Adaptive filter theory (2nd ed.)
Adaptive filter theory (2nd ed.)
Independent Component Analysis: Principles and Practice
Independent Component Analysis: Principles and Practice
Fuzzy adaptive predictive flow control of ATM network traffic
IEEE Transactions on Fuzzy Systems
Traffic models in broadband networks
IEEE Communications Magazine
Hi-index | 0.00 |
In this paper we present a hybrid ICA-fuzzy adaptive algorithm for traffic flow separation and control in contemporary computer networks. Our approach is composed by an ICA Block corresponding to the gradient algorithm proposed by Bell and Sejnowski for the information maximization at the output of a neural network as well as a Fuzzy Control System Block. The ICA algorithm is used to separate the controllable to the non-controllable network traffic sources. Additionally, we developed a predictive fuzzy controller following the Takagi and Sugeno fuzzy modeling. The combination of blind separation and control algorithm is applied to real network traffic traces. Finally, we verify that the proposed ICA-fuzzy adaptive control algorithm yields prominent control performances for single buffer server network environments.