Power load prediction system based on AI assistance
By dividing the area into sub-regions and using AI to monitor the electricity consumption during peak and trough periods, calculating the power load balance coefficient and prediction coefficient, the problems of uneven distribution of power resources and the impact of environmental factors are solved, and accurate monitoring of power load is achieved and predict to ensure power balance within the power grid.
Patent Information
- Application Number
- CN202411398468.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-09
- Publication Date
- 2024-11-05
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The existing power load monitoring system lacks monitoring of the unbalanced distribution of power resources in the regional power grid, and ignores the impact of environmental factors on power load, resulting in power supply balance problems and judgment errors.
Using an AI-based power load prediction system, by dividing the management area into sub-regions, monitoring the power consumption during peak and trough periods in real time, calculating the power load equalization coefficient and equalization prediction coefficient, judging and predicting power load abnormalities, ensuring power in the power grid Load balancing.
Effectively monitor and predict power loads, avoid misjudgment caused by environmental factors, ensure the balance and accuracy of power loads in the regional power grid, and improve the management and planning capabilities of the power system.
Smart Images

Figure CN118899849A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of power load monitoring, and in particular to an AI-assisted power load forecasting system. Background Art
[0002] Power load parameters are key indicators that describe the total amount of power or power consumption required by a power system or equipment at a certain moment or over a period of time. Therefore, power load monitoring is of great significance for the planning, operation and management of power systems.
[0003] The existing power load monitoring has the following problems: 1. There are differences in the distribution of power resources in regional power grids. This uneven distribution of resources will lead to differences in power supply. There is currently a lack of monitoring of the balance of power loads in various distribution areas within the regional power grid, which affects the balance of power supply in the entire regional power grid; 2. Currently, the judgment of power load is mostly based on the comparison of real-time load conditions with set targets, ignoring that the power load may be affected by current environmental factors, such as weather, which may lead to errors in judgment. Therefore, this application proposes an AI-assisted power load forecasting system. Summary of the invention
[0004] The purpose of the present invention is to provide an AI-assisted power load forecasting system to solve the above technical problems: The purpose of the present invention can be achieved through the following technical solutions: An AI-assisted power load forecasting system includes: a power load parameter monitoring module, a data processing module, a data analysis module and an evaluation module; The electric load parameter monitoring module is used to monitor the active power data of the electric power in the management area in real time; The data processing module is used to process the active power data acquired by the electric load parameter monitoring module and store it in the system database; The data analysis module is used to analyze the active power data in the system database; The evaluation module is used to predict and evaluate the power load in the management area according to the analysis results of the data analysis module.
[0005] As a further description of the solution of the present invention, the specific working mode of the electric load parameter monitoring module is: Divide the management area into n sub-areas, and number each sub-area in the following order: 1, 2, ..., n; Each day is divided into peak and off-peak hours, and then AI is used to monitor the real-time electricity consumption during peak and off-peak hours in all areas.
[0006] As a further description of the solution of the present invention, the working process of the data analysis module includes: Take 24 hours as a monitoring cycle and obtain the hourly average power consumption during the peak hours of the current monitoring cycle in the i-th sub-area ; Get the hourly average power consumption during the off-peak period of the current monitoring cycle in the i-th sub-area ; Get the hourly average power consumption of the i-th sub-area in the current monitoring period ; Construct a mathematical calculation model for the power load balancing coefficient, the expression is: ; In the formula, , and are the weight coefficients corresponding to the peak period, the trough period and the entire period, respectively, and > > , is the power load index of the ith sub-region in the current cycle, is the weight coefficient corresponding to the i-th sub-region, is the power load balancing coefficient of the i-th sub-region in the current cycle.
