations, and pushes them to terminal devices in real time through a 3D GIS visualization platform;

[0012] The model optimization module is based on an online learning mechanism and uses real-time feedback of early warning effect data to update the prediction model parameters and improve the system iteration accuracy.

[0013] Preferably, the missing value interpolation method of the data preprocessing module includes:

[0014] For the missing part of meteorological station observation data, the spatiotemporal Kriging interpolation algorithm is used, and the interpolation value calculation satisfies the following relationship:

[0015]

[0016] Where Z(s0,t0) is the interpolated value of the target position s0 at time t0, λ i and γ j are the spatial and temporal weight coefficients, determined by optimizing the semivariogram; Represents the time gradient operator, which is used to capture the temporal variation trend of meteorological elements.

[0017] Preferably, the workflow of the spatiotemporal feature fusion module includes the following steps:

[0018] The spatial texture features of the radar echo image are extracted through the CNN branch, and the hole convolution layer is used to expand the receptive field to capture the large-scale weather system structure;

[0019] The topological relationship graph between meteorological stations is constructed through GAT branches. The node characteristics include wind speed, temperature, and humidity. The edge weight is determined by the geographical distance between stations and meteorological correlation.

[0020] A multi-head attention mechanism is used to dynamically weight the spatiotemporal features and generate a feature matrix containing the regional meteorological evolution laws.

[0021] Preferably, the meteorological disaster prediction model includes the following sub-models:

[0022] Typhoon path prediction sub-model: Based on the improved U-Net architecture, it inputs satellite cloud images and sea temperature field data and outputs a probability distribution map of the movement track of the tropical cyclone center;

[0023] Short-term strong wind prediction sub-model: This model uses a bidirectional LSTM network coupled with physical constraint equations. Its wind speed prediction value satisfies the following dynamic correction conditions:

[0024]

[0025] Among them, α is the machine learning weight coefficient, is the pressure gradient force, v obs is the current observed wind speed;

[0026] Icing risk assessment sub-model: Based on the random forest algorithm, it comprehensively considers temperature, humidity, wind speed, and equipment surface material parameters to calculate the growth rate of conductor ice thickness.

[0027] Preferably, the dynamic warning threshold generation module performs the following operations:

[0028] According to the IEC wind resistance grade standard for wind turbines, the maximum tolerable wind speed threshold v of different wind turbine types is divided into max ;

[0029] Based on the equipment aging detection data, the life attenuation factor β(t) = e is introduced -kt Dynamically lower the threshold, where k is the material fatigue coefficient;

[0030] Combined with real-time grid load demand, the high temperature warning threshold is raised in power supply emergencies to avoid unnecessary shutdowns.

[0031] Preferably, the defense strategy suggestion generating method of the early warning decision module includes:

[0032] When the predicted wind speed exceeds 80% of the design threshold, a preliminary warning is triggered and the wind turbine yaw system self-check is started;

[0033] When the predicted precipitation triggers the regional flood risk index R flood When the value is >0.7, the substation waterproof gate closing instruction and backup power supply switching plan will be generated;

[0034] For photovoltaic power stations, the cleaning robot operation priority queue is dynamically adjusted according to the predicted optical thickness τ of the sandstorm.

[0035] Preferably, the model optimization module adopts a federated learning framework to implement distributed model training for multi-regional power companies, and its parameter aggregation process satisfies:

[0036]

[0037] in, is the weight parameter of the i-th local model in the t-th round of training, D i is the amount of local data, D total The total amount of global data.

[0038] Preferably, the three-dimensional GIS visualization platform integrates the following functions:

[0039] The thermal layer displays the real-time wind speed field and predicted path, and overlays terrain elevation data to analyze areas of enhanced canyon effect;

[0040] Dynamically render the power grid topology, highlighting transmission lines and substations at risk from meteorological events;

[0041] The embedded AR interface enables inspection personnel to obtain real-time micro-meteorological information around the equipment through smart glasses.

