Power load prediction method and device based on intelligent flexible regulation and control terminal

Abstract

The invention provides a power load prediction method and device based on an intelligent flexible regulation and control terminal, and belongs to the technical field of power system control. The method comprises the following steps: collecting historical power load data, meteorological data, holiday and festival arrangement and economic activity data, extracting a load prediction characteristic value based on the historical power load data, and associating the meteorological data, the holiday and festival arrangement and economic activity data with the load prediction characteristic value; in the power load prediction model, defining the associated load prediction characteristic values as input conditions to train the power load prediction model; based on the latest weather forecast data and the latest holiday arrangement, utilizing the trained power load prediction model to predict the power load in a future preset time period; and outputting the power load prediction result to the intelligent flexible regulation and control terminal, so that the intelligent flexible regulation and control terminal automatically adjusts the operation state of the power system based on the power load prediction result. Accurate prediction and intelligent regulation and control of a power system can be realized.

Description

Technical Field

[0001] The present application belongs to the field of power system control technology, and specifically relates to a power load forecasting method and device based on an intelligent flexible control terminal. Background Art

[0002] With socioeconomic development and improved living standards, electricity demand is growing rapidly. Simultaneously, with the large-scale integration of renewable energy into the power grid, the operational characteristics of the power system are becoming more complex and uncertain. Accurate power load forecasting is crucial for ensuring the safe and stable operation of the power system, improving energy efficiency, and reducing environmental pollution.

[0003] However, traditional power load forecasting methods mainly rely on historical load data and lack comprehensive consideration of multiple factors such as meteorological conditions, holiday effects and economic activities, resulting in limited forecasting accuracy and difficulty in meeting the needs of modern power systems. Summary of the Invention

[0004] In order to solve at least one technical problem existing in the background technology, the present application provides a power load forecasting method based on an intelligent flexible control terminal, which can comprehensively consider the influence of multiple factors, has high adaptability, and realizes accurate prediction and intelligent control of the power system.

[0005] A second aspect of the present application provides a power load forecasting device based on an intelligent flexible control terminal.

[0006] The technical solutions adopted in this application are:

[0007] The first embodiment of the present application provides a method for predicting power load based on an intelligent flexible control terminal, comprising:

[0008] Collecting historical power load data, meteorological data, holiday schedules, and economic activity data, extracting load forecast characteristic values based on the historical power load data, and associating the meteorological data, the holiday schedules, and the economic activity data with the load forecast characteristic values;

[0009] In a power load forecasting model, defining the associated load forecasting characteristic value as an input condition to train the power load forecasting model;

[0010] Based on the latest weather forecast data and the latest holiday schedule, the trained power load forecasting model is used to predict the power load within a preset time period in the future;

[0011] The power load prediction result is output to the intelligent flexible control terminal, so that the intelligent flexible control terminal automatically adjusts the operating state of the power system based on the power load prediction result.

[0012] According to the power load forecasting method based on the intelligent flexible control terminal provided in the embodiment of the first aspect of the present application, historical power load data, meteorological data, holiday arrangements and economic activity data are collected, and load forecast characteristic values are extracted based on the historical power load data, and the meteorological data, holiday arrangements and economic activity data are associated with the load forecast characteristic values: This step ensures that the input information of the prediction model is rich and comprehensive by comprehensively collecting data on various factors affecting the power load, thereby improving the prediction accuracy of the model. In particular, associating various types of data with load forecast characteristic values can more accurately capture the impact of different factors on the power load, providing a high-quality data foundation for subsequent model training; in the power load forecasting model, the associated load forecast characteristic values are defined as input conditions to train the power load forecasting model: by using the associated characteristic values as input conditions to train the model, the inherent connections between various data can be fully utilized, and the learning and generalization capabilities of the model can be enhanced. This method not only improves the prediction accuracy of the model, but also enhances the model's adaptability to new data. The power load forecasting model is trained to predict the power load in a preset time period in the future based on the latest weather forecast data and the latest holiday schedule. The latest data is used for prediction to ensure the timeliness and accuracy of the prediction results. Especially during holidays or special weather conditions, this method can timely reflect the impact of these special circumstances on the power load, provide a scientific basis for the dispatch of the power system, and help to take measures in advance to deal with possible load peaks. The power load forecast results are output to the intelligent flexible control terminal so that the intelligent flexible control terminal automatically adjusts the operating state of the power system based on the power load forecast results. By directly applying the prediction results to the intelligent flexible control terminal, the automatic management of the power system is realized, which not only improves the response speed and operating efficiency of the system, but also reduces the errors of human operation and ensures the stable operation of the power system. In addition, the intelligent flexible control terminal can flexibly adjust the operating state of the power system according to the prediction results, further optimize resource allocation and reduce operating costs. In summary, the power load forecasting method based on the intelligent flexible control terminal provided in the first embodiment of the present application, by comprehensively analyzing multiple influencing factors, constructs a high-precision power load forecasting model, and applies it to the intelligent control of the power system, which significantly improves the accuracy of power load forecasting and the operating efficiency of the power system.

