IEC Type 3: Autonomous vehicles as the edge for Integrated Edge Cloud (IEC) Blueprint Family

Blueprint species:

Use Case Attributes	Description	Informational
Type	New
Blueprint Family	Integrated Edge Cloud (IEC)
Use Case	Safety and security, driving assistant
Blueprint proposed Name	IEC Type 3: Autonomous vehicles as the edge
Initial POD Cost (capex)	N/A
Scale & Type	One per vehicle
Applications	Video Processing for AutoDriving (especially training deep learning models) lane guidance safety and security applications remote control
Power and memory restrictions	Autonoumous vehicles are power and memory constrained.
Infrastructure orchestration	Need Geolocation correlation with deep learning model (the trained ones in binary format)
SDN	Calico and K8s, and Containers serving as client/server (a database to collect raw videos/video streams) and server/client (a database for trained models in binary format)
Workload Type	Containers (Tensoflow, Keras containers) VMs
Dataplane	VPP w/ Direct GPU (e.g. GPUnet)
Additional Details	Different bus connection: Ethernet, CANbus, etc. There are mainly 4 pieces: a database to collect raw videos/video streams tons of containers with various models on training a database for trained models in binary format a database for queries records and transactions of database mentioned in 1 and 3.

Proposed PTL:

Ken Yi

Contributors:

@soshun@soshun.arai@arm.com

Committers:

Ken Yi