Mobile-edge computing (MEC) is a promising technology, which allows reducing latency and energy consumption, thereby making the user experience better. Although MEC can support various types of services, differentiated Quality-of-Service (QoS) requirements bring difficulties and challenges to the allocation of radio resources and computing resources of the MEC system. In this article, we jointly optimize subchannel allocation, as well as the local central processing unit (CPU) speed scaling, user association, subcarrier assignment, power allocation, and video quality decision for MEC systems to study the total cost saving problem. Considering the traffic variations, we develop an online algorithm by using the Lyapunov optimization technique to solve this problem, referred to as dynamic subchannel allocation and resource allocation (DSARA). Particularly, the proposed DSARA algorithm only needs to track the state of the current network without requiring any prior knowledge. Besides, we prove that our proposed algorithm can asymptotically achieve the minimum total cost value (such as minimizing the power consumption and maximizing quality satisfaction). Simulation results show that the DSARA can achieve a good tradeoff between the total cost and delay, and outperforms the existing schemes in terms of the total cost expenditure.

中文翻译：

---

移动边缘计算中面向服务特征的无线与计算资源分配联合优化


移动边缘计算（MEC）是一项很有前途的技术，它可以减少延迟和能源消耗，从而改善用户体验。虽然MEC可以支持多种类型的业务，但差异化的服务质量（QoS）要求给MEC系统的无线资源和计算资源的分配带来了困难和挑战。在本文中，我们联合优化MEC系统的子通道分配以及本地中央处理单元（CPU）速度缩放、用户关联、子载波分配、功率分配和视频质量决策，以研究总成本节省问题。考虑到流量变化，我们利用Lyapunov优化技术开发了一种在线算法来解决这个问题，称为动态子信道分配和资源分配（DSARA）。特别是，所提出的 DSARA 算法只需要跟踪当前网络的状态，而不需要任何先验知识。此外，我们证明我们提出的算法可以渐近地实现最小总成本值（例如最小化功耗和最大化质量满意度）。仿真结果表明，DSARA能够在总成本和延迟之间实现良好的权衡，并且在总成本支出方面优于现有方案。