A review on the integrated optimization techniques and machine learning approaches for modeling, prediction, and decision making on integrated energy systems

Abstract

21 The optimal co-planning of the integrated energy system (IES) and machine learning (ML) 22 application on the multivariable prediction of IES parameters have mostly been carried out 23 separately in the literature. Meanwhile, the synergy of optimization methods and ML 24 techniques can enhance the feasibility of a zero-emission IES, boost realistic planning, and 25 promote accurate day-ahead scheduling. Thus, a comprehensive review of integrated 26 optimization and ML techniques in IES is crucial and hereby presented in this study. Critical 27 issues such as an overview of IES structure, IES modeling approaches and techniques, 28 application of ML in IES research, and the trends of integrating ML and optimization 29 techniques for optimal and feasible planning of IES were presented. Specifically, extant studies 30 on the integrated approach were reviewed under ML hyperparameter tuning using optimization, 31 combined uncertainty estimation and decision making, integrated ML and scenario generation, 32 integrated prediction, and optimal decision-making techniques. Findings from this review show 33 that the IES structure depends on the available technologies, the multi-energy demand patterns, 34 the available renewable resources, and the planner's objective. It was also revealed that despite 35 the popularity of ML models and the benefits of synergizing them with optimization models, 36