Application of a Clustering Framework to UK Domestic Electricity Data

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 work uses data collected in Milton Keynes around 1990 and shows that clusters of households can be identified demonstrating the appropriateness of defining more stereotypical electricity usage patterns 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