[0013] According to one embodiment of the present application, the historical power load data, meteorological data, holiday schedules, and economic activity data are collected, and load forecast feature values are extracted based on the historical power load data, and the meteorological data, the holiday schedules, and the economic activity data are associated with the load forecast feature values, specifically:

[0014] Calculate the daily average load, maximum load, minimum load, standard deviation and variance, and extract the shape of the daily load curve, load growth rate and periodic characteristics;

[0015] The average load, maximum load, minimum load, standard deviation, variance, shape of daily load curve, load growth rate and periodic characteristics are spliced into the load forecast feature value according to timestamps to generate a high-dimensional feature matrix.

[0016] According to one embodiment of the present application, in the power load forecasting model, the associated load forecasting feature value is defined as an input condition to train the power load forecasting model, specifically:

[0017] The associated load forecast feature value is used as the input feature of training data, and the historical power load data is used as the output scalar or time series.

[0018] According to one embodiment of the present application, based on the latest weather forecast data and the latest holiday schedule, the trained power load forecasting model is used to predict the power load within a preset time period in the future, specifically:

[0019] Obtain the latest weather forecast data and the latest holiday schedule, and preprocess and standardize the latest weather forecast data and the latest holiday schedule with the same features used in training the model;

[0020] Combine the latest processed weather forecast data and the latest holiday schedule with the load forecast characteristic values to construct the characteristic matrix required for prediction;

[0021] The constructed feature matrix is input into the trained power load forecasting model to generate power load forecast results within a future preset time period.

[0022] According to one embodiment of the present application, the constructed feature matrix is input into a trained power load forecasting model to generate a power load forecast result for a preset time period in the future, specifically:

[0023] Convert the feature matrix into the number of samples, time steps and features;

[0024] The sample number, the time step and the characteristic number are input into the power load forecasting model to generate a power load forecast result within a future preset time period, and the power load forecast result is inversely normalized to restore it to the original load value.

[0025] According to one embodiment of the present application, the outputting of the power load forecast result to the intelligent flexible control terminal so that the intelligent flexible control terminal automatically adjusts the operating state of the power system based on the power load forecast result is specifically:

[0026] Transmitting the power load forecast result to the intelligent flexible control terminal through a communication interface;

[0027] Based on the power load forecast result, the generator output, energy storage device charging and discharging status and load distribution of the power system are adjusted.

[0028] According to one embodiment of the present application, the method further includes:

[0029] Display the comparison results between the power load forecast results and the actual load data through a visualization tool;

[0030] Based on the comparison results, the model training data set is updated according to a preset period.

[0031] A second embodiment of the present application provides a power load forecasting device based on an intelligent flexible control terminal, comprising:

[0032] a data association module, configured to collect historical power load data, meteorological data, holiday schedules, and economic activity data, extract load forecast characteristic values based on the historical power load data, and associate the meteorological data, the holiday schedules, and the economic activity data with the load forecast characteristic values;

[0033] A model training module, configured to define the associated load prediction characteristic value as an input condition in a power load prediction model to train the power load prediction model;

[0034] The power load forecasting module is used to predict the power load within a preset time period in the future based on the latest weather forecast data and the latest holiday schedule using the trained power load forecasting model;

[0035] The control module is used to output the power load forecast result to the intelligent flexible control terminal, so that the intelligent flexible control terminal automatically adjusts the operating state of the power system based on the power load forecast result.

[0036] An embodiment of the third aspect of the present application provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, the power load forecasting method based on the intelligent flexible control terminal as described in any embodiment of the first aspect as described above is implemented.