[0042] Preferably, it also includes a wind-solar complementary optimization module, which performs:

[0043] Calculation of regional wind-solar energy complementarity index C based on Kendall rank correlation coefficient ws :

[0044]

[0045] Among them, N c N is the number of periods where wind and solar output change in the same direction. d is the number of reverse change periods;

[0046] With the goal of minimizing grid fluctuations, find the optimal installed capacity ratio Its objective function is:

[0047]

[0048] in, are the variances of wind and solar output, σ ws is its covariance.

[0049] Preferably, the multi-source meteorological data includes meteorological station observation data, radar reflectivity data, satellite remote sensing data, numerical weather forecast data and atmospheric reanalysis data; the power equipment operation data includes the operating status of wind turbines, photovoltaic power station output power and grid load parameters.

[0050] Compared with related technologies, the artificial intelligence-based meteorological monitoring and early warning system for power equipment provided by the present invention has the following beneficial effects:

[0051] The present invention provides an artificial intelligence-based meteorological monitoring and early warning system for electric power equipment. The system integrates multi-source heterogeneous data from meteorological stations, radars, satellites, and electric power equipment through a data acquisition module, solving the problem of single data dimension in traditional monitoring systems. The data preprocessing module adopts a spatiotemporal Kriging interpolation algorithm to fuse spatiotemporal gradient operators, significantly improving data interpolation accuracy in complex terrain areas. The spatiotemporal feature fusion module extracts multi-scale meteorological features based on a CNN-GAT hybrid network, enhancing the ability to identify small and medium-scale weather systems. The meteorological disaster prediction model combines a deep reinforcement learning framework with physical constraint equations to achieve high-precision prediction of typhoon paths, short-term strong winds, and icing risks. The dynamic warning threshold generation module introduces an equipment aging factor and a grid load coordination mechanism to establish an adaptive hierarchical warning standard. The warning decision module realizes visual positioning of the disaster impact range through a three-dimensional GIS platform and generates equipment-level defense strategies. The model optimization module adopts a federated learning framework to achieve co-evolution of multi-region models to ensure continuous optimization of the prediction model. The wind-solar complementary optimization module establishes an optimal capacity ratio model based on wind-solar output correlation analysis to effectively smooth out fluctuations in new energy grid connection. The synergistic effect of these modules comprehensively improves the warning accuracy and defense response efficiency of the power system in response to meteorological disasters. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 This is a principle block diagram of the artificial intelligence-based meteorological monitoring and early warning system for power equipment provided by the present invention. DETAILED DESCRIPTION

[0053] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0054] Please refer to Figure 1 ,in, Figure 1 This is a block diagram of the principle of the artificial intelligence-based meteorological monitoring and early warning system for power equipment provided by the present invention. The artificial intelligence-based meteorological monitoring and early warning system for power equipment includes:

[0055] A data acquisition module, which is used to acquire multi-source meteorological data and power equipment operation data in real time;

[0056] Among them, multi-source meteorological data include meteorological station observation data, radar reflectivity data, satellite remote sensing data, numerical weather forecast data and atmospheric reanalysis data; power equipment operation data include wind turbine operating status, photovoltaic power station output power and grid load parameters.

[0057] A data preprocessing module, connected to the data acquisition module, for performing quality control, missing value interpolation, and time-space consistency correction on the original data to generate a standardized meteorological data set;

[0058] The missing value interpolation methods of the data preprocessing module include:

[0059] For the missing part of meteorological station observation data, the spatiotemporal Kriging interpolation algorithm is used, and the interpolation value calculation satisfies the following relationship:

[0060]

[0061] Where Z(s0,t0) is the interpolated value of the target position s0 at time t0, λ i and γ j are the spatial and temporal weight coefficients, determined by optimizing the semivariogram; Represents the time gradient operator, which is used to capture the temporal variation trend of meteorological elements.

[0062] A spatiotemporal feature fusion module, which extracts spatial correlation features and time series dependencies of meteorological data based on convolutional neural networks and graph attention networks, integrates the geographical distribution information of power equipment, and constructs a multidimensional spatiotemporal feature matrix;

[0063] The workflow of the spatiotemporal feature fusion module includes the following steps:

[0064] The spatial texture features of the radar echo image are extracted through the CNN branch, and the hole convolution layer is used to expand the receptive field to capture the large-scale weather system structure;

[0065] The topological relationship graph between meteorological stations is constructed through GAT branches. The node characteristics include wind speed, temperature, and humidity. The edge weight is determined by the geographical distance between stations and meteorological correlation.

