Fitness Functions’ Improvement of Evolutionary Algorithm in WSN

Document Type : Persian Original Article

Authors

1 Babol Noshirvani Univ. of Tech. Shariati Av.

2 Mazandaran University Of Science And Technology, Babol, Iran.

3 Department Of Electrical And Computer Engineering, Babol Noshiravani University Of Technology, Iran.

4 Sharif University of Technology, Tehran, Iran

Abstract

Wireless sensor networks (WSN) besides being an emerging technology with a wide range of applications, have some challenges such as energy consumption, localization, security, etc. that for solving these problems, evolutionary algorithm will be used mostly.The most important part of every evolutionary algorithm is its Fitness Function because this function leads the algorithm close to final solution. The fitness functions that are used in most of the WSN papers, have problems such as, ignoring the units of parameter when combining them in an equation and also ignoring the dependency of the parameters value’s alterations on the total amount of function’s value. In this paper, the problems of fitness functions will be investigated and then for correcting these problems some solutions will be suggested.

Keywords

Journal of Soft Computing and Information Technology
Volume 1, Issue 1 - Serial Number 1
January 2011
Pages 63-70

Files

Share

How to cite

Statistics