An Intelligent Model to Control Preemption Rate of Instantaneous Request Calls in Networks with Book-Ahead Reservation

Abstract

Abstract--Resource sharing between Book-Ahead (BA) and Instantaneous Request (IR) reservation often results in high preemption rate of on-going IR calls. High IR call preemption rate causes interruption to service continuity which is considered as detrimental in a QoS-enabled network. A number of call admission control models have been proposed in literature to reduce the preemption rate of on-going IR calls. Many of these models use a tuning parameter to achieve certain level of preemption rate. This paper presents an Artificial Neural Network (ANN) model to dynamically control the preemption rate of on-going calls in a QoS-enabled network. The model maps network traffic parameters and desired level of preemption rate into appropriate tuning parameter. Once trained, this model can be used to automatically estimate the tuning parameter value necessary to achieve the desired level of preemption rate. Simulation results show that the preemption rate attained by the model closely matches with the target rate.

A Comparative Study of Call Admission Control in Mobile Multimedia Networks using Soft Computing

“…Once the model is trained it automatically estimate the tuning parameter value essential to achieve the desired level of preemption rate. The simulation result clearly identified that the model closely matche's with the target rate and reduce the preemption rate of on-going IR calls [5].…”

“…Training algorithms SCR &BR provide mean error 2.51% &1.88% respectively [5]. Link capacity optimization is created by on-line training with back propagation.…”

Optimizing Call Drops in Cellular Network using Artificial Intelligence based Handover Schema

“…A paper inspired from developing various mathematical approaches to solving the call admission control problem is described for the usage of Markov decision process, fuzzy logic, neural networks and genetic algorithms was introduced Which was trained through certain learning process able maintain automatically dynamically resource shearing between previous allocated resources and new instantaneous call request to achieve the desired level of preemption rate for new call [11] [12]. In this research paper proposed a fuzzy neural approach for call admission control in heterogeneous network having different class traffic and load for upcoming based new generation cellular network.…”