Estimation of Node Localization with a Real-Coded Genetic Algorithm in WSNs

• Published in: 2007 International Conference on Machine Learning and Cybernetics Vol. 2; pp. 873 - 878
• Main Authors: Guo-Fang Nan, Min-Qiang Li, Jie Li
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.08.2007
• Subjects: Application software; Cybernetics; Genetic algorithm; Genetic algorithms; Genetic engineering; Global Positioning System; Intelligent networks; Machine learning; Node localization; Positioning systems; Sensor phenomena and characterization; Sensor systems; Wireless sensor network; Wireless sensor networks
• ISBN: 1424409721; 9781424409723
• ISSN: 2160-133X
• DOI: 10.1109/ICMLC.2007.4370265

Location knowledge of sensor nodes in a network is essential for many tasks such as routing, cooperative sensing, or service delivery in ad hoc, mobile, or sensor networks, and it is hard to get the precision solution by traditional node localization algorithm, while genetic algorithm is an effective methodology for solving combinatorial optimization problems, so, in this paper, a real-coded version of the commonly used genetic algorithm is described in order to evaluate the precision of node localization problem in wireless sensor networks, meanwhile, the corresponding fitness function and genetic operators are designed. The algorithms presented in this paper are validated on a combined Windows XP and MATLAB simulation on a sensor network with fixed number of nodes whose distance measurements are corrupted by Gaussian noise. The results show that the proposed scheme gives accurate location of nodes.