Predicting The Energy Performance and Consumption of Buildings Using Machine Learning: A Review

Abstract

As the world's population, urban infrastructure, and technological capabilities continue to expand at a breakneck pace, so too does the need for energy.  As a result, improving the energy efficiency of the construction industry has become a critical goal in order to minimise greenhouse gas emissions and fossil fuel usage. One of the best ways to reduce down on carbon dioxide emissions and energy use from new buildings is to prioritise energy efficiency. However, the energy performance of the existing stock may be improved by effective energy management and clever renovations. For effective decision making, all these strategies need precise energy forecasting. Machine learning (ML) approaches have been suggested in recent years for energy consumption and performance predictions in buildings. All of these are discussed in this work as they relate to building energy forecasts. We present prior studies of these models and their respective applications.