[0066] A multi-head attention mechanism is used to dynamically weight the spatiotemporal features and generate a feature matrix containing the regional meteorological evolution laws.

[0067] A meteorological disaster prediction model, which uses a deep reinforcement learning framework to input the multidimensional spatiotemporal feature matrix and outputs meteorological disaster risk levels and predicted values of key parameters within a preset future time period, including wind speed, precipitation, temperature anomalies, and tropical cyclone path probabilities;

[0068] The meteorological disaster prediction model includes the following sub-models:

[0069] Typhoon path prediction sub-model: Based on the improved U-Net architecture, it inputs satellite cloud images and sea temperature field data and outputs a probability distribution map of the movement track of the tropical cyclone center;

[0070] Short-term strong wind prediction sub-model: This model uses a bidirectional LSTM network coupled with physical constraint equations. Its wind speed prediction value satisfies the following dynamic correction conditions:

[0071]

[0072] Among them, α is the machine learning weight coefficient, is the pressure gradient force, v obs is the current observed wind speed;

[0073] Icing risk assessment sub-model: Based on the random forest algorithm, it comprehensively considers temperature, humidity, wind speed, and equipment surface material parameters to calculate the growth rate of conductor ice thickness.

[0074] A dynamic warning threshold generation module, which adaptively calculates meteorological risk thresholds for different power equipment types, regional locations, and operating stages based on historical disaster data and equipment disaster resistance indicators;

[0075] The dynamic warning threshold generation module performs the following operations:

[0076] According to the IEC wind resistance grade standard for wind turbines, the maximum tolerable wind speed threshold v of different wind turbine types is divided into max ;

[0077] Based on the equipment aging detection data, the life attenuation factor β(t) = e is introduced -kt Dynamically lower the threshold, where k is the material fatigue coefficient;

[0078] Combined with real-time grid load demand, the high temperature warning threshold is raised in power supply emergencies to avoid unnecessary shutdowns.

[0079] An early warning decision module compares the prediction results with dynamic thresholds, generates graded early warning signals and defense strategy recommendations, and pushes them to terminal devices in real time through a 3D GIS visualization platform;

[0080] The defense strategy recommendation generation method of the early warning decision module includes:

[0081] When the predicted wind speed exceeds 80% of the design threshold, a preliminary warning is triggered and the wind turbine yaw system self-check is started;

[0082] When the predicted precipitation triggers the regional flood risk index R flood When the value is >0.7, the substation waterproof gate closing instruction and backup power supply switching plan will be generated;

[0083] For photovoltaic power stations, the cleaning robot operation priority queue is dynamically adjusted according to the predicted optical thickness τ of the sandstorm.

[0084] The 3D GIS visualization platform integrates the following functions:

[0085] The thermal layer displays the real-time wind speed field and predicted path, and overlays terrain elevation data to analyze areas of enhanced canyon effect;

[0086] Dynamically render the power grid topology, highlighting transmission lines and substations at risk from meteorological events;

[0087] The embedded AR interface enables inspection personnel to obtain real-time micro-meteorological information around the equipment through smart glasses.

[0088] The model optimization module is based on an online learning mechanism and uses real-time feedback of early warning effect data to update the prediction model parameters and improve the system iteration accuracy.

[0089] The model optimization module uses a federated learning framework to implement distributed model training for multi-regional power companies. Its parameter aggregation process satisfies the following requirements:

[0090]

[0091] in, is the weight parameter of the i-th local model in the t-th round of training, D i is the amount of local data, D total The total amount of global data.

[0092] It also includes a wind-solar hybrid optimization module, which performs:

[0093] Calculation of regional wind-solar energy complementarity index C based on Kendall rank correlation coefficient ws :

[0094]

[0095] Among them, N c N is the number of periods where wind and solar output change in the same direction. d is the number of reverse change periods;

[0096] With the goal of minimizing grid fluctuations, find the optimal installed capacity ratio Its objective function is:

[0097]

[0098] in, are the variances of wind and solar output, σ ws is its covariance.

