Neural modelling and performance analysis of the link occupancy distribution for wireless broadband transmissions. (7th September 2007)

• Record Type: Journal Article
• Authors: Lokshina, Izabella; Bartolacci, Michael R.
• Is Part Of: International journal of mobile network design and innovation. Volume 2:Number 2(2007)
• Page Start: 129
• Page End: 133
• Publication Date: 2007-09-07
• Subjects: artificial intelligence -- neural networks -- Markov reward models -- discrete time Markov chains -- communication networks -- performance analysis -- link occupancy distribution -- wireless networks -- broadband transmissions -- mobile networks -- neural modelling; Mobile communication systems -- Periodicals; Wireless communication systems -- Design and construction -- Periodicals; 384.535
• Languages: English
• ISSNs: 1744-2869

Abstract

This paper is devoted to neural modelling and performance analysis of the link occupancy distribution for wireless broadband transmission. Multiclass models of a single link transmission for rigid, adaptive and elastic traffic are developed, based on Markov rewards models. The link occupancy distribution is introduced as embedded, discrete time Markov chains researched with the use of Vector Quantification (VQ). Link occupancy performance is simulated as a combination of single queues with random distributions of arrival processes and holding time service phases. The density of occupancy probability is determined using Learning Vector Quantification (LVQ) in a two-layered neural structure.