LAUSR

In multi-access edge computing (MEC), computation tasks offloaded from users are usually associated with specific services that need to be cached in MEC nodes to enable task execution. The decisions as to which services to cache and which tasks to execute on each resource-limited MEC node are critical to maximizing the offloading efficiency. Moreover, quality of experience (QoE) is a key factor driving offloading decisions, so that limited computing resources can be effectively utilized to keep users satisfied. Therefore, in this letter, we introduce a new QoE-based utility optimization approach to address the problem of joint service caching and task offloading in MEC systems. Our utility model reflects the trade-off between the user’s perception of service latency and the cost the user pays for the allocated computing resources. We formulate total utility maximization as an integer nonlinear programming problem and propose a genetic-based algorithm to solve it efficiently. Finally, evaluation results show that our proposal can significantly improve total user utility over traditional baselines.