Lightweight Non-Intrusive Load Monitoring Employing Pruned Sequence-to-Point Learning

Jack Barber, Heriberto Cuayáhuitl, Mingjun Zhong, Wenpeng Luan

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

1 Citation (Scopus)

Abstract

Non-intrusive load monitoring (NILM) is the process in which a household's total power consumption is used to determine the power consumption of household appliances. Previous work has shown that sequence-to-point (seq2point) learning is one of the most promising methods for tackling NILM. This process uses a sequence of aggregate power data to map a target appliance's power consumption at the midpoint of that window of power data. However, models produced using this method contain upwards of thirty million weights, meaning that the models require large volumes of resources to perform disaggregation. This paper addresses this problem by pruning the weights learned by such a model, which results in a lightweight NILM algorithm for the purpose of being deployed on mobile devicessuch as smart meters. The pruned seq2point learning algorithm was applied to the REFIT data, experimentally showing that the performance was retained comparing to the original seq2point learning whilst the number of weights was reduced by 87%. Code:http://github.com/JackBarber98/pruned-nilm

Original languageEnglish
Title of host publicationNILM 2020 - Proceedings of the 5th International Workshop on Non-Intrusive Load Monitoring
PublisherAssociation for Computing Machinery, Inc
Pages11-15
Number of pages5
ISBN (Electronic)9781450381918
DOIs
Publication statusPublished - 18 Nov 2020
Event5th International Workshop on Non-Intrusive Load Monitoring, NILM 2020, co-located with ACM BuildSys 2020 - Virtual, Online, Japan
Duration: 18 Nov 2020 → …

Publication series

NameNILM 2020 - Proceedings of the 5th International Workshop on Non-Intrusive Load Monitoring

Conference

Conference5th International Workshop on Non-Intrusive Load Monitoring, NILM 2020, co-located with ACM BuildSys 2020
Country/TerritoryJapan
CityVirtual, Online
Period18/11/20 → …

Keywords

  • deep learning
  • Energy disaggregation

Fingerprint

Dive into the research topics of 'Lightweight Non-Intrusive Load Monitoring Employing Pruned Sequence-to-Point Learning'. Together they form a unique fingerprint.

Cite this