Using existing building stock to predict electricity load profiles of new supermarkets

Using existing building stock to predict electricity load profiles of new supermarkets

Senior researcher Ramon Granell presented a paper at the Energy Systems Conference 2018 recently, in a session on Demand Management.

The paper presented was "Using existing building stock to predict the electricity load profiles of new supermarkets", authored by Ramon with co-authors Professor David Wallom (University of Oxford Department of Engineering Science) and Colin Axon and Maria Kolokotroni (both Brunel University London).

The food retail sector accounts for 3-5% of total electricity consumption in the UK; supermarkets are energy intensive buildings due to refrigeration, heating, ventilation and cooling systems, and lighting. The researchers were given access to a data-set of hourly electricity demand readings for 196 UK supermarkets from 2012 to 2015. The work aims to predict the electricity demand of a new supermarket to help with energy management, i.e. what should be normal for that new property.

Traditional energy usage estimation methods rely on thermal engineering models of the building which have the disadvantage of missing the usage drivers of energy consumption. The researchers developed a data-driven approach to forecast the ‘electricity daily load profile’ (EDLP) of a new supermarket, applying data mining techniques to profiles of stores with similar (though not identical) building and retail-related features. Preliminary results show that the EDLP of smaller supermarkets can be accurately predicted.