分裂dnn时变边缘计算系统的最优任务分配

Davide Callegaro, Yoshitomo Matsubara, M. Levorato
{"title":"分裂dnn时变边缘计算系统的最优任务分配","authors":"Davide Callegaro, Yoshitomo Matsubara, M. Levorato","doi":"10.1109/GLOBECOM42002.2020.9322344","DOIUrl":null,"url":null,"abstract":"Many modern applications rely on complex machine learning algorithms, such as Deep Neural Networks (DNNs), to analyze images. However, both mobile and edge computing strategies may fail to provide satisfactory performance in some parameter regions. To mitigate this issue, the research community recently proposed methods to split the execution of DNNs to optimize the balance between computing load allocation and channel usage. Building on this set of results, this paper presents an optimization framework that enables the dynamic control of how images are processed in mobile device-edge server systems. The system is modeled as a Markov process, and a Linear Fractional Program is defined to identify the optimal stationary state-action distribution minimizing the overall average inference time under a constraint on the number of discarded images. Results indicate the advantage of using a dynamic control strategy with respect to available fixed strategies.","PeriodicalId":12759,"journal":{"name":"GLOBECOM 2020 - 2020 IEEE Global Communications Conference","volume":"83 1","pages":"1-6"},"PeriodicalIF":0.0000,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"5","resultStr":"{\"title\":\"Optimal Task Allocation for Time-Varying Edge Computing Systems with Split DNNs\",\"authors\":\"Davide Callegaro, Yoshitomo Matsubara, M. Levorato\",\"doi\":\"10.1109/GLOBECOM42002.2020.9322344\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Many modern applications rely on complex machine learning algorithms, such as Deep Neural Networks (DNNs), to analyze images. However, both mobile and edge computing strategies may fail to provide satisfactory performance in some parameter regions. To mitigate this issue, the research community recently proposed methods to split the execution of DNNs to optimize the balance between computing load allocation and channel usage. Building on this set of results, this paper presents an optimization framework that enables the dynamic control of how images are processed in mobile device-edge server systems. The system is modeled as a Markov process, and a Linear Fractional Program is defined to identify the optimal stationary state-action distribution minimizing the overall average inference time under a constraint on the number of discarded images. Results indicate the advantage of using a dynamic control strategy with respect to available fixed strategies.\",\"PeriodicalId\":12759,\"journal\":{\"name\":\"GLOBECOM 2020 - 2020 IEEE Global Communications Conference\",\"volume\":\"83 1\",\"pages\":\"1-6\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2020-12-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"5\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"GLOBECOM 2020 - 2020 IEEE Global Communications Conference\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/GLOBECOM42002.2020.9322344\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"GLOBECOM 2020 - 2020 IEEE Global Communications Conference","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/GLOBECOM42002.2020.9322344","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 5

摘要

许多现代应用依赖于复杂的机器学习算法,如深度神经网络(dnn)来分析图像。然而,移动和边缘计算策略在某些参数区域可能无法提供令人满意的性能。为了缓解这个问题,研究团体最近提出了分割dnn执行的方法,以优化计算负载分配和信道使用之间的平衡。基于这组结果,本文提出了一个优化框架,可以动态控制在移动设备边缘服务器系统中如何处理图像。将系统建模为马尔可夫过程,定义线性分数阶规划,在给定丢弃图像数量的约束下,以最小的总体平均推理时间识别最优稳态-动作分布。结果表明,相对于可用的固定策略,使用动态控制策略具有优势。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Optimal Task Allocation for Time-Varying Edge Computing Systems with Split DNNs
Many modern applications rely on complex machine learning algorithms, such as Deep Neural Networks (DNNs), to analyze images. However, both mobile and edge computing strategies may fail to provide satisfactory performance in some parameter regions. To mitigate this issue, the research community recently proposed methods to split the execution of DNNs to optimize the balance between computing load allocation and channel usage. Building on this set of results, this paper presents an optimization framework that enables the dynamic control of how images are processed in mobile device-edge server systems. The system is modeled as a Markov process, and a Linear Fractional Program is defined to identify the optimal stationary state-action distribution minimizing the overall average inference time under a constraint on the number of discarded images. Results indicate the advantage of using a dynamic control strategy with respect to available fixed strategies.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信