Part of #CONGESTION CONTROL MODELLING BASED ON LOCALLY LINEAR NEUROFUZZY NETWORK# :
Publishing year : 2006
Conference : Fourteenth Iranian Conference on Electrical Engineering
Number of pages : 4
Abstract: In this paper, a sample of congestion control data will be modeled by a neuro-fuzzy algorithm. To build the neuro-fuzzy model, a locally linear learning algorithm, namely, the Locally Linear Mode Tree (LoLiMoT) is used. Then, a congestion controller is applied to the identified model. This intelligent algorithm provides more speed, less training time and less square error in simulation than MLP. Simulation will be done with some cell loss data that is fetched from a broadband integrated services digital network (B-ISDN), and it represents not only maximizing in speed but also make less square error in parameter optimization.