TY - GEN
T1 - Distributed iteratively quantized Kalman filtering for wireless sensor networks
AU - Msechu, Erie J.
AU - Roumeliotis, Stergios I.
AU - Ribeiro, Alejandro
AU - Giannakis, Georsios B.
PY - 2007
Y1 - 2007
N2 - Estimation and tracking of generally nonstationary Markov processes is of paramount importance for applications such as localization and navigation. In this context, ad hoc wireless sensor networks (WSNs) offer distributed Kalman filtering (KF) based algorithms with documented merits over centralized alternatives. Adhering to the limited power and bandwidth resources WSNs must operate with, this paper introduces a novel distributed KF estimator based on quantized measurement innovations. The quantized observations and the distributed nature of the iteratively quantized KF algorithm are amenable to the resource constraints of the ad hoc WSNs. Analysis and simulations show that KF-like tracking based on m bits of iteratively quantized innovations communicated among sensors exhibits MSE performance identical to a KF based on analog-amplitude observations applied to an observation model with noise variance increased by a factor of [1 - (1-2/π)m]-1. With minimal communication overhead, the mean square error (MSE) of the distributed KF-like tracker based on 2-3 bits is almost indistinguishable from that of the clairvoyant KF.
AB - Estimation and tracking of generally nonstationary Markov processes is of paramount importance for applications such as localization and navigation. In this context, ad hoc wireless sensor networks (WSNs) offer distributed Kalman filtering (KF) based algorithms with documented merits over centralized alternatives. Adhering to the limited power and bandwidth resources WSNs must operate with, this paper introduces a novel distributed KF estimator based on quantized measurement innovations. The quantized observations and the distributed nature of the iteratively quantized KF algorithm are amenable to the resource constraints of the ad hoc WSNs. Analysis and simulations show that KF-like tracking based on m bits of iteratively quantized innovations communicated among sensors exhibits MSE performance identical to a KF based on analog-amplitude observations applied to an observation model with noise variance increased by a factor of [1 - (1-2/π)m]-1. With minimal communication overhead, the mean square error (MSE) of the distributed KF-like tracker based on 2-3 bits is almost indistinguishable from that of the clairvoyant KF.
KW - Distributed state estimation
KW - Kalman filtering
KW - Limited-rate communication
KW - Quantized observations
KW - Wireless sensor networks
UR - http://www.scopus.com/inward/record.url?scp=50249092157&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=50249092157&partnerID=8YFLogxK
U2 - 10.1109/ACSSC.2007.4487293
DO - 10.1109/ACSSC.2007.4487293
M3 - Conference contribution
AN - SCOPUS:50249092157
SN - 9781424421107
T3 - Conference Record - Asilomar Conference on Signals, Systems and Computers
SP - 646
EP - 650
BT - Conference Record of the 41st Asilomar Conference on Signals, Systems and Computers, ACSSC
T2 - 41st Asilomar Conference on Signals, Systems and Computers, ACSSC
Y2 - 4 November 2007 through 7 November 2007
ER -