Distributed constrained consensus least-mean square algorithms with adjustable constraints

Yi Yu; Rodrigo C. de Lamare; Yuriy Zakharov; Haiquan Zhao

doi:10.1109/ICDSP.2017.8096091

Distributed constrained consensus least-mean square algorithms with adjustable constraints

Yi Yu, Rodrigo C. de Lamare, Yuriy Zakharov, Haiquan Zhao

Electronic Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

This paper presents novel constrained consensus least mean square (cLMS) algorithms with adjustable constraints that can improve the learning performance of distributed estimation problems in sensor networks by exploiting the spatial diversity of the estimates. For the first algorithm, the constraint vectors are adjusted by combining the components of the estimate orthogonal to its neighbor estimates. To further speed up the convergence, the second algorithm only uses one of these orthogonal components corresponding to the maximum angle between the estimate and its neighbor estimates to compute the constraint vectors. Simulation results show that both proposed algorithms provide faster convergence than the existing cLMS and diffusion LMS algorithms.

Original language	English
Title of host publication	22nd International Conference on Digital Signal Processing (DSP)
Pages	1-5
Number of pages	5
DOIs	https://doi.org/10.1109/ICDSP.2017.8096091
Publication status	Published - 23 Aug 2017

Access to Document

10.1109/ICDSP.2017.8096091

Cite this

@inproceedings{e4de913b4c664a1a8bd41946b497e0f9,

title = "Distributed constrained consensus least-mean square algorithms with adjustable constraints",

abstract = "This paper presents novel constrained consensus least mean square (cLMS) algorithms with adjustable constraints that can improve the learning performance of distributed estimation problems in sensor networks by exploiting the spatial diversity of the estimates. For the first algorithm, the constraint vectors are adjusted by combining the components of the estimate orthogonal to its neighbor estimates. To further speed up the convergence, the second algorithm only uses one of these orthogonal components corresponding to the maximum angle between the estimate and its neighbor estimates to compute the constraint vectors. Simulation results show that both proposed algorithms provide faster convergence than the existing cLMS and diffusion LMS algorithms.",

author = "Yi Yu and {de Lamare}, {Rodrigo C.} and Yuriy Zakharov and Haiquan Zhao",

year = "2017",

month = aug,

day = "23",

doi = "10.1109/ICDSP.2017.8096091",

language = "English",

isbn = "978-1-5386-1895-0",

pages = "1--5",

booktitle = "22nd International Conference on Digital Signal Processing (DSP)",

}

TY - GEN

T1 - Distributed constrained consensus least-mean square algorithms with adjustable constraints

AU - Yu, Yi

AU - de Lamare, Rodrigo C.

AU - Zakharov, Yuriy

AU - Zhao, Haiquan

PY - 2017/8/23

Y1 - 2017/8/23

N2 - This paper presents novel constrained consensus least mean square (cLMS) algorithms with adjustable constraints that can improve the learning performance of distributed estimation problems in sensor networks by exploiting the spatial diversity of the estimates. For the first algorithm, the constraint vectors are adjusted by combining the components of the estimate orthogonal to its neighbor estimates. To further speed up the convergence, the second algorithm only uses one of these orthogonal components corresponding to the maximum angle between the estimate and its neighbor estimates to compute the constraint vectors. Simulation results show that both proposed algorithms provide faster convergence than the existing cLMS and diffusion LMS algorithms.

AB - This paper presents novel constrained consensus least mean square (cLMS) algorithms with adjustable constraints that can improve the learning performance of distributed estimation problems in sensor networks by exploiting the spatial diversity of the estimates. For the first algorithm, the constraint vectors are adjusted by combining the components of the estimate orthogonal to its neighbor estimates. To further speed up the convergence, the second algorithm only uses one of these orthogonal components corresponding to the maximum angle between the estimate and its neighbor estimates to compute the constraint vectors. Simulation results show that both proposed algorithms provide faster convergence than the existing cLMS and diffusion LMS algorithms.

U2 - 10.1109/ICDSP.2017.8096091

DO - 10.1109/ICDSP.2017.8096091

M3 - Conference contribution

SN - 978-1-5386-1895-0

SP - 1

EP - 5

BT - 22nd International Conference on Digital Signal Processing (DSP)

ER -