Learning to shift thermostatically controlled loads

Antoine Lesage-Landry, Joshua A. Taylor

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

8 Scopus citations


Demand response is a key mechanism for accommodating renewable power in the electric grid. Models of loads in demand response programs are typically assumed to be known a priori, leaving the load aggregator the task of choosing the best command. However, accurate load models are often hard to obtain. To address this problem, we propose an online learning algorithm that performs demand response while learning the model of an aggregation of thermostatically controlled loads. Specifically, we combine an adversarial multi-armed bandit framework with a standard formulation of load-shifting. We develop an Exp3-like algorithm to solve the learning problems. Numerical examples based on Ontario load data confirm that the algorithm achieves sub-linear regret and performs within 1% of the ideal case when the load is perfectly known.

Original languageEnglish (US)
Title of host publicationProceedings of the 50th Annual Hawaii International Conference on System Sciences, HICSS 2017
EditorsTung X. Bui, Ralph Sprague
PublisherIEEE Computer Society
Number of pages8
ISBN (Electronic)9780998133102
StatePublished - 2017
Externally publishedYes
Event50th Annual Hawaii International Conference on System Sciences, HICSS 2017 - Big Island, United States
Duration: Jan 3 2017Jan 7 2017

Publication series

NameProceedings of the Annual Hawaii International Conference on System Sciences
ISSN (Print)1530-1605


Conference50th Annual Hawaii International Conference on System Sciences, HICSS 2017
Country/TerritoryUnited States
CityBig Island

All Science Journal Classification (ASJC) codes

  • General Engineering


Dive into the research topics of 'Learning to shift thermostatically controlled loads'. Together they form a unique fingerprint.

Cite this