Power grid dynamic monitoring and early warning method and system based on meteorological information and storage medium

Abstract

The invention discloses a power grid dynamic monitoring early warning method and system based on meteorological information and a storage medium, and relates to the technical field of power grid dynamic monitoring, and the power grid dynamic monitoring early warning system comprises a meteorological data acquisition module which comprises a meteorological data acquisition unit and a power grid data acquisition unit; and the data analysis module comprises a meteorological data analysis unit and a power grid operation data analysis unit, and the meteorological data analysis unit is used for analyzing and outputting predicted air temperature, humidity, air pressure, wind speed and precipitation data. The power grid operation data analysis unit is used for analyzing, outputting and predicting temperature, voltage, current, active power and reactive power data of power grid equipment; and the early warning issuing module analyzes whether each operation data is in a normal range or not, and sends a power grid operation early warning to the outside. And signs of extreme weather events can be found in advance, so that the disaster early warning capability is enhanced.

Description

Technical Field

[0001] The present invention relates to the technical field of power grid dynamic monitoring, and in particular to a power grid dynamic monitoring and early warning method, system and storage medium based on meteorological information. Background Art

[0002] With the rapid development of modern society, electricity has become an indispensable and important energy source to support the national economy and social life. However, the stable operation of the power grid faces many challenges, among which extreme weather conditions are one of the important factors affecting the safety and stability of the power grid. Natural disasters such as ice cover, wildfires, typhoons, heavy rains, and lightning will not only damage power grid equipment, but may also cause large-scale power outages, causing serious impacts on the social economy and people's lives. In order to meet these challenges, the power industry continues to explore and apply new technologies to improve the disaster prevention and mitigation capabilities and operation management level of the power grid. In recent years, with the rapid advancement of meteorological forecasting technology, the accuracy and timeliness of meteorological information have been significantly improved, providing new possibilities for dynamic monitoring and early warning of the power grid.

[0003] In the Chinese invention application with authorization announcement number CN204089886U, a power grid dynamic monitoring and early warning system based on meteorological information is disclosed, including a meteorological collection server that transmits the collected meteorological information to a data bridging workstation through a reverse physical isolation device I, and the meteorological information is then transmitted from the data bridging workstation to a power grid dynamic monitoring and early warning server through a reverse physical isolation device II. At the same time, the EMS system (energy management system) server transmits the EMS data to the power grid dynamic monitoring and early warning server.

[0004] In the Chinese invention application with application publication number CN115549292A, a power grid operation monitoring system and method thereof are disclosed, including a data acquisition module for acquiring power grid operation data and meteorological data; a data analysis module for analyzing the power grid operation data and the meteorological data to obtain analysis results; and an early warning scheduling module for issuing early warning information and performing scheduling planning when abnormal events occur in the analysis results.

[0005] In the above invention application, the geographic information of meteorological access and the geographic information of power equipment are used to accurately analyze the impact of local weather changes and extreme weather on the safe operation of the power grid, and to prepare defense and solutions for the emergency work of the power grid in advance. However, the meteorological information accessed is not actually collected, and the data that is not actually collected may not be customized for specific areas or specific needs. For the power grid dynamic monitoring and early warning system, it is necessary to carry out targeted meteorological monitoring and early warning for the actual operation of the power grid equipment and the environment in which it is located. If the data lacks pertinence, the warning effect may be greatly reduced.

[0006] To this end, the present invention provides a method, system and storage medium for dynamic monitoring and early warning of a power grid based on meteorological information. Summary of the invention

[0007] 1. Technical issues to be solved

[0008] In view of the deficiencies in the prior art, the present invention provides a method, system and storage medium for dynamic monitoring and early warning of power grids based on meteorological information. The present invention collects temperature, humidity, air pressure, wind speed and precipitation in real time, analyzes and outputs predicted temperature, humidity, air pressure, wind speed and precipitation data, analyzes real-time power grid equipment temperature, voltage, current, active power and reactive power data, and outputs predicted power grid equipment temperature, voltage, current, active power and reactive power data. Signs of extreme weather events (such as heavy rain, typhoon, drought, etc.) can be discovered in advance, thereby enhancing disaster early warning capabilities, and potential problems in power grid operation can be discovered in a timely manner, which helps to optimize energy scheduling and allocation, thereby solving the technical problems recorded in the background technology.

