iVFC: A proactive methodology for task offloading in VFC
- Publication Type:
- Thesis
- Issue Date:
- 2023
Open Access
Copyright Clearance Process
- Recently Added
- In Progress
- Open Access
This item is open access.
The Internet of Things plays an important role in the development of the Internet of Vehicles, where vehicles have become more connected and intelligent. This has led to the emergence of many vehicular applications such as self-driving applications. However, these applications require a large number of computational resources and generate a huge number of tasks that requires a large amount of computation and storage capacity. As a result, the demand for more computational and communication resources from these vehicles has increased. To meet the increasing demand for enhanced computation and communication capacities in IoV, the common solution is to process these tasks using the high-capacity servers remotely located in the cloud. However, the cloud is not an ideal solution due to the long transmission distance and latency between the source vehicles and the cloud servers, which leads to an increase in latency and network congestion. Therefore, vehicular fog computing (VFC) has been proposed as a promising solution to address the limitations of traditional cloud computing.
In VFC, the idle resources of moving and parked vehicles can be used for computation purposes by offloading tasks from the edge servers or vehicles to nearby fog node vehicles for execution. However, the offloading decision is a complicated process and the selection of an appropriate target node is a crucial decision that the source node has to make.
After studying the recent literature on task offloading in VFC, we found that many solutions have been proposed in the literature to handle the task offloading process, however, most solutions are reactive-based. This means that each fog node vehicle will offload its computation tasks when it consumes all of its resources and becomes overloaded, which slows down the task execution process and affects the performance of the VFC network.
This thesis presents a novel and intelligent methodology for task offloading in VFC. The novelty of the proposed methodology lies in its proactive nature. By leveraging prior utilization-based prediction techniques, our methodology can proactively determine the need to offload a task to a target fog node vehicle based on the prior utilization-based prediction technique. Particularly, under the proposed methodology, the vehicle’s need for computational resources in the next time slot is intelligently predicted and this prediction is used as the criterion for target node selection and task offloading. Furthermore, the proposed methodology includes an incentive mechanism to motivate fog node vehicles (FNvs) to accept an incoming task.
Please use this identifier to cite or link to this item: