期刊
IEEE COMMUNICATIONS MAGAZINE
卷 56, 期 8, 页码 14-19出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/MCOM.2018.1701069
关键词
-
资金
- National Natural Science Foundation of China [61771374, 61771373, 61601357]
- China 111 Project [B16037]
- Fundamental Research Fund for the Central Universities [JB171501, JB181506, JB181507, JB181508]
The ultra-dense network (UDN) is envisioned to be an enabling and highly promising technology to enhance spatial multiplexing and network capacity in future 5G networks. Moreover, to address the conflict between computation-intensive applications and resource-constrained IoT mobile devices (MDs), multi-access mobile edge computing (MA-MEC), which provides the IoT MDs with cloud capabilities at the edge of radio access networks, has been proposed. UDN and MA-MEC are regarded as two distinct but complementary enabling technologies for 5G IoT applications. Over the past several years, lots of research on mobile edge computation offloading (MECO) - the key technique in MA-MEC has emerged. However, it is noticed that all these works focused on the single-tier base station scenario and computation offloading between the MD and the MEC server connected to the macro base station, and few works can be found on the problem of computation offloading for MA-MEC in UDN (i.e., a multi-user ultra-dense MEC server scenario). Toward this end, we study in this article the MECO problem in UDN and propose a heuristic greedy offloading scheme as our solution. Extensive numerical results and comparisons demonstrate the necessity for and superior performance of conducting computation offloading over multiple MEC servers.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据