Comparing Bottom-Up Energy Consumption Models Using The Wasserstein Distance Between Load Profile Histograms

This paper presents a comparison of bottom up models that generate appliance load profiles. The comparison is based on their ability to accurately distribute load over time-of-day. This is a key feature of model performance if the model is used to assess the impact of low carbon technologies and practices on the network. No work has yet assessed models on this basis. In this work, the temporal characteristics of load are captured using histograms, and similarity between the histogram representations of measured and generated data is assessed using the Wasserstein distance. This is then applied to compare the results of three models, which were developed here by adopting approaches used in previous research. One is based on occupant presence, one on occupant activity, and one on empirical data. Typical statistical tests showed that the comparison method is robust and can be used for this purpose.