International Journal of Computer Theory and Engineering

Abstract

In this paper we propose a novel intelligent technique for reducing the location update and paging cost. This paper focuses on the location management procedure, which is the process that allows the network to identify the exact location of a mobile terminal (MT) for a call delivery. Location management occurs in two stages: locations updates and call delivery. When a mobile terminal moves from one location area to another it performs a location update procedure that provides the network with its location information. On the other hand, call delivery means that the network is queried for location information on the called MT. In order to actually deliver the call, the network needs to identify the exact location of the called MT using a paging procedure. In this paper we present a user pattern learning strategy using intelligent algorithm called Cascaded Correlation Neural Network to find the called MT’s current cell, within its registered Location Area, in the most accurate and efficient way possible. We compare the proposed algorithm with cayrici’s strategy and standard UMTS procedure. The search cost and update cost are used for performance analysis. The experimental results show that the proposed technique is more efficient than the other existing techniques.