Distributed blind system identification in sensor networks

This paper studies the blind identification of multi-channel FIR systems in the context of sensor networks. Distributed identification algorithms are developed for both noise-free and noise-contaminated networked systems. The proposed algorithms distribute the data storage and computational load among multiple agents connected by a specified topology, and are fulfilled via information exchanges among neighboring agents without the need of fusion centers. In the presence of measurement noises, a stabilized distributed algorithm is provided which can avoid trivial estimations of the multiple channels. In addition, convergence properties of the proposed algorithms are provided, and simulation examples are given to show the performances of the proposed algorithms.