Supporting NGNs Core Software Services: A Hybrid Architecture and its Performance Analysis

Abstract

In the last few years telco providers are striving to migrate their services from the traditional Public Switch Telephone Network to so called Next Generation Networks (NGNs) based on standard IP connectivity. This switch is expected to produce a cost degression of 50% for CAPital EXpenditure, while OPerating EXpences remains fairly stable due to network management and energy costs. At the same time, the instantiation of new telco services (Voice over IP, video conferencing, etc.) and the support of third party applications (such as support to smartphone applications, etc.) are expected to produce a big increase of the load of a telco provider at the core level. The goal of this work is to show how management and energy costs can be effectively reduced by leveraging autonomic approaches to move some NGN services toward the telco network edge while still providing Quality of Service (QoS) levels comparable with those provided by a traditional fully-managed infrastructure. This is done by taking into consideration the increase of the load of such services that is expected to raise by one order of magnitude in the near future. Specifically, we propose a hybrid architecture letting telco administrators reduce the number of servers in the provider managed network by exploiting home devices in the computation and by organizing them in a self-configuring Peer to Peer system; in this way it is possible to reduce the overall system and operational costs. Our claims are supported by an experimental study based on both simulations and theoretical models that analyze the trade-off between the number of servers and home devices in order to guarantee a service within QoS constraints. Experiments are carried out on a realistic model that abstracts the lookup procedures within the NGN of a big telco provider (i.e., finding the IP address of a given unique user profile).