A Reality Check on Inference at Mobile Networks Edge

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F19%3APU132061" target="_blank" >RIV/00216305:26230/19:PU132061 - isvavai.cz</a>

Výsledek na webu

<a href="https://dl.acm.org/citation.cfm?doid=3301418.3313946" target="_blank" >https://dl.acm.org/citation.cfm?doid=3301418.3313946</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1145/3301418.3313946" target="_blank" >10.1145/3301418.3313946</a>

Jazyk výsledku

angličtina

Název v původním jazyce

A Reality Check on Inference at Mobile Networks Edge

Popis výsledku v původním jazyce

Edge computing is considered a key enabler to deploy ArtificialIntelligence platforms to provide real-time applications such asAR/VR or cognitive assistance. Previous works show computingcapabilities deployed very close to the user can actually reduce theend-to-end latency of such interactive applications. Nonetheless,the main performance bottleneck remains in the machine learninginference operation. In this paper, we question some assumptionsof these works, as the network location where edge computing isdeployed, and considered software architectures within the frame-work of a couple of popular machine learning tasks. Our experimen-tal evaluation shows that after performance tuning that leveragesrecent advances in deep learning algorithms and hardware, net-work latency is now the main bottleneck on end-to-end applicationperformance. We also report that deploying computing capabilitiesat the first network node still provides latency reduction but, over-all, it is not required by all applications. Based on our findings, weoverview the requirements and sketch the design of an adaptivearchitecture for general machine learning inference across edgelocations.

Název v anglickém jazyce

A Reality Check on Inference at Mobile Networks Edge

Popis výsledku anglicky

Edge computing is considered a key enabler to deploy ArtificialIntelligence platforms to provide real-time applications such asAR/VR or cognitive assistance. Previous works show computingcapabilities deployed very close to the user can actually reduce theend-to-end latency of such interactive applications. Nonetheless,the main performance bottleneck remains in the machine learninginference operation. In this paper, we question some assumptionsof these works, as the network location where edge computing isdeployed, and considered software architectures within the frame-work of a couple of popular machine learning tasks. Our experimen-tal evaluation shows that after performance tuning that leveragesrecent advances in deep learning algorithms and hardware, net-work latency is now the main bottleneck on end-to-end applicationperformance. We also report that deploying computing capabilitiesat the first network node still provides latency reduction but, over-all, it is not required by all applications. Based on our findings, weoverview the requirements and sketch the design of an adaptivearchitecture for general machine learning inference across edgelocations.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2019

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Proceedings of the 2nd ACM International Workshop on Edge Systems, Analytics and Networking (EDGESYS '19)

ISBN

978-1-4503-6275-7

ISSN

—

e-ISSN

—

Počet stran výsledku

6

Strana od-do

54-59

Název nakladatele

Association for Computing Machinery

Místo vydání

Dressden

Místo konání akce

Dressden

Datum konání akce

25. 3. 2019

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000470896200010