Approaches to Latency Management: Combining Hopby-Hop and End-to-End Networking (2020)

By Sebnem Ozer, Ph.D., Carl Klatsky, Dan Rice & John Chrostowski, Comcast

MSO networks that deliver services between the source and destination ends consist of multiple hops, i.e. different network segments. Customer experience is shaped by many Quality of Service (QoS) features that may be defined per hop-by-hop and end-to-end views. Traditionally, speed performance has been addressed as the main contribution to Quality of Experience in an MSO network. However, latency and jitter have a significant impact on many current and emerging services. MSOs have started modeling, monitoring and managing a more complete performance concept, including speed, latency, jitter, packet loss, security and reliability. The importance of this approach has been reiterated in lockstep with a significant increase in traffic volumes, across a very different mix of residential services, and because of a sudden pandemic, as MSOs who adopted this approach were successful supporting additional traffic volumes. This paper will describe current work on latency measurement, optimization and management platforms with hop-by-hop and end-to-end features. We will present current achievements and results for lower latency systems in the cable industry, and ongoing work on new optimization techniques and bigdata analytics. Architectural examples will be provided for a data-driven and knowledge-based converged access network with low latency service assurance and agility. Finally, we will discuss roadmap items MSOs may adopt to provide low latency services within their 10G initiative.

By clicking the "Download Paper" button, you are agreeing to our terms and conditions.

Similar Papers

Roaring into the ‘20s with 10G
By Dr. Robert Howald, Robert Thompson, Sebnem Ozer, Daniel Rice & Larry Wolcott, Comcast; Dr. Tom Cloonan, Dr. Ruth Cloonan & John Ulm, CommScope; Jan Ariesen, Technetix
Applying the Software Defined Networking Paradigm to MSO Commercial networks
By Nagesh Nandiraju , Ph.D. and Sebnem Ozer, Ph.D., ARRIS Inc.
Quality-of-Experience Monitoring, Optimization and Management: A Unified End-to-End Solution
By Zhou Wang, PhD, FIEEE, University of Waterloo; Abdul Rehman, PhD, SSIMWAVE Inc.
What is 10G – The Technology Foundation
By Dr. Robert Howald, Dr. Sebnem Ozer, Robert Thompson, Saif Rahman, Dr. Richard Prodan & Jorge Salinger, Comcast
A Machine Learning Pipeline for D3.1 Profile Management
By Maher Harb, Jude Ferreira, Dan Rice, Bryan Santangelo & Rick Spanbauer, Comcast
Next Generation VOD Asset Management Managing The Vod Chain End To End
By Chris Stasi
A Proposed End-to-End SDN Architecture for MSO
By Mohcene Mezhoudi, Benjamin Y. Tang, Jean-Philippe Joseph & Enrique Hernandez-Valencia, Bell Labs Consulting
A Proactive Network Management Scheme for Mid-Split Deployment
By Lei Zhou, Robert Thompson, Robert Howald, John Chrostowski & Daniel Rice, Comcast Cable
Leakage in a High Split World: Detecting and Measuring Upstream Leakage Levels in a One Gpbs Symmetrical High Split Hybrid Fiber Coax Network
By John Chrostowski, Benny Lewandowski & Dan Rice, Comcast; Greg Tresness, Arcom Digital, LLC.
Convolutional Neural Networks for Proactive Network Management
By Jude Ferreira, Maher Harb, Karthik Subramanya, Bryan Santangelo & Dan Rice, Comcast
More Results >>