Resource management employing pseudo-delay for IP networks

A shift in customer requirements together with a growth in more demanding applications has exposed the limitations of the best-effort service offered in IP networks. The paper presents a novel approach to managing traffic demand across IP networks by modifying existing routing algorithms and employing agent-based intelligence. A hybrid multi-agent architecture to manage quality of service (QoS) provisioning in the Internet is detailed. This achieves a balance between centralisation and distribution to improve both robustness and scalability. Intelligent agents are employed in this system to anticipate congestion and respond to changes in traffic patterns and other network stresses. A pseudo-delay mechanism is used to reroute less vital traffic from optimal routes. Results indicate that routing such traffic along sub-optimal paths enhances traffic performance in multi-class networks.