A dynamic task offloading method in vehicle fog environment for urban roads
- 1Anhui Communications Vocational & Technical College
Abstract
In urban road environments, efficient task offloading in Vehicular Ad Hoc Networks (VANETs) is critical for maximizing local resource utilization, reducing latency, and enhancing resource efficiency in dynamic vehicular fog systems. This paper proposes CDDPGM, a hierarchical task-offloading framework that combines vehicle clustering, Deep Deterministic Policy Gradient (DDPG), and inter-cluster Max-Max scheduling. The vehicle-RSU clustering stage first groups vehicles according to communication bandwidth and mobility; the DDPG scheduler then learns intra-cluster offloading decisions by jointly considering vehicle speed, bandwidth, task deadlines, and computing-resource constraints; finally, the Max-Max strategy redistributes waiting tasks among clusters when local cluster resources are insufficient. The novelty of CDDPGM lies in coupling bandwidth-aware clustering, continuous-control reinforcement learning, and cross-cluster workload redistribution in one hierarchical vehicle-fog-RSU-cloud framework, whereas most existing DRL offloading methods focus on a single RSU/MEC layer or optimize only local offloading actions. Simulation results show that, compared with NSGA-II, PSO, and Random offloading, CDDPGM reduces the average number of uncompleted tasks by 30.17%, 36.25%, and 42.23%, reduces average execution time by 2.38%, 4.65%, and 7.87%, and reduces cloud-side instruction execution by 15.34%, 18.68%, and 26.29%, respectively.
Related
- Rationale and study design for the Social Environment and Cognitive Health in Urban and Rural Areas study
- Climate change and human health in the urban environment of the Eastern Mediterranean and Middle East: A workshop report.
- Built environment and emergency medical services response time in a high-density megacity: multilevel evidence from urban–suburban
- The effect of differences in viewing environment and method on physiological responses and perceptual stability while viewing three-dimensional images
- Urban Sprawl and Traffic-Related Air Pollution in Greater Gaborone: A Spatial Analysis of the Land Use–Transport–Environment Relationship
BibTeX
@article{yang2026dynamic,
title = {{A dynamic task offloading method in vehicle fog environment for urban roads}},
author = {Liqun Yang},
journal = {Scientific Reports},
year = {2026},
month = aug,
doi = {10.1038/s41598-026-64894-x},
url = {https://doi.org/10.1038/s41598-026-64894-x},
note = {CC BY},
}
RIS
TY - JOUR
TI - A dynamic task offloading method in vehicle fog environment for urban roads
AU - Liqun Yang
PY - 2026
DA - 2026/08/01
JO - Scientific Reports
DO - 10.1038/s41598-026-64894-x
UR - https://doi.org/10.1038/s41598-026-64894-x
AB - In urban road environments, efficient task offloading in Vehicular Ad Hoc Networks (VANETs) is critical for maximizing local resource utilization, reducing latency, and enhancing resource efficiency in dynamic vehicular fog systems. This paper proposes CDDPGM, a hierarchical task-offloading framework that combines vehicle clustering, Deep Deterministic Policy Gradient (DDPG), and inter-cluster Max-Max scheduling. The vehicle-RSU clustering stage first groups vehicles according to communication bandwidth and mobility; the DDPG scheduler then learns intra-cluster offloading decisions by jointly considering vehicle speed, bandwidth, task deadlines, and computing-resource constraints; finally, the Max-Max strategy redistributes waiting tasks among clusters when local cluster resources are insufficient. The novelty of CDDPGM lies in coupling bandwidth-aware clustering, continuous-control reinforcement learning, and cross-cluster workload redistribution in one hierarchical vehicle-fog-RSU-cloud framework, whereas most existing DRL offloading methods focus on a single RSU/MEC layer or optimize only local offloading actions. Simulation results show that, compared with NSGA-II, PSO, and Random offloading, CDDPGM reduces the average number of uncompleted tasks by 30.17%, 36.25%, and 42.23%, reduces average execution time by 2.38%, 4.65%, and 7.87%, and reduces cloud-side instruction execution by 15.34%, 18.68%, and 26.29%, respectively.
SN - 2045-2322
ER -