Double deep Q-networks for optimizing electricity cost of a water heater

Kadir Amasyali, Kuldeep Kurte, Helia Zandi, Jeffrey Munk, Olivera Kotevska, Robert Smith

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

4 Scopus citations

Abstract

Electric water heaters represent 14% of the electricity consumption in the residential buildings and the cost associated with domestic water heating account for a good portion of the household expenses in the United States. In this context, intelligent control of water heaters gained a lot of research attention. In recent years, a significant number of intelligent water heater controllers, with various methods and intended uses, have been proposed. However, existing studies are mostly model-based approaches that require an accurate modelling of the water heater. Towards addressing this research gap, this paper presents a model-free reinforcement learning-based controller for a day-ahead price market. The controller aims to minimize the cost of domestic water heating while maintaining the user comfort. The results showed that the developed controller can help save energy cost while maintaining the temperatures within the desired comfort band.

Original languageEnglish
Title of host publication2021 IEEE Power and Energy Society Innovative Smart Grid Technologies Conference, ISGT 2021
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781728188973
DOIs
StatePublished - Feb 16 2021
Event2021 IEEE Power and Energy Society Innovative Smart Grid Technologies Conference, ISGT 2021 - Washington, United States
Duration: Feb 16 2021Feb 18 2021

Publication series

Name2021 IEEE Power and Energy Society Innovative Smart Grid Technologies Conference, ISGT 2021

Conference

Conference2021 IEEE Power and Energy Society Innovative Smart Grid Technologies Conference, ISGT 2021
Country/TerritoryUnited States
CityWashington
Period02/16/2102/18/21

Keywords

  • Artificial neural networks
  • Deep Q-networks
  • Deep reinforcement learning
  • Water heater

Fingerprint

Dive into the research topics of 'Double deep Q-networks for optimizing electricity cost of a water heater'. Together they form a unique fingerprint.

Cite this