TY - JOUR
T1 - Computation Offloading for Mobile Edge Computing Enabled Vehicular Networks
AU - Wang, Jun
AU - Feng, Daquan
AU - Zhang, Shengli
AU - Tang, Jianhua
AU - Quek, Tony Q.S.
N1 - Funding Information:
This work was supported in part by the Natural Science Foundation of China under Grant 61701317 and Grant 61771315, in part by the Young Elite Scientists Sponsorship Program by the CAST under Grant 2018QNRC001, in part by the Guangdong Natural Science Foundation under Grant 2017A030310371, in part by the Guangdong Education Project under Grant 2016KZDXM006, in part by the Shenzhen Basic Research Program under Grant JCYJ20170302150006125, Grant JCYJ20160226192223251, Grant JCYJ20170412104656685, and Grant JCYJ20170302142312688, in part by the Start-up Fund of Shenzhen University under Grant 2017076, in part by the Tencent ‘‘Rhinoceros Birds’’ Scientific Research Foundation for Young Teachers of Shenzhen University, and in part by the Start-up Fund of the Peacock Project.
PY - 2019
Y1 - 2019
N2 - The emergence of computation-intensive and delay-sensitive vehicular applications poses a great challenge for individual vehicles with limited computation resources. Mobile edge computing (MEC) is a new paradigm shift that can enhance vehicular services through computation offloading. However, the high mobility of vehicles will affect offloading performance. In this paper, we investigate the vehicular user (VU) computation overhead minimization problem in MEC-enabled vehicular networks by jointly optimizing the computation and communication resources' allocation (transmit power and uploading time for communication, and the offloading ratio and local CPU frequency for computation). This optimization problem is nonconvex and difficult to solve directly. To deal with this issue, we first transform the original problem into an equivalent one. Then, we decompose the equivalent problem into a two-level problem. In addition, we develop a low-complexity algorithm to obtain the optimal solution. The numerical results demonstrate that the proposed algorithm can significantly outperform benchmark algorithms in terms of computation overhead.
AB - The emergence of computation-intensive and delay-sensitive vehicular applications poses a great challenge for individual vehicles with limited computation resources. Mobile edge computing (MEC) is a new paradigm shift that can enhance vehicular services through computation offloading. However, the high mobility of vehicles will affect offloading performance. In this paper, we investigate the vehicular user (VU) computation overhead minimization problem in MEC-enabled vehicular networks by jointly optimizing the computation and communication resources' allocation (transmit power and uploading time for communication, and the offloading ratio and local CPU frequency for computation). This optimization problem is nonconvex and difficult to solve directly. To deal with this issue, we first transform the original problem into an equivalent one. Then, we decompose the equivalent problem into a two-level problem. In addition, we develop a low-complexity algorithm to obtain the optimal solution. The numerical results demonstrate that the proposed algorithm can significantly outperform benchmark algorithms in terms of computation overhead.
UR - http://www.scopus.com/inward/record.url?scp=85066848274&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85066848274&partnerID=8YFLogxK
U2 - 10.1109/ACCESS.2019.2915959
DO - 10.1109/ACCESS.2019.2915959
M3 - Article
AN - SCOPUS:85066848274
VL - 7
SP - 62624
EP - 62632
JO - IEEE Access
JF - IEEE Access
SN - 2169-3536
M1 - 8712145
ER -