| Abstrakt: |
Intelligent applications in smart transportation necessitate substantial computational power and energy resources. Nevertheless, the constraints imposed by IoT devices, such as limited processing power, memory, and energy resources, pose challenges for performing local processing on these devices. To tackle these challenges, vehicular fog computing has emerged as an innovative solution that aims to mitigate operational costs, enhance the efficiency of intelligent driving systems, and reduce energy consumption. In this paper, a cooperative energy-driven prediction algorithm based on V2V communication is proposed for offloading node selection in vehicular fog networks. It is utilized in a proposed multi-level intelligent adaptive mechanism to increase decision-making accuracy for offloading node selection, with the goal of minimizing energy consumption, maximizing vehicle capacity utilization, and improving the transportation system computational efficiency. The experimental results demonstrate that the proposed mechanism outperforms previous algorithms by improving system efficiency by 6.53% and 2.95%. Additionally, it enhances workload distribution by 53.52% and 5.57% compared to the aforementioned algorithms. The proposed algorithm aims to optimize energy consumption in the overall transportation network, achieving an average energy consumption of 0.49 based on the considered objective function and constraints. [ABSTRACT FROM AUTHOR] |
Full text from SpringerLink