Q-Learning based Maximum Power Point Tracking Control for Microbial Fuel Cell

• Published in: International journal of electrochemical science Vol. 15; no. 10; pp. 9917 - 9932
• Main Authors: Fan, Li-ping, Feng, Xiang
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.10.2020
• Subjects: greedy policy; maximum power point tracking; microbial fuel cell; perturbation and observation; Q-Learning; perturbation and observation; Q-Learning; microbial fuel cell; greedy policy; maximum power point tracking
• ISSN: 1452-3981; 1452-3981
• DOI: 10.20964/2020.10.63

Microbial fuel cell (MFC) is a promising technology for wastewater treatment with simultaneous bioenergy production. To improve the power generation efficiency of MFCs, maximum power point tracking control is a good choice. Three kinds of Q-Learning-based maximum power point tracking control scheme based on s-greedy exploration, Boltzmann exploration and greedy policy are proposed for MFCs. The results show that the maximum power point tracking control based on Q-Learning has better power tracking capabilities than perturbation and observation method. With the introduction of Q- Learning based on greedy policy, the time required for MFC to stabilize at the maximum power point is greatly shortened by setting the action list of Q-Learning reasonably. In this case, the whole process from start-up to stabilization at the maximum power point was 42.9% faster than that of MFC using s- greedy exploration, and 50% faster than that of MFC using Boltzmann exploration. Q-Learning algorithm based on greedy policy is an effective method to realize MPPT in MFC system.