[0009] (II) Technical solution

[0010] To achieve the above objectives, the present invention is implemented through the following technical solutions: a method for dynamic monitoring and early warning of power grid based on meteorological information, comprising the following steps:

[0011] Collect temperature, humidity, air pressure, wind speed, and precipitation to build a meteorological database. Collect power grid equipment temperature, voltage, current, active power, and reactive power to build a power grid operation database. Transmit meteorological data and power grid operation data to a data center or cloud platform.

[0012] Used to analyze the real-time temperature, humidity, air pressure, wind speed, and precipitation data, and output the predicted temperature, humidity, air pressure, wind speed, and precipitation data; and to analyze the real-time power grid equipment temperature, voltage, current, active power, and reactive power data, and output the predicted power grid equipment temperature, voltage, current, active power, and reactive power data;

[0013] According to the historical operation data of the power grid, the normal range of each power grid operation data is obtained, and it is judged whether the predicted temperature Wd, voltage Dy, current Dl, active power Yg, and reactive power Wg data are respectively within the normal range, and a power grid operation warning is sent out.

[0014] Furthermore, temperature sensors are used to measure ambient temperature, and common ones include thermistors and thermocouples. Humidity sensors measure ambient humidity, and common ones include capacitive and resistive humidity sensors. Pressure sensors are used to measure atmospheric pressure, and common ones include piezoresistive and piezoelectric pressure sensors. Wind speed sensors are used to measure wind speed, and common ones include mechanical (such as wind cup) and ultrasonic. Precipitation sensors are used to measure precipitation, and common ones include tipping bucket rain gauges and laser rain sensors.

[0015] Voltage transformer (PT) and current transformer (CT) are basic devices used to measure voltage and current in power grids. PT converts high voltage to low voltage, and CT converts high current to low current for easy measurement and transmission. These transformers are usually used in conjunction with power meters to achieve accurate measurement of voltage and current.

[0016] A power meter is a meter specifically used to measure active power and reactive power. It calculates the power value by measuring the phase difference and amplitude of voltage and current. In modern power systems, multifunctional power meters often have integrated the function of a power meter, which can measure and display active power and reactive power at the same time.

[0017] Furthermore, the meteorological data and power grid operation data are transmitted to the data center or cloud platform via wired (such as RS-485, CAN bus, etc.) or wireless (such as LoRa, NB-IoT, 4G / 5G, etc.) means.

[0018] Furthermore, the meteorological dataset is divided into training set, validation set and test set, with the division ratio of 70% training set, 15% validation set and 15% test set. The training set is used to train the model, the validation set is used to adjust the model parameters, and the test set is used to evaluate the model performance. A meteorological prediction model is built based on the regression model, the model is trained using the training set data, the trained model is verified using the validation set data, and the meteorological prediction model is derived.

[0019] Furthermore, the collected real-time temperature, humidity, air pressure, wind speed, and precipitation data are imported into the meteorological prediction model to output the predicted temperature, humidity, air pressure, wind speed, and precipitation data.

[0020] Furthermore, the power grid operation data set is divided into training set, validation set and test set, with the division ratio of 70% training set, 15% validation set and 15% test set. The training set is used to train the model, the validation set is used to adjust the model parameters, and the test set is used to evaluate the model performance. A power grid operation prediction model is built based on the regression model, the model is trained using the training set data, the trained model is verified using the validation set data, and the power grid operation prediction model is derived.

