Abstract
Electricity disaggregation focuses on identifying individual appliances from one or more aggregate signals. By reporting detailed appliance usage to consumers, disaggregation has the potential to significantly reduce electrical waste in residential and commercial sectors. However, application of existing methods is limited by two critical shortcomings. First, supervised learning methods implicitly assume error- free labels in training data, an unrealistic expectation for imperfectly-labeled consumer data. Second, supervised and unsupervised learning methods require parameters to be tuned to individual appliances and/or datasets, limiting widespread application. To address these limitations, this paper introduces the implementation of Bayesian changepoint detection (BCD) with necessary adaptations to electricity disaggregation. We introduce an algorithm to effectively apply BCD to automatically correct labels. We then apply BCD to event detection to identify transitions between appliances' on and off states. Performance is evaluated using 3 publicly available datasets containing over 250 appliances across 11 houses. Results show both BCD applications are competi-Tive and in some cases outperform existing state-of-The-Art methods without the need for parameter tuning, advancing disaggregation towards widespread, real-world deployment.
Original language | English (US) |
---|---|
Title of host publication | 16th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2017 |
Editors | Sanmay Das, Edmund Durfee, Kate Larson, Michael Winikoff |
Publisher | International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS) |
Pages | 990-998 |
Number of pages | 9 |
ISBN (Electronic) | 9781510855076 |
State | Published - 2017 |
Event | 16th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2017 - Sao Paulo, Brazil Duration: May 8 2017 → May 12 2017 |
Publication series
Name | Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS |
---|---|
Volume | 2 |
ISSN (Print) | 1548-8403 |
ISSN (Electronic) | 1558-2914 |
Other
Other | 16th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2017 |
---|---|
Country/Territory | Brazil |
City | Sao Paulo |
Period | 5/8/17 → 5/12/17 |
Bibliographical note
Publisher Copyright:© Copyright 2017, International Foundation for Autonomous Agents and Multiagent Systems (www.ifaamas.org). All rights reserved.
Keywords
- Change detection
- Electricity disaggregation
- Event detection
- Label correction
- Supervised unsupervised learning