|
|
 |
| |
|
|
|
Effective MEC assisted Internet of Vehicles Task Offloading Framework with DRL |
|
|
|
PP: 485-495 |
|
|
doi:10.18576/amis/200214
|
|
|
|
Author(s) |
|
|
|
Sulieman Shelash Mohammad,
Hamza Abu Owida,
Hanan Jadallah,
Asokan Vasudevan,
Mohammad Faleh Ahmmad Hunitie,
|
|
|
|
Abstract |
|
|
| The Internet of Vehicles (IoV) is a new paradigm that is being driven by advancements in automotive networking and communications. One well-liked method for bolstering delayed applications for entertainment is cloud computing. Nevertheless, cloud computing may cause significant delays for complex applications sensitive to latency, such as autonomous and assisted driving systems and emergency failure management. Mobile edge computing’s efficient processing capabilities near devices have led to extensive integration with the IoV.Therefore, this paper proposes an Effective Mobile Edge Computing-based Internet of Vehicles Task Offloading Framework (EMEC-IoVTOF) with deep reinforcement learning to reduce the latency in vehicular communication networks. The first step is to examine the limitations imposed by the car terminals’ usage of energy and communication bandwidth. Secondly, this paper uses the mathematical approach for computing the offloading cost of vehicle communication network processing is needed. The next step is to find the best offloading technique by applying particle swarm optimization to job offloading. Additionally, the inertia weight factor is engineered to adaptively vary in response to the objective function value to evade local optimization. In conclusion, the results of the simulation tests demonstrate that the suggested algorithm can efficiently distribute computing workloads in the IoV. |
|
|
|
|
|
|
|
