微电网内分布式电源与储能功率分配方法
By using a long short-term memory neural network in a microgrid to predict the SOC change trend of an energy storage system and combining it with a fuzzy logic rule base to dynamically adjust the weight coefficients, a multi-objective power allocation model is constructed. This solves the problems of overcharging and over-discharging of the energy storage system and mode switching impact, realizing forward-looking control and seamless switching of the microgrid, and improving the economy and power supply reliability of the grid.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- HEBANG POWER TECH CO LTD
- Filing Date
- 2026-04-29
- Publication Date
- 2026-07-17
AI Technical Summary
Existing microgrid power allocation methods lack the ability to predict future trends, leading to overcharging and over-discharging of energy storage systems, affecting battery life, and easily generating voltage and frequency surges during mode switching, affecting power quality and power supply reliability.
A long short-term memory neural network is used to predict the SOC change trend of the energy storage system. Combined with a fuzzy logic rule base to dynamically adjust the weight coefficients, a multi-objective power allocation model is constructed. Pre-synchronization optimization is performed before mode switching to achieve forward-looking control and seamless switching.
It effectively avoids overcharging and over-discharging of energy storage systems, extends battery life, improves the economy and stability of microgrids, eliminates electrical shocks during mode switching, and improves power quality and power supply reliability.
Smart Images
Figure CN122118982B_ABST