Skip to main navigation Skip to search Skip to main content

Distribution Network Reconfiguration Using Deep Reinforcement Learning

  • Mukesh Gautam
  • , Mohammed Benidris

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

11 Scopus citations

Abstract

This paper proposes a deep reinforcement learning (DRL)-based framework for distribution network reconfiguration (DNR). The objective of the proposed framework is to minimize power losses in the network and various reliability indices including System Average Interruption Frequency Index (SAIFI), System Average Interruption Duration Index (SAIDI), and Average Curtailed Power (ACP). Constraints of the optimization problem are radial topology constraint and all nodes traversing constraint. The distribution network is modeled as a graph and the optimal network configuration is determined by searching for an optimal spanning tree. Contrary to existing analytical and population-based approaches, where the entire analysis and computation is to be repeated to find the optimal network configuration for each system operating state, DRL-based DNR, if properly trained, can determine optimal or near-optimal configuration quickly even with changes in system states. The Q-learning, a model-free reinforcement learning algorithm, is used by the proposed DRL-based framework to learn the action-value function. The effectiveness and efficacy of the proposed framework for DNR is demonstrated through a case study performed on 33-node distribution test system.

Original languageEnglish
Title of host publication2022 17th International Conference on Probabilistic Methods Applied to Power Systems, PMAPS 2022
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781665412117
DOIs
StatePublished - 2022
Externally publishedYes
Event17th International Conference on Probabilistic Methods Applied to Power Systems, PMAPS 2022 - Manchester, United Kingdom
Duration: Jun 12 2022Jun 15 2022

Publication series

Name2022 17th International Conference on Probabilistic Methods Applied to Power Systems, PMAPS 2022

Conference

Conference17th International Conference on Probabilistic Methods Applied to Power Systems, PMAPS 2022
Country/TerritoryUnited Kingdom
CityManchester
Period06/12/2206/15/22

Keywords

  • and spanning trees
  • Deep Q Network
  • distribution system reliability
  • network reconfiguration
  • reinforcement learning

Fingerprint

Dive into the research topics of 'Distribution Network Reconfiguration Using Deep Reinforcement Learning'. Together they form a unique fingerprint.

Cite this