Validating Clustering Frameworks for Electric Load Demand Profiles

Large-scale deployment of smart meters has made it possible to collect sufficient and high-resolution data residential electric demand profiles. Clustering analysis these profiles is important further analyze comment on electricity consumption patterns. Although many clustering techniques have been proposed in the literature over years, often noticed that different fit best for datasets. To identify most suitable technique, standard validity indices are used. These focus primarily intrinsic characteristics results. Moreover, give conflicting recommendations, which can only be clarified with heuristics about dataset and/or expected cluster structures-information rarely available practical situations. This article presents a novel scheme validate compare results objectively. Additionally, considers all steps prior algorithm, including preprocessing dimensionality reduction steps, order provide recommendations complete framework. Accordingly, strategy shown better, unbiased, uniform as compared indices.