[0007] As a further description of the solution of the present invention, the working process of the data analysis module also includes: Obtain the hourly average electricity consumption over time during the peak period of the ith sub-region in each monitoring period within the historical time period, and generate the hourly average electricity consumption over time function during the peak period of the ith sub-region ; Obtain the time-varying data of the hourly average electricity consumption during the off-peak period of the ith sub-region in each monitoring period within the historical time period, and generate the time-varying function of the hourly average electricity consumption during the off-peak period of the ith sub-region ; Obtain the time-varying data of the hourly average electricity consumption of the ith sub-region in each monitoring period during the historical time period, and generate the time-varying function of the hourly average electricity consumption of the ith sub-region ; Construct a mathematical calculation model for the power load balancing prediction coefficient, the expression is: ; In the formula, is the weight coefficient, The cumulative index of power load in the ith sub-region, is the power load balancing prediction coefficient of the i-th sub-region, is the initial monitoring period, The current monitoring period.
[0008] As a further description of the solution of the present invention, the working process of the evaluation module includes: The power load balancing coefficient of the i-th sub-region in the current cycle The power load balancing coefficient threshold of the i-th sub-area is set Compare; If the power load balancing coefficient of the i-th sub-region in the current cycle Greater than or equal to the set power load balancing coefficient threshold of the i-th sub-area , it means that the power load of the ith sub-region in the current cycle is abnormal, and it is recommended to take relevant measures to correct the power load situation of the ith sub-region to ensure the balance of power load in the entire regional power grid; If the power load balancing coefficient of the i-th sub-region in the current cycle Less than the set power load balancing coefficient threshold of the i-th sub-region , it indicates that the power load of the ith sub-region is normal in the current cycle, and predicts whether there is potential abnormality in the power load of the ith sub-region.
[0009] As a further description of the solution of the present invention, the working process of predicting whether there is a potential abnormality in the power load of the i-th sub-area includes: The power load balancing prediction coefficient of the i-th sub-region The power load balancing prediction coefficient threshold of the i-th sub-region is set Compare; If the power load balancing prediction coefficient of the i-th sub-region Greater than or equal to the set power load balancing prediction coefficient threshold of the i-th sub-region , it means that there is a potential abnormality in the power load of the ith sub-region in the current cycle. It is recommended to take relevant measures to correct the power load situation of the ith sub-region to ensure the balance of power load in the entire regional power grid; If the power load balancing prediction coefficient of the i-th sub-region Less than the set power load balancing prediction coefficient threshold of the i-th sub-region , it means that there is no potential abnormality in the power load of the i-th sub-area in the current cycle.
[0010] Beneficial effects of the present invention: 1. The present invention divides a single monitoring cycle into peak time and off-peak time, monitors the hourly average power consumption of a single monitoring cycle in the peak time and off-peak time respectively, and then calculates the power load balancing coefficient of each sub-area in the current cycle according to the hourly average power consumption in the peak time and off-peak time of the current single monitoring cycle and the hourly average power consumption of the current single monitoring cycle, and judges whether the power load of each monitoring sub-area is abnormal according to the power load balancing coefficient. At the same time, in order to avoid misjudgment caused by environmental factors, the present invention calculates the power load balancing prediction coefficient of each monitoring sub-area according to the change of the hourly average power consumption in the peak time and off-peak time over time, and predicts and evaluates whether there is potential abnormality in the power load of each monitoring sub-area according to the power load balancing prediction coefficient, so as to ensure the balance of power load in the regional power grid. BRIEF DESCRIPTION OF THE DRAWINGS
[0011] The present invention will be further described below in conjunction with the accompanying drawings.
[0012] Figure 1 It is a structural schematic diagram of the AI-assisted power load forecasting system of the present invention. DETAILED DESCRIPTION
[0013] 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.
[0014] See also Figure 1 As shown, the present invention provides an AI-assisted power load forecasting system, comprising: a power load parameter monitoring module, a data processing module, a data analysis module and an evaluation module; The electric load parameter monitoring module is used to monitor the active power data of the electric power in the management area in real time; The data processing module is used to process the active power data acquired by the electric load parameter monitoring module and store it in the system database; The data analysis module is used to analyze the active power data in the system database; The evaluation module is used to predict and evaluate the power load in the management area according to the analysis results of the data analysis module.
