Learning-Based Call Admission Control Framework for QoS Management in Heterogeneous Networks

Date Added: Jun 2010
Format: PDF

This paper presents a novel framework for Quality of Service (QoS) management based on the supervised learning approach, Bayesian Belief Networks (BBNs). Apart from proposing the conceptual framework, it provides solution to the problem of Call Admission Control (CAC) in the converged IP-based Next Generation Network (NGN). A detailed description of the modelling procedure and the mathematical underpinning is presented to demonstrate the applicability of the authors' approach. Finally, the theoretical claims have been substantiated through simulations and comparative results are provided as a proof of concept.