Linear model to predict energy consumption using historical data from cold stores

Abstract

This study was developed to predict energy consumption, based on the amount fruit stored and environmental factors, using a multiple linear regression model (MLR) in a New Zealand cold store. In this study, linear regression models of a cold store were selected to show the capability of simple models to reduce margins of error in energy auditing projects. The final MLR models developed were based on weekly numbers avocado and kiwifruit bins and outside temperatures. The comparison between different models demonstrated the amount of stored fruits have more sensitivity than the outside temperatures in cold stores. Comparing actual and predicted energy usage in the studied cold store showed that the MLR model could be fitted to energy usage data and accounted for around 79% of the variance.