Improvement of MPLS Performance by Implementation of a Multi-Agent System

Multi-Protocol Label Switching (MPLS) is a network layer packet forwarding technology that provides flexible circuit switched traffic engineering solutions in packet switched networks by explicit path routing. However, the actual weakness of MPLS resides in its inability to provide application-level routing intelligence, which is a fundamental component especially for voice delivery. In this paper we propose to introduce a Multi-Agent System (MAS) within the MPLS network to improve its performance. The introduction of agents takes place into the decision points in MPLS at the flow level, and distributes traffic based on the quality of service required by the type of traffic. We also propose an intelligent framework for network as well as an architecture of our agent in order to improve the efficiency of the Quality of Service (QoS) within MPLS.

[1]  Ana L. C. Bazzan,et al.  Agents in Traffic Modelling - From Reactive to Social Behaviour , 1999, KI.

[2]  Michael Wooldridge,et al.  Multiagent Systems: A Modern Approach to Distributed Artificial Intelligence , 1999 .

[3]  David L. Black,et al.  An Architecture for Differentiated Service , 1998 .

[4]  Pattie Maes,et al.  Trafficopter: A Distributed Collection System for Traffic Information , 1998, CIA.

[5]  Alexis Drogoul,et al.  Agent-based interaction analysis of consumer behavior , 2002, AAMAS '02.

[6]  Leïla Merghem,et al.  Agents: a solution for telecommunication network simulation , 2002, Net-Con.

[7]  Alexis Drogoul,et al.  How to Combine Reactivity and Anticipation: The Case of Conflicts Resolution in a Simulated Road Traffic , 2000, MABS.

[8]  Guy Pujolle,et al.  On Using Multi-agent Systems in End to End Adaptive Monitoring , 2003, MMNS.

[9]  Vijay Srinivasan,et al.  RSVP-TE: Extensions to RSVP for LSP Tunnels , 2001, RFC.

[10]  Meejeong Lee,et al.  Dynamic Load Distribution in MPLS Networks , 2003, ICOIN.

[11]  Jörg Liebeherr,et al.  Simple alternate routing for differentiated services networks , 2001, Comput. Networks.

[12]  Jaime Simão Sichman,et al.  MAS and Social Simulation: A Suitable Sommitment , 1998, MABS.

[13]  Scott Shenker,et al.  Integrated Services in the Internet Architecture : an Overview Status of this Memo , 1994 .

[14]  G.J. Minden,et al.  A survey of active network research , 1997, IEEE Communications Magazine.

[15]  Jim Doran,et al.  Agent-Based Modelling of Ecosystems for Sustainable Resource Management , 2001, EASSS.

[16]  Bilel Jamoussi,et al.  Applicability Statement for CR-LDP , 2002, RFC.

[17]  Christophe Cambier,et al.  SIMULATING THE INTERACTION BETWEEN A SOCIETY AND A RENEWABLE RESOURCE , 1993 .

[18]  K. Suzanne Barber,et al.  Dynamic Adaptive Autonomy in Multiagent Systems: Representation and Justification , 2001, Int. J. Pattern Recognit. Artif. Intell..

[19]  Jacques Ferber,et al.  Multi-agent systems - an introduction to distributed artificial intelligence , 1999 .

[20]  Cristiano Castelfranchi,et al.  From Reaction to Cognition , 1993, Lecture Notes in Computer Science.

[21]  Eric C. Rosen,et al.  Multiprotocol Label Switching Architecture , 2001, RFC.