Clustering of residential electricity customers using load time series

•A big dataset of electricity load time series of residential customers is modelled.•Small sets of modelled parameters are used to summarise the lengthy load time series.•The customers are clustered by the similarity of their time series’ model parameters.•The 12 clusters show 61% distinction and 6.75% improved coincidence factor on average.•The clustering method is reasonably robust against a limited form of mixed noise.