Hussain, FarookhHamdi, Aisha Muhammad A2023-11-262023-11-262023-11-16https://hdl.handle.net/20.500.14154/69848In vehicular fog computing, the idle resources of moving and parked vehicles can be used for computation purposes to minimize the processing delay of compute-intensive vehicular applications 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. Therefore, this thesis introduces an innovative and proactive methodology for task offloading in VFC. The key novelty of this approach is the use of utilization-based prediction techniques to predict a vehicle's future computational resource requirements. This predictive approach enables the intelligent selection of target nodes for task offloading, ensuring tasks are offloaded before resource exhaustion occurs. Moreover, the methodology proposed in this thesis includes an incentive mechanism to motivate fog node vehicles to accept incoming tasks and a service provider selection mechanism to help the overloaded node to find the most optimal target node vehicle that can effectively handle the offloaded task. The proactive nature of this approach promises an efficient, real-time, and responsive task offloading process, which is essential for meeting the demands of the Internet of vehicle applications.228enInternet of ThingsIoTInternet of VehiclesIoVVehicular fog computingVFCtask offloadingProactive-based offloadingTime-series predictionmachine learningMLIncentive mechanismService provider selectionThesis