Abstract
The introduction of mobile edge computing (MEC) in vehicular network has been a promising paradigm to improve vehicular services by offloading computation‐intensive tasks to the MEC server. To avoid the overload phenomenon in MEC server, the vast idle resources of parked vehicles can be utilized to effectively relieve the computational burden on the server. Furthermore, unbalanced load allocation may cause larger latency and energy consumption. To solve the problem, the reported works preferred to allocate workload between MEC server and single parked vehicle. In this paper, a multiple parked vehicle‐assisted edge computing (MPVEC) paradigm is first introduced. A joint load balancing and offloading optimization problem is formulated to minimize the system cost under delay constraint. In order to accomplish the offloading tasks, a multiple offloading node selection algorithm is proposed to select several appropriate PVs to collaborate with the MEC server in computing tasks. Furthermore, a workload allocation strategy based on dynamic game is presented to optimize the system performance with jointly considering the workload balance among computing nodes. Numerical results indicate that the offloading strategy in MPVEC scheme can significantly reduce the system cost and load balancing of the system can be achieved.
Highlights
As road traffic density continues to increase and traffic data explodes, the limited computing capacity of onboard terminals cannot meet the communication and computing demand of computationally intensive onboard applications [1, 2]
The offloading strategy is proposed to solve the optimization problem, which includes offloading node selection and workload allocation (ii) Considering the parked probability and resource availability of PVs, a multiple offloading nodes selection algorithm is adopted to select several candidate offloading nodes among vehicles and mobile edge computing (MEC) server (iii) Considering the sequential nature of offloading decisions and the resource consumption during task execution, an efficient workload allocation strategy based on dynamic game is proposed to optimize system utility while considering load balancing
Considering that the resource states of MEC servers and PVs are time-varying during task execution, an efficient workload allocation strategy is developed to optimize system performance and keep the load balancing
Summary
As road traffic density continues to increase and traffic data explodes, the limited computing capacity of onboard terminals cannot meet the communication and computing demand of computationally intensive onboard applications [1, 2]. Compared with remote cloud computing, it can use resource-rich servers at the roadside unit (RSU) to provide users with low-latency, high-bandwidth application services [7] Onboard applications such as augmented reality and autonomous driving are with higher demands on data processing and storage capabilities and still require more available resources [8, 9]. The offloading strategy is proposed to solve the optimization problem, which includes offloading node selection and workload allocation (ii) Considering the parked probability and resource availability of PVs, a multiple offloading nodes selection algorithm is adopted to select several candidate offloading nodes among vehicles and MEC server (iii) Considering the sequential nature of offloading decisions and the resource consumption during task execution, an efficient workload allocation strategy based on dynamic game is proposed to optimize system utility while considering load balancing.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
