...
Use Case Attributes | Description | Informational | |
Type | New Blueprint for AI on the Edge |
| |
Blueprint Family | Integrated Edge Cloud (IEC) |
| |
Use Case | Safety, security, and surveillance |
| |
Blueprint proposed Name | AI on the edge |
| |
Initial POD Cost (capex) | Leverage Unicycle POD - less than $150K |
| |
Scale & Type | up to 7 servers, x86/ Arm server or deep edge class With nVIDIA Tesla K80 GPUs |
| |
Applications | 1. Small scale IoT data aggregation and machine learning platform 2. Small scale deep learning models training for video data 3. Model training for AcumosApps |
| |
Power and memory restrictions | Less than 10Kw K8s 1.12.5 or above- Container Orchestration OS –CentOS 7.0 or above |
| |
Infrastructure orchestration | Docker 1.13.1 or above |
| |
SDN | Calico and K8s, and Containers serving as client/server (a database to collect raw data streams) and server/client (a database for trained models in binary format) |
| |
Dataplane | VPP | ||
Workload Type |
|
| |
Additional Details | There are mainly 4 pieces:
|
|
...