INVESTIGATING MACHINE LEARNING APPLICATIONS FOR SMART GRID-CONNECTED BUILDINGS FOR ENERGY EFFICIENCY: A COMPREHENSIVE REVIEW
TL;DR
The review highlights the significance of machine learning for load forecasting and the prediction of energy usage in buildings, and investigates cutting-edge modelling techniques such as digital twin technology, demonstrating its potential to contribute to energy efficiency.
Abstract
Machine learning (ML) application in the smart grid-to-building sector presents a significant opportunity to reduce energy consumption, mitigate CO 2 emissions, and address climate change. In recent years, many reviews have explored different strategies for reducing energy consumption in buildings. However, the application of ML in smart grid-to-building systems for energy efficiency and management remains largely unexplored. This review aims to fill this gap by comprehensively analyzing various machine learning techniques, workflows and mechanisms applied in smart grid-to-buildings. A comprehensive search of three major databases, Web of Science, Google Scholar, and ScienceDirect, was conducted using various keyword combinations. The focus was on machine learning techniques like ANN, SVM, RL, and DL, as well as terms specific to smart grids and building energy management. The review highlights the significance of machine learning for load forecasting and the prediction of energy usage in buildings. Furthermore, it investigates cutting-edge modelling techniques such as digital twin technology, demonstrating its potential to contribute to energy efficiency. The review also serves as a valuable resource for future researchers aiming to optimize energy consumption using machine learning in buildings through smart grid technologies.