Incomplete clustering of electricity consumption: an empirical analysis with industrial and residential datasets

In this paper, we study the role of analytics for electricity consumption in smart grids and their possible applications like detecting fraud. Using data-sets of industrial as well as residential consumers, we show how incomplete clustering can help to reduce the search space for these applications. We provide a framework for iterative incomplete clustering and illustrate results in our data-sets. We find, incomplete clustering via correlation coefficients can identify a variety of different households and industries with unique characteristics that are missed with other clustering approaches.