Application of Genetic Algorithms for QoS Routing in Broadband Networks

Abstract

The networks of today are passing through a rapid evolution and are opening a new era of Information Technology (IT). In this information age, customers are requesting an ever-increasing number of new services, and each service will generate other requirements. This large span of requirements introduces the need for flexible networks. Also, future networks are expected to support a wide range of multimedia applications which raises new challenges for the next generation broadband networks. One of the key issues is the Quality of Service (QoS) routing (Baransel, Dobosiewicz, & Gburzynski, 1995; Black, 2000; Chen & Nahrstedt, 1998; Wang, 2001). To cope with multimedia transmission, the routing algorithms must be adaptive, flexible, and intelligent (Barolli, Koyama, Yamada, & Yokoyama, 2000, 2001). Use of intelligent algorithms based on Genetic Algorithm (GA), Fuzzy Logic (FL), and Neural Networks (NN) can prove to be efficient for telecommunication networks (Douligeris, Pistillides, & Panno, 2002). As opposed to non-linear programming, GA, FL and NN use heuristic rules to find an optimal solution.