Reinforcement learning-based differential evolution for solving economic dispatch problems

Thammarsat Visutarrom, Tsung Che Chiang, Abdullah Konak, Sadan Kulturel-Konak

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

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.

Original languageEnglish (US)
Title of host publication2020 IEEE International Conference on Industrial Engineering and Engineering Management, IEEM 2020
PublisherIEEE Computer Society
Pages913-917
Number of pages5
ISBN (Electronic)9781538672204
DOIs
StatePublished - Dec 14 2020
Event2020 IEEE International Conference on Industrial Engineering and Engineering Management, IEEM 2020 - Virtual, Singapore, Singapore
Duration: Dec 14 2020Dec 17 2020

Publication series

NameIEEE International Conference on Industrial Engineering and Engineering Management
Volume2020-December
ISSN (Print)2157-3611
ISSN (Electronic)2157-362X

Conference

Conference2020 IEEE International Conference on Industrial Engineering and Engineering Management, IEEM 2020
CountrySingapore
CityVirtual, Singapore
Period12/14/2012/17/20

All Science Journal Classification (ASJC) codes

  • Business, Management and Accounting (miscellaneous)
  • Industrial and Manufacturing Engineering
  • Safety, Risk, Reliability and Quality

Fingerprint Dive into the research topics of 'Reinforcement learning-based differential evolution for solving economic dispatch problems'. Together they form a unique fingerprint.

Cite this