Learning automata-based reservation scheme for channel allocation in wireless networks

Abstract

In this paper, we propose a learning automata (LA) based channel reservation scheme, which determines the optimal number of reserved channels in a wireless network. The proposed scheme is tested on two different models named as Single Traffic No Queues (STNQ) with LA and Single Traffic With Queues (STWQ) using LA. STNQ deals with two types of calls as originating calls and handoff calls but maintain any queue for any type of call. STWQ deals with single traffic like real time or non-real time and maintains queue for both originating and handoff calls. These proposed algorithms are based on distributed dynamic channel allocation policies. Channel allocation based on the type of the cell and the user mobility increases the performance of the systems further. The results show that the proposed systems performance is better when compared to the bequest systems. © 2011 Springer-Verlag.