No abstract

Mobile edge computing (MEC) has been developed as a key technique to handle the explosive computation demands of vehicles. However, it is non-trivial to realize high-reliable and low-latency vehicular requirements among distributed and capacity-constrained MEC nodes. Besides, the dynamic and uncertain vehicular environments bring extra challenges to preserve the long-term satisfactory user experience. In this paper, an adaptive resource allocation approach is investigated to enhance the user experience in vehicular edge computing networks. Specifically, leveraging the idea of task scalability, a model for balancing computing quality and resource consumption is introduced to exploit the computational resources fully. Towards the goal of minimizing the long-term computing quality loss by specifying the needed resource and the expected quality of each running task, a mix-integer non-linear stochastic optimization problem is formulated to jointly optimize the allocation of radio and computing resources, as well as the task placement. Due to the unpredictable network states and the high computational complexity of the formulated problem, the long-term optimization problem is firstly decomposed into a series of one-slot problems, and then, an iterative algorithm is provided to derive a computation efficient solution. Finally, both rigorous theoretical analysis and extensive trace-driven simulations validate the efficacy of our proposed approach. INDEX TERMS Vehicular edge computing, long-term user experience, computing quality optimization, adaptive resource allocation.

No abstract

In vehicular relay networks, the quality of communication link has a significant impact on the stable and reliable communication requirements. Most earlier studies focused on the influence of relay probability on link connectivity while little attention has been paid to the impact of packet collision. In complex mobile scenarios, vehicle density is proportional to relay probability, while proportional to data packet collision probability. Meanwhile, vehicle density and packet collision affect the quality of communication link in the relay network. This condition inspires them to study the link connectivity in vehicular relay networks based on carrier sense multiple access with collision avoidance. First, the relationships among vehicle density, vehicle speed, packet collision probability and relay probability are studied in relay communication. Second, due to the high‐speed movement of vehicles, an analysis model, considering the mobility of vehicle nodes, is conducted to analyse the downlink performance in relay communication networks. Finally, a platoon scheme is proposed to reduce packet collision probability, considering the vehicle density and backoff window size on vehicle‐to‐roadside unit communication. Extensive numerical results indicate that the platoon model has a great advantage in terms of downlink performance, especially in the case of dense traffic flow.

No abstract