IRS-assisted Edge Computing for Vehicular Networks: A Generative Diffusion Model-based Stackelberg Game Approach

2025-02-14

AI Summary

To address the low-latency and high-energy-efficiency requirements of computation-intensive and delay-sensitive tasks in vehicle-infrastructure cooperative systems, this paper proposes an intelligent reflecting surface (IRS)-assisted multi-access edge computing (MEC) joint optimization framework. The framework jointly optimizes task offloading decisions, IRS phase-shift vectors, and edge computing resource allocation. Innovatively, a generative diffusion model is integrated into a Stackelberg game framework to overcome the computational bottlenecks of traditional mixed-integer nonlinear programming (MINLP) methods under dynamic environments, enabling real-time multi-objective co-optimization. Simulation results demonstrate that, compared with deep reinforcement learning (DRL) and heuristic baselines, the proposed approach reduces total task latency by 37.2% and decreases system-wide energy consumption by 31.5%, significantly enhancing both the optimization performance and practicality of IRS-MEC systems.

Technology Category

• Search and Optimization: Mixed Discrete/Continuous Search
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Multiagent Systems: Mechanism Design

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Recent advancements in intelligent reflecting surfaces (IRS) and mobile edge computing (MEC) offer new opportunities to enhance the performance of vehicular networks. However, meeting the computation-intensive and latency-sensitive demands of vehicles remains challenging due to the energy constraints and dynamic environments. To address this issue, we study an IRS-assisted MEC architecture for vehicular networks. We formulate a multi-objective optimization problem aimed at minimizing the total task completion delay and total energy consumption by jointly optimizing task offloading, IRS phase shift vector, and computation resource allocation. Given the mixed-integer nonlinear programming (MINLP) and NP-hard nature of the problem, we propose a generative diffusion model (GDM)-based Stackelberg game (GDMSG) approach. Specifically, the problem is reformulated within a Stackelberg game framework, where generative GDM is integrated to capture complex dynamics to efficiently derive optimal solutions. Simulation results indicate that the proposed GDMSG achieves outstanding performance compared to the benchmark approaches.

Problem

• Optimizing vehicular network performance
• Minimizing task delay and energy
• Using IRS and MEC technologies

Innovation

• Generative Diffusion Model-based Stackelberg Game
• Joint optimization of task offloading
• IRS phase shift vector optimization