QoE-Driven Multi-Task Offloading for Semantic-Aware Edge Computing Systems

doi:10.1109/TNSE.2026.3662899

QoE-Driven Multi-Task Offloading for Semantic-Aware Edge Computing Systems

2026-02-09

0

PRE

AI

DOI：10.1109/TNSE.2026.3662899

Original

Original request for help

Save

Abstract

En 中文

Mobile edge computing (MEC) provides low-latency offloading solutions for computationally intensive tasks, effectively improving the computing efficiency and battery life of mobile devices. However, for data-intensive tasks or scenarios with limited uplink bandwidth, network congestion might occur due to massive simultaneous offloading nodes, increasing transmission latency, and affecting task performance. In this paper, we propose a semantic-aware multi-task offloading framework to address the challenges posed by limited uplink bandwidth. By introducing a semantic extraction factor, we balance the tradeoff among transmission latency, computation energy consumption, and task performance. To measure the offloading performance of different tasks, we design a unified and fair quality of experience (QoE) metric that includes execution latency, energy consumption, and task performance. We formulate the QoE optimization problem as a Markov decision process (MDP) and exploit the semantic-aware multi-agent proximal policy optimization (MAPPO) reinforcement learning algorithm to jointly optimize the semantic extraction factor and communication and computing resources allocation to maximize overall QoE. Experimental results show that the proposed method achieves a 12.68% improvement in user QoE compared with the semantic-unaware approach. Moreover, the proposed approach can be easily extended to models with different user preferences.

Keywords:

Mobile edge computing

resource allocation

task offloading

semantic-aware

QoE-Driven Multi-Task Offloading for Semantic-Aware Edge Computing Systems

Abstract

Journal

Organization