基于深度学习负荷预测与模型预测控制的水电站AGC协同优化方法及装置
By employing deep learning-based load forecasting and model predictive control methods, combined with multi-source data and multi-objective optimization, the problems of control lag and single optimization objective in hydropower station AGC systems under high-proportion renewable energy grid integration were solved. This approach achieved high-precision forecasting and collaborative optimization, thereby improving grid stability and hydropower station operational efficiency.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- QU ZHOU SHI XIN AN SHUI DIAN KAI FA YOU XIAN GONG SI
- Filing Date
- 2025-11-17
- Publication Date
- 2026-07-17
AI Technical Summary
Existing hydropower station AGC systems suffer from control lag, low precision, poor adaptability, and a single optimization objective when facing a high proportion of renewable energy grid connection, making it difficult to cope with the challenges of drastic fluctuations in grid power and new energy output.
A method based on deep learning load forecasting and model predictive control is adopted. By fusing real-time data from multiple sources, a hybrid deep learning model (such as Transformer-LSTM) is used to perform high-precision ACE forecasting. Under the model predictive control (MPC) framework, a multi-objective optimization function is designed to collaboratively optimize the unit's operating performance, including power point tracking accuracy, equipment wear, operating efficiency, and safety and stability.
It achieves high-precision and forward-looking prediction of the ACE signal of the power grid, improves the power point tracking accuracy and the frequency stability of the power grid, optimizes the operation economy and equipment health of hydropower stations, ensures the safety of the units and the reliability of the system, and adapts to the long-term evolution of the power grid structure and unit characteristics.
Smart Images
Figure CN121367187B_ABST
Abstract
Citation Information
Patent Citations
Method for multi-source cooperative participation in system load frequency control
CN116526511A
Wind power plant AGC optimization control method and system based on model predictive control
CN120896268A