Title: Channel allocation scheme for cellular networks using evolutionary computing

Authors: Narendran Rajagopalan; C. Mala

Addresses: Department of Computer Science and Engineering, National Institute of Technology, Trichy, 620015, India ' Department of Computer Science and Engineering, National Institute of Technology, Trichy, 620015, India

Abstract: The usage of mobile communications systems has grown exponentially. But, the bandwidth available for mobile communications is finite. Hence, there is a desperate attempt to optimise the channel assignment schemes. In this work, some of the quality of service parameters such as residual bandwidth, number of users, duration of calls, frequency of calls, priority, time of calls and mean opinion score are considered. Genetic algorithm and artificial neural networks is used to determine the optimal channel assignment considering the quality of service parameters. The simulation results show that genetic algorithm performs better than frequency assignment at random, a heuristic method. But application of artificial neural networks outperforms genetic algorithm and frequency assignment at random method by a considerable margin. Channel allocation can be optimised using these soft computing techniques resulting in better throughput.

Keywords: genetic algorithms; channel allocation; quality of service; QoS; artificial neural networks; ANNs; throughput; cellular networks; evolutionary computing; mobile communications; simulation.

DOI: 10.1504/IJAISC.2014.062827

International Journal of Artificial Intelligence and Soft Computing, 2014 Vol.4 No.2/3, pp.212 - 227

Accepted: 01 Dec 2013
Published online: 28 Jun 2014 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article