Lightweight AI Framework for Joint PQC and NOMA Optimization in Edge Systems

A research paper proposes a lightweight agentic AI framework for joint optimization of Post-Quantum Cryptography (PQC) and Non-Orthogonal Multiple Access (NOMA) resource allocation in mobile edge devices. The scheme addresses energy consumption overhead of PQC modules and high complexity of traditional algorithms by constructing a multi-stage stochastic Mixed Integer Nonlinear Programming (MINLP) model with static power-consumption constraints. Using Lyapunov optimization theory, the long-term problem is decoupled, and a linear complexity algorithm solves nonconvex NOMA power allocation challenges. The framework targets intelligent computing and edge (ICE) systems, aiming to enable real-time decision-making in quantum-secure scenarios.