科研成果详情

发表状态已发表Published
题名DNN acceleration in vehicle edge computing with mobility-awareness: A synergistic vehicle–edge and edge–edge framework
作者
发表日期2024-09-01
发表期刊Computer Networks
ISSN/eISSN1389-1286
卷号251
摘要

In recent years, vehicular networks have seen a proliferation of applications and services such as image tagging, lane detection, and speech recognition. Many of these applications rely on Deep Neural Networks (DNNs) and demand low-latency computation. To meet these requirements, Vehicular Edge Computing (VEC) has been introduced to augment the abundant computation capacity of vehicular networks to complement limited computation resources on vehicles. Nevertheless, offloading DNN tasks to MEC (Multi-access Edge Computing) servers effectively and efficiently remains a challenging topic due to the dynamic nature of vehicular mobility and varying loads on the servers. In this paper, we propose a novel and efficient distributed DNN Partitioning And Offloading (DPAO), leveraging the mobility of vehicles and the synergy between vehicle–edge and edge–edge computing. We exploit the variations in both computation time and output data size across different layers of DNN to make optimized decisions for accelerating DNN computations while reducing the transmission time of intermediate data. In the meantime, we dynamically partition and offload tasks between MEC servers based on their load differences. We have conducted extensive simulations and testbed experiments to demonstrate the effectiveness of DPAO. The evaluation results show that, compared to offloaded all tasks to MEC server, DPAO reduces the latency of DNN tasks by 2.4x. DPAO with queue reservation can further reduce the task average completion time by 10%.

关键词Deep neural networks Task partitioning Vehicular edge computing
DOI10.1016/j.comnet.2024.110607
URL查看来源
收录类别SCIE
语种英语English
WOS研究方向Computer Science ; Engineering ; Telecommunications
WOS类目Computer Science, Hardware & Architecture ; Computer Science, Information Systems ; Engineering, Electrical & Electronic ; Telecommunications
WOS记录号WOS:001266229700001
Scopus入藏号2-s2.0-85197449541
引用统计
文献类型期刊论文
条目标识符https://repository.uic.edu.cn/handle/39GCC9TT/11723
专题理工科技学院
通讯作者Cui, Lin
作者单位
1.Department of Computer Science,Jinan University,Guangzhou,China
2.Guangdong Key Laboratory of Data Security and Privacy Preserving,China
3.Department of Computer Science,Loughborough University,United Kingdom
4.BNU-UIC Institute of Artificial Intelligence and Future Networks,Beijing Normal University (BNU Zhuhai),China
5.BNU-HKBU United International College,Zhuhai,China
推荐引用方式
GB/T 7714
Zheng, Yuxin,Cui, Lin,Tso, Fung Poet al. DNN acceleration in vehicle edge computing with mobility-awareness: A synergistic vehicle–edge and edge–edge framework[J]. Computer Networks, 2024, 251.
APA Zheng, Yuxin, Cui, Lin, Tso, Fung Po, Li, Zhetao, & Jia, Weijia. (2024). DNN acceleration in vehicle edge computing with mobility-awareness: A synergistic vehicle–edge and edge–edge framework. Computer Networks, 251.
MLA Zheng, Yuxin,et al."DNN acceleration in vehicle edge computing with mobility-awareness: A synergistic vehicle–edge and edge–edge framework". Computer Networks 251(2024).
条目包含的文件
条目无相关文件。
个性服务
查看访问统计
谷歌学术
谷歌学术中相似的文章
[Zheng, Yuxin]的文章
[Cui, Lin]的文章
[Tso, Fung Po]的文章
百度学术
百度学术中相似的文章
[Zheng, Yuxin]的文章
[Cui, Lin]的文章
[Tso, Fung Po]的文章
必应学术
必应学术中相似的文章
[Zheng, Yuxin]的文章
[Cui, Lin]的文章
[Tso, Fung Po]的文章
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。