期刊
IEEE WIRELESS COMMUNICATIONS LETTERS
卷 9, 期 8, 页码 1182-1186出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/LWC.2020.2984620
关键词
Accidents; Computational modeling; Task analysis; Delays; Data integrity; Data models; Autonomous vehicles; Autonomous driving; mobile edge computing; deep learning; computation offloading
资金
- U.S. Office of the Under Secretary of Defense for Research and Engineering [FA8750-15-2-0119]
- A*STAR under its RIE2020 Advanced Manufacturing and Engineering Industry Alignment Fund-Pre Positioning [A19D6a0053]
This letter proposes an edge learning-based offloading framework for autonomous driving, where the deep learning tasks can be offloaded to the edge server to improve the inference accuracy while meeting the latency constraint. Since the delay and the inference accuracy are incurred by wireless communications and computing, an optimization problem is formulated to maximize the inference accuracy subject to the offloading probability, the pre-braking probability, and data quality. Simulations demonstrate the superiority of the proposed offloading framework.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据