<?xml version="1.0" encoding="UTF-8"?> <article key="pdf/10010114" mdate="2019-02-01 00:00:00"> <author>Ioannis P. Panapakidis and Marios N. Moschakis</author> <title>Consumer Load Profile Determination with EntropyBased KMeans Algorithm</title> <pages>144 - 149</pages> <year>2019</year> <volume>13</volume> <number>3</number> <journal>International Journal of Energy and Power Engineering</journal> <ee>https://publications.waset.org/pdf/10010114</ee> <url>https://publications.waset.org/vol/147</url> <publisher>World Academy of Science, Engineering and Technology</publisher> <abstract>With the continuous increment of smart meter installations across the globe, the need for processing of the load data is evident. Clusteringbased load profiling is built upon the utilization of unsupervised machine learning tools for the purpose of formulating the typical load curves or load profiles. The most commonly used algorithm in the load profiling literature is the Kmeans. While the algorithm has been successfully tested in a variety of applications, its drawback is the strong dependence in the initialization phase. This paper proposes a novel modified form of the Kmeans that addresses the aforementioned problem. Simulation results indicate the superiority of the proposed algorithm compared to the Kmeans. </abstract> <index>Open Science Index 147, 2019</index> </article>