A preliminary study towards conceptualization and implementation of a load learning model for smart automated demand response

Ajay Singh, Shashank Vyas, Rajesh Kumar

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

6 Citations (Scopus)

Abstract

Demand Response is an essential paradigm under the smart grid framework. The emergence of deregulated markets and dynamic pricing schemes have given an impetus to active participation from the load side. The demand patterns of a residential building show interesting trends that can provide valuable information for predicting the likelihood of occurrence of a particular load at a particular time. This work discusses a data processing and pattern recognition framework for estimating the presence of a particular load at a given instant of time. The domestic appliance data of a household in the United Kingdom has been taken and feature reduction has been applied on the same in order to characterize loads with significant consumption variation. This feature reduced data has been used to forecast the likely consumption for such loads. There are instances of large error however the instances for which load availability is given have shown the correct prediction of trend and value.

Original languageEnglish
Title of host publication2016 IEEE 7th Power India International Conference, PIICON 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781467389624
DOIs
Publication statusPublished - 19 Oct 2017
Externally publishedYes
Event7th IEEE Power India International Conference, PIICON 2016 - Bikaner, Rajasthan, India
Duration: 25 Nov 201627 Nov 2016

Publication series

Name2016 IEEE 7th Power India International Conference, PIICON 2016

Conference

Conference7th IEEE Power India International Conference, PIICON 2016
Country/TerritoryIndia
CityBikaner, Rajasthan
Period25/11/1627/11/16

Keywords

  • Demand response
  • Feature selection
  • Forecasting
  • Machine learning
  • Regression

ASJC Scopus subject areas

  • Energy Engineering and Power Technology
  • Electrical and Electronic Engineering
  • Safety, Risk, Reliability and Quality

Fingerprint

Dive into the research topics of 'A preliminary study towards conceptualization and implementation of a load learning model for smart automated demand response'. Together they form a unique fingerprint.

Cite this