Closed-Form MSE Performance of the Distributed LMS Algorithm

Author

Mateos, Gonzalo ; Schizas, Ioannis D. ; Giannakis, Georgios B.

Author_Institution

Dept. of ECE, Univ. of Minnesota, Minneapolis, MN

fYear

2009

fDate

4-7 Jan. 2009

Firstpage

66

Lastpage

71

Abstract

Mean-square error (MSE) performance analysis is conducted for a novel distributed least-mean square (D-LMS) algorithm, which is based on consensus, in-network, adaptive estimation using wireless sensor networks (WSNs). For sensor observations that are linearly related to the time-invariant parameter of interest and independent Gaussian data, exact closed-form expressions are derived for the global and sensor-level MSE evolution and steady-state limiting values. Tracking performance is also investigated when the true parameter adheres to a random-walk model. Remarkably for small step-sizes the results accurately extend to the pragmatic setup whereby sensors acquire temporally-correlated (non-)Gaussian data.

Keywords

Gaussian processes; least mean squares methods; wireless sensor networks; adaptive estimation; distributed LMS algorithm; distributed least-mean square algorithm; independent Gaussian data; mean-square error performance analysis; random-walk model; wireless sensor networks; Adaptive estimation; Analysis of variance; Closed-form solution; Covariance matrix; Fluctuations; Least squares approximation; Performance analysis; Signal processing algorithms; Steady-state; Wireless sensor networks; LMS algorithm; Wireless sensor networks; distributed estimation; performance analysis;

fLanguage

English

Publisher

ieee

Conference_Titel

Digital Signal Processing Workshop and 5th IEEE Signal Processing Education Workshop, 2009. DSP/SPE 2009. IEEE 13th

Conference_Location

Marco Island, FL

Print_ISBN

978-1-4244-3677-4

Electronic_ISBN

978-1-4244-3677-4

Type

conf

DOI

10.1109/DSP.2009.4785897

Filename

4785897