The rapid growth of distributed energy resources (DERs), transportation electrification, and bidirectional charging is increasing the need for coordinated operation of energy assets. To address this need, electric vehicles (EVs) enabled by bidirectional vehicle-to-everything (V2X) technologies are proposed in this article as grid-interactive mobile microgrids—dynamic energy hubs that extend the operational flexibility of power systems. Grid-interactive mobile microgrids can provide temporary and location-flexible energy support, but global objectives must be reconciled with local physical, communication, and user constraints in their operation. In such microgrids, energy management is increasingly affected by non-stationarity and sub-optimality due to unpredictable EV charging demands, diverse mobility patterns, and intermittent DERs. Under such conditions, context-aware optimal power dispatch at the grid edge becomes difficult, and conventional energy management frameworks face challenges in scalability, responsiveness, and optimal decision making and execution. In this article, edge agentic artificial intelligence (EAAI) is introduced as an architectural framework for the future operation of grid-interactive mobile microgrids. In the proposed architecture, a supervisory large language model is employed as an operator-facing interface for grid-interactive mobile microgrids, providing system-level reasoning and orchestrating operations, and candidate schedules are computed by domain optimization tools. At the edge level, small language models select locally appropriate operating controls, and authority over physical actuation is retained through safety validation, physics-constrained control with safety shield, and protection, executed through small action models. By separating reasoning, optimization, and edge execution, the proposed EAAI framework can provide a practical foundation for scalable and context-aware operation while enhancing system-wide coordination and resilience of grid-interactive mobile microgrids.
Provides society information that may include news, reviews or technical notes that should be of interest to practitioners and researchers.
Modern power grids are evolving into highly interconnected cyber-physical systems (CPSs), enabling advanced monitoring, automation, and control. While these innovations improve efficiency and reliability, they also introduce new vulnerabilities. A well-devised single cyberattack can cascade across the grid, disrupting essential services to the society and economy. This has been demonstrated in major critical infrastructure attacks, such as the Ukraine power grid hack (2015), and Colonial pipeline attack (2021). Traditional cybersecurity measures alone fall short as threats grow more sophisticated. Artificial intelligence (AI) offers a transformative approach to safeguarding smart distribution systems by enabling proactive detection and self-healing capabilities before the anomalies escalate into major disruptions. By leveraging AI’s ability to learn patterns, anticipate adversarial behavior, and coordinate defense across distributed assets, utilities can enhance resilience against evolving cyber threats. This article explores how AI-driven strategies can become a shield for the future grid security. It highlights their potential to enhance operational resilience and outlines a vision for integrating intelligent defense into the infrastructure of modern electric power distribution systems.
