Electricity Consumption Data Clustering for Load Profiling Using Generalized Self-Organizing Neural Networks with Evolving Splitting-Merging Structures
Marian B. Gorzałczany, Jakub Piekoszewski, Filip Rudziński · 2018
The main goal of the paper is the application of our clustering technique based on generalized self-organizing neural networks with evolving tree-like splitting-merging structures to the clustering of electricity consumption data collected as a part of a smart metering pilot study conducted by Irish Commission for Energy Regulation (CER). First, the Irish CER data are briefly characterized. Then, the operation of our clustering technique is outlined and illustrated using a benchmark data set. In turn, the application of our approach to the Irish CER data clustering is presented, evaluated, and discussed as well as a comparative analysis with several alternative approaches is performed.