Machine learning based hybrid energy storage device coordinated control method and system
By using machine learning to predict load spectrum and adaptive control mode, and combining reinforcement learning to optimize power allocation, the lifespan loss problem of mobile energy storage and charging devices under tidal operation characteristics has been solved, achieving a balance between health and efficiency throughout the entire life cycle.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- STATE GRID ANHUI ELECTRIC POWER CO LTD FEIXI POWER SUPPLY CO
- Filing Date
- 2026-05-08
- Publication Date
- 2026-06-05
AI Technical Summary
Existing technologies cannot effectively adapt to the tidal and intermittent operation characteristics of mobile energy storage and charging devices, resulting in accelerated lifespan loss during peak periods and lack of health maintenance during idle periods, making it difficult to achieve the optimal balance between asset health and overall benefits throughout the entire life cycle.
The machine learning-based collaborative control method for hybrid energy storage devices adaptively selects performance-priority, lifespan balancing, maintenance, or economic benefit modes by predicting future load spectra and equipment health status. It also optimizes power allocation by combining reinforcement learning, monitors lifespan loss in real time, and updates control strategies accordingly.
It achieves a balance between performance and economic requirements under different operating scenarios, effectively suppresses the lifespan loss of energy storage components, and ensures the optimization of asset health and overall benefits throughout the entire life cycle of the hybrid energy storage system.
Smart Images
Figure CN122159328A_ABST