For Full-Text PDF, please login, if you are a member of IEICE,|
or go to Pay Per View on menu list, if you are a nonmember of IEICE.
Dynamic Path Assignment for Broadband Networks Based on Neural Computation
Akira CHUGO Ichiro IIDA
IEICE TRANSACTIONS on Communications
Publication Date: 1992/07/25
Print ISSN: 0916-8516
Type of Manuscript: Special Section PAPER (Special Section on Network Planning)
neural network, routing, path assignment, B-ISDN,
Full Text: PDF(585.5KB)>>
This paper describes the application of a neural network to the optimal routing problem in broadband multimedia networks, where the objective is to maximize network utilization while considering the performance required for each call. In a multimedia environment, the performance required for each call is different, and an optimal path must be found whenever a call arrives. A neural network is appropriate for the computation of an optimal path, as it provides real-time solutions to difficult optimization problems. We formulated optimal routing based on the Hop field neural network model, and evaluated the basic behavior of neural networks. This evaluation confirmed the validity of the neural network formulation, which has a small computation time even if there are many nodes. This characteristic is especially suitable for a large-scale system. In addition, we performed a computer simulation of the proposed routing scheme and compared it with conventional alternate routing schemes. The results show the benefit of neural networks for the routing problem, as our scheme always balances the network load and attains high network utilization.