[0021] Regression model is a commonly used data analysis method, which is mainly used to predict and understand the relationship between variables. By establishing a mathematical model, regression analysis can find out how one or more independent variables (independent variables) affect the dependent variable (dependent variable). This model is widely used in many fields, such as economy, society, medicine, education, etc. There are many types of regression models, including linear regression, logistic regression, polynomial regression, ridge regression, lasso regression, etc. Among them, linear regression is the most basic and commonly used model. In the linear regression model, the dependent variable is continuous, the independent variable can be continuous or discrete, and the nature of the regression line is linear. It establishes a relationship between the dependent variable and one or more independent variables through the best fit straight line (i.e., regression line). The regression model can quantify the degree of influence of the independent variable on the dependent variable and help understand the specific relationship between the variables. Through the regression model, the future value of the dependent variable can be predicted to provide a basis for decision making. In addition, the regression model can handle the situation of multiple independent variables, and the scope of application of the model can be expanded by introducing nonlinear terms.

[0022] Furthermore, the predicted temperature, humidity, air pressure, wind speed, precipitation data and the power grid equipment temperature, voltage, current, active power, and reactive power data are imported into the power grid operation prediction model to output the predicted temperature, voltage, current, active power, and reactive power data.

[0023] Furthermore, the normal range of each power grid operation data is obtained based on the historical operation data of the power grid, the normal range of temperature is (min(Wd), max(Wd)), the normal range of voltage is (min(Dy), max(Dy)), the normal range of current is (min(Dl), max(Dl)), the normal range of active power is (min(Yg), max(Yg)), and the normal range of reactive power is (min(Wg), max(Wg));

[0024] Among them, min(Wd) is the minimum temperature at which the power grid can operate normally in history, max(Wd) is the maximum temperature at which the power grid can operate normally in history, min(Dy) is the minimum voltage at which the power grid can operate normally in history, max(Dy) is the maximum voltage at which the power grid can operate normally in history, min(Dl) is the minimum current at which the power grid can operate normally in history, max(Dl) is the maximum current at which the power grid can operate normally in history, min(Yg) is the minimum active power at which the power grid can operate normally in history, max(Yg) is the maximum active power at which the power grid can operate normally in history, min(Wg) is the minimum reactive power at which the power grid can operate normally in history, and max(Wg) is the maximum reactive power at which the power grid can operate normally in history.

[0025] Furthermore, it is determined whether the predicted temperature Wd, voltage Dy, current Dl, active power Yg, and reactive power Wg data are respectively within the normal range. If they are within the normal range, 1 is returned, otherwise 0 is returned. If 0 is returned, a power grid operation warning is sent out.

[0026] Furthermore, the return value of each predicted power grid operation data is obtained, summed up, and recorded as the predicted abnormality index. If the predicted abnormality index is less than 4, a power grid operation warning is sent out.

[0027] A power grid dynamic monitoring and early warning system based on meteorological information, comprising:

[0028] The meteorological data acquisition module includes a meteorological data acquisition unit and a power grid data acquisition unit. The meteorological data acquisition unit is used to collect temperature, humidity, air pressure, wind speed, and precipitation to build a meteorological database. The power grid data acquisition unit is used to collect power grid equipment temperature, voltage, current, active power, and reactive power to build a power grid operation database.

[0029] The data analysis module includes a meteorological data analysis unit and a power grid operation data analysis unit. The meteorological data analysis unit is used to analyze the real-time temperature, humidity, air pressure, wind speed, and precipitation data, and output the predicted temperature, humidity, air pressure, wind speed, and precipitation data. The power grid operation data analysis unit is used to analyze the real-time power grid equipment temperature, voltage, current, active power, and reactive power data, and output the predicted power grid equipment temperature, voltage, current, active power, and reactive power data.

[0030] The early warning release module obtains the predicted temperature Wd, voltage Dy, current Dl, active power Yg, and reactive power Wg data, analyzes whether each operating data is within the normal range, and sends out power grid operation early warnings.

