TY - GEN
T1 - Reinforcement learning-based differential evolution for solving economic dispatch problems
AU - Visutarrom, Thammarsat
AU - Chiang, Tsung Che
AU - Konak, Abdullah
AU - Kulturel-Konak, Sadan
N1 - Publisher Copyright:
© 2020 IEEE.
PY - 2020/12/14
Y1 - 2020/12/14
N2 - In power systems, economic dispatch (ED) deals with the power allocation of power generation units to meet the power demand and minimize the cost. Many metaheuristics have been proposed to solve the ED problem with promising results. However, the performance of these algorithms might be sensitive to their parameter settings, and parameter tuning requires considerable effort. In this paper, a reinforcement learning (RL)-based differential evolution (DE) is proposed to solve the ED problem. We develop an RL mechanism to adaptively set two critical parameters, crossover rate (CR) and scaling factor (F), of DE. The performance of the proposed RLDE is compared with the canonical DE and several algorithms in the literature using three test systems. Our algorithm shows good solution quality and strong robustness.
AB - In power systems, economic dispatch (ED) deals with the power allocation of power generation units to meet the power demand and minimize the cost. Many metaheuristics have been proposed to solve the ED problem with promising results. However, the performance of these algorithms might be sensitive to their parameter settings, and parameter tuning requires considerable effort. In this paper, a reinforcement learning (RL)-based differential evolution (DE) is proposed to solve the ED problem. We develop an RL mechanism to adaptively set two critical parameters, crossover rate (CR) and scaling factor (F), of DE. The performance of the proposed RLDE is compared with the canonical DE and several algorithms in the literature using three test systems. Our algorithm shows good solution quality and strong robustness.
KW - Differential evolution
KW - Economic dispatch
KW - Reinforcement learning
UR - http://www.scopus.com/inward/record.url?scp=85099737924&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85099737924&partnerID=8YFLogxK
U2 - 10.1109/IEEM45057.2020.9309983
DO - 10.1109/IEEM45057.2020.9309983
M3 - Conference contribution
AN - SCOPUS:85099737924
T3 - IEEE International Conference on Industrial Engineering and Engineering Management
SP - 913
EP - 917
BT - 2020 IEEE International Conference on Industrial Engineering and Engineering Management, IEEM 2020
PB - IEEE Computer Society
T2 - 2020 IEEE International Conference on Industrial Engineering and Engineering Management, IEEM 2020
Y2 - 14 December 2020 through 17 December 2020
ER -