A Lightweight Neural Network for Energy Disaggregation Employing Depthwise Separable Convolution

Ruiqi Zhang, Wenpeng Luan, Bo Liu*, Mingjun Zhong

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingPublished conference contribution

1 Citation (Scopus)

Abstract

Non-Intrusive Load Monitoring (NILM) is a blind source separation problem which aims to estimate the electricity usage of individual appliances by decomposing a household's aggregate electricity consumption. Recent state-of-the-art neural network models have delivered a good performance on load disaggregation, however these models have tremendous model size with huge numbers of parameters to tune and require large amounts of data for training, thus are computation and memory demanding, which makes it difficult to be practically implemented. To address this problem, we study the mechanism of depthwise separable convolution and propose a modified convolutional neural network model, which results in a lightweight NILM algorithm with the aim to be deployed on edge devices with limited computation power as mobile phones or smart meters. The lightweight NILM algorithm is evaluated with public available dataset: UKDALE. Assessment results prove that the proposed model delivers acceptable disaggregation performance with dramatically reduced model size and computation requirements.

Original languageEnglish
Title of host publicationProceedings - 2021 IEEE Sustainable Power and Energy Conference
Subtitle of host publicationEnergy Transition for Carbon Neutrality, iSPEC 2021
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages4109-4114
Number of pages6
ISBN (Electronic)9781665414395
DOIs
Publication statusPublished - 2021
Event2021 IEEE Sustainable Power and Energy Conference, iSPEC 2021 - Nanjing, China
Duration: 22 Dec 202124 Dec 2021

Publication series

NameProceedings - 2021 IEEE Sustainable Power and Energy Conference: Energy Transition for Carbon Neutrality, iSPEC 2021

Conference

Conference2021 IEEE Sustainable Power and Energy Conference, iSPEC 2021
Country/TerritoryChina
CityNanjing
Period22/12/2124/12/21

Keywords

  • Depthwise separable convolution
  • Lightweight neural network
  • Non-intrusive load monitoring

Fingerprint

Dive into the research topics of 'A Lightweight Neural Network for Energy Disaggregation Employing Depthwise Separable Convolution'. Together they form a unique fingerprint.

Cite this