一种配变负荷预测及重过载预警方法及系统
By combining temporal convolutional networks and extreme gradient boosting tree models, the problems of prediction accuracy and external factors in distribution transformer load forecasting are solved, achieving high-precision distribution transformer load forecasting and heavy overload early warning, thus ensuring the stable operation of the power system.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- STATE GRID HUNAN ELECTRIC POWER COMPANY LIMITED
- Filing Date
- 2022-11-09
- Publication Date
- 2026-07-17
AI Technical Summary
Existing technologies for distribution transformer load forecasting suffer from low forecast accuracy, significant influence from external factors, and inaccurate judgment of peak times, resulting in insufficient accuracy in early warning of heavy overload of distribution transformers.
A method combining temporal convolutional networks and extreme gradient boosting tree models is adopted. By performing feature analysis and cleaning on load measurement data and weather data in the power distribution area, a high-quality time series sample set is generated. The model parameters are optimized using a Bayesian optimization algorithm to perform load forecasting and heavy overload early warning.
It improves the accuracy of distribution transformer load forecasting and heavy overload early warning, enabling early assessment of distribution transformer operational risks and ensuring a balance between power supply and demand.
Smart Images
Figure CN115587672B_ABST