Application of Fuzzy Comprehensive Evaluation in Cognitive Networks for Optimal Network Selection

Network selection mechanisms play a vital role in ensuring quality of service (QoS) in the cognitive networks environment. In this paper we develop a network selection scheme for an integrated UMTS/WLAN system to guarantee mobile users being always best connected. We focus on the optimization of resource utilization, while ensuring acceptable QoS provision to the end users. The proposed scheme comprises three parts. First one is to detect the availability of access networks by following cognitive network architecture under the cross-layer design paradigm. While the second is to apply fuzzy comprehensive evaluation to decide the relative weights of evaluative criteria set according to network condition and service applications. Thirdly, a novel approach using quantum genetic algorithm to adjust the weights of fuzzy comprehensive evaluation is adopted. Extensive computer based simulation experiments were carried out. Simulation results show that this method gives better performance in throughput, delay and average packet loss, hence proves that this method is superior to the traditional methods of link capacity and network capacity.