Distributed conjugate gradient strategies for parameter estimation over sensor networks

TL;DR

This paper introduces distributed conjugate gradient algorithms for sensor networks, offering improved real-time adaptive parameter estimation with performance close to RLS methods, suitable for dynamic environments.

Contribution

It develops novel distributed CG and MCG algorithms for sensor networks, enhancing adaptive estimation with better accuracy and responsiveness.

Findings

Distributed CG algorithms outperform LMS in mean square error.

Modified CG algorithms approach RLS performance.

Algorithms operate in real-time and adapt to environmental changes.

Abstract

This paper presents distributed adaptive algorithms based on the conjugate gradient (CG) method for distributed networks. Both incremental and diffusion adaptive solutions are all considered. The distributed conventional (CG) and modified CG (MCG) algorithms have an improved performance in terms of mean square error as compared with least-mean square (LMS)-based algorithms and a performance that is close to recursive least-squares (RLS) algorithms . The resulting algorithms are distributed, cooperative and able to respond in real time to changes in the environment.