Application of a clustering framework to UK domestic electricity data

TL;DR

This study applies a clustering framework to UK domestic electricity data, revealing distinct usage patterns and demonstrating the need for more detailed load profiles to improve demand management strategies.

Contribution

It adapts and evaluates a clustering approach for UK data, showing that the Portuguese method is unsuitable and identifying up to nine meaningful household clusters.

Findings

Up to nine distinct household clusters identified

Portuguese clustering method not suitable for UK data

More detailed load profiles are justified for demand management

Abstract

This paper takes an approach to clustering domestic electricity load profiles that has been successfully used with data from Portugal and applies it to UK data. Clustering techniques are applied and it is found that the preferred technique in the Portuguese work (a two stage process combining Self Organised Maps and Kmeans) is not appropriate for the UK data. The work shows that up to nine clusters of households can be identified with the differences in usage profiles being visually striking. This demonstrates the appropriateness of breaking the electricity usage patterns down to more detail than the two load profiles currently published by the electricity industry. The paper details initial results using data collected in Milton Keynes around 1990. Further work is described and will concentrate on building accurate and meaningful clusters of similar electricity users in order to better direct demand side management initiatives to the most relevant target customers.