[0099] The artificial intelligence-based meteorological monitoring and early warning system for electric power equipment provided by the present invention is deployed in a hybrid architecture of edge computing nodes and cloud platforms, in which: the edge performs real-time data preprocessing and low-latency early warning generation; the cloud performs large-scale model training and cross-regional meteorological pattern assimilation calculations; and the entire early warning decision-making process is recorded through blockchain evidence storage technology to ensure operational traceability.

[0100] Compared with related technologies, the artificial intelligence-based meteorological monitoring and early warning system for power equipment provided by the present invention has the following beneficial effects:

[0101] The present invention provides an artificial intelligence-based meteorological monitoring and early warning system for electric power equipment. The system integrates multi-source heterogeneous data from meteorological stations, radars, satellites, and electric power equipment through a data acquisition module, solving the problem of single data dimension in traditional monitoring systems. The data preprocessing module uses a spatiotemporal Kriging interpolation algorithm to fuse spatiotemporal gradient operators, significantly improving data interpolation accuracy in complex terrain areas. The spatiotemporal feature fusion module extracts multi-scale meteorological features based on a CNN-GAT hybrid network, enhancing the ability to identify small and medium-scale weather systems. The meteorological disaster prediction model combines a deep reinforcement learning framework with physical constraint equations to achieve high-precision predictions of typhoon paths, short-term strong winds, and icing risks. The dynamic warning threshold generation module introduces an equipment aging factor and a grid load coordination mechanism to establish an adaptive hierarchical warning standard. The warning decision module uses a three-dimensional GIS platform to visualize the disaster impact range and generate equipment-level defense strategies. The model optimization module uses a federated learning framework to achieve the co-evolution of multi-region models, ensuring the continuous optimization of the prediction model. The wind-solar complementary optimization module establishes an optimal capacity ratio model based on wind-solar output correlation analysis to effectively smooth out fluctuations in the grid connection of new energy. The synergistic effect of these modules comprehensively improves the warning accuracy and defense response efficiency of the power system in response to meteorological disasters.

[0102] The above descriptions are merely embodiments of the present invention and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention description and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. An artificial intelligence-based meteorological monitoring and early warning system for power equipment, characterized in that: include: A data acquisition module, which is used to acquire multi-source meteorological data and power equipment operation data in real time; A data preprocessing module, connected to the data acquisition module, for performing quality control, missing value interpolation, and time-space consistency correction on the original data to generate a standardized meteorological data set; A spatiotemporal feature fusion module, which extracts spatial correlation features and time series dependencies of meteorological data based on convolutional neural networks and graph attention networks, integrates the geographical distribution information of power equipment, and constructs a multidimensional spatiotemporal feature matrix; A meteorological disaster prediction model, which uses a deep reinforcement learning framework to input the multidimensional spatiotemporal feature matrix and outputs meteorological disaster risk levels and predicted values of key parameters within a preset future time period, including wind speed, precipitation, temperature anomalies, and tropical cyclone path probabilities; A dynamic warning threshold generation module, which adaptively calculates meteorological risk thresholds for different power equipment types, regional locations, and operating stages based on historical disaster data and equipment disaster resistance indicators; An early warning decision module compares the prediction results with dynamic thresholds, generates graded early warning signals and defense strategy recommendations, and pushes them to terminal devices in real time through a 3D GIS visualization platform; The model optimization module is based on an online learning mechanism and uses real-time feedback of early warning effect data to update the prediction model parameters and improve the system iteration accuracy.

2. The artificial intelligence-based meteorological monitoring and early warning system for electric power equipment according to claim 1 is characterized in that: The missing value interpolation method of the data preprocessing module includes: For the missing part of meteorological station observation data, the spatiotemporal Kriging interpolation algorithm is used, and the interpolation value calculation satisfies the following relationship: Where Z(s0,t0) is the interpolated value of the target position s0 at time t0, λ i and γ j are the spatial and temporal weight coefficients, determined by optimizing the semivariogram; Represents the time gradient operator, which is used to capture the temporal variation trend of meteorological elements.

