基于极限Q学习算法的微电网自动发电控制

Automatic Generation Control of Micro Grid Based on Extreme Q-learning Algorithm

本文针对分布式电源接入微电网的下垂控制环节,设计基于Q 强化学习改进的极限Q 学习算法,实现自动调频与经济调度同步完成。在Matlab/Simulink 平台上建立5 个节点的仿真模型。仿真结果表明所提算法能有效提高微电网的自动调频能力,能够较好调节分布式电源给系统带来的不确定性和波动性。

In this paper, an extreme Q-learning algorithm based on Q reinforcement learning is designed for the droop control link of the distributed power supply connected to the micro grid to realize synchronous completion of automatic frequency modulation and economic scheduling. A simulation model of 5 nodes was established on Matlab/Simulink platform. Simulation results show that the proposed algorithm can effectively improve the automatic frequency modulation capability of the microgrid, and can better adjust the uncertainty and volatility brought by the distributed power supply to the system.