[0037] The fourth aspect of the present application provides a non-volatile computer storage medium storing computer executable instructions. When the computer executes the executable instructions, it implements the power load forecasting method based on the intelligent flexible control terminal in any embodiment of the first aspect as described above. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0039] Figure 1 A flow chart of a method for predicting power load based on an intelligent flexible control terminal according to an embodiment of the present application;

[0040] Figure 2 A schematic diagram of the structure of a power load forecasting device based on an intelligent flexible control terminal provided in an embodiment of the present application;

[0041] Figure 3 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application.

[0042] Reference numerals:

[0043] 110. Data association module; 120. Model training module; 130. Power load forecasting module; 140. Control module;

[0044] 810 , processor; 820 , communication interface; 830 , memory; 840 , communication bus. DETAILED DESCRIPTION

[0045] In order to more clearly illustrate the overall concept of the present application, a detailed description is given below in an illustrative manner in conjunction with the accompanying drawings.

[0046] The following description sets forth many specific details to facilitate a thorough understanding of the present application. However, the present application may also be implemented in other ways than those described herein, and therefore, the scope of protection of the present application is not limited by the specific embodiments disclosed below. It should be noted that the embodiments of the present application and the features of each embodiment may be combined with each other unless there is a conflict.

[0047] In this application, unless otherwise expressly specified and limited, a first feature "above" or "below" a second feature may be that the first and second features are in direct contact, or the first and second features are in indirect contact through an intermediate medium. In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in an appropriate manner in any one or more embodiments or examples.

[0048] like Figure 1 As shown, the first embodiment of the present application provides a method for predicting power load based on an intelligent flexible control terminal, comprising:

[0049] Step 100: Collect historical power load data, meteorological data, holiday schedules and economic activity data, extract load forecast feature values based on the historical power load data, and associate the meteorological data, holiday schedules and economic activity data with the load forecast feature values.

[0050] Step 200: In the power load forecasting model, the associated load forecasting feature value is defined as an input condition to train the power load forecasting model.

[0051] Step 300: Based on the latest weather forecast data and the latest holiday schedule, the trained power load forecasting model is used to forecast the power load within a preset time period in the future.

[0052] Step 400: Output the power load forecast result to the intelligent flexible control terminal, so that the intelligent flexible control terminal automatically adjusts the operating state of the power system based on the power load forecast result.

[0053] In step 100, historical power load data is the most basic input data, including power load records at various time points over a period of time. This data reflects the actual operation of the power system and is the basis for predicting future loads.

[0054] Meteorological data includes meteorological parameters such as temperature, humidity, wind speed, and precipitation. Meteorological conditions have a significant impact on power load. For example, hot weather usually leads to increased electricity consumption for air conditioning, while cold weather may lead to increased electricity consumption for heating.

[0055] Holiday arrangements include statutory holidays, weekends, and special events (such as major sporting events, important conferences, etc.). Holidays and special events affect people's daily lives and work patterns, which in turn affects power load.

[0056] Economic activity data includes economic indicators such as industrial production, commercial activity, and household consumption. Changes in economic activity directly affect electricity demand. For example, electricity demand is generally higher during economic booms, while it may decline during economic recessions.

[0057] Useful characteristic values are extracted from historical power load data, such as daily load curves, weekly load curves, monthly load curves, etc. These characteristic values can reflect the periodic and trend changes of load.

[0058] Feature extraction methods can include statistical analysis, time series analysis, spectrum analysis, etc., with the goal of extracting information useful for prediction from large amounts of data.

[0059] The extracted load forecast feature values are associated with meteorological data, holiday schedules, and economic activity data. The key to this step is to find the inherent connections between these data, such as the relationship between temperature and load, and the relationship between holidays and load.

[0060] Data association can be achieved through correlation analysis, regression analysis, machine learning, etc. The purpose is to build a comprehensive data set containing multiple influencing factors for subsequent model training.

[0061] By comprehensively considering multiple influencing factors, the model can more comprehensively capture the changing patterns of power load, thereby improving forecast accuracy. Single-factor models often fail to fully explain load fluctuations, while multi-factor models can better reflect actual conditions. By correlating multiple data sets, the model can better handle abnormal data and noise, improving its adaptability and stability in diverse environments. For example, even in extreme weather or emergencies, the model can still provide reliable forecasts. Accurate load forecasting helps power systems prepare resources in advance, rationalize power generation plans and scheduling strategies, and avoid supply and demand imbalances caused by sudden load fluctuations. This not only improves system efficiency but also reduces operating costs.

