Intelligent dynamic service pricing strategy for multi-user vehicle-aided MEC networks

With the increasing popularity of smart user equipments (UEs), numerous exciting wireless big data services are coming into life. However, due to the constraints of physical size, UEs are struggling with limited battery energy and computation capacity. In this paper, we propose a multi-user vehicle-aided multi-access edge computing (MEC) network architecture by deploying parked vehicles as the temporary computation service providers. A dynamic pricing strategy is proposed to minimize the energy consumption of UEs under the constraints on quality of service while maximize mobile service providers (MSPs)’ revenue. A differential evolution (DE) algorithm is proposed to determine UE’s fine-grained offloading decision. Moreover, a Q-learning algorithm is utilized to assist the DE algorithm in selecting the proper unit service price. The results show that the proposed dynamic pricing strategy can achieve better performance than the fixed pricing strategy and the differential pricing strategy regarding the overall cumulative cost. In addition, the proposed approach promises higher resource efficiency in comparison with all local execution and random offloading algorithms. The results obtained in this paper can be applied to design the future healthcare service pricing scheme of the IoT-based intelligent system.