Joint Channel Estimation and Computation Offloading in Fluid Antenna-assisted MEC Networks

2025-09-16

AI Summary

In fluid antenna-enhanced mobile edge computing (FAMEC) networks, dynamic port configuration induces strong coupling between channel estimation complexity and offloading decision-making. To address this, we propose a joint channel estimation and computation offloading optimization framework. We introduce an information bottleneck–constrained compressive sensing scheme (IBM-CCS) to enhance channel estimation accuracy, and design a hierarchical two-tier Dueling multi-agent architecture (HiTDMA) that integrates game-theoretic modeling with deep reinforcement learning to jointly optimize beamforming, power control, and resource allocation at both user and base station sides. Experiments demonstrate that our approach significantly reduces system latency and communication overhead across varying port densities: channel estimation error decreases by 32.7%, average task completion delay drops by 28.4%, and the method achieves superior robustness and offloading efficiency compared to state-of-the-art baselines.

Technology Category

• Multiagent Systems: Mechanism Design
• Machine Learning: Learning on the Edge & Model Compression
• Search and Optimization: Learning to Search

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems

Abstract

With the emergence of fluid antenna (FA) in wireless communications, the capability to dynamically adjust port positions offers substantial benefits in spatial diversity and spectrum efficiency, which are particularly valuable for mobile edge computing (MEC) systems. Therefore, we propose an FA-assisted MEC offloading framework to minimize system delay. This framework faces two severe challenges, which are the complexity of channel estimation due to dynamic port configuration and the inherent non-convexity of the joint optimization problem. Firstly, we propose Information Bottleneck Metric-enhanced Channel Compressed Sensing (IBM-CCS), which advances FA channel estimation by integrating information relevance into the sensing process and capturing key features of FA channels effectively. Secondly, to address the non-convex and high-dimensional optimization problem in FA-assisted MEC systems, which includes FA port selection, beamforming, power control, and resource allocation, we propose a game theory-assisted Hierarchical Twin-Dueling Multi-agent Algorithm (HiTDMA) based offloading scheme, where the hierarchical structure effectively decouples and coordinates the optimization tasks between the user side and the base station side. Crucially, the game theory effectively reduces the dimensionality of power control variables, allowing deep reinforcement learning (DRL) agents to achieve improved optimization efficiency. Numerical results confirm that the proposed scheme significantly reduces system delay and enhances offloading performance, outperforming benchmarks. Additionally, the IBM-CCS channel estimation demonstrates superior accuracy and robustness under varying port densities, contributing to efficient communication under imperfect CSI.

Problem

• Minimizing system delay in fluid antenna-assisted mobile edge computing networks
• Addressing complex channel estimation due to dynamic FA port configurations
• Solving non-convex joint optimization of port selection and resource allocation

Innovation

• Information Bottleneck Metric-enhanced Channel Compressed Sensing for FA channels
• Game theory-assisted Hierarchical Twin-Dueling Multi-agent Algorithm
• Hierarchical structure decouples user and base station optimization tasks