Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

An Integrated Communication and Computing Scheme for Wi-Fi Networks based on Generative AI and Reinforcement Learning

Xinyang Du, Xuming Fang

TL;DR

This work targets MEC-enabled Wi-Fi networks by jointly optimizing offloading decisions and resource allocation under 802.11ax constraints. It introduces a Diffusion Twin Delayed DDPG (DTD3) framework that combines a Generative Diffusion Model with TD3 to mitigate sparse-sample issues and accelerate convergence, followed by a Hungarian algorithm-based RU allocation for Wi-Fi-specific resource scheduling. Empirical results demonstrate significant reductions in system latency and energy consumption, improved QoS, and faster convergence compared with traditional RL baselines. The approach enables efficient computation-communication integration in dense Wi-Fi edge environments and offers a path toward scalable, distributed RL in multi-AP MEC deployments.

Abstract

The continuous evolution of future mobile communication systems is heading towards the integration of communication and computing, with Mobile Edge Computing (MEC) emerging as a crucial means of implementing Artificial Intelligence (AI) computation. MEC could enhance the computational performance of wireless edge networks by offloading computing-intensive tasks to MEC servers. However, in edge computing scenarios, the sparse sample problem may lead to high costs of time-consuming model training. This paper proposes an MEC offloading decision and resource allocation solution that combines generative AI and deep reinforcement learning (DRL) for the communication-computing integration scenario in the 802.11ax Wi-Fi network. Initially, the optimal offloading policy is determined by the joint use of the Generative Diffusion Model (GDM) and the Twin Delayed DDPG (TD3) algorithm. Subsequently, resource allocation is accomplished by using the Hungarian algorithm. Simulation results demonstrate that the introduction of Generative AI significantly reduces model training costs, and the proposed solution exhibits significant reductions in system task processing latency and total energy consumption costs.

An Integrated Communication and Computing Scheme for Wi-Fi Networks based on Generative AI and Reinforcement Learning

TL;DR

This work targets MEC-enabled Wi-Fi networks by jointly optimizing offloading decisions and resource allocation under 802.11ax constraints. It introduces a Diffusion Twin Delayed DDPG (DTD3) framework that combines a Generative Diffusion Model with TD3 to mitigate sparse-sample issues and accelerate convergence, followed by a Hungarian algorithm-based RU allocation for Wi-Fi-specific resource scheduling. Empirical results demonstrate significant reductions in system latency and energy consumption, improved QoS, and faster convergence compared with traditional RL baselines. The approach enables efficient computation-communication integration in dense Wi-Fi edge environments and offers a path toward scalable, distributed RL in multi-AP MEC deployments.

Abstract

The continuous evolution of future mobile communication systems is heading towards the integration of communication and computing, with Mobile Edge Computing (MEC) emerging as a crucial means of implementing Artificial Intelligence (AI) computation. MEC could enhance the computational performance of wireless edge networks by offloading computing-intensive tasks to MEC servers. However, in edge computing scenarios, the sparse sample problem may lead to high costs of time-consuming model training. This paper proposes an MEC offloading decision and resource allocation solution that combines generative AI and deep reinforcement learning (DRL) for the communication-computing integration scenario in the 802.11ax Wi-Fi network. Initially, the optimal offloading policy is determined by the joint use of the Generative Diffusion Model (GDM) and the Twin Delayed DDPG (TD3) algorithm. Subsequently, resource allocation is accomplished by using the Hungarian algorithm. Simulation results demonstrate that the introduction of Generative AI significantly reduces model training costs, and the proposed solution exhibits significant reductions in system task processing latency and total energy consumption costs.
Paper Structure (15 sections, 19 equations, 4 figures, 1 algorithm)

This paper contains 15 sections, 19 equations, 4 figures, 1 algorithm.

Table of Contents

  1. Introduction
  2. System Model
  3. Network Model
  4. Wireless Transmisson Model
  5. Computing Model
  6. Problem Formulation
  7. Offloading and Resource Allocation Scheme Based on DTD3
  8. Three Key Elements for RL
  9. DTD3 Offloading Decision Algorithm
  10. Resource Allocation Scheme
  11. Simulation Result
  12. Scenario with Varying Computing STAs
  13. Scenario with Varying Capacity of MEC
  14. Convergence Analysis
  15. Conclusion

Figures (4)

  • Figure 1: System model
  • Figure 2: The performance of algorithms with varying computing STAs: (a) total cost verus the number of computing STAs, (b) QoS verus the number of computing STAs, (c) communication success rate verus the number of computing STAs
  • Figure 3: The performance of algorithms with varying capacity of MEC: (a) total cost verus the capacity of MEC, (b) QoS verus the capacity of MEC, (c) communication success rate verus the capacity of MEC
  • Figure 4: The convergence of algorithms