Variability of Behaviour in Electricity Load Profile Clustering; Who Does Things at the Same Time Each Day?

TL;DR

This paper investigates how variability in household electricity usage patterns, identified through motif analysis, can improve clustering consistency and enhance targeted interventions in the UK electricity market.

Contribution

It introduces a novel approach using variability of regular behaviour via motifs for clustering households, outperforming traditional load profile methods.

Findings

Motif-based variability yields more consistent household clusters.

Clustering based on behaviour variability improves intervention targeting.

Different algorithms show increased agreement with motif-based clustering.

Abstract

UK electricity market changes provide opportunities to alter households' electricity usage patterns for the benefit of the overall electricity network. Work on clustering similar households has concentrated on daily load profiles and the variability in regular household behaviours has not been considered. Those households with most variability in regular activities may be the most receptive to incentives to change timing. Whether using the variability of regular behaviour allows the creation of more consistent groupings of households is investigated and compared with daily load profile clustering. 204 UK households are analysed to find repeating patterns (motifs). Variability in the time of the motif is used as the basis for clustering households. Different clustering algorithms are assessed by the consistency of the results. Findings show that variability of behaviour, using motifs, provides more consistent groupings of households across different clustering algorithms and allows for more efficient targeting of behaviour change interventions.