Dynamic connectivity management with an intelligent route service control point

  • Authors:

  • J. Van der Merwe;A. Cepleanu;K. D'Souza;B. Freeman;A. Greenberg;D. Knight;R. McMillan;D. Moloney;J. Mulligan;H. Nguyen;M. Nguyen;A. Ramarajan;S. Saad;M. Satterlee;T. Spencer;D. Toll;S. Zelingher

  • Affiliations:

  • AT&T Labs;AT&T Labs;AT&T Labs;AT&T Labs;AT&T Labs;AT&T Labs;AT&T Labs;AT&T Labs;AT&T Labs;AT&T Labs;AT&T Labs;AT&T Labs;AT&T Labs;AT&T Labs;AT&T Labs;AT&T Labs;AT&T Labs

  • Venue:
  • Proceedings of the 2006 SIGCOMM workshop on Internet network management
  • Year:
  • 2006

Quantified Score

Hi-index 0.00

Visualization

Abstract

Increased use of demanding network applications, as well as the increase of unwanted network traffic in the form of DDoS attacks, are putting new pressures on service providers to meet the expectations of customers in terms of network availability and performance. Providers are expected to deal with potential problems in near real-time fashion. Further, many of these demanding application, such as VoIP and online gaming, are very sensitivity to even small periods of disruption. In this work we therefore specifically focus on dynamic connectivity management, which we broadly define as the ability to dynamically manage how and where traffic flows across a network. Because it is intimately involved with how traffic flows through the network, BGP would be an ideal candidate for many of these management tasks. Unfortunately, BGP is itself a complicated protocol and up to now the prospect of using it to perform routine management tasks has not been considered a feasible approach. In this paper we show how the simplification introduced by a centralized Intelligent Route Service Control Point (IRSCP) that allows route selection to be performed outside the routers and also allows such route selection to be informed by external network intelligence, address this quandary. We present several examples of connectivity management tasks that can benefit from our approach. We describe our trial implementation of the IRSCP and show how our approach raise the level of abstraction, allowing operators to focus on what functions need to be performed, rather than getting bogged down with how to perform them.