[0031] A meteorological information-based power grid dynamic monitoring and early warning storage medium stores a computer program. When the computer program is executed by a processor, the processor executes the steps of a meteorological information-based power grid dynamic monitoring and early warning method.

[0032] (III) Beneficial effects

[0033] The present invention provides a method, system and storage medium for dynamic monitoring and early warning of a power grid based on meteorological information, which has the following beneficial effects:

[0034] 1. Collecting temperature, humidity, air pressure, wind speed, and precipitation to build a meteorological database; collecting power grid equipment temperature, voltage, current, active power, and reactive power to build a power grid operation database can ensure the comprehensiveness and accuracy of the data, which is crucial to improving the accuracy of weather forecasts, real-time monitoring of the operating status of the power grid, timely detection of potential faults and early warning, and ensuring the safe and stable operation of the power grid.

[0035] 2. Analyze the real-time temperature, humidity, air pressure, wind speed, and precipitation data, and output the predicted temperature, humidity, air pressure, wind speed, and precipitation data. Analyze the real-time power grid equipment temperature, voltage, current, active power, and reactive power data, and output the predicted power grid equipment temperature, voltage, current, active power, and reactive power data. Signs of extreme weather events (such as heavy rain, typhoons, droughts, etc.) can be discovered in advance, thereby enhancing disaster warning capabilities, and potential problems in power grid operation can be discovered in a timely manner, which helps to optimize energy scheduling and allocation.

[0036] 3. Obtain the predicted temperature Wd, voltage Dy, current Dl, active power Yg, and reactive power Wg data, analyze whether each operating data is within the normal range, and send out power grid operation warnings. Through the early warning system, potential problems can be discovered and handled in a timely manner to avoid the expansion of problems and more serious consequences. This helps reduce equipment maintenance costs and extend the service life of equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 A schematic diagram of a flow chart of a method for dynamic monitoring and early warning of a power grid based on meteorological information according to the present invention;

[0038] Figure 2 The present invention is a schematic structural diagram of a power grid dynamic monitoring and early warning system based on meteorological information. DETAILED DESCRIPTION

[0039] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. 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 creative work are within the scope of protection of the present invention.

[0040] See also Figure 1 The present invention provides a method for dynamic monitoring and early warning of a power grid based on meteorological information, comprising the following steps:

[0041] Step 1: Collect the temperature, humidity, air pressure, wind speed, and precipitation to build a meteorological database. Collect the temperature, voltage, current, active power, and reactive power of power grid equipment to build a power grid operation database. Transmit the meteorological data and power grid operation data to the data center or cloud platform.

[0042] The step 1 includes the following contents:

[0043] Step 101: collect temperature, humidity, air pressure, wind speed, and precipitation to build a meteorological database.

[0044] Temperature sensors are used to measure ambient temperature. Common sensors include thermistors and thermocouples. Humidity sensors are used to measure ambient humidity. Common sensors include capacitive and resistive humidity sensors. Pressure sensors are used to measure atmospheric pressure. Common sensors include piezoresistive and piezoelectric pressure sensors. Wind speed sensors are used to measure wind speed. Common sensors include mechanical (such as wind cup) and ultrasonic. Precipitation sensors are used to measure precipitation. Common sensors include tipping bucket rain gauges and laser rain gauges.

[0045] Step 102: Collect the temperature, voltage, current, active power and reactive power of the power grid equipment to build a power grid operation database.

[0046] Voltage transformer (PT) and current transformer (CT) are basic devices used to measure voltage and current in power grids. PT converts high voltage to low voltage, and CT converts high current to low current for easy measurement and transmission. These transformers are usually used in conjunction with power meters to achieve accurate measurement of voltage and current.

[0047] A power meter is a meter specifically used to measure active power and reactive power. It calculates the power value by measuring the phase difference and amplitude of voltage and current. In modern power systems, multifunctional power meters often have integrated the function of a power meter, which can measure and display active power and reactive power at the same time.

