The transition to renewable-dominated energy systems requires operational frameworks that can manage variability, maintain grid reliability, and improve economic performance under increasingly complex multi-asset conditions. This review examines how digital twins and artificial intelligence (AI) support system-level optimization across solar, wind, battery storage, and integrated energy networks. Using a structured literature review of studies published from 2015 to March 2026, the paper synthesizes advances in digital modeling, machine-learning-based forecasting, predictive maintenance, and multi-objective optimization for renewable energy operations. In contrast to earlier asset-focused reviews, this study emphasizes system-level integration, techno-economic effects, scalability constraints, and governance requirements. Quantitative evidence from the literature is interpreted as improved forecasting, reduced curtailment, operational cost savings, enhanced flexibility, and support for reliability. At the same time, critical limitations such as computational burden, interoperability gaps, cyber risk, and model transparency are also discussed. The review further presents a representative optimization framework linking real-time data, predictive analytics, and operational decision-making. Overall, digitalized renewable energy systems show strong potential to improve resilience, flexibility, and market readiness when supported by interoperable infrastructure and adaptive policy design.
Devarajan et al. (2026) studied this question.