Predictive connectionist approach for VoD bandwidth management

Abstract

This paper describes a step-by-step improvement process of a predictive connectionist module applied in the context of Video on Demand Service Providers (VDSP) applications. The aim at the end is to provide a methodology based on estimation to right size bandwidth usage. The improvement methodology [G. Gomes, Un Modèle Connexioniste pour la Prédiction e l’Optimization de la Bande Passante: Approche Basée sur la Nature Autosimulaire du Trafic Vidéo IP, doctorat thesis presented at Université d’Evry – Val d’Essonne, France (2004)] consists of three phases named examples-based level, modular solution and HVS (Heuristic for Variable Selection) [Y. Bennani, M. Yacoub, Features selection and architecture optimization in connectionist systems, International Journal of Neural Systems 10(5) (2000) 379–395]. In the first phase the “sliding and overlaying” technique is used for enabling the Predictive Connectionist Module (PCM) to be aware of dynamic input. In the second phase a new connectionist network is added to the first one so that the proactive function with prediction could be achieved through a modular architecture. Finally, the HVS method is used in the third phase for identifying optimized connectionist models with higher accuracy. Simulations results are provided which cover learning, prediction and evaluation phases.