3. The artificial intelligence-based meteorological monitoring and early warning system for electric power equipment according to claim 1 is characterized in that: The workflow of the spatiotemporal feature fusion module includes the following steps: The spatial texture features of the radar echo image are extracted through the CNN branch, and the hole convolution layer is used to expand the receptive field to capture the large-scale weather system structure; The topological relationship graph between meteorological stations is constructed through GAT branches. The node characteristics include wind speed, temperature, and humidity. The edge weight is determined by the geographical distance between stations and meteorological correlation. A multi-head attention mechanism is used to dynamically weight the spatiotemporal features and generate a feature matrix containing the regional meteorological evolution laws.

4. The artificial intelligence-based meteorological monitoring and early warning system for electric power equipment according to claim 1 is characterized in that: The meteorological disaster prediction model includes the following sub-models: Typhoon path prediction sub-model: Based on the improved U-Net architecture, it inputs satellite cloud images and sea temperature field data and outputs a probability distribution map of the movement track of the tropical cyclone center; Short-term strong wind prediction sub-model: This model uses a bidirectional LSTM network coupled with physical constraint equations. Its wind speed prediction value satisfies the following dynamic correction conditions: Among them, α is the machine learning weight coefficient, is the pressure gradient force, v obs is the current observed wind speed; Icing risk assessment sub-model: Based on the random forest algorithm, it comprehensively considers temperature, humidity, wind speed, and equipment surface material parameters to calculate the growth rate of conductor ice thickness.

5. The artificial intelligence-based meteorological monitoring and early warning system for electric power equipment according to claim 1 is characterized in that: The dynamic warning threshold generation module performs the following operations: According to the IEC wind resistance grade standard for wind turbines, the maximum tolerable wind speed threshold v of different wind turbine types is divided into max ; Based on the equipment aging detection data, the life attenuation factor β(t) = e is introduced -kt Dynamically lower the threshold, where k is the material fatigue coefficient; Combined with real-time grid load demand, the high temperature warning threshold is raised in power supply emergencies to avoid unnecessary shutdowns.

6. The artificial intelligence-based meteorological monitoring and early warning system for electric power equipment according to claim 1 is characterized in that: The defense strategy suggestion generation method of the early warning decision module includes: When the predicted wind speed exceeds 80% of the design threshold, a preliminary warning is triggered and the wind turbine yaw system self-check is started; When the predicted precipitation triggers the regional flood risk index R flood When the value is >0.7, the substation waterproof gate closing instruction and backup power supply switching plan will be generated; For photovoltaic power stations, the cleaning robot operation priority queue is dynamically adjusted according to the predicted optical thickness τ of the sandstorm.

7. The artificial intelligence-based meteorological monitoring and early warning system for electric power equipment according to claim 1 is characterized in that: The model optimization module adopts a federated learning framework to implement distributed model training for multi-regional power companies. Its parameter aggregation process satisfies: in, is the weight parameter of the i-th local model in the t-th round of training, D i is the amount of local data, D total The total amount of global data.

8. The artificial intelligence-based meteorological monitoring and early warning system for electric power equipment according to claim 1 is characterized in that: The 3D GIS visualization platform integrates the following functions: The thermal layer displays the real-time wind speed field and predicted path, and overlays terrain elevation data to analyze areas of enhanced canyon effect; Dynamically render the power grid topology, highlighting transmission lines and substations at risk from meteorological events; The embedded AR interface enables inspection personnel to obtain real-time micro-meteorological information around the equipment through smart glasses.

9. The artificial intelligence-based meteorological monitoring and early warning system for electric power equipment according to claim 1 is characterized in that: It also includes a wind-solar hybrid optimization module, which performs: Calculation of regional wind-solar energy complementarity index C based on Kendall rank correlation coefficient ws : Among them, N c N is the number of periods where wind and solar output change in the same direction. d is the number of reverse change periods; With the goal of minimizing grid fluctuations, find the optimal installed capacity ratio Its objective function is: in, are the variances of wind and solar output, σ ws is its covariance.

10. The artificial intelligence-based meteorological monitoring and early warning system for electric power equipment according to claim 1, characterized in that: The multi-source meteorological data includes meteorological station observation data, radar reflectivity data, satellite remote sensing data, numerical weather forecast data and atmospheric reanalysis data; the power equipment operation data includes the operating status of wind turbines, photovoltaic power station output power and grid load parameters.

Images