Robust Linear Decentralized Tracking of a Time-Varying Sparse Parameter Relying on Imperfect CSI

Robust linear decentralized tracking of a time varying sparse parameter is studied in multiple-input multiple-output (MIMO) wireless sensor network (WSN) under channel state information (CSI) uncertainty. Initially, assuming perfect CSI availability, novel Bayesian learning-based Kalman filtering (SBL-KF) framework developed order to track the parameter. Subsequently, an optimization problem formulated minimize mean square error (MSE) each slot, followed by design fast block coordinate descent (FBCD)-based iterative algorithm. A unique aspect proposed technique that it requires only single iteration per slot obtain transmit precoder (TPC) matrices for all nodes (SNs) and receiver combiner (RC) matrix fusion center (FC) online fashion. The recursive Cramer Rao bound (BCRB) also derived benchmarking performance estimation (LDE) scheme. Furthermore, considering practical scenario having uncertainty, robust SBL-KF (RSBL-KF) unknown vector interest conception transceiver design. Our simulation results show schemes designed outperform both traditional sparsity-agnostic KF state-of-the-art reconstruction methods. as compared uncertainty-agnostic design, architecture conceived shown provide improved performance, making eminently suitable applications.