USING A NEURAL NETWORK FOR THE VERTICAL HANDOVER PROCEDURE

Abstract

The deployment of modern heterogeneous networks transmitting different types of traffic from mobile stations, which move at a quite high speed, has led to increased requirements for the quality of vertical handover operation. The handover procedure or handover is a key mechanism that allows mobile subscribers to move seamlessly across the network. At the same time, due to the influence of a large number of parameters and characteristics of the network, traditional decision-making schemes that work with only one criterion are ineffective. Therefore, there is a task to develop a handover mechanism taking into account several parameters and providing the intelligent handover. One of the promising fields of modern technology is artificial neural networks. An important feature of neural networks is the parallel processing of information by a large number of neurons at the same time. Typical tasks that can be solved using neural networks are: control, encoding and decoding of information, classification, forecasting, automation of a decision-making process, pattern recognition and more. Neural networks are used in wireless communication systems to solve the following tasks: access control, handover, channel allocation, traffic forecasting, adaptive routing, signal propagation prediction, mobile station location. The paper proposes to utilize a neural network in the intelligent algorithm of multicriterial vertical handover. After creating a software or hardware solution for the neural network, a mathematical model must be created and the network training must be performed.  The neural network proposed in this paper is a multilayer perceptron. Simulation of the neural network operation in Matlab program was performed.