AI-Driven Fairness-Aware Resource Scheduling and Optimization in Constrained Cyber-Physical Infrastructures
DOI:
https://doi.org/10.66280/ijair.v1i1.9Keywords:
cyber-physical systems; resource scheduling; fairness; multi-objective optimization; edge computing; reinforcement learningAbstract
Resource scheduling in constrained cyber-physical infrastructures (e.g., industrial production systems, distribution IoT, and edge collaboration networks) must jointly satisfy latency, energy, reliability, and fairness objectives. Static optimization is often insufficient under rapidly chang- ing workloads and system states. This paper proposes an AI-driven fairness-aware scheduling framework that uses learning-assisted demand prediction and state estimation to guide multi- objective scheduling within feasibility constraints, while enforcing explicit fairness constraints to prevent long-term resource bias under high load. We construct a unified task–resource model with timing and energy constraints, define fairness objectives based on the Jain index and min- imum satisfaction, and introduce a hierarchical solution strategy (prediction–planning–online correction). Across simulated and scenario-based comparisons, the proposed method improves fairness and tail latency while meeting deadline and energy constraints, demonstrating scalabil- ity and practical applicability for multi-constraint CPS infrastructures.
Downloads
Published
Versions
- 2026-03-02 (2)
- 2026-02-25 (1)
How to Cite
Issue
Section
License
Copyright (c) 2026 International Journal of Artificial Intelligence Research

This work is licensed under a Creative Commons Attribution 4.0 International License.
This article is published under the Creative Commons Attribution 4.0 International License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.



