SearcharxivSearch

arXiv subjects

Fragkiskos Sardis

Publications and source records attributed to Fragkiskos Sardis.

2 recordsLinked to original sources

The Making of 5G: Building an End-to-End 5G-Enabled System

This article documents one of the world's first standards-compliant pre-commercial end-to-end 5th generation (5G) systems. Focus is on a standardized 5G architecture which includes the underlying 3GPP components but also the ETSI Network Function Virtualization (NFV) management and orchestration capabilities. The truly innovative character of 5G enabling fundamental changes to architecture and implementation is discussed, and details of monitoring and orchestration approaches that are deemed instrumental in unlocking the full potential of 5G. Finally, it is important to us to share the lessons learned which we hope are of use to industry and academia alike when building, deploying and testing emerging 5G systems.

cs.NI

Towards adaptive state consistency in distributed SDN control plane

State synchronisation in clustered Software Defined Networking controller deployments ensures that all instances of the controller have the same state information in order to provide redundancy. Current implementations of controllers use a strong consistency model, where configuration changes must be synchronised across a number of instances before they are applied on the network infrastructure. For large deployments, this blocking process increases the delay of state synchronisation across cluster members and consequently has a detrimental effect on network operations that require rapid response, such as fast failover and Quality of Service applications. In this paper, we introduce an adaptive consistency model for SDN Controllers that employs concepts of eventual consistency models along with a novel `cost-based' approach where strict synchronisation is employed for critical operations that affect a large portion of the network resources while less critical changes are periodically propagated across cluster nodes. We use simulation to evaluate our model and demonstrate the potential gains in performance.

cs.NI