[0048] Step 103: Transmit the meteorological data and power grid operation data to a data center or cloud platform via wired (such as RS-485, CAN bus, etc.) or wireless (such as LoRa, NB-IoT, 4G / 5G, etc.) means.

[0049] When using, combine the contents in steps 101 to 103:

[0050] By collecting data on air temperature, humidity, air pressure, wind speed, and precipitation to build a meteorological database, and collecting data on power grid equipment temperature, voltage, current, active power, and reactive power to build a power grid operation database, we can ensure the comprehensiveness and accuracy of the data, which is crucial to improving the accuracy of weather forecasts, monitoring the operating status of the power grid in real time, promptly discovering potential faults and issuing early warnings, and ensuring the safe and stable operation of the power grid.

[0051] Step 2: Analyze the real-time temperature, humidity, air pressure, wind speed, and precipitation data, and output the predicted temperature, humidity, air pressure, wind speed, and precipitation data; and analyze the real-time power grid equipment temperature, voltage, current, active power, and reactive power data, and output the predicted power grid equipment temperature, voltage, current, active power, and reactive power data.

[0052] The step 2 includes the following contents:

[0053] Step 201, divide the meteorological data set into a training set, a validation set and a test set, with a division ratio of 70% training set, 15% validation set and 15% test set. The training set is used to train the model, the validation set is used to adjust the model parameters, and the test set is used to evaluate the model performance. Build a meteorological prediction model based on the regression model, use the training set data to train the model, and use the validation set data to verify the trained model, and derive the meteorological prediction model.

[0054] The sample code of the weather forecast model is as follows:

[0055] import pandas as pd

[0056] from sklearn.model_selection import train_test_split

[0057] from sklearn.preprocessing import StandardScaler

[0058] #Suppose there is a CSV file containing this data

[0059] data=pd.read_csv('weather_data.csv')

[0060] #Assume that the CSV file has the following columns: timestamp, temperature, humidity, pressure, wind_speed, precipitation

[0061] #And timestamp has been converted to a format suitable for model processing (such as year, month, day, hour, etc.)

[0062] #Extract features and target variables

[0063] X=data.drop(['temperature','humidity','pressure','wind_speed','precipitation'],axis=1)

[0064] y=data[['temperature','humidity','pressure','wind_speed','precipitation']]

[0065] # Divide the dataset

[0066] X_train,X_test,y_train,y_test=train_test_split(X,y,test_size=0.2,random_state=42)

[0067] #Feature scaling

[0068] scaler = StandardScaler()

[0069] X_train_scaled=scaler.fit_transform(X_train)

[0070] X_test_scaled=scaler.transform(X_test)

[0071] from sklearn.ensemble import RandomForestRegressor

[0072] from sklearn.multioutput import MultiOutputRegressor

[0073] # Initialize multi-output random forest regressor

[0074] regressor=MultiOutputRegressor(RandomForestRegressor(n_estimators=100,random_state=42))

[0075] #Train model

[0076] regressor.fit(X_train_scaled,y_train)

[0077] #Predict the test set

[0078] y_pred=regressor.predict(X_test_scaled)

[0079] #Evaluation model (RMSE is used as an example here)

[0080] from sklearn.metrics import mean_squared_error

[0081] def rmse(y_true,y_pred):

[0082] return np.sqrt(mean_squared_error(y_true,y_pred))

[0083] #Calculate the RMSE for each meteorological variable

[0084] rmse_scores={var:rmse(y_test[var],y_pred[:,i])for i,var in enumerate(y.columns)}

[0085] print(rmse_scores)

[0086] Step 202: Import the collected real-time temperature, humidity, air pressure, wind speed, and precipitation data into the meteorological prediction model, and output the predicted temperature, humidity, air pressure, wind speed, and precipitation data.

