Versions Compared

Key

  • This line was added.
  • This line was removed.
  • Formatting was changed.

...

Attributes

Description

Type

New

Industry Sector

TelcoHealthCare, CloudEducation

Business driver•With

coronavirus With corona virus spreading worldwide, video conferences with software terminals are used frequently during remote work   

•For vertical industries such as online education, remote telemedicine, and first response, some XR information will be added on the video conference, all these need low latency and high bandwidth network. 

62% Rural kids are missing their classes since the Pandemic started, due to no or very low internet bandwidth. While teachers and students are predominantly from surrounding areas, there is no need for the video feeds to be processed 100s or 1000s of miles away from the rural network. Processing at the edge will allow localized educational platform to operate with low internet bandwidth.
Patients and doctors need very high definition video to engage with real impact. 5G provides low latency/high bandwidth opportunity but unless the processing is done at the edge, near to where the doctor and patient is, the opportunity can't be utilized to improve doctor-patient engagements.

Business use cases

  1.  Video Processing : Enhance Engagement Quality, Augment Video with information, Create Virtual environment, Transcribe engagements
  2.  Telehealth : Appointment Scheduling, Payment Processing, Electronic Health Records
  3.  Gamification : Reinforce Corrective Behavior, Track Progress, Generate Trends
  4.  Learning Management System : AI Teacher Assist, Early Progress Prediction

Business use cases

1.  video conference on edge

2.  AR/VR on video conference on edge

Business Cost - Initial Build Cost Target Objective

Move currently public cloud-based zoom video applications to Host Video applications, Health Application, LMS on the edge, we can still remain the control plane on the cloud, and media plane to be close to customer site such as MEC servers in telco central offices.

We choose ARM X86 server to deploy the MEC platform to reduce the cost.

In order to support vertical industry specific AR/XR features during video conference, ARM server need have GPU inside. 

•2 ARM Nodes

•2 X86 Nodes ( The PowerEdge XE2420 provides a short-depth, dense, Dual-socket, 2U server)

•Kubernetes v 1.17 for ARM(Open Source)

•GPU (NVIDIA V100/s or NVIDIA RTX6000) for AR/VR and AI GPU (AMD, NVIDIA)

Business Cost – Target Operational Objective

It more like a cloud platform, but it's specific for the edge site.  

•It needs Helm and Ansible for the automation and management tools to keep operational cost lower

•Maintain a mixed edge platform including x86 and Arm. It's more complexARM. 

•Kubernetes v1.17 for ARM

Android 10.0

17 

•Android, IOS 

•GPU ( NVIDIA V100/s or NVIDIA RTX6000•GPU (AMD, NVIDIA)

•Both Arm ARM and X86 can support it.

Security need

Security is very important in this use case, especially for containerized applicationsmechanisms that can be implemented at each layer of abstraction

Regulations

N/A

Other restrictions

N/A

Additional details

N/A

...

Case Attributes

Description

Type

New

Blueprint Family - Proposed   Name

Tami COVID-19 Blueprint Family

Use CaseVideo Conference

  1. Health Application on Edge
  2. Education Application on Edge

Blueprint proposed Name

Tami COVID-19 Blueprint Family: Remote cooperation based on video conference on EdgeRuralEdge


2 PowerEdge XE2420

Initial POD Cost (capex)

2 Arm bare metal machines Dual-socket, 2U server, 1 10G switch, 1 AMD GPU

Scale & Type

For the smallest deployment, this requires 2 Arm X86 bare metal machines. For large deployments, this could span to large number of bare metal machines.

ApplicationsVideo conference for large scale soft-terminals, Online education, telemedicine, remote command in first response

.Online Education(Sage.Camp), Telehealth(docs@home), Gamification(Roblox), Video Processing

Power Restrictions

N/A

Infrastructure orchestration

Host:

•Orchestrator: Kubernetes

•Bare Metal Provisioning:AnsibleProvisioning : Ansible

•Kubernetes Provisioning:KuDProvisioning: KuD

•OS: Ubuntu

•Database: MySQL /MariaDB

•Application: Python, Node.js, React

•GPU Driver: AMD X86,NVIDIA:

•Network: OVS, WebRTC

GPU Driver (AMDX86, NVIDIA)



SDN

N/A

Workload Type

•Android /IOS applications 

Additional Details

N/A


As per the Akraino Community process and directed by TSC, a blueprint which has only one nominee for Project Technical Lead (PTL) will be the elected lead once at least one committer seconds the nomination after the close of nominations.  If there are two or more, an election will take place.

Self Nominations begins on 16 December 2020 and will conclude on 23 December 2020


Committer

Committer

Company

 Committer Contact Info

Committer Bio

Committer Picture

Self Nominate for PTL (Y/N)

Arm


N
Wenhui Zhang
Biswajit Dedocs@home
Bytedance

wenhui.zhang@bytedance.com

wenhuizhang.psu@gmail.com



N
Biswajit De
hibisu2006@gmail.com


Surojit BanerjeeAWSsurojitb@amazon.com

Y
K. Daya
sdayak@gmail.com


Apoorv SalariaDHSapoorvsalaria@gmail.com


Subhranshu DasEricssonsubhranshu.das@gmail.com