Power system county power demand dynamic prediction method and system
By constructing a general time-series prediction knowledge base and the TimeMOE model, and combining county-level feature embedding and expert network precise activation, the data acquisition problem in county-level electricity demand forecasting was solved, achieving highly reliable and accurate dynamic forecasting of electricity demand.
CN122198241APending Publication Date: 2026-06-12ECONOMIC TECH RES INST STATE GRID HUNAN ELECTRIC POWER +2
View PDF 0 Cites 0 Cited by
Patent Information
- Application Number
- CN202610339576.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2026-03-19
- Publication Date
- 2026-06-12
AI Technical Summary
Technical Problem
Existing county-level electricity demand forecasting schemes rely on a large amount of high-quality historical data, which is difficult to obtain, resulting in poor reliability and accuracy.
Method used
By constructing a general time-series prediction knowledge base, using the TimeMOE model for zero-sample adaptation, and combining county-level feature embedding and expert network for precise activation, dynamic prediction of electricity demand can be achieved.
Benefits of technology
It achieves highly reliable and accurate electricity demand forecasting even without historical data for the target county, reduces the demand for computing resources, and improves the consistency of multi-scale forecast results.
✦ Generated by Eureka AI based on patent content.
Smart Images
Figure CN122198241A_ABST
Abstract
The application discloses a kind of electric power system county electric power demand dynamic prediction method, including obtaining the data information of target county and its electric power system;General time sequence prediction knowledge base is constructed;Zero sample adaptation of target county scene is carried out;The electric power demand dynamic prediction of target county is carried out;The obtained prediction result is verified and optimized, and the dynamic prediction of the electric power demand of target electric power system county is completed.The application also discloses a kind of system for realizing the electric power system county electric power demand dynamic prediction method.The application not only realizes the dynamic prediction of electric power system county electric power demand, but also has higher reliability, better accuracy.
Need to check novelty before this filing date? Find Prior Art