FUKUYAMA Yoshikazu    Department   Undergraduate School  , School of Interdisciplinary Mathematical Sciences    Position   Professor
Date	2018/11/06
Presentation Theme	Swarm Reinforcement Learning to Operational Planning of Energy Plants
Conference	Workshop on System and Smart Facility Technologies in IEE of Japan
Promoters	System Technology and Smart Facility Technology Comittees in IEE of Japan
Conference Type	Workshop/Symposium
Presentation Type	Speech (General)
Contribution Type	Collaborative
Venue	Kagurazaka Campus, Tokyo University of Science
Publisher and common publisher	Mayuko Sato, Yoshikazu Fukuyama
Details	This paper proposes operation planning of energy plants in mid and small buildings by swarm reinforcement learning in order to reduce engineering man-hours. Although it takes many man-hours to develop optimization methods based operational planning, utilization of swarm reinforcement learning has a possibility to reduce the engineering man-hours. The results of the proposed method are compared with those of a basic Q learning based method and a basic particle swarm optimization based method. It is verified that energy cost can be reduced by the proposed method more than those by the original Q-learning based method.