Dispatching thermostatically controlled loads for frequency regulation using adversarial multi-armed bandits

Amr Mohamed, Antoine Lesage-Landry, Joshua A. Taylor

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

5 Scopus citations

Abstract

Utilizing residential Thermostatically Controlled Loads (TCLs) for demand response stands to offer a more economical and environmentally friendly alternative to procuring energy storage and generation facilities for grid ancillary services. We use the adversarial multi-armed bandit framework to learn the signal response of TCLs and determine which TCLs to activate for demand response in real-time. We demonstrate the performance of our proposed approach by invoking theoretical bounds on the performance of an Exp3.M-based algorithm, and comparing the performance with a greedy algorithm. A sub-linear regret shows that the algorithm is able to learn and identify high-performing TCLs, and activate them more frequently as more information is acquired about the TCLs' signal response.

Original languageEnglish (US)
Title of host publication2017 IEEE Electrical Power and Energy Conference, EPEC 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1-6
Number of pages6
ISBN (Electronic)9781538608173
DOIs
StatePublished - Jul 2 2017
Externally publishedYes
Event2017 IEEE Electrical Power and Energy Conference, EPEC 2017 - Saskatoon, Canada
Duration: Oct 22 2017Oct 25 2017

Publication series

Name2017 IEEE Electrical Power and Energy Conference, EPEC 2017
Volume2017-October

Conference

Conference2017 IEEE Electrical Power and Energy Conference, EPEC 2017
Country/TerritoryCanada
CitySaskatoon
Period10/22/1710/25/17

All Science Journal Classification (ASJC) codes

  • Electrical and Electronic Engineering
  • Renewable Energy, Sustainability and the Environment
  • Energy Engineering and Power Technology

Keywords

  • demand response
  • frequency regulation
  • multi-armed bandit
  • online learning
  • thermostatically controlled loads

Fingerprint

Dive into the research topics of 'Dispatching thermostatically controlled loads for frequency regulation using adversarial multi-armed bandits'. Together they form a unique fingerprint.

Cite this