Towards adaptive anomaly detection in buildings with deep reinforcement learning

Tong Wu, Jorge Ortiz

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

Abstract

In this paper, we present early results on the use of deep reinforcement learning (DRL) for maximizing anomaly detection performance in buildings. We conjecture that DRL can improve performance by exploring the entire parameter space for all sensors, individually. Many anomaly detection algorithms are designed to use a single parameter for ease of use, however there are usually many parameter values that are pre-set, a priori. We hypothesize that a single threshold cannot work well for all sensors and propose the use of DRL to explore the entire parameter space. We use a deterministic policy gradient algorithm - Deep Deterministic Policy Gradient (DDPG)[4] - and use a building-specific anomaly detection algorithm, Strip, Bind, and Search (SBS) [2]. We find that while the maximum performance achieved by both approaches is similar, the DRL-based approach is significantly less biased, more consistent - up to 3x smaller standard deviation across individual sensor scores.

Original languageEnglish (US)
Title of host publicationBuildSys 2019 - Proceedings of the 6th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation
PublisherAssociation for Computing Machinery, Inc
Pages380-382
Number of pages3
ISBN (Electronic)9781450370059
DOIs
StatePublished - Nov 13 2019
Event6th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation, BuildSys 2019 - New York, United States
Duration: Nov 13 2019Nov 14 2019

Publication series

NameBuildSys 2019 - Proceedings of the 6th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation

Conference

Conference6th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation, BuildSys 2019
CountryUnited States
CityNew York
Period11/13/1911/14/19

All Science Journal Classification (ASJC) codes

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

Keywords

  • Anomaly detection
  • HBI
  • Reinforcement learning
  • Smart building

Fingerprint Dive into the research topics of 'Towards adaptive anomaly detection in buildings with deep reinforcement learning'. Together they form a unique fingerprint.

Cite this