Extracting urban water usage habits from smart meter data: a functional clustering approach

Through automated meter reading systems, recent development of smart grids offers the opportunity for an efficient and responsible management of water resources. The present paper describes a novel methodology for identifying relevant usage profiles from hourly water consumption series collected by smart meters located on a water distribution network. The proposed approach operates in two stages. First, an additive time series decomposition model is used in order to extract seasonal patterns from the time series. Then, two functional clustering approaches are used to group the extracted seasonal patterns into homogeneous clusters: a functional version of the well-known K-means algorithm, and a Fourier regression mixture-model-based algorithm. The two clustering strategies are applied to real world data from a smart grid deployed on a large water distribution network in France and a realistic interpretation of the consumption habits is given to each cluster.