Tracking Performance of Incremental LMS Algorithm over Adaptive Distributed Sensor Networks

TL;DR

This paper analyzes the tracking performance of an incremental LMS algorithm in adaptive sensor networks, focusing on time-varying weights and Rayleigh fading channels, with theoretical derivations validated by simulations.

Contribution

It provides closed-form expressions for MSE, MSD, and EMSE in tracking time-varying channels, advancing understanding of adaptive network performance.

Findings

Theoretical and simulation results match perfectly.

Derived closed-form relations for MSE, MSD, and EMSE.

Effective tracking of Rayleigh fading channels demonstrated.

Abstract

In this paper we focus on the tracking performance of incremental adaptive LMS algorithm in an adaptive network. For this reason we consider the unknown weight vector to be a time varying sequence. First we analyze the performance of network in tracking a time varying weight vector and then we explain the estimation of Rayleigh fading channel through a random walk model. Closed-form relations are derived for mean square error (MSE), mean square deviation (MSD) and excess mean square error (EMSE)of analyzed network in tracking Rayleigh fading channel and random walk model. Comparison between theoretical and simulation results shows a perfect match and verifies performed calculations.