One for Many: Transfer Learning for Building HVAC Control

Shichao Xu, Yixuan Wang, Yanzhi Wang, Zheng O'Neill, Qi Zhu

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

5 Scopus citations

Abstract

The design of building heating, ventilation, and air conditioning (HVAC) system is critically important, as it accounts for around half of building energy consumption and directly affects occupant comfort, productivity, and health. Traditional HVAC control methods are typically based on creating explicit physical models for building thermal dynamics, which often require significant effort to develop and are difficult to achieve sufficient accuracy and efficiency for runtime building control and scalability for field implementations. Recently, deep reinforcement learning (DRL) has emerged as a promising data-driven method that provides good control performance without analyzing physical models at runtime. However, a major challenge to DRL (and many other data-driven learning methods) is the long training time it takes to reach the desired performance. In this work, we present a novel transfer learning based approach to overcome this challenge. Our approach can effectively transfer a DRL-based HVAC controller trained for the source building to a controller for the target building with minimal effort and improved performance, by decomposing the design of neural network controller into a transferable front-end network that captures building-agnostic behavior and a back-end network that can be efficiently trained for each specific building. We conducted experiments on a variety of transfer scenarios between buildings with different sizes, numbers of thermal zones, materials and layouts, air conditioner types, and ambient weather conditions. The experimental results demonstrated the effectiveness of our approach in significantly reducing the training time, energy cost, and temperature violations.

Original languageEnglish (US)
Title of host publicationBuildSys 2020 - Proceedings of the 7th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation
PublisherAssociation for Computing Machinery, Inc
Pages230-239
Number of pages10
ISBN (Electronic)9781450380614
DOIs
StatePublished - Nov 18 2020
Event7th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation, BuildSys 2020 - Virtual, Online, Japan
Duration: Nov 18 2020Nov 20 2020

Publication series

NameBuildSys 2020 - Proceedings of the 7th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation

Conference

Conference7th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation, BuildSys 2020
Country/TerritoryJapan
CityVirtual, Online
Period11/18/2011/20/20

Keywords

  • Data-driven
  • Deep reinforcement learning
  • HVAC control
  • Smart Buildings
  • Transfer learning

ASJC Scopus subject areas

  • Renewable Energy, Sustainability and the Environment
  • Electrical and Electronic Engineering
  • Building and Construction
  • Architecture
  • Computer Networks and Communications
  • Information Systems

Fingerprint

Dive into the research topics of 'One for Many: Transfer Learning for Building HVAC Control'. Together they form a unique fingerprint.

Cite this