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-modal task offloading framework to address the challenges posed by limited uplink bandwidth. By introducing a semantic extraction factor, we balance the relationship among transmission latency, computation energy consumption, and task performance. To measure the offloading performance of multi-modal tasks, we design a unified and fair quality of experience (QoE) metric that includes execution latency, energy consumption, and task performance. Lastly, we formulate the optimization problem as a Markov decision process (MDP) and exploit the multi-agent proximal policy optimization (MAPPO) reinforcement learning algorithm to jointly optimize the semantic extraction factor, communication resources, and computing resources to maximize overall QoE. Experimental results show that the proposed method achieves a reduction in execution latency and energy consumption of 18.1% and 12.9%, respectively compared with the semantic-unaware approach. Moreover, the proposed approach can be easily extended to models with different user preferences.

翻译：移动边缘计算（MEC）为计算密集型任务提供了低延迟卸载解决方案，有效提升了移动设备的计算效率和电池续航。然而，对于数据密集型任务或上行带宽受限的场景，大量节点同时卸载可能导致网络拥塞，增加传输延迟并影响任务性能。本文提出一种语义感知的多模态任务卸载框架，以应对上行带宽受限带来的挑战。通过引入语义提取因子，我们平衡了传输延迟、计算能耗与任务性能之间的关系。为衡量多模态任务的卸载性能，我们设计了一个统一且公平的体验质量（QoE）度量标准，该标准涵盖了执行延迟、能耗和任务性能。最后，我们将该优化问题建模为马尔可夫决策过程（MDP），并利用多智能体近端策略优化（MAPPO）强化学习算法，联合优化语义提取因子、通信资源和计算资源，以最大化整体QoE。实验结果表明，与无语义感知方法相比，所提方法在执行延迟和能耗上分别降低了18.1%和12.9%。此外，该方法可轻松扩展至具有不同用户偏好的模型。