BP State: Incubation BP. It has already been approved and voted by Akraino TSC Incubation Review at TSC 2022-06-28 (Tuesday) 7:00 am Pacific - Akraino - Akraino Confluence .
V2X、artificial Intelligence app、enterprise OA
Real World needs:
-92 percent of respondents reported having a multi-cloud strategy* and has multi cloud vendors.
-Hybrid cloud management including public cloud, on premise and edge cloud.
-Multi-cluster deployment strategy to achieve high availability.
-Disaster recovery scenario. The application system is usually deployed in the geo-redundant mode.
Business use cases
According to the CFN Ubiquitous Computing Force Scheduling, the computing force of public cloud, edge cloud and external third parties is managed to achieve consistent cluster, policy, configuration and traffic management, and to achieve resource-level and task-level scheduling.
* Ubiquitous Computing Force concept：Logically, the computing force is more three-dimensional, including three levels: center, edge and terminal. Physically, resources span data centers in different regions. The kernel is heterogeneous, including general computing force ( x86/ARM ) and special computing force ( GPU/DPU... ).
Business Cost - Initial Build Cost Target Objective
Set up the infrastructure environment preparation to achieve multiple clusters management. Multi Cloud environment should be deployed in more than 3 servers in a single rack at a low cost.
Business Cost – Target Operational Objective
Build the Ubiquitous Computing Force Scheduling BP which includes:
-Set up the infrastructure environment to achieve multiple clusters management, and expand cluster from central cloud to edge cloud;
-Scheduling mechanism based on cloud-edge collaboration, such as traffic governance and scheduling across nodes;
-The management and monitoring of cloud and edge clusters;
-Enrich scheduling strategy;（such as latency, task type, etc.）
more details see the attachment please
Blueprint Family - Proposed Name
|CFN (Computing Force Network) family
XR, Video Streaming, V2X，Ubiquitous Computing Force Scheduling
Blueprint proposed Name
Initial POD Cost (capex)
|At least 10 virtual machines, depends on deployment scale
Scale & Type
For large deployments, this could span to large number of virtual machines.
|XR, Video Streaming, V2X（to be discussed）
Upstream: Docker/K8s - Container Orchestration
OS - Linux, such as Ubuntu
|Committer Contact Info
|Contributor Contact Info