[0087] Step 203: Divide the power grid operation data set into a training set, a validation set, and a test set, with a division ratio of 70% training set, 15% validation set, and 15% test set. The training set is used to train the model, the validation set is used to adjust the model parameters, and the test set is used to evaluate the model performance. Build a power grid operation prediction model based on the regression model, use the training set data to train the model, use the validation set data to verify the trained model, and derive the power grid operation prediction model.

[0088] Regression model is a commonly used data analysis method, which is mainly used to predict and understand the relationship between variables. By establishing a mathematical model, regression analysis can find out how one or more independent variables (independent variables) affect the dependent variable (dependent variable). This model is widely used in many fields, such as economy, society, medicine, education, etc. There are many types of regression models, including linear regression, logistic regression, polynomial regression, ridge regression, lasso regression, etc. Among them, linear regression is the most basic and commonly used model. In the linear regression model, the dependent variable is continuous, the independent variable can be continuous or discrete, and the nature of the regression line is linear. It establishes a relationship between the dependent variable and one or more independent variables through the best fit straight line (i.e., regression line). The regression model can quantify the degree of influence of the independent variable on the dependent variable and help understand the specific relationship between the variables. Through the regression model, the future value of the dependent variable can be predicted to provide a basis for decision making. In addition, the regression model can handle the situation of multiple independent variables, and the scope of application of the model can be expanded by introducing nonlinear terms.

[0089] Step 204: Import the predicted temperature, humidity, air pressure, wind speed, precipitation data and the power grid equipment temperature, voltage, current, active power, and reactive power data into the power grid operation prediction model, and output the predicted temperature, voltage, current, active power, and reactive power data.

[0090] When using, combine the contents in steps 201 to 204:

[0091] By analyzing the real-time temperature, humidity, air pressure, wind speed, and precipitation data, and outputting predicted temperature, humidity, air pressure, wind speed, and precipitation data, and analyzing the real-time power grid equipment temperature, voltage, current, active power, and reactive power data, and outputting predicted power grid equipment temperature, voltage, current, active power, and reactive power data, it is possible to detect signs of extreme weather events (such as heavy rains, typhoons, droughts, etc.) in advance, thereby enhancing disaster warning capabilities, and timely discovering potential problems in power grid operations, which helps to optimize energy scheduling and allocation.

[0092] Step 3: Obtain the normal range of each power grid operation data based on the historical power grid operation data, determine whether the predicted temperature Wd, voltage Dy, current Dl, active power Yg, and reactive power Wg data are within the normal range, and send a power grid operation warning to the outside.

[0093] The step three includes the following contents:

[0094] Step 301, obtain the normal range of each power grid operation data based on the historical operation data of the power grid, the normal range of temperature is (min(Wd), max(Wd)), the normal range of voltage is (min(Dy), max(Dy)), the normal range of current is (min(Dl), max(Dl)), the normal range of active power is (min(Yg), max(Yg)), and the normal range of reactive power is (min(Wg), max(Wg)).

[0095] Among them, min(Wd) is the minimum temperature at which the power grid can operate normally in history, max(Wd) is the maximum temperature at which the power grid can operate normally in history, min(Dy) is the minimum voltage at which the power grid can operate normally in history, max(Dy) is the maximum voltage at which the power grid can operate normally in history, min(Dl) is the minimum current at which the power grid can operate normally in history, max(Dl) is the maximum current at which the power grid can operate normally in history, min(Yg) is the minimum active power at which the power grid can operate normally in history, max(Yg) is the maximum active power at which the power grid can operate normally in history, min(Wg) is the minimum reactive power at which the power grid can operate normally in history, and max(Wg) is the maximum reactive power at which the power grid can operate normally in history.

[0096] Step 302: Determine whether the predicted temperature Wd, voltage Dy, current Dl, active power Yg, and reactive power Wg data are within the normal range. If they are within the normal range, return 1 (or 100%), otherwise return 0.

[0097] Step 303: Get the return value of each predicted power grid operation data, sum it up, and record it as the predicted abnormality index. If the predicted abnormality index is less than 4, it means that the current meteorological conditions may cause abnormal power grid operation, and a power grid operation warning is sent out.