[0015] Through the above technical scheme, the present application divides a single monitoring cycle into peak hours and off-peak hours, monitors the hourly average electricity consumption of a single monitoring cycle in peak hours and off-peak hours respectively, and then calculates the power load balancing coefficient of the current cycle of each sub-area based on the hourly average electricity consumption in the peak hours and off-peak hours of the current single monitoring cycle and the hourly average electricity consumption of the current single monitoring cycle, and judges whether the power load of each monitoring sub-area is abnormal based on the power load balancing coefficient. At the same time, in order to avoid misjudgment caused by environmental factors, the present application calculates the power load balancing prediction coefficient of each monitoring sub-area based on the changes in the hourly average electricity consumption in the peak hours and off-peak hours over time, and predicts and evaluates whether there is potential abnormality in the power load of each monitoring sub-area based on the power load balancing prediction coefficient, so as to ensure the balance of power load in the regional power grid.
[0016] As a further description of the solution of the present invention, the specific working mode of the electric load parameter monitoring module is: Divide the management area into n sub-areas, and number each sub-area in the following order: 1, 2, ..., n; Each day is divided into peak and off-peak hours, and then AI is used to monitor the real-time electricity consumption during peak and off-peak hours in all areas.
[0017] Through the above technical solution, this application takes into account the differences in the distribution of power resources in the regional power grid, divides the management area into n sub-areas, and numbers each sub-area to ensure the accuracy of the power load forecast.
[0018] As a further description of the solution of the present invention, the working process of the data analysis module includes: Take 24 hours as a monitoring cycle and obtain the hourly average power consumption during the peak period of the current monitoring cycle in the i-th sub-area ; Get the hourly average power consumption during the off-peak period of the current monitoring cycle in the i-th sub-area ; Get the hourly average power consumption of the i-th sub-area in the current monitoring period ; Construct a mathematical calculation model for the power load balancing coefficient, the expression is: ; In the formula, , and are the weight coefficients corresponding to the peak period, the trough period and the entire period, respectively, and > > , is the power load index of the ith sub-region in the current cycle, is the weight coefficient corresponding to the i-th sub-region, is the power load balancing coefficient of the i-th sub-region in the current cycle.
[0019] As a further description of the solution of the present invention, the working process of the evaluation module includes: The power load balancing coefficient of the i-th sub-region in the current cycle The power load balancing coefficient threshold of the i-th sub-area is set Compare; If the power load balancing coefficient of the i-th sub-region in the current cycle Greater than or equal to the set power load balancing coefficient threshold of the i-th sub-area , it means that the power load of the ith sub-region in the current cycle is abnormal, and it is recommended to take relevant measures to correct the power load situation of the ith sub-region to ensure the balance of power load in the entire regional power grid; If the power load balancing coefficient of the i-th sub-region in the current cycle Less than the set power load balancing coefficient threshold of the i-th sub-region , it indicates that the power load of the ith sub-region is normal in the current cycle, and predicts whether there is potential abnormality in the power load of the ith sub-region.
[0020] Through the above technical solution, this embodiment takes 24 hours as a monitoring cycle to obtain the hourly average power consumption during the peak period of the current monitoring cycle in the i-th sub-area. , Average hourly electricity consumption during off-peak hours and hourly average electricity consumption , and then calculate the power load balancing coefficient of the i-th sub-region in the current cycle according to the formula, and convert the power load balancing coefficient of the i-th sub-region in the current cycle into The power load balancing coefficient threshold of the i-th sub-area is set Compare and determine whether the power load of the i-th sub-area in the current cycle is abnormal according to the comparison result.
