Comparison of clustering techniques for residential load profiles in South Africa

Toussaint, W and Moodley, D (2019) Comparison of clustering techniques for residential load profiles in South Africa, Proceedings of South African Forum for Artificial Intelligence Research, 4-6 December 2019, Cape town, South Africa, 2540, 117-132, CEUR.

[img] Text
FAIR2019_paper_55.pdf - Published Version
Available under License Creative Commons Attribution.

Download (963kB)

Abstract

This work compares techniques for clustering metered residential energy consumption data to construct representative daily load profiles in South Africa. The input data captures a population with high variability across temporal, geographic, social and economic dimensions. Different algorithms, normalisation and pre-binning techniques are evaluated to determine their effect on producing a good clustering structure. A Combined Index is developed as a relative score to ease the comparison of experiments across different metrics. The study shows that normalisation, specifically unit norm and the zero-one scaler, produce the best clusters. Pre-binning appears to improve clustering structures as a whole, but its effect on individual experiments remains unclear. Like several previous studies, the k-means algorithm produces the best results. To our knowledge this is the first work that rigorously compares state of the art cluster analysis techniques in the residential energy domain in a developing country context.

Item Type: Conference paper
Subjects: Computing methodologies > Machine learning > Learning paradigms > Unsupervised learning
Alternate Locations: http://ceur-ws.org/Vol-2540/FAIR2019_paper_55.pdf
Date Deposited: 05 Mar 2020 11:45
Last Modified: 05 Mar 2020 11:45
URI: http://pubs.cs.uct.ac.za/id/eprint/1377

Actions (login required)

View Item View Item