Distributed Reinforcement Learning Algorithm for Dynamic Economic Dispatch with Unknown Generation Cost Functions

Pengcheng Dai, Wenwu Yu, Guanghui Wen, Simone Baldi

Research output: Contribution to journalArticleScientificpeer-review

27 Downloads (Pure)

Abstract

In this article, the dynamic economic dispatch (DED) problem for smart grid is solved under the assumption that no knowledge of the mathematical formulation of the actual generation cost functions is available. The objective of the DED problem is to find the optimal power output of each unit at each time so as to minimize the total generation cost. To address the lack of a priori knowledge, a new distributed reinforcement learning optimization algorithm is proposed. The algorithm combines the state-action-value function approximation with a distributed optimization based on multiplier splitting. Theoretical analysis of the proposed algorithm is provided to prove the feasibility of the algorithm, and several case studies are presented to demonstrate its effectiveness.

Original languageEnglish
Pages (from-to)2258-2267
JournalIEEE Transactions on Industrial Informatics
Volume16
Issue number4
DOIs
Publication statusPublished - 2020

Keywords

  • Distributed reinforcement learning
  • dynamic economic dispatch (DED)
  • multiplier splitting
  • state-action-value function approximation

Fingerprint Dive into the research topics of 'Distributed Reinforcement Learning Algorithm for Dynamic Economic Dispatch with Unknown Generation Cost Functions'. Together they form a unique fingerprint.

  • Cite this