A Next-Move Prediction Algorithm for Implementation of Selective Reservation Concept in Wireless Networks

The future mobile networks will have to support increasing number of mobile users and provide efficient services that are context sensitive. Because of the limited amount of wireless resources, the better utilization of system resources is required. Lately there has been an increasing interest to develop predictive algorithms for user movements in order to provide better optimization. In this paper we suggest an algorithm for the implementation of the selective reservation concept for handover resources. We propose a next-move prediction scheme using the history of the user´s movement directions and a backpropagation neural network algorithm. We show that for certain types of movement patterns the accuracy of 100% can be achieved. The developed algorithm is light-weight and does not require excessive computing power, and could be into terminals.