The Application of a Data Mining Framework to Energy Usage Profiling in Domestic Residences using UK data

TL;DR

This paper explores a data mining framework to create representative energy usage profiles for UK domestic electricity users, aiming to simplify and improve current profiling methods using clustering and analysis techniques.

Contribution

It adapts and applies data mining and clustering approaches to UK energy data to develop archetypical user profiles for better energy consumption analysis.

Findings

Initial results using Milton Keynes data demonstrate the potential of the approach.

Consideration of temperature-based splits to enhance profiling accuracy.

Framework adaptation shows promise for improving energy usage characterization.

Abstract

This paper describes a method for defining representative load profiles for domestic electricity users in the UK. It considers bottom up and clustering methods and then details the research plans for implementing and improving existing framework approaches based on the overall usage profile. The work focuses on adapting and applying analysis framework approaches to UK energy data in order to determine the effectiveness of creating a few (single figures) archetypical users with the intention of improving on the current methods of determining usage profiles. The work is currently in progress and the paper details initial results using data collected in Milton Keynes around 1990. Various possible enhancements to the work are considered including a split based on temperature to reflect the varying UK weather conditions.