[0062] In step 200, by using multiple feature values as input, the model can more comprehensively capture the diverse factors that influence power load fluctuations, thereby improving forecast accuracy. Single-feature models often fail to fully explain load fluctuations, while multi-feature models can better reflect actual conditions. Multi-feature input enables the model to process data from diverse environments and conditions, improving its generalization capabilities. For example, even in extreme weather or emergencies, the model can still provide reliable forecasts.

[0063] In step 300, the latest weather forecast data includes the predicted values of weather parameters such as temperature, humidity, wind speed, precipitation, etc. in the next few days or weeks. These data can be obtained from the meteorological bureau or other professional weather service providers.

[0064] The latest holiday schedule includes the dates of statutory holidays, weekends, and special events (such as major sporting events, important conferences, etc.) in the coming period. This information can be obtained from government announcements, news media, and other channels.

[0065] If necessary, the latest economic activity data, such as industrial production, business activities, consumer spending and other indicators, can also be collected to further improve the accuracy of the forecast.

[0066] Using the latest weather forecast data and holiday schedule information, forecast results reflect current and future realities in a timely manner. This helps the power system prepare for potential load fluctuations and avoid supply and demand imbalances caused by emergencies. Real-time forecast updates enable the power system to quickly adjust its operating status, such as preemptively starting backup generators and adjusting load distribution on transmission lines. This improves system flexibility and responsiveness, ensuring the stability and reliability of power supply.

[0067] In summary, step 300 predicts the power load within a preset time period in the future by utilizing the latest weather forecast data and holiday schedule information, combined with a trained power load forecasting model, which significantly improves the timeliness and accuracy of the forecast and provides strong technical support for the intelligent management and optimized operation of the power system.

[0068] In step 400, after receiving the prediction results, the control terminal analyzes the data and extracts key information, such as the predicted load value and predicted time period. Based on the prediction results, the decision module within the control terminal conducts analysis and judgment to determine the optimal control strategy. For example, it may decide whether to activate backup generators or adjust the load distribution of transmission lines. Based on the results of the decision module, specific control actions are executed, such as adjusting the output power of the generators or controlling the opening and closing of load switches. After executing the control actions, the control terminal can monitor the system's operating status in real time and feed actual operating data back to the prediction model to continuously optimize the prediction and control strategies.

[0069] Intelligent flexible control terminals receive real-time power load forecasts and respond immediately to adjust the power system's operating status. This significantly improves system responsiveness and ensures timely and stable power supply. Based on these forecasts, the control terminals can proactively activate backup generators and adjust load distribution on transmission lines to avoid supply-demand imbalances caused by sudden load changes. This helps optimize resource allocation and improve system efficiency.

[0070] In summary, step 400 achieves automated management and optimized operation of the power system by outputting the power load forecast results to the intelligent flexible control terminal. This process significantly improves the system's response speed, resource utilization, and operational efficiency.

[0071] According to the power load forecasting method based on the intelligent flexible control terminal provided in the embodiment of the first aspect of the present application, historical power load data, meteorological data, holiday arrangements and economic activity data are collected, and load forecast characteristic values are extracted based on the historical power load data, and the meteorological data, holiday arrangements and economic activity data are associated with the load forecast characteristic values: This step ensures that the input information of the prediction model is rich and comprehensive by comprehensively collecting data on various factors affecting the power load, thereby improving the prediction accuracy of the model. In particular, associating various types of data with load forecast characteristic values can more accurately capture the impact of different factors on the power load, providing a high-quality data foundation for subsequent model training; in the power load forecasting model, the associated load forecast characteristic values are defined as input conditions to train the power load forecasting model: by using the associated characteristic values as input conditions to train the model, the inherent connections between various data can be fully utilized, and the learning and generalization capabilities of the model can be enhanced. This method not only improves the prediction accuracy of the model, but also enhances the model's adaptability to new data. The power load forecasting model is trained to predict the power load in a preset time period in the future based on the latest weather forecast data and the latest holiday schedule. The latest data is used for prediction to ensure the timeliness and accuracy of the prediction results. Especially during holidays or special weather conditions, this method can timely reflect the impact of these special circumstances on the power load, provide a scientific basis for the dispatch of the power system, and help to take measures in advance to deal with possible load peaks. The power load forecast results are output to the intelligent flexible control terminal so that the intelligent flexible control terminal automatically adjusts the operating state of the power system based on the power load forecast results. By directly applying the prediction results to the intelligent flexible control terminal, the automatic management of the power system is realized, which not only improves the response speed and operating efficiency of the system, but also reduces the errors of human operation and ensures the stable operation of the power system. In addition, the intelligent flexible control terminal can flexibly adjust the operating state of the power system according to the prediction results, further optimize resource allocation and reduce operating costs. In summary, the power load forecasting method based on the intelligent flexible control terminal provided in the first embodiment of the present application, by comprehensively analyzing multiple influencing factors, constructs a high-precision power load forecasting model, and applies it to the intelligent control of the power system, which significantly improves the accuracy of power load forecasting and the operating efficiency of the power system.

