NFV orchestration over disaggregated metro optical networks with end-to-end multi-layer slicing enabling crowdsourced live video streaming

Abstract

Network infrastructure must support emerging applications, fulfill 5G requirements and respond to the sudden increase of societal need for remote communications. Remarkably, Crowdsourced Live Video Streaming (CLVS) challenges operators' infrastructure with tides of users attending major sport or public events that demand high bandwidth and low latency jointly with computing capabilities at the networks' edge. The Metro-Haul project entered in scene proposing a cost-effective, agile and disaggregated infrastructure for the metro segment encompassing optical and packet resources jointly with computing capabilities. Recently, a major Metro-Haul outcome took the form of a field trial of Network Function Virtualization (NFV) orchestration over multi-layer packet and disaggregated optical network testbed that demonstrated a CLVS use case. We showcased the average service creation time below 5 minutes, which met the Key Performance Indicator (KPI) as defined by 5G PPP. In this paper, we expand our field trial demonstration with a detailed view of the Metro-Haul testbed for the CLVS use case, the employed components and their performance. The throughput of the service is increased from approximately 9.6 Gbps up to 35 Gbps per VLAN with high-performance VNFs based on SR-IOV technology.

Kubernetes Orchestration in SDN-based Edge Network Infrastructure

“…Such flat K8s network, also called Pod network, does not account for network constraints in terms of limited bandwidth or bounded latency. For this reason, deploying K8s in edge computing environments over metro optical infrastructures to serve latency/QoS-critical applications (e.g., [2,3]) requires a specifically designed and comprehensive framework. In particular, specific workflows are needed to efficiently interface K8s with various components such as Software Defined Networking (SDN) controller, Service Level Agreement (SLA) broker, and Telemetry Collector.…”

Advances in SDN control and telemetry for beyond 100G disaggregated optical networks [Invited]

“…The role of optical networks is increasing in this scope. A significant number of works have addressed research related to how to setup optical connections in support of the logical links that interconnected such functions (for example, see [39]). Recent work covers the concept of "spectrum services" and "transport network slicing".…”

Enabling P4 Network Telemetry in Edge Micro Data Centers With Kubernetes Orchestration

“…For this reason, deploying Kubernetes in edge computing environments requires specifically designed and comprehensive solutions able to provide flexible network control and traffic telemetry. This is especially true in the case QoSQuality of service (QoS)-critical applications have to be supported and the cluster machines are distributed at different locations, e.g., over a metropolitan area network [8], [9].…”