Enabling Inference Inside Software Switches

Yung Sheng Lu, Ching-Ju Lin

研究成果: Conference contribution同行評審

7 引文 斯高帕斯(Scopus)

摘要

Software Defined Networking (SDN) has been emerged to solve the problem of traditional network architectures. The ability of programmable switches renders us an opportunity to have computational tasks done in the switches. With this nice property, in this work, we investigate the potential of enabling machine learning inside a network. To this end, we propose a new architecture, Intra-Network Inference (INI), which equips each switch with a recently released component, called neural compute stick (NCS), to enable intra-switch neural network inference. Unlike conventional SDN architectures, which relay backend servers to enable inference, our INI performs inference locally at switches and, thereby, reduces the data forwarding overhead and inference latency.

原文English
主出版物標題2019 20th Asia-Pacific Network Operations and Management Symposium
主出版物子標題Management in a Cyber-Physical World, APNOMS 2019
發行者Institute of Electrical and Electronics Engineers Inc.
ISBN(電子)9784885523205
DOIs
出版狀態Published - 9月 2019
事件20th Asia-Pacific Network Operations and Management Symposium, APNOMS 2019 - Matsue, 日本
持續時間: 18 9月 201920 9月 2019

出版系列

名字2019 20th Asia-Pacific Network Operations and Management Symposium: Management in a Cyber-Physical World, APNOMS 2019

Conference

Conference20th Asia-Pacific Network Operations and Management Symposium, APNOMS 2019
國家/地區日本
城市Matsue
期間18/09/1920/09/19

指紋

深入研究「Enabling Inference Inside Software Switches」主題。共同形成了獨特的指紋。

引用此