Al for Cyber Physical Energy Systems

Introduction: 

As energy infrastructures evolve towards digitalization and intelligence, cyber-physical energy systems (CPESs) have become a cornerstone for the modern power and energy paradigm. By integrating advanced sensing, communication, computation, and control technologies, CPESs interconnect the physical layer of power systems with the cyber layer of data analytics and decision-making. This integration enables real-time monitoring, adaptive control, and cooperative optimization across energy generation, transmission, distribution, and consumption. However, the increasing penetration of renewable energy resources, electric vehicles, and flexible demand introduces unprecedented complexity, uncertainty, and coupling between cyber and physical domains. To address these issues, the rapid development of artificial intelligence (AI)—particularly machine learning, deep reinforcement learning, and deep learning—offers promising solutions. By harnessing AI to model, learn, and optimize the behaviors of complex CPESs, researchers can significantly improve operational efficiency, reliability, and security.

This special issue aims to bring together leading researchers, engineers, and practitioners from academia and industry to address the technical challenges and research gaps in applying AI for CPESs. The goal is to promote safe, interpretable, and efficient AI technologies that strengthen the synergy between the cyber and physical layers, thereby supporting secure, reliable, and sustainable operation of CPESs.

Topics of interest for this call for papers included but are not limited to:

• AI-empowered framework and models for CPESs
• Deep learning for Intelligent monitoring, anomaly detection, and fault diagnosis in CPESs
• Reinforcement learning for energy management and control in CPESs
• Trustworthy and explainable AI methods for critical energy infrastructures
• AI-driven cybersecurity, intrusion detection, and resilience enhancement in CPESs
• Federated and privacy-preserving learning for cross-domain energy data
• Knowledge-graph and hybrid modeling for cyber-physical interaction mechanisms
• Edge and cloud intelligence for real-time control of CPESs
• Multi-energy power flow calculation based on AI algorithms
• Human-in-the-loop learning, decision support, and control in CPESs
• Data-driven predictive maintenance and lifecycle management of energy assets
• AI-based stability assessment, risk analysis, and emergency control
• Applications, testbeds, and demonstrators of AI in real-world CPESs scenarios

Submission Instructions: 

Please read the Guide for Authors  before submitting. All articles should be submit online, please select [AI4CPESs] on submission.

Important Dates:

• Submission Deadline: 31 March 2026
• Final Manuscript Submission Deadline: 30 June 2026
• Published (expected): August-September 2026

Guest Editors:

• Yan Zhang, University of Electronic Science and Technology of China, China. Email: yanzhang@ieee.org

• Yushuai Li, Aalborg University, Denmark. Email: yushuaili@ieee.org

• Rui Fan, University of Denver, USA. Email: ruifan@outlook.com

• Qianwen Xu, KTH, Sweden. Email: qianwenx@kth.se

• Yan Xu, Nanyang Technological University, Singapore. Email: xuyan@ntu.edu.sg

• Dong Jin, University of Arkansas, USA. Email: dongjin@uark.edu

• Yuemin Ding, University of Navarra, Spain. Email: yueminding@tecnun.es

• Mo-Yuen Chow, Shanghai Jiao Tong University, China / North Carolina State University, USA. Email: moyuen.chow@sjtu.edu.cn