Mobile edge computing (MEC) brings a breakthrough for Internet of Things (IoT) for its ability of offloading tasks from user equipments (UEs) to nearby servers which have rich computation resource. 5G network brings a huge breakthrough on transmission rate. Together with MEC and 5G, both execution delay of tasks and time delay from downloading would be shorter and the quality of experience (QoE) of UEs can be improved. Considering practical conditions, the computation resource of an MEC server is finite to some extent. Therefore, how to prevent the abuse of MEC resource and further allocate the resource reasonably becomes a key point for an MEC system. In this paper, an MEC system with multi-user is considered where a base station (BS) with an MEC server, which can not only provide computation offloading service but also data cache service. Especially, we take the charge for both data transmission and task computation as one part of total cost of UEs, and then explore a joint optimization for downlink resource allocation, offloading decision and computation resource allocation to minimize the total cost in terms of the time delay and the charge to UEs. The proposed problem is formulated as a mixed integer programming (MIP) one which is NP-hard. Therefore, we decouple the original problem into two subproblems which are downlink resource allocation problem and joint offloading decision and computation resource allocation problem. Then we address these two subproblems by using convex and nonconvex optimization techniques, respectively. An iterative algorithm is proposed to obtain a suboptimal solution in polynomial time. Simulation results show that our proposed algorithm performs better than benchmark algorithms.

中文翻译：

---

移动边缘计算中的联合卸载和费用成本最小化

移动边缘计算（MEC）为物联网（IoT）带来了突破，因为它能够将任务从用户设备（UE）卸载到具有丰富计算资源的附近服务器。5G网络在传输速率上带来了巨大突破。与MEC和5G一起，任务执行延迟和下载时间延迟都将更短，并且可以提高UE的体验质量（QoE）。考虑到实际情况，MEC服务器的计算资源在一定程度上是有限的。因此，如何防止MEC资源的滥用和合理分配资源成为MEC系统的关键。在本文中，考虑了具有多用户的MEC系统，其中带有MEC服务器的基站（BS）不仅可以提供计算分流服务，还可以提供数据缓存服务。特别是，我们将数据传输和任务计算两者的费用作为UE总成本的一部分，然后针对下行资源分配，卸载决策和计算资源分配进行联合优化，以最大程度地减少时延。并向UE收费。提出的问题被公式化为一个混合整数规划（MIP），它是NP难的。因此，我们将原始问题分解为两个子问题，即下行资源分配问题和联合卸载决策与计算资源分配问题。然后，我们分别通过使用凸和非凸优化技术来解决这两个子问题。提出了一种迭代算法来获得多项式时间的次优解。