[0021] As a further description of the solution of the present invention, the working process of the data analysis module also includes: Obtain the hourly average electricity consumption over time during the peak period of the ith sub-region in each monitoring period within the historical time period, and generate the hourly average electricity consumption over time function during the peak period of the ith sub-region ; Obtain the time-varying data of the hourly average electricity consumption during the off-peak period of the ith sub-region in each monitoring period within the historical time period, and generate the time-varying function of the hourly average electricity consumption during the off-peak period of the ith sub-region ; Obtain the time-varying data of the hourly average electricity consumption of the ith sub-region in each monitoring period during the historical time period, and generate the time-varying function of the hourly average electricity consumption of the ith sub-region ; Construct a mathematical calculation model for the power load balancing prediction coefficient, the expression is: ; In the formula, is the weight coefficient, The cumulative index of power load in the ith sub-region, is the power load balancing prediction coefficient of the i-th sub-region, is the initial monitoring period, The current monitoring period.
[0022] As a further description of the solution of the present invention, the working process of predicting whether there is a potential abnormality in the power load of the i-th sub-area includes: The power load balancing prediction coefficient of the i-th sub-region The power load balancing prediction coefficient threshold of the i-th sub-region is set Compare; If the power load balancing prediction coefficient of the i-th sub-region Greater than or equal to the set power load balancing prediction coefficient threshold of the i-th sub-region , it means that there is a potential abnormality in the power load of the ith sub-region in the current cycle. It is recommended to take relevant measures to correct the power load situation of the ith sub-region to ensure the balance of power load in the entire regional power grid; If the power load balancing prediction coefficient of the i-th sub-region Less than the set power load balancing prediction coefficient threshold of the i-th sub-region , it means that there is no potential abnormality in the power load of the i-th sub-area in the current cycle.
[0023] Through the above technical solution, in order to avoid the current cycle being affected by environmental factors and other factors, resulting in misjudgment, this embodiment obtains the hourly average power consumption change data of the peak period of the ith sub-region of each monitoring period in the historical time period, the hourly average power consumption change data of the trough period and the average power consumption change data, and constructs the hourly average power consumption change function of the peak period of the ith sub-region of each monitoring period in the historical time period, the hourly average power consumption change function of the trough period and the average power consumption change function, and then calculates the power load balancing prediction coefficient of the ith sub-region through the formula, and converts the power load balancing prediction coefficient of the ith sub-region into the power load balancing prediction coefficient of the ith sub-region. The power load balancing prediction coefficient threshold of the i-th sub-region is set Compare and predict whether there is potential abnormality in the power load of the i-th sub-area according to the comparison result.
[0024] Working principle: Step S1, divide the management area into n sub-areas, and number each sub-area, the numbers are: 1, 2, ..., n; Step S2, taking 24 hours as a monitoring cycle, obtaining the hourly average power consumption during the peak period, the hourly average power consumption during the off-peak period, and the hourly average power consumption during the current monitoring period of each sub-area; Step S3, calculating the power load balancing coefficient of each sub-area in the current monitoring period; Step S4, judging whether the power load of each sub-area in the current monitoring period is abnormal according to the power load balancing coefficient of each sub-area in the current monitoring period, if there is no abnormality, proceeding to step S6; Step S6, obtaining the hourly average power consumption change data over time during the peak period of each sub-region in each monitoring period, the hourly average power consumption change data over time during the valley period, and the average power consumption change data over time; Step S7, calculating the power load balancing prediction coefficient of each sub-area; Step S8: predict whether there is a potential abnormality in the power load of each sub-region based on the power load balance prediction coefficient of each sub-region.
[0025] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.
Claims
1. An AI-assisted power load forecasting system, characterized in that: include: Electric load parameter monitoring module, data processing module, data analysis module and evaluation module; The electric load parameter monitoring module is used to monitor the active power data of the electric power in the management area in real time; The data processing module is used to process the active power data acquired by the electric load parameter monitoring module and store it in the system database; The data analysis module is used to analyze the active power data in the system database; The evaluation module is used to predict and evaluate the power load in the management area according to the analysis results of the data analysis module.
2. According to claim 1, an AI-assisted power load forecasting system is characterized in that: The specific working mode of the electric load parameter monitoring module is: Divide the management area into n sub-areas, and number each sub-area in the following order: 1, 2, ..., n; Each day is divided into peak and off-peak hours, and then AI is used to monitor the real-time electricity consumption during peak and off-peak hours in all areas.
