Exploiting dynamic sparsity for time reversal underwater acoustic communication under rapidly time varying channels

Underwater acoustic (UWA) communication encounters significant difficulties posed by the simultaneous presence of multipath and time variations. It has been recognized that, under the assumption that channel keeps static within the processing windows, time reversal (TR) processing approach is capable of mitigating multipath via the spatial-temporal focusing. However, for a rapidly time-varying UWA channel, the replica channel impulse response in time reversal processor need to be updated frequently to avoid performance degradation, which leads to huge computational complexity and significant overhead. Consider that after time reversal processing the resulting time-reversed channel response exhibits much more slow time variations compared to the original channel impulse response, previously Kalman filtering has been adopted to track the time-reversed channel response to alleviate the requirement of frequent channel update. Under the framework of dynamic compressed sensing (DCS), in this paper the time-reversed channel is formulated as a sparse set consisting of constant and slowly time-varying supports to derive the Kalman Filtered Compressed Sensing (KF-CS) channel estimation algorithm for time reversal communication. Based on the receiver structure by coupling the KF-CS estimator driven time reversal processor with a single channel decision-feedback equalizer (TR-DCS-DFE), shallow water experimental results with field data are provided to demonstrate the effectiveness of the proposed algorithm, compared to the classic time reversal communication scheme. (C) 2020 Elsevier Ltd. All rights reserved.