[0098] When using, combine the contents in steps 301 to 303:

[0099] Obtain the predicted temperature Wd, voltage Dy, current Dl, active power Yg, and reactive power Wg data, analyze whether each operating data is within the normal range, and send out power grid operation warnings. Through the early warning system, potential problems can be discovered and handled in a timely manner to avoid the expansion of problems and more serious consequences. This helps reduce equipment maintenance costs and extend the service life of equipment.

[0100] See also Figure 2 The present invention provides a power grid dynamic monitoring and early warning system based on meteorological information, comprising:

[0101] The meteorological data acquisition module includes a meteorological data acquisition unit and a power grid data acquisition unit; the meteorological data acquisition unit is used to collect temperature, humidity, air pressure, wind speed, and precipitation to build a meteorological database; the power grid data acquisition unit is used to collect power grid equipment temperature, voltage, current, active power, and reactive power to build a power grid operation database;

[0102] The data analysis module includes a meteorological data analysis unit and a power grid operation data analysis unit. The meteorological data analysis unit is used to analyze the real-time temperature, humidity, air pressure, wind speed, and precipitation data, and output the predicted temperature, humidity, air pressure, wind speed, and precipitation data; the power grid operation data analysis unit is used to analyze the real-time power grid equipment temperature, voltage, current, active power, and reactive power data, and output the predicted power grid equipment temperature, voltage, current, active power, and reactive power data;

[0103] The early warning release module obtains the predicted temperature Wd, voltage Dy, current Dl, active power Yg, and reactive power Wg data, analyzes whether each operating data is within the normal range, and sends out power grid operation early warnings.

[0104] A meteorological information-based power grid dynamic monitoring and early warning storage medium stores a computer program. When the computer program is executed by a processor, the processor executes the steps of a meteorological information-based power grid dynamic monitoring and early warning method.

[0105] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented using software, the above embodiments may be implemented in whole or in part in the form of a computer program product. A person of ordinary skill in the art may appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein may be implemented in electronic hardware, or in a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution.

[0106] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0107] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. A method for dynamic monitoring and early warning of power grid based on meteorological information, characterized in that: The steps include: Collect temperature, humidity, air pressure, wind speed, and precipitation to build a meteorological database. Collect power grid equipment temperature, voltage, current, active power, and reactive power to build a power grid operation database. Transmit meteorological data and power grid operation data to a data center or cloud platform. Used to analyze the real-time temperature, humidity, air pressure, wind speed, and precipitation data, and output the predicted temperature, humidity, air pressure, wind speed, and precipitation data; and to analyze the real-time power grid equipment temperature, voltage, current, active power, and reactive power data, and output the predicted power grid equipment temperature, voltage, current, active power, and reactive power data; According to the historical operation data of the power grid, the normal range of each power grid operation data is obtained, and it is judged whether the predicted temperature Wd, voltage Dy, current Dl, active power Yg, and reactive power Wg data are respectively within the normal range, and a power grid operation warning is sent out.

2. A method for dynamic monitoring and early warning of power grid based on meteorological information according to claim 1, characterized in that: The meteorological dataset is divided into training set, validation set and test set, with the division ratio of 70% training set, 15% validation set and 15% test set. The training set is used to train the model, the validation set is used to adjust the model parameters, and the test set is used to evaluate the model performance. A meteorological prediction model is built based on the regression model, the model is trained using the training set data, the trained model is verified using the validation set data, and the meteorological prediction model is exported.

3. A method for dynamic monitoring and early warning of power grid based on meteorological information according to claim 1, characterized in that: The collected real-time temperature, humidity, air pressure, wind speed and precipitation data are imported into the meteorological prediction model, and the predicted temperature, humidity, air pressure, wind speed and precipitation data are output.

