The renewable energy transition is a central component of global strategies to mitigate climate change and achieve sustainable development. However, the large-scale integration of renewable energy sources introduces significant challenges related to variability, system complexity, and operational efficiency. In recent years, artificial intelligence (AI) has emerged as a promising enabler for addressing these challenges through advanced data-driven forecasting, optimization, and decision-support capabilities. This study presents a systematic bibliometric and thematic review of peer-reviewed research on AI applications in the renewable energy transition published between 2015 and 2025, and was conducted following the PRISMA framework. Using the Scopus database, a total of 595 journal articles were analyzed through bibliometric performance indicators, network analysis, and thematic synthesis. The results reveal a rapidly growing and highly collaborative research field, characterized by strong international co-authorship and increasing methodological diversity. Early research predominantly focused on prediction and forecasting tasks, while more recent studies emphasize system-level optimization, energy management, and integrative AI applications across renewable technologies. The review further highlights key research trends, conceptual framing, and methodological orientations shaping the field. By consolidating dispersed literature and mapping its evolution, this study provides a structured overview that supports future research, policy development, and practical implementation of AI-enabled solutions for a sustainable energy transition.
Saadi et al. (Thu,) studied this question.