[0072] In some embodiments of the present application, historical power load data, meteorological data, holiday schedules, and economic activity data are collected, and load forecast feature values are extracted based on the historical power load data. The meteorological data, holiday schedules, and economic activity data are associated with the load forecast feature values, specifically:

[0073] Calculate the daily average load, maximum load, minimum load, standard deviation and variance, and extract the shape of the daily load curve, load growth rate and periodic characteristics;

[0074] The average load, maximum load, minimum load, standard deviation, variance, shape of daily load curve, load growth rate and periodic characteristics are spliced into the load forecast feature value according to the timestamp to generate a high-dimensional feature matrix.

[0075] Specifically, by extracting a variety of detailed load characteristic values, such as average load, maximum load, minimum load, standard deviation, variance, daily load curve shape, load growth rate, and periodic characteristics, the model can more comprehensively capture the changing patterns of power load. This significantly improves load forecasting accuracy, especially in situations with large load fluctuations. The high-dimensional feature matrix contains rich information, enabling the model to better handle data under diverse environments and conditions, improving its generalization capabilities. For example, the model can still provide reliable forecasts under special circumstances such as extreme weather or holidays. By extracting and combining multiple characteristic values in detail, it is possible to more accurately select the features that have the greatest impact on forecast results. This not only improves model efficiency but also reduces waste of computing resources. By linking meteorological data, holiday schedules, and economic activity data with load characteristic values, the model can comprehensively consider the influence of multiple factors. This helps to identify interactions between different factors and provides more comprehensive support for power system decision-making.

[0076] In some embodiments of the present application, in the power load forecasting model, the associated load forecasting feature value is defined as an input condition to train the power load forecasting model, specifically:

[0077] The associated load forecast feature values are used as input features of the training data, and the historical power load data are used as the output scalar or time series.

[0078] The historical power load data is used as a scalar or time series output. Specifically, the power load value of a certain time period in the future (such as the next day, week, etc.) can be used as the output label.

[0079] By incorporating multiple detailed load characteristics as input features, the model can more comprehensively capture the changing patterns of power load, significantly improving the accuracy of load forecasting, especially under conditions of large load fluctuations.

[0080] In some embodiments of the present application, based on the latest weather forecast data and the latest holiday schedule, the trained power load forecasting model is used to predict the power load within a preset time period in the future, specifically:

[0081] Obtain the latest weather forecast data and the latest holiday schedule, and preprocess and standardize the latest weather forecast data and the latest holiday schedule with the same features used in training the model;

[0082] Combine the latest processed weather forecast data and the latest holiday schedule with the load forecast characteristic values to construct the characteristic matrix required for prediction;

[0083] The constructed feature matrix is input into the trained power load forecasting model to generate the power load forecast results for the future preset time period.

[0084] Specifically, obtain weather forecast data for the next few days or weeks from the Meteorological Bureau or other professional meteorological service providers, including temperature, humidity, wind speed, precipitation, etc. Obtain the dates of statutory holidays, weekends, and special events (such as major sporting events, important meetings, etc.) in the coming period from government announcements, news media, and other channels.

[0085] Using the latest weather forecast data and holiday schedule information, forecast results can promptly reflect current and future realities. This helps the power system prepare for possible load fluctuations and avoid supply and demand imbalances caused by emergencies. Real-time updated forecast results enable the power system to quickly adjust its operating status, such as preemptively starting backup generators and adjusting the load distribution of transmission lines. This improves the system's flexibility and responsiveness, ensuring the stability and reliability of power supply. Accurate load forecasts help the power system rationally plan power generation and dispatch strategies, avoiding unnecessary resource waste. For example, power generation capacity can be increased in advance during peak load periods and reduced during low load periods, thereby optimizing resource utilization and reducing operating costs.

[0086] In summary, by obtaining the latest weather forecast data and holiday schedule information, combined with the trained power load forecasting model, the power load within the preset time period in the future is predicted, which significantly improves the timeliness and accuracy of the forecast.

