Quantum-inspired Multi-Agent Computation Offloading in Edge Intelligence-aided IoT Networks

The rise of Internet-of- Things (IoT) applications has increased data generation, necessitating efficient computational strategies. Traditional cloud computing faces high latency and system bandwidth issues. Edge intelligence, which processes data closer to the source, offers a solution. This paper explores integrating quantum-inspired algorithms with multi-agent systems for computation offloading in edge intelligence-aided IoT net-works. By leveraging quantum principles like superposition and entanglement, we propose a quantum-inspired multi-agent deep-deterministic policy gradient algorithm (Q-MADDPG), which enhances computation decision-making, optimizes resource allocation, and reduces latency. The approach improves IoT network efficiency and scalability, addressing the dynamic nature of edge computing environments. The experimental results affirm the effectiveness of the proposed approach compared to the existing state-of-the-art approaches.