Soft Decision Directed Dual-layer Channel Estimation for Time-Varying MIMO Channels

In this paper, we study soft decision directed channel estimation algorithms for joint data detection and channel estimation over time-varying multiple-input multiple-output (MIMO) channels. The optimal Wiener filter (OWF) channel estimator is data dependent, and requires high complexity due to the computation of matrix inversion at each time instance. We develop a low-complexity, dual-layer channel estimation algorithm aiming to achieve the performance of OWF with a significantly reduced complexity. Excellent performance of the proposed design is achieved for both the soft minimum mean square error (soft-MMSE) MIMO detector and the Markov Chain Monte Carlo (MCMC) MIMO detector. The MCMC detector is shown to be significantly more robust to channel estimation error than the soft-MMSE detector.