You are viewing an old version of this page. View the current version.

Compare with Current View Page History

« Previous Version 12 Next »

A blueprint family which showcases end-to-end solution for edge services with KubeEdge edge stack. The first release will focus on the ML inference offloading use case. 

KubeEdge is a CNCF sandbox project widely adopted as a key industry reference Edge Computing architecture. With KubeEdge, application vendors can push a wide range of applications at the edge, including Mobile Edge services. It is an upstream project to Akraino community. There are other Akraino Blueprint projects with KubeEdge incorporated. This project family will focus on solutions centered around KubeEdge. Future releases may incorporate various components, e.g. hardware infrastructure etc. 


Case Attributes

Description

Informational

Type

New


Blueprint Family 

KubeEdge Offloading Family


Use Case

Emotion Identification Inference Offloading


Blueprint proposed

Edge ML Inference Offloading

Initial POD Cost (capex)

Less than 100KUSD


Scale

Multi-server; 5U Rack; 42U Rack


Applications

Application offloading from devices to edge


Power Restrictions

Less than 50KW


Preferred Infrastructure   orchestration

OpenStack - VM orchestration

KubeEdge performs application orchestration

OS - Linux

VNF Orchestration - ONAP


Additional Details

Submitter to provide additional use case   details






Committer

Committer

Company

 Committer Contact Info

Committer Bio

Committer Picture

Self Nominate for PTL (Y/N)

Jane ShenFuturewei jane.shen@futurewei.com


Yin DingFutureweiyin.ding@futurewei.com

Y
Tina TsouARMtina.tsou@arm.com


Xuan JiaChina Mobilejiaxuan@chinamobile.com


Jiafeng ZhuFutureweijiafeng.zhu@futurewei.com


Hanyu DingChina Mobiledinghanyu@chinamobile.com


Jeff BrowerSignalogicjbrower@signalogic.com










  • No labels