Summary

International Symposium on Nonlinear Theory and its Applications

2010

Session Number:A2L-D

Session:

Number:A2L-D3

Improvement of Accuracy and Processing Speed of a Maximum Neural Network Algorithm for the Channel Assignment Problem

Kazunori Nemoto,  Junji Kitamichi,  

pp.127-130

Publication Date:2010/9/5

Online ISSN:2188-5079

DOI:10.34385/proc.44.A2L-D3

PDF download (187.9KB)

Summary:
In recent years, the popularity of cellular mobile communication systems increases steady. However, the usable frequency spectrum or channels for the Cellular Radio Networks(CRNs) are limited. Thus, algorithms for an efficient utilization of channels: the Channel Assignment Problem(CAP) have become important. In this paper, we propose an improved Neural Network Algorithm (NNA) with parallelism to improve solution accuracy and speed-up processing for the static CAP in CRNs. Our proposed algorithm achieves the improved solution accuracy because of large hill-climbing. In addition, parallel processing using multi-thread can achieve faster processing. We verify performance through simulations using benchmark problems and our proposed algorithm can search better solutions and obtains faster processing speeds than the existing one.