4. A method for dynamic monitoring and early warning of power grid based on meteorological information according to claim 1, characterized in that: The power grid operation data set is divided into training set, validation set and test set, with the division ratio of 70% training set, 15% validation set and 15% test set. The training set is used to train the model, the validation set is used to adjust the model parameters, and the test set is used to evaluate the model performance. A power grid operation prediction model is built based on the regression model, the model is trained using the training set data, the trained model is verified using the validation set data, and the power grid operation prediction model is derived.

5. The method for dynamic monitoring and early warning of a power grid based on meteorological information according to claim 1 is characterized in that: The predicted temperature, humidity, air pressure, wind speed, precipitation data and the power grid equipment temperature, voltage, current, active power and reactive power data are imported into the power grid operation prediction model, and the predicted temperature, voltage, current, active power and reactive power data are output.

6. A method for dynamic monitoring and early warning of power grid based on meteorological information according to claim 1, characterized in that: According to the historical operation data of the power grid, the normal range of each power grid operation data is obtained. The normal range of temperature is (min(Wd), max(Wd)), the normal range of voltage is (min(Dy), max(Dy)), the normal range of current is (min(Dl), max(Dl)), the normal range of active power is (min(Yg), max(Yg)), and the normal range of reactive power is (min(Wg), max(Wg)); Among them, min(Wd) is the minimum temperature at which the power grid can operate normally in history, max(Wd) is the maximum temperature at which the power grid can operate normally in history, min(Dy) is the minimum voltage at which the power grid can operate normally in history, max(Dy) is the maximum voltage at which the power grid can operate normally in history, min(Dl) is the minimum current at which the power grid can operate normally in history, max(Dl) is the maximum current at which the power grid can operate normally in history, min(Yg) is the minimum active power at which the power grid can operate normally in history, max(Yg) is the maximum active power at which the power grid can operate normally in history, min(Wg) is the minimum reactive power at which the power grid can operate normally in history, and max(Wg) is the maximum reactive power at which the power grid can operate normally in history.

7. A method for dynamic monitoring and early warning of power grid based on meteorological information according to claim 1, characterized in that: Determine whether the predicted temperature Wd, voltage Dy, current Dl, active power Yg, and reactive power Wg data are within the normal range. If they are within the normal range, return 1, otherwise return 0. If 0 is returned, a power grid operation warning is sent out.

8. The method for dynamic monitoring and early warning of a power grid based on meteorological information according to claim 1, characterized in that: The return value of each predicted power grid operation data is obtained, and after summing up, it is recorded as the predicted abnormality index. If the predicted abnormality index is less than 4, a power grid operation warning is sent out.

9. A power grid dynamic monitoring and early warning system based on meteorological information, used to implement the method according to any one of claims 1 to 8, comprising: The meteorological data acquisition module includes a meteorological data acquisition unit and a power grid data acquisition unit. The meteorological data acquisition unit is used to collect temperature, humidity, air pressure, wind speed, and precipitation to build a meteorological database. The power grid data acquisition unit is used to collect power grid equipment temperature, voltage, current, active power, and reactive power to build a power grid operation database. The data analysis module includes a meteorological data analysis unit and a power grid operation data analysis unit. The meteorological data analysis unit is used to analyze the real-time temperature, humidity, air pressure, wind speed, and precipitation data, and output the predicted temperature, humidity, air pressure, wind speed, and precipitation data. The power grid operation data analysis unit is used to analyze the real-time power grid equipment temperature, voltage, current, active power, and reactive power data, and output the predicted power grid equipment temperature, voltage, current, active power, and reactive power data. The early warning release module obtains the predicted temperature Wd, voltage Dy, current Dl, active power Yg, and reactive power Wg data, analyzes whether each operating data is within the normal range, and sends out power grid operation early warnings.

10. A power grid dynamic monitoring and early warning storage medium based on meteorological information, characterized in that: The storage medium stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the method for dynamic monitoring and early warning of meteorological information in a power grid as claimed in any one of claims 1 to 8.

Images