3. The AI-assisted power load forecasting system according to claim 2 is characterized in that: The working process of the data analysis module includes: Take 24 hours as a monitoring cycle and obtain the hourly average power consumption during the peak period of the current monitoring cycle in the i-th sub-area ; Get the hourly average power consumption during the off-peak period of the current monitoring cycle in the i-th sub-area ; Get the hourly average power consumption of the i-th sub-area in the current monitoring period ; Construct a mathematical calculation model for the power load balancing coefficient, the expression is: ; In the formula, , and are the weight coefficients corresponding to the peak period, the trough period and the entire period, respectively, and > > , is the power load index of the ith sub-region in the current cycle, is the weight coefficient corresponding to the i-th sub-region, is the power load balancing coefficient of the i-th sub-region in the current cycle.
4. The AI-assisted power load forecasting system according to claim 3 is characterized in that: The working process of the data analysis module also includes: Obtain the hourly average electricity consumption over time during the peak period of the ith sub-region in each monitoring period within the historical time period, and generate the hourly average electricity consumption over time function during the peak period of the ith sub-region ; Obtain the time-varying data of the hourly average electricity consumption during the off-peak period of the ith sub-region in each monitoring period within the historical time period, and generate the time-varying function of the hourly average electricity consumption during the off-peak period of the ith sub-region ; Obtain the time-varying data of the hourly average electricity consumption of the ith sub-region in each monitoring period during the historical time period, and generate the time-varying function of the hourly average electricity consumption of the ith sub-region ; Construct a mathematical calculation model for the power load balancing prediction coefficient, the expression is: ; In the formula, is the weight coefficient, The cumulative index of power load in the ith sub-region, is the power load balancing prediction coefficient of the i-th sub-region, is the initial monitoring period, The current monitoring period.
5. The AI-assisted power load forecasting system according to claim 4 is characterized in that: The working process of the evaluation module includes: The power load balancing coefficient of the i-th sub-region in the current cycle The power load balancing coefficient threshold of the i-th sub-area is set Compare; If the power load balancing coefficient of the i-th sub-region in the current cycle Greater than or equal to the set power load balancing coefficient threshold of the i-th sub-area , it means that the power load of the ith sub-region in the current cycle is abnormal, and it is recommended to take relevant measures to correct the power load situation of the ith sub-region to ensure the balance of power load in the entire regional power grid; If the power load balancing coefficient of the i-th sub-region in the current cycle Less than the set power load balancing coefficient threshold of the i-th sub-region , it indicates that the power load of the ith sub-region is normal in the current cycle, and predicts whether there is potential abnormality in the power load of the ith sub-region.
6. The AI-assisted power load forecasting system according to claim 5 is characterized in that: The process of predicting whether there is a potential abnormality in the power load of the i-th sub-area includes: The power load balancing prediction coefficient of the i-th sub-region The power load balancing prediction coefficient threshold of the i-th sub-region is set Compare; If the power load balancing prediction coefficient of the i-th sub-region is greater than or equal to the set power load balancing prediction coefficient threshold of the i-th sub-region , it means that there is a potential abnormality in the power load of the ith sub-region in the current cycle. It is recommended to take relevant measures to correct the power load situation of the ith sub-region to ensure the balance of power load in the entire regional power grid; If the power load balancing prediction coefficient of the i-th sub-region Less than the set power load balancing prediction coefficient threshold of the i-th sub-region , it means that there is no potential abnormality in the power load of the i-th sub-area in the current cycle.
Citation Information
Patent Citations
Short-term power load prediction method based on TSA-LSTM model under peak-valley value characteristics
CN114970961A
Automatic dispatching method and system for smart power grid
CN117895659A
Power load prediction method and system
CN117955094A
Smart community load intelligent management method and system based on big data
CN118569605A
Power distribution and sale competitive situation-based regional power distribution network gridding load interval prediction method
WO2023010759A1
