Predicting Appliance Usage Status in Home Like Environments

Jie Jiang, Mark Hoogendoorn, Qiuqiang Kong, Diederik M. Roijers, Nigel Gilbert

Research output: Chapter in Book / Report / Conference proceedingConference contributionAcademicpeer-review

Abstract

Household activities nowadays heavily rely on electrical and electronic devices, the operation of which are largely reflected in the household energy usage. With the advance of sensor technology, smart meters are increasingly adopted in people's homes, which makes it easier to access finer-grained energy consumption data and more importantly enables the study of household activities via the patterns in energy consumption. In this paper, we investigate the application of k-nearest Neighbours algorithm (k-NN) and Convolutional Neutral Network (CNN) to predict whether specific appliances are being used (on/off status) at different times based on the total energy consumption of a whole house. The experiment results on three types of appliances in one household show that CNN in general achieves better performance than k-NN and both methods perform better on the appliances with relatively large energy consumption.

Original languageEnglish
Title of host publication2018 IEEE 23rd International Conference on Digital Signal Processing, DSP 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781538668115
DOIs
Publication statusPublished - 31 Jan 2019
Event23rd IEEE International Conference on Digital Signal Processing, DSP 2018 - Shanghai, China
Duration: 19 Nov 201821 Nov 2018

Conference

Conference23rd IEEE International Conference on Digital Signal Processing, DSP 2018
CountryChina
CityShanghai
Period19/11/1821/11/18

Keywords

  • activity recognition
  • appliance usage
  • internet of things
  • nonintrusive load monitoring

Fingerprint

Dive into the research topics of 'Predicting Appliance Usage Status in Home Like Environments'. Together they form a unique fingerprint.

Cite this