Application of a clustering framework to UK domestic electricity data

Abstract—The UK electricity industry will shortly have available a massively increased amount of data from domestic households and this paper is a step towards deriving useful information from non intrusive household level monitoring of electricity. The paper takes an approach to clustering dome...

Full description

Bibliographic Details
Main Authors: Dent, Ian, Aickelin, Uwe, Rodden, Tom
Format: Conference or Workshop Item
Online Access:https://eprints.nottingham.ac.uk/2021/
_version_ 1848790706313756672
author Dent, Ian
Aickelin, Uwe
Rodden, Tom
author_facet Dent, Ian
Aickelin, Uwe
Rodden, Tom
author_sort Dent, Ian
building Nottingham Research Data Repository
collection Online Access
description Abstract—The UK electricity industry will shortly have available a massively increased amount of data from domestic households and this paper is a step towards deriving useful information from non intrusive household level monitoring of electricity. The paper takes an approach to clustering domestic load profiles that has been successfully used in Portugal and applies it to UK data. It is found that the preferred technique in the Portuguese work (a process combining Self Organised Maps and Kmeans) is not appropriate for the UK data. The workuses data collected in Milton Keynes around 1990 and shows that clusters of households can be identified demonstrating the appropriateness of defining more stereotypical electricity usagepatterns than the two load profiles currently published by the electricity industry. The work is part of a wider project to successfully apply demand side management techniques to gain benefits across the whole electricity network.
first_indexed 2025-11-14T18:16:52Z
format Conference or Workshop Item
id nottingham-2021
institution University of Nottingham Malaysia Campus
institution_category Local University
last_indexed 2025-11-14T18:16:52Z
recordtype eprints
repository_type Digital Repository
spelling nottingham-20212020-05-04T20:34:31Z https://eprints.nottingham.ac.uk/2021/ Application of a clustering framework to UK domestic electricity data Dent, Ian Aickelin, Uwe Rodden, Tom Abstract—The UK electricity industry will shortly have available a massively increased amount of data from domestic households and this paper is a step towards deriving useful information from non intrusive household level monitoring of electricity. The paper takes an approach to clustering domestic load profiles that has been successfully used in Portugal and applies it to UK data. It is found that the preferred technique in the Portuguese work (a process combining Self Organised Maps and Kmeans) is not appropriate for the UK data. The workuses data collected in Milton Keynes around 1990 and shows that clusters of households can be identified demonstrating the appropriateness of defining more stereotypical electricity usagepatterns than the two load profiles currently published by the electricity industry. The work is part of a wider project to successfully apply demand side management techniques to gain benefits across the whole electricity network. Conference or Workshop Item PeerReviewed Dent, Ian, Aickelin, Uwe and Rodden, Tom Application of a clustering framework to UK domestic electricity data. In: UKCI 2011, the 11th Annual Workshop on Computational Intelligence, 2011, Manchester. (Unpublished)
spellingShingle Dent, Ian
Aickelin, Uwe
Rodden, Tom
Application of a clustering framework to UK domestic electricity data
title Application of a clustering framework to UK domestic electricity data
title_full Application of a clustering framework to UK domestic electricity data
title_fullStr Application of a clustering framework to UK domestic electricity data
title_full_unstemmed Application of a clustering framework to UK domestic electricity data
title_short Application of a clustering framework to UK domestic electricity data
title_sort application of a clustering framework to uk domestic electricity data
url https://eprints.nottingham.ac.uk/2021/