%0 Journal Article
%A KE Zhong-ming
%A LIU Jin-hua
%A ZHOU Wen-hui
%T Reinforcement Learning Based Energy Dispatch Strategy and Control Optimization of Microgrid
%D 2020
%R 10.13190/j.jbupt.2019-040
%J Journal of Beijing University of Posts and Telecommunications
%P 28-34
%V 43
%N 1
%X Aiming at the economic benefit problem, charging efficiency optimization problem, system load fluctuation problem and carbon emissions problem of energy scheduling in microgrid, application of reinforcement learning to energy scheduling in microgrid is presented. By establishing a complete microgrid model and using reinforcement learning to obtain the optimal strategy in the continuous iterative process, economic benefits tended to be maximized, charging power is relatively stable, load fluctuation of the system is reduced, and carbon emissions is tended minimized. These four joint optimization objectives are reached. Simulations show that the control strategy used in this system can not only maximize the convergence of economic benefits and minimize carbon emissions, but also make the charging power relatively stable, and reduce the load of microgrid. The stability of this system will be improved greatly.
%U https://journal.bupt.edu.cn/EN/10.13190/j.jbupt.2019-040