[0087] In some embodiments of the present application, the constructed feature matrix is input into a trained power load forecasting model to generate a power load forecast result for a preset time period in the future, specifically:

[0088] Convert the feature matrix into the number of samples, time steps and features;

[0089] The number of samples, time step and feature number are input into the power load forecasting model to generate the power load forecast results for the future preset time period, and the power load forecast results are denormalized to restore them to the original load value.

[0090] Specifically, determine the number of samples in the feature matrix, that is, the number of data points in each time period. For example, if you are predicting load for the next week, with each day as a sample, then the number of samples is 7.

[0091] Determine the time step size of each sample, that is, the number of time points contained in each sample. For example, if each sample contains 24 hours of data, the time step size is 24.

[0092] Determine the number of features within each time step, that is, the number of features at each time point. For example, if there are 5 features at each time point (average load, maximum load, minimum load, temperature, humidity), the number of features is 5.

[0093] Convert the feature matrix into a format suitable for model input, typically a 3D array (number of samples, time steps, number of features). For example, for a load forecast for the next week, the feature matrix has a shape of (7, 24, 5).

[0094] Through inverse normalization processing, the standardized prediction results generated by the model are restored to the original load values, so that the prediction results can be directly used in practical applications, improving the usability and interpretability of the prediction results.

[0095] In some embodiments of the present application, the power load forecast result is output to the intelligent flexible control terminal so that the intelligent flexible control terminal automatically adjusts the operating state of the power system based on the power load forecast result, specifically:

[0096] Transmit the power load forecast results to the intelligent flexible control terminal through the communication interface;

[0097] Adjust the generator output, energy storage device charging and discharging status, and load distribution of the power system based on the power load forecast results.

[0098] Communication interface selection: Select an appropriate communication interface to transmit the power load forecast results to the intelligent flexible control terminal. Common communication interfaces include:

[0099] MQTT: Suitable for IoT devices, supports publish / subscribe mode, lightweight and low power consumption.

[0100] HTTP / HTTPS: Applicable to web services, supporting data transmission and reception.

[0101] Modbus: Suitable for industrial control systems, supports serial communication and TCP / IP communication.

[0102] OPC UA: Suitable for industrial automation systems, supporting security and interoperability.

[0103] Data format conversion: Convert the power load forecast results into a data format that can be recognized and processed by the intelligent flexible control terminal, such as JSON, XML or CSV.

[0104] Data transmission: The prediction results are transmitted to the intelligent flexible control terminal through the selected communication interface to ensure the security and reliability of data transmission.

[0105] Based on the received load forecast results, analyze the future load change trend. For example, determine whether the load will rise or fall sharply within a certain period of time.

[0106] Strategy generation: Generate corresponding control strategies based on load forecast results. Common control strategies include:

[0107] Generator output adjustment: Adjust the generator output according to the predicted load value to ensure sufficient power supply without over-generation.

[0108] Adjustment of the charging and discharging status of energy storage equipment: During the low load period, the energy storage equipment is used to charge; during the peak load period, the energy storage equipment is released to smooth the load curve.

[0109] Load distribution adjustment: According to the load forecast results, adjust the load distribution of the transmission lines and optimize the operating status of the power system.

[0110] Based on the generated control strategy, specific control commands are generated, such as commands to adjust generator output, control the charging and discharging of energy storage devices, and adjust load distribution.

[0111] Command execution: Send the generated control commands to the corresponding actuators, such as generator controllers, energy storage device controllers, load switches, etc.

[0112] Status Monitoring: After executing a command, the system monitors the power system's operating status in real time to ensure effective implementation of control strategies. If an abnormal situation occurs, the system promptly adjusts the strategy or issues an alarm.

[0113] In some embodiments of the present application, the method further comprises:

[0114] Use visualization tools to show the comparison between power load forecast results and actual load data;

[0115] Based on the comparison results, the model training dataset is updated according to the preset period.

[0116] You can choose from a variety of visualization tools, such as Matplotlib, Seaborn, Plotly, Tableau, etc. Using interactive visualization tools (such as Plotly and Tableau) can provide more interactive functions, such as zooming, hovering to display detailed information, etc.

[0117] You can also generate charts:

[0118] Line chart: Draw a line chart of the predicted load and actual load to visually show the comparison between the two.

[0119] Scatter plot: Draw a scatter plot of the predicted load and actual load to observe the relationship between the two.

[0120] Error Plot: Plots a graph of the prediction error (the difference between the predicted value and the actual value) to evaluate the accuracy of the prediction.

