Distributed Estimation in Wireless Sensor Networks with Heterogeneous Sensors
Zhenxing Luo, Department of Electrical and Computer Engineering, the University of Alabama at Birmingham, AL, USA.
Manuscript received on October 01, 2012. | Revised Manuscript received on October 20, 2012. | Manuscript Published on September 10, 2012. | PP: 79-82 | Volume-1 Issue-4, September 2012. | Retrieval Number:D0268081412/2012©BEIESP
Open Access | Ethics and Policies | Cite
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: In this paper, a robust distributed estimation method in wireless sensor networks (WSNs) with heterogeneous sensors is presented. Particularly, a single parameter is estimated based on decisions from heterogeneous sensors, which have different signal gains. The sensor gains follow uniform distributions. Using the distributions of sensor gains, we calculated the probability density function of the signal received by sensors. Then, the overall likelihood function for a given decision vector is derived and a maximum likelihood estimation (MLE) method is used to estimate the unknown parameter. To evaluate estimation performance, the Cramer-Rao lower bound (CRLB) is also derived. Simulation results showed that if the range of sensor gains was narrow, the RMS errors were close to CRLB. If the range of sensor gains was wide, the RMS errors deviated from CRLB.
Keywords: Distributed Estimation, Maximum Lestimation, Wireless Sensor Networks.