Benefiting from its abundant computing resourcesand low computing latency, mobile edge computing (MEC) isa promising approach for enhancing the computing capacity ofthe 5G Internet of vehicles (IoV). Because of the high mobility,handover is frequent a...
Benefiting from its abundant computing resourcesand low computing latency, mobile edge computing (MEC) isa promising approach for enhancing the computing capacity ofthe 5G Internet of vehicles (IoV). Because of the high mobility,handover is frequent and inevitable in IoV networks. In thispaper, we investigate an edge collaborative task offloading andsplitting strategy in MEC-enabled IoV networks, in which thetask is splitted on the edge and paralleling executed by eachpart of the task on several MEC servers when handover isoccured. Applications in IoV networks have flexible requirementson latency and energy consumption. To realize the tradeoffbetween latency and energy consumption, we formulate the taskoffloading and splitting as an optimization problem with the aimof minimizing the total cost of latency and energy consumptionby jointly optimizing the task splitting ratio and uplink transmitpower of vehicle terminal (VT). Because the proposed problemis non-smooth and non-convex, we divide the original probleminto two convex subproblems, and apply an alternate convexsearch (ACS) algorithm to obtain the optimized solution withlow computational complexity. Numerical simulation results showthat the proposed method can adjust the offloading strategyproperly according to task preference, and obtain a lower totalcost compared with the baseline algorithms.