QoS and Fairness Oriented Dynamic Computation Offloading in the Internet of Vehicles based on Estimate Time of Arrival

The rapid development of Internet of Vehicles (IoV) and Mobile Edge Computing (MEC) enables vehicles to offload their applications to Roadside Units (RSU). However, without knowledge of vehicles' future locations, wireless connections between vehicles and RSUs are too vulnerable to finish offloading processes. Most existing methods allocate computation tasks statically, ignoring latency between task reception and processing in real IoV environments. Moreover, multiple services running on RSUs limit the availability of resources for offloading which require an efficient allocation of limited available resources. Therefore, this paper addresses the vehicular computation offloading problem by predicting vehicle mobility. We first introduce the Estimated Time of Arrival service into the vehicular MEC architecture to predict vehicles' driving state. Second, we formulate vehicular computation offloading as a dynamic process that efficiently selects the offloading location for each computation task and satisfies the constraints of limited available resources to balance QoS and response fairness. Thirdly, the cooperation among RSUs in our work optimizes the task QoS, but it increases the search space causing a high time consumption. We use the Dynamic Programming algorithm to optimize QoS and response fairness in the cooperative computation offloading problem and propose two offloading algorithms. To obtain the performance of our algorithms close to real IoV environments, we propose a fine-grained simulation method based on Veins. We evaluate our and existing algorithms based on real datasets from Erlangen, Germany, and Shenzhen, China.