Real-Time Task Offloading With Task-Level Multi-Agent Transformer in Heterogeneous Multi-Access Edge Computing

Hui Huang

doi:10.1109/tcc.2026.3741463

Real-Time Task Offloading With Task-Level Multi-Agent Transformer in Heterogeneous Multi-Access Edge Computing

2026-10-08

0

PRE

AI

DOI：10.1109/tcc.2026.3741463

Original

Original request for help

Save

Abstract

En 中文

Multi-access Edge Computing (MEC) has emerged as a promising paradigm that extends cloud computing capabilities to the network edge. It supports real-time and deadline-sensitive applications running on Mobile Devices (MDs) by deploying computation, storage, and communication resources in close proximity to MDs, thereby improving service reliability and responsiveness in heterogeneous MEC systems. Nevertheless, real-time task offloading in heterogeneous MEC systems remains highly challenging due to dynamic wireless conditions, heterogeneous MD capabilities, resource contention among MDs, and stringent deadline constraints under limited MEC resources. As a result, optimal task offloading becomes a crucial yet nontrivial problem in MEC systems. Existing Multi-Agent Deep Reinforcement Learning (MADRL)-based offloading methods typically follow the Centralized Training and Decentralized Execution (CTDE) paradigm, where MDs update their policies based on explicit parameter sharing and aggregated local observations, often leading to suboptimal offloading decisions and excessive computational overhead. To address these limitations, we propose a novel MADRL-based offloading approach, termed TMAT-O, which integrates Centralized Training and Centralized Execution (CTCE) with Task-level Multi-Agent Transformer (TMAT). Technically, the real-time offloading problem is formulated as a Multi-agent Markov Decision Process (MMDP) and solved using the proposed TMAT. By leveraging self-attention and autoregressive sequence modeling, TMAT learns task-level dependencies globally within centralized sequential task decision-making, thereby deriving more effective offloading policies. Extensive simulation results demonstrate that TMAT-O consistently outperforms representative baseline approaches, achieving a minimum reduction of 2.2% in task completion time while consistently lowering deadline-miss rates across diverse MEC configurations.

Keywords:

Heterogeneous multi-access edge computing

multi-agent transformer

real-time task offloading

Real-Time Task Offloading With Task-Level Multi-Agent Transformer in Heterogeneous Multi-Access Edge Computing

Abstract

Journal

Organization

Cited Papers