A comparative study of clustering techniques for electrical load pattern segmentation

RENEWABLE & SUSTAINABLE ENERGY REVIEWS

卷:120

Article

Rajabi, Amin¹  Eskandari, Mohsen¹  Ghadi, Mojtaba Jabbari¹  Li, Li¹  Zhang, Jiangfeng¹  Siano, Pierluigi² 

[1] Univ Technol Sydney, Fac Engn & Informat Technol, POB 123, Broadway, NSW 2007, Australia

[2] Univ Salerno, Dept Ind Engn, Via Giovanni Paolo II 132, I-84084 Fisciano, SA, Italy

关键词: Smart grids;    Smart meters;    Load pattern;    Data mining;    Clustering algorithms;    Comparative study;   

DOI  :  10.1016/j.rser.2019.109628

来源: Elsevier

【 摘 要 】

Smart meters have been widely deployed in power networks since the last decade. This trend has resulted in an enormous volume of data being collected from the electricity customers. To gain benefits for various stakeholders in power systems, proper data mining techniques, such as clustering, need to be employed to extract the underlying patterns from energy consumptions. In this paper, a comparative study of different techniques for load pattern clustering is carried out. Different parameters of the methods that affect the clustering results are evaluated and the clustering algorithms are compared for two data sets. In addition, the two suitable and commonly used data size reduction techniques and feature definition/extraction methods for load pattern clustering are analysed. Furthermore, the existing studies on clustering of electricity customers are reviewed and the main results are highlighted. Finally, the future trends and major applications of clustering consumption patterns are outlined to inform industry practitioners and academic researchers to optimize smart meter operational use and effectiveness.

【 授权许可】

Free