返回
Task Offloading Oriented Cluster Generation Scheme in Vehicular Networks
DOI:10.1109/TVT.2024.3358792.png)
摘要
En 中文
In the ever-expanding and collaborative vehicular network, the formation of vehicle clusters is crucial for maintaining stable communications within each cluster. However, traditional cluster generation schemes often prioritize prolonged maintenance time rather than the better collaboration performance. This is due to the inherent conflict between extended maintenance and optimal collaboration. To tackle this issue, a novel cluster generation scheme is introduced with a specific focus on collaboration, particularly task offloading. The scheme jointly optimizes task offloading and cluster generating decisions to minimize the total task execution delay, while considering the cluster stability issue. Moreover, to ensure efficient resource utilization for vehicles with limited resources, the scheme jointly optimizes the allocation of computing resource and transmission power. To solve the optimization problem, an alternating iterative algorithm with fast convergence is designed. Numerical results demonstrate that, compared with the baseline schemes, the proposed scheme can achieve the minimum total task execution delay and enhance cluster stability.
Keyword:
Task analysis
Delays
Optimization
Collaboration
Iterative methods
Stability criteria
Convex functions
Vehicular networks
cluster generating
task offloading
alternating iterative algorithm
期刊
IF:
7.1
论文数:
1.8W
被引数:
6.6W
机构
引用论文
Task Partitioning and Offloading in DNN-Task Enabled Mobile Edge Computing Networks支持DNN任务的移动边缘计算网络中的任务划分和卸载

