This chapter reviews edge computing and artificial intelligence (AI) applications in digitalized energy infrastructures, addressing data processing challenges in smart grids and microgrids. By relocating analytics to field devices, Edge AI facilitates rapid decision-making and mitigates issues of bandwidth, privacy, and cybersecurity. The review examines edge-enabled solutions across five key domains: wide-area grid automation, microgrid and distributed energy resource management, demand response, electric vehicle charging networks, and predictive maintenance. Based on peer-reviewed studies and industry pilots, the analysis maps these applications to sustainability dimensions, including energy efficiency, cost-effectiveness, scalability, resilience, and emissions reduction. Findings indicate that edge solutions reduce control latency and upstream data traffic, defer network upgrades, and support increased renewable energy integration and demand-side flexibility, thereby lowering CO₂ emissions. The chapter also critically examines persistent challenges such as interoperability, hardware constraints, cyber-resilience, and large-scale orchestration, proposing a research agenda. Ultimately, Edge AI is presented as a crucial technology for a secure, low-carbon, and economically viable energy transition, contingent on addressing existing technical and institutional gaps.
Tuan et al. (Mon,) studied this question.