Adaptive Computation Offloading With Edge for 5G-Envisioned Internet of Connected Vehicles

Authors:
Publisher website
Google Scholar
Abstract
Nowadays, the applications related to Internet of connected vehicles (IoCV) have been greatly promoted by the roadside units (RSUs). To improve the transmission efficiency by the RSUs, 5G is introduced to the IoCV scenario for offering sufficient communication bandwidth. Generally, the traditional offloading destinations of the computing tasks in IoCV are the distant cloud servers, which consequently increases the response time of the tasks. Edge servers, placed together with macro base stations (MABSs) in 5G and RSUs, offer alternatives to host the tasks. However, the complicated locations of MABSs and RSUs make it difficult to distinguish the offloading destinations of the computing tasks in IoCV. In view of this, an adaptive computation offloading method, named ACOM, is devised for edge computing in 5G-envisioned IoCV to optimize the task offloading delay and resource utilization of the edge system. More specifically, the multi-objective evolutionary algorithm based on decomposition (MOEA/D) is fully leveraged to generate the available solutions. Then, the optimal offloading solution is obtained by utility evaluation. Eventually, the experimental results demonstrate the effectiveness of ACOM.
Funding Information
  • National Key Research and Development Program of China (2019YFE0190500)
  • National Natural Science Foundation of China (61872219, 61702277, 61601235)
  • Natural Science Foundation of Jiangsu Province of China (BK20160972)
  • Priority Academic Program Development of Jiangsu Higher Education Institutions (PAPD) fund

This publication has 27 references indexed in Scilit: