A review of robust distributed estimation strategies over wireless sensor networks

• Published in: Signal processing Vol. 188; p. 108150
• Main Authors: Modalavalasa, Sowjanya, Sahoo, Upendra Kumar, Sahoo, Ajit Kumar, Baraha, Satyakam
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.11.2021
• Subjects: Distributed processing; Impulsive noise; Outliers; Robust estimation; Outliers; Distributed processing; Impulsive noise; Robust estimation
• ISSN: 0165-1684; 1872-7557
• DOI: 10.1016/j.sigpro.2021.108150

•To handle impulsive noise environments, robust cost functions derived from the theory of robust statistics and special functions of residual error should be utilized.•The study of robust techniques in impulsive noise contaminated distributed scenarios is not available in the literature, and a literature review is much needed for further development of novel robust algorithms to tackle outliers.•The manuscript reviews robust distributed algorithms available in the literature for parameter estimation and it mainly focuses on robust distributed estimation using loss functions. Distributed estimation strategies over wireless sensor networks are one of the active areas of research due to the wide range of applications in a variety of fields ranging from agriculture to surveillance. The classical least squares based algorithms are simple and effective when the noise follows Gaussian distribution. In practical scenarios, the noise may have heavy tailed distributions unlike the Gaussian distribution. The presence of outliers or impulsive noise in distributed networks is unavoidable in practical scenarios due to atmospheric phenomena, electric machinery, saturation effects, link or node failures, etc. To handle such impulsive noise environments, robust cost functions derived from the theory of robust statistics and special robust functions of residual error should be utilized. The study of such robust techniques in distributed scenarios is not available in the literature, and such a literature review is much needed for the further development of novel robust algorithms to tackle outliers. A review of such robust distributed algorithms available in the literature for parameter estimation is presented in this manuscript.