Swarm-based Active Tunable Routing for Overhead Reduction in Multiservice Networks
Date Issued
2006
Abstract
The explosive growth of multimedia and other bandwidth intensive applications has resulted a rapid increase in the size of the traffic loads that needs to be supported by modern networks. This paper describes the combination of the active network concept with swarm based control method for optimized multiclass QoS priority routing. This hybrid scenario uses the bandwidth clustering approach (triggered clusters). The packets follow a predetermined path initialized and allocated by swarm based packets, blindly and without any global knowledge of network conditions. In this work this mechanism is associated with the triggered pheromone explored at different simulation sessions and does not require message brokers to fulfill multiclass QoS demands. The pheromone enforcement model that is indicated increases the overall response of the system. Simulation results depict the performance and robustness of the scheme in terms of the end-to-end delay, available bandwidth and packet loss under different traffic measures.