[0121] Heat map: Draw a heat map of load forecast and actual load to show the load distribution in different time periods.

[0122] Chart analysis:

[0123] Trend analysis: Observe the trends of predicted load and actual load, and analyze the accuracy of the prediction results.

[0124] Error analysis: Calculate common error metrics such as root mean square error (RMSE), mean absolute error (MAE), coefficient of determination (R 2 ), etc., to evaluate the accuracy of the prediction.

[0125] Anomaly detection: Identify anomalies in prediction results and analyze possible causes, such as data collection errors and model overfitting.

[0126] By regularly updating the model training dataset, the model can continuously learn from new data and improve the accuracy and robustness of predictions.

[0127] like Figure 2 As shown, the second embodiment of the present application provides a power load forecasting device based on an intelligent flexible control terminal, comprising:

[0128] The data association module 110 is used to collect historical power load data, meteorological data, holiday schedules, and economic activity data, extract load forecast feature values based on the historical power load data, and associate the meteorological data, holiday schedules, and economic activity data with the load forecast feature values;

[0129] A model training module 120 is used to define the associated load prediction feature value as an input condition in the power load prediction model to train the power load prediction model;

[0130] The power load forecasting module 130 is used to forecast the power load within a preset time period in the future based on the latest weather forecast data and the latest holiday schedule using the trained power load forecasting model;

[0131] The control module 140 is used to output the power load forecast result to the intelligent flexible control terminal, so that the intelligent flexible control terminal automatically adjusts the operating state of the power system based on the power load forecast result.

[0132] The power load prediction device based on the intelligent flexible control terminal provided in the second aspect embodiment of this application can realize the power load prediction method based on the intelligent flexible control terminal in any embodiment of the first aspect above, and thus can realize any technical effect of the power load prediction method based on the intelligent flexible control terminal above, which will not be repeated here.

[0133] like Figure 3 As shown, the third aspect of the present application provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, the power load forecasting method based on the intelligent flexible control terminal in any of the above embodiments is implemented.

[0134] Figure 3 An example of a physical structure diagram of an electronic device is shown below. Figure 3 As shown, the electronic device may include: a processor 810, a communication interface 820, a memory 830, and a communication bus 840, wherein the processor 810, the communication interface 820, and the memory 830 communicate with each other via the communication bus 840. The processor 810 may call the logic instructions in the memory 830 to execute the power load forecasting method based on the intelligent flexible control terminal in any of the above embodiments, which may specifically include:

[0135] Step 100: Collect historical power load data, meteorological data, holiday schedules and economic activity data, extract load forecast feature values based on the historical power load data, and associate the meteorological data, holiday schedules and economic activity data with the load forecast feature values.

[0136] Step 200: In the power load forecasting model, the associated load forecasting feature value is defined as an input condition to train the power load forecasting model.

[0137] Step 300: Based on the latest weather forecast data and the latest holiday schedule, the trained power load prediction model is used to predict the power load within a preset time period in the future.

[0138] Step 400: Output the power load forecast result to the intelligent flexible control terminal, so that the intelligent flexible control terminal automatically adjusts the operating state of the power system based on the power load forecast result.

[0139] In addition, the logic instructions in the above-mentioned memory 830 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0140] In another aspect, the present invention further provides a non-volatile computer storage medium storing computer-executable instructions. When a computer executes the executable instructions, the method for predicting power load based on an intelligent flexible control terminal in any of the above embodiments is implemented. The method may specifically include:

[0141] Step 100: Collect historical power load data, meteorological data, holiday schedules and economic activity data, extract load forecast feature values based on the historical power load data, and associate the meteorological data, holiday schedules and economic activity data with the load forecast feature values.

[0142] Step 200: In the power load forecasting model, the associated load forecasting feature value is defined as an input condition to train the power load forecasting model.

[0143] Step 300: Based on the latest weather forecast data and the latest holiday schedule, the trained power load forecasting model is used to forecast the power load within a preset time period in the future.

[0144] Step 400: Output the power load forecast result to the intelligent flexible control terminal, so that the intelligent flexible control terminal automatically adjusts the operating state of the power system based on the power load forecast result.

[0145] Anything not described in this application can be achieved by adopting or drawing on existing technologies.

[0146] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments.

[0147] The foregoing is merely an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should all be included in the protection scope of the present application.

