International Journal of Computer Applications |
Foundation of Computer Science (FCS), NY, USA |
Volume 68 - Number 9 |
Year of Publication: 2013 |
Authors: Odekunle K. A, Alese B. K., Abiola O. B. |
10.5120/11607-6976 |
Odekunle K. A, Alese B. K., Abiola O. B. . Neuro-Fuzzy System for Routing in a Computer Network. International Journal of Computer Applications. 68, 9 ( April 2013), 16-24. DOI=10.5120/11607-6976
This research offers a new method to message routing in a Computer Network using a Neuro-Fuzzy System (NFS) model. A NFS employed in this research combines the learning ability of artificial neural network with the intelligence of fuzzy logic to route messages from source to destination. The model displays the stored knowledge in terms of fuzzy linguistic rules, which allows the model decision – making process to be examined and understood in detail. According to previous research, routing in a network is difficult because the network topology may change constantly and available state information for routing is inherently indefinite. Therefore NFS will work with vague information and selects the most qualified route/path with sufficient resources to satisfy a certain delay and bandwidth requirement in a dynamic environment. The NFS is tested on hypothetical computer network and the advantages are discussed using the case study. The result revealed that the NFS developed was better in performance than the traditional Random and Shortest path method.