基于时空注意力LSTM的负荷需求预测方法、模型和构建方法
By capturing the correlation between renewable energy output and load demand changes using a spatiotemporal attention LSTM model, the problem of insufficient load forecasting accuracy in high-proportion renewable energy scenarios is solved, achieving more accurate load demand forecasting and supporting reliable power system dispatch.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- 山东智源电力设计咨询有限公司
- Filing Date
- 2025-11-25
- Publication Date
- 2026-07-17
AI Technical Summary
Traditional load forecasting methods struggle to effectively mine spatiotemporal multidimensional information in scenarios with a high proportion of renewable energy, leading to a significant decrease in forecast accuracy.
A load demand forecasting method based on spatiotemporal attention LSTM is adopted. The spatiotemporal attention model adaptively captures the multidimensional correlation characteristics of new energy output, charging and discharging regulation and load demand changes, and uses LSTM network to learn its long-term time series dependencies to build a forecasting model.
It significantly improves the accuracy of load forecasting, provides a more reliable basis for power system dispatch and energy management, and adapts to multi-scale spatiotemporal dynamic changes in scenarios with a high proportion of new energy sources.
Smart Images
Figure CN121546554B_ABST