Claims

1. A method for predicting power load based on intelligent flexible control terminal, characterized in that: include: Collecting historical power load data, meteorological data, holiday schedules, and economic activity data, extracting load forecast characteristic values based on the historical power load data, and associating the meteorological data, the holiday schedules, and the economic activity data with the load forecast characteristic values; In a power load forecasting model, defining the associated load forecasting characteristic value as an input condition to train the power load forecasting model; Based on the latest weather forecast data and the latest holiday schedule, the trained power load forecasting model is used to predict the power load within a preset time period in the future; The power load prediction result is output to the intelligent flexible control terminal, so that the intelligent flexible control terminal automatically adjusts the operating state of the power system based on the power load prediction result.

2. The power load forecasting method based on intelligent flexible control terminal according to claim 1 is characterized in that: The collecting of historical power load data, meteorological data, holiday schedules, and economic activity data, extracting load forecast characteristic values based on the historical power load data, and associating the meteorological data, the holiday schedules, and the economic activity data with the load forecast characteristic values, is specifically as follows: Calculate the daily average load, maximum load, minimum load, standard deviation and variance, and extract the shape of the daily load curve, load growth rate and periodic characteristics; The average load, maximum load, minimum load, standard deviation, variance, shape of daily load curve, load growth rate and periodic characteristics are spliced into the load forecast feature value according to timestamps to generate a high-dimensional feature matrix.

3. The power load forecasting method based on intelligent flexible control terminal according to claim 2 is characterized in that: In the power load forecasting model, the associated load forecasting characteristic value is defined as an input condition to train the power load forecasting model, specifically: The associated load forecast feature value is used as the input feature of training data, and the historical power load data is used as the output scalar or time series.

4. The power load forecasting method based on intelligent flexible control terminal according to claim 1 is characterized in that: Based on the latest weather forecast data and the latest holiday schedule, the trained power load forecasting model is used to predict the power load in a preset time period in the future, specifically: Obtain the latest weather forecast data and the latest holiday schedule, and preprocess and standardize the latest weather forecast data and the latest holiday schedule with the same features used in training the model; Combine the latest processed weather forecast data and the latest holiday schedule with the load forecast characteristic values to construct the characteristic matrix required for prediction; The constructed feature matrix is input into the trained power load forecasting model to generate power load forecast results within a future preset time period.

5. The power load forecasting method based on intelligent flexible control terminal according to claim 4 is characterized in that: The constructed feature matrix is input into the trained power load forecasting model to generate the power load forecast result within the future preset time period, specifically: Convert the feature matrix into the number of samples, time steps and features; The sample number, the time step and the characteristic number are input into the power load forecasting model to generate a power load forecast result within a future preset time period, and the power load forecast result is inversely normalized to restore it to the original load value.

6. The power load forecasting method based on intelligent flexible control terminal according to claim 1 is characterized in that: Outputting the power load forecast result to the intelligent flexible control terminal so that the intelligent flexible control terminal automatically adjusts the operating state of the power system based on the power load forecast result is specifically: Transmitting the power load forecast result to the intelligent flexible control terminal through a communication interface; Based on the power load forecast result, the generator output, energy storage device charging and discharging status and load distribution of the power system are adjusted.

7. The power load forecasting method based on intelligent flexible control terminal according to claim 1 is characterized in that: The method also includes: Display the comparison results between the power load forecast results and the actual load data through a visualization tool; Based on the comparison results, the model training data set is updated according to a preset period.

8. A power load forecasting device based on an intelligent flexible control terminal, characterized in that: include: a data association module, configured to collect historical power load data, meteorological data, holiday schedules, and economic activity data, extract load forecast characteristic values based on the historical power load data, and associate the meteorological data, the holiday schedules, and the economic activity data with the load forecast characteristic values; A model training module, configured to define the associated load prediction characteristic value as an input condition in a power load prediction model to train the power load prediction model; The power load forecasting module is used to predict the power load within a preset time period in the future based on the latest weather forecast data and the latest holiday schedule using the trained power load forecasting model; The control module is used to output the power load forecast result to the intelligent flexible control terminal, so that the intelligent flexible control terminal automatically adjusts the operating state of the power system based on the power load forecast result.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the power load forecasting method based on the intelligent flexible control terminal as described in any one of claims 1 to 7 is implemented.

10. A non-volatile computer storage medium storing computer executable instructions, characterized in that: When executing the executable instructions, the computer implements the power load forecasting method based on the intelligent flexible control terminal as described in any one of claims 1 to 7.

Images