 Machine learning, ML, models have become increasingly popular in the modeling, design, and prediction of energy systems over the last two decades. In this paper, we present a comprehensive review of the literature on ML models applied to energy systems, as well as a novel taxonomy of these models and their applications. We also discuss the advantages and disadvantages of each model, as well as the potential for future research. Our analysis shows that hybrid ML models have proven to be effective in improving the accuracy, robustness, precision, and generalization ability of energy system models. These models have also made significant contributions to energy efficiency and governance, leading to greater sustainability. This article was authored by Amir Mozavi, Mohsen Salimi, Sina Faisalalazadar Dabali, and others.