Diffusion LMS Strategies in Sensor Networks with Noisy Input Data

Abstract

We investigate the performance of distributed least-mean square (LMS) algorithms for parameter estimation over sensor networks where the regression data of each node are corrupted by white measurement noise. Under this condition, we show that the estimates produced by distributed LMS algorithms will be biased if the regression noise is excluded from consideration. We propose a bias-elimination technique and develop a novel class of diffusion LMS algorithms that can mitigate the effect of regression noise and obtain an unbiased estimate of the unknown parameter vector over the network. In our development, we first assume that the variances of the regression noises are known a-priori. Later, we relax this assumption by estimating these variances in real-time. We analyze the stability and convergence of the proposed algorithms and derive closed-form expressions to characterize their mean-square error performance in transient and steady-state regimes. We further provide computer experiment results that illustrate the efficiency of the proposed algorithms and support the analytical findings.

IEEE/ACM Transaction on Networking, 2014

Cited by in corpus (9)

• Diffusion Adaptation over Multi-Agent Networks with Wireless Link Impairments
• Diffusion Leaky Zero Attracting Least Mean Square Algorithm and Its Performance Analysis
• Diffusion leaky LMS algorithm: analysis and implementation
• Diffusion Adaptation Framework for Compressive Sensing Reconstruction
• Distributed interference cancellation in multi-agent scenarios
• Set-membership NLMS algorithm based on bias-compensated and regression noise variance estimation for noisy inputs
• A Class of Diffusion Algorithms with Logarithmic Cost over Adaptive Sparse Volterra Network
• Maximum Total Correntropy Diffusion Adaptation over Networks with Noisy Links
• When Adaptive Diffusion Algorithm Converges to True Parameter?