Agentic AI Systems in Electrical Power Systems Engineering: Current State-of-the-Art and Challenges

2025-11-18

AI Summary

The field lacks a precise definition and multidimensional taxonomy for “Agentic AI,” hindering clear differentiation from conventional AI agents and generative AI. Method: This paper introduces, for the first time in power engineering, a rigorous definition and a multi-dimensional classification framework for Agentic AI—explicitly characterizing paradigmatic distinctions in autonomy, goal-directedness, and environmental interaction. It integrates generative AI, multi-agent collaborative modeling, and fault mode analysis to build deployable Agentic AI systems. Contribution/Results: The approach is validated across four representative power-system scenarios: dynamic security assessment, survival analysis of battery-swapping station pricing strategies, and two others. Results demonstrate automated research workflows, standardized benchmarking, and enhanced decision robustness. The paper further proposes engineering deployment guidelines emphasizing safety, reliability, and accountability—advancing Agentic AI toward practical, trustworthy implementation in critical infrastructure.

Technology Category

• Multiagent Systems: Agent/AI Theories and Architectures
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Philosophy and Ethics of AI: Safety, Robustness & Trustworthiness

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Agentic AI systems have recently emerged as a critical and transformative approach in artificial intelligence, offering capabilities that extend far beyond traditional AI agents and contemporary generative AI models. This rapid evolution necessitates a clear conceptual and taxonomical understanding to differentiate this new paradigm. Our paper addresses this gap by providing a comprehensive review that establishes a precise definition and taxonomy for "agentic AI," with the aim of distinguishing it from previous AI paradigms. The concepts are gradually introduced, starting with a highlight of its diverse applications across the broader field of engineering. The paper then presents four detailed, state-of-the-art use case applications specifically within electrical engineering. These case studies demonstrate practical impact, ranging from an advanced agentic framework for streamlining complex power system studies and benchmarking to a novel system developed for survival analysis of dynamic pricing strategies in battery swapping stations. Finally, to ensure robust deployment, the paper provides detailed failure mode investigations. From these findings, we derive actionable recommendations for the design and implementation of safe, reliable, and accountable agentic AI systems, offering a critical resource for researchers and practitioners.

Problem

• Establishing precise definition and taxonomy for agentic AI
• Demonstrating practical applications in electrical engineering systems
• Providing safety recommendations for reliable agentic AI deployment

Innovation

• Defining agentic AI taxonomy and precise definition
• Developing advanced agentic framework for power systems
• Creating novel system for battery pricing analysis