Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Yixian Wang, Geng Sun, Zemin Sun, Long He, Jiacheng Wang, Shiwen Mao

TL;DR

This work tackles the joint optimization of task offloading, IRS phase shifts, and computation resource allocation in an IRS-assisted MEC for vehicular networks with strict latency and energy requirements. It introduces a GDMSG framework that reformulates the problem as a Stackelberg game and leverages a generative diffusion model to efficiently explore the nonconvex solution space. Vehicle QoE and BS revenue are embedded in the objective, and a dynamic reward mechanism with a DDPM-based training procedure learns effective policies. Simulations with six vehicles show GDMSG achieving lower total delay and higher QoE and BS revenue than baselines, while demonstrating good scalability at the cost of higher energy usage.

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.

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

TL;DR

This work tackles the joint optimization of task offloading, IRS phase shifts, and computation resource allocation in an IRS-assisted MEC for vehicular networks with strict latency and energy requirements. It introduces a GDMSG framework that reformulates the problem as a Stackelberg game and leverages a generative diffusion model to efficiently explore the nonconvex solution space. Vehicle QoE and BS revenue are embedded in the objective, and a dynamic reward mechanism with a DDPM-based training procedure learns effective policies. Simulations with six vehicles show GDMSG achieving lower total delay and higher QoE and BS revenue than baselines, while demonstrating good scalability at the cost of higher energy usage.

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.

Paper Structure

This paper contains 21 sections, 27 equations, 2 figures, 2 algorithms.

Table of Contents

  1. Introduction
  2. System Model and Problem Formulation
  3. System Model
  4. Communication Model
  5. Computation Model
  6. Service Delay
  7. Energy Consumption
  8. Problem Formulation
  9. GDMSG for IRS-assisted MEC System
  10. Stackelberg Game Formulation
  11. QoE of vehicles
  12. Revenue of BS
  13. GDM-based Stackelberg Game Solution
  14. Modeling the IRS-assisted Vehicular Network Environment
  15. Configuring GDM with Stackelberg Game and Dynamic Reward Mechanism
  16. ...and 6 more sections

Figures (2)

  • Figure 1: IRS-assisted MEC architecture for vehicular networks.
  • Figure 2: System performance with time. (a) Total task completion delay. (b) Total energy consumption. (c) QoE of vehicles. (d) Revenue of BS.