PRINCIPLES OF NEURO-FUZZY-BASED INTELLIGENT ROUTING IN DATA COMMUNICATION NETWORKS

Abstract

The development of data communication networks and the increasing complexity of their topologies have increased the demand for efficient routing methods. This thesis considers the principles of intelligent routing based on Neuro-Fuzzy Systems in data communication networks. The proposed approach is based on integrating the learning capability of artificial neural networks with the decision-making mechanism of fuzzy logic. Interface buffer load, routing metrics generated by routing protocols, and route reliability are selected as the main parameters. The study results indicate that Neuro-Fuzzy systems represent a promising approach for processing uncertain information and forming intelligent routing mechanisms.