Mobile-Edge Computation Offloading for Ultradense IoT Networks
Mobile-Edge Computation Offloading for Ultradense IoT Networks
复制标题
超密集物联网网络的移动边缘计算卸载
DOI：
10.1109/jiot.2018.2838584
复制
发表时间：
2018-12-01
影响因子：
10.6
通讯作者：
Kato, Nei
中科院分区：
文献类型：
--
作者：
Guo, Hongzhi;Liu, Jiajia;Kato, Nei
大规模物联网（IoT）移动的设备（MD）的出现和超密集5G小区的部署推动了IoT向超密集IoT网络的演进。为了满足不断增长的物联网应用对服务质量和体验质量的多样化需求，超密集物联网网络面临着前所未有的挑战。其中，如何解决物联网移动的应用对资源的需求与物联网移动设备对资源的需求之间的矛盾是一个根本问题。通过将物联网MD的计算任务卸载到部署在无线电接入基础设施（包括宏基站（MBS）和小小区）的边缘服务器，移动边缘计算卸载（MECO）为我们提供了一种有前途的解决方案。然而，请注意，现有的MECO研究主要集中在单层基站场景和MD与连接到MBS的边缘服务器之间的计算卸载。在超密集物联网网络中执行MECO的工作很少，即，多用户超密集边缘服务器场景。为此，我们提供了这篇论文来研究超密集物联网网络中的MECO问题，并提出了一个双层博弈论贪婪卸载方案作为我们的解决方案。大量的数值结果证实了在超密集物联网网络中的多个边缘服务器之间进行计算卸载的上级性能。
The emergence of massive Internet of Things (IoT) mobile devices (MDs) and the deployment of ultradense 5G cells have promoted the evolution of IoT toward ultradense IoT networks. In order to meet the diverse quality-of-service and quality of experience demands from the ever-increasing IoT applications, the ultradense IoT networks face unprecedented challenges. Among them, a fundamental one is how to address the conflict between the resource-hungry IoT mobile applications and the resource-constrained IoT MDs. By offloading the IoT MDs’ computation tasks to the edge servers deployed at the radio access infrastructures, including macro base station (MBS) and small cells, mobile-edge computation offloading (MECO) provides us a promising solution. However, note that available MECO research mostly focused on single-tier base station scenario and computation offloading between the MDs and the edge server connected to the MBS. Little works can be found on performing MECO in ultradense IoT networks, i.e., a multiuser ultradense edge server scenario. Toward this end, we provide this paper to study the MECO problem in ultradense IoT networks, and propose a two-tier game-theoretic greedy offloading scheme as our solution. Extensive numerical results corroborate the superior performance of conducting computation offloading among multiple edge servers in ultradense IoT networks.