What is it about?

This paper explains how artificial intelligence can help improve the resilience of interconnected critical infrastructure systems, such as power grids, communication networks, and transportation systems. Instead of treating each infrastructure as an isolated system, the paper views them as a system-of-systems, where failures in one system can spread to others through physical, cyber, and operational links. The study does not propose a new AI algorithm; rather, it provides a systems engineering framework that shows how AI can support cross-system situational awareness, coordinated decision-making, adaptive response, and recovery. The framework positions AI as a decision-support and coordination layer, not as a centralized controller, so that each infrastructure system can retain its own autonomy while benefiting from better coordination.

Featured Image

Why is it important?

Modern infrastructure failures are rarely isolated. A power outage can weaken communication services, communication failures can reduce power system monitoring capability, and uncoordinated responses can worsen cascading failures. This paper is important because it shifts the focus from local system optimization to cross-system resilience mechanisms. The illustrative power–communication case study shows that AI-enabled coordination can substantially improve service availability, reduce cascading propagation, and shorten recovery time compared with decentralized responses without coordination. This makes the work timely for future smart cities and critical infrastructure systems, where resilience depends not only on stronger individual systems, but also on better interaction and coordination among them.

Perspectives

What I find most meaningful about this work is its mechanism-oriented view of AI-enabled resilience. Many AI studies focus mainly on algorithmic accuracy or local optimization, but this paper emphasizes how AI should be embedded into infrastructure governance and coordination processes. By treating AI as a transparent decision-support layer, the framework better aligns with the practical needs of critical infrastructure operation, where human oversight, institutional responsibility, and system autonomy remain essential. Overall, this work provides a useful conceptual foundation for designing trustworthy AI-enabled resilience strategies across interdependent infrastructure systems.

Chair, IEEE PES EICC Task Force on AI-Enabled Resilience of CPES|Clarivate HCR|AE: IEEE TSG/TSTE/TII Yang Li
Northeast Electric Power University

Read the Original

This page is a summary of: AI-Enabled System-of-Systems Resilience for Critical Infrastructure: A Systems Engineering Framework and Mechanism-Oriented Analysis, April 2026, Institute of Electrical & Electronics Engineers (IEEE),
DOI: 10.1109/syscon66367.2026.11503502.
You can read the full text:

Read

Contributors

The following have contributed to this page