AUTHOR=Ardabili Sina , Abdolalizadeh Leila , Mako Csaba , Torok Bernat , Mosavi Amir 

TITLE=Systematic Review of Deep Learning and Machine Learning for Building Energy

JOURNAL=Frontiers in Energy Research

VOLUME=Volume 10 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/energy-research/articles/10.3389/fenrg.2022.786027

DOI=10.3389/fenrg.2022.786027

ISSN=2296-598X

ABSTRACT=The building energy (BE) sector has a vital role in urban sustainability. This sector contains the two most important subjects including energy consumption and energy demand which are important for developing smart cities and urban planning. Recently, Machine learning (ML) and Deep Learning (DL) cooperate in the advancement of technologies to estimate demand and consumption in BE systems. The present study provides a comprehensive state of the art of ML and DL-based techniques applied for handling BE system and evaluates the performance of these techniques. Through a systematic review and a comprehensive taxonomy, the advances of ML and DL-based techniques are carefully investigated and promising models are introduced. According to the results obtained for energy demand forecasting, hybrid and ensemble methods are located in high robustness range, SVM-based methods are located in good robustness limitation, ANN-based methods are located in medium robustness limitation and linear regression models are located in low robustness limitations. On the other hand, for energy consumption forecasting, DL-based, hybrid, and ensemble-based models provided the highest robustness score. ANN, SVM, and single Ml-based models provided good and medium robustness and LR-based models provided the lower robustness score. Also for energy load forecasting, LR-based models provided the lower robustness score. The hybrid and ensemble-based models provided higher robustness scores. The DL-based and SVM-based techniques provided a Good robustness score and ANN-based techniques provided a medium robustness score.