A multi-layered solution for supporting isp traffic demand using genetic algorithm

Abstract

This paper proposes a unique feedback governed multi layered architectural model to support ISP's traffic demands with multiple quality of service(QoS) constraints. The proposed model consists of different modules each responsible for a particular set of tasks. The most challenging task involved in satisfying the demands is routing the traffic subject to multiple QoS constraints for multiple internet service providers (ISP). Routing the traffic subject to multiple constraints itself is known to be an NP-hard problem. This paper addresses the problem of finding the optimum routes to satisfy the demands of different ISPs, where different ISPs have different demands and their priority of QoS keep changing. A genetic algorithm (GA) which makes use of heuristic technique is proposed in this paper. All the optimum routes are found in one run of the program, therefore the chromosome selected encodes all the demanded routes. This paper also makes use of employing a tournament selection mechanism where the diversity of the population is preserved while the best chromosomes are carried to the next generation. The evolutionary property of GA is utilised in this paper to evolve to suit the changing demands. The performance and the evolutionary property of the proposed solution are shown with the simulation tests.