Robust Distributed Block LMS over WSN in Impulsive Noise

Abstract

In wireless sensor network each sensor node collects data related to some unknown parameters, corrupted by independent Gaussian noise. Then the objective is to estimate the parameter from the data collected across the network in distributed manner. The distributed estimation algorithm should be energy efficient, provides high estimation accuracy, and is fast in convergence. But the conventional distributed algorithm involves significant communication overhead and is also not robust to the impulsive noise which is common in wireless sensor network environment. Consequently these algorithms defeat the basic purpose of wireless sensor network. This paper studies the problem of robust adaptive estimation in impulsive noise environment using robust cost function like Wilcoxon norm and Huber cost function. Further in order to reduce the amount of communication overhead, block distributed LMS is incorporated.