z-logo
Premium
Decentralized estimation over noisy channels in cluster‐based wireless sensor networks
Author(s) -
Liu Guiyun,
Xu Bugong,
Chen Hongbin
Publication year - 2012
Publication title -
international journal of communication systems
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.344
H-Index - 49
eISSN - 1099-1131
pISSN - 1074-5351
DOI - 10.1002/dac.1308
Subject(s) - estimator , computer science , wireless sensor network , cluster (spacecraft) , fusion center , cluster analysis , binary number , energy (signal processing) , energy consumption , algorithm , statistics , wireless , computer network , artificial intelligence , telecommunications , mathematics , cognitive radio , ecology , arithmetic , biology
SUMMARY In this paper, the problem of decentralized parameter estimation over noisy channels in a cluster‐based sensor network is studied. Each cluster head generates a local estimate by adopting a sample mean estimator. The local estimates from all cluster heads are compressed by using a one‐bit quantizer and then the bits are transmitted to a fusion center over independent binary symmetric channels. Two maximum likelihood estimators are proposed for estimating the parameter based on the received bits in two different scenarios: (i) all clusters have the same number of cluster members and (ii) the number of cluster members in the clusters are different. The Cramér–Rao lower bounds for the proposed estimators in both scenarios are derived. Simulation results show that the estimation performance for clustering with the same number of cluster members can be comparable to that for cluster‐free sensor networks. However, the estimation performance for clustering with a different number of cluster members is not as good as that for cluster‐free sensor networks. The trade off between estimation performance and energy consumption exists in both scenarios. The energy consumed for executing the estimation task in cluster‐based sensor networks is less than that in cluster‐free sensor networks. Copyright © 2011 John Wiley & Sons, Ltd.

This content is not available in your region!

Continue researching here.

Having issues? You can contact us here