Generalized Least Squares Based Channel Estimation for FBMC-OQAM

The presence of intrinsic inter-carrier interference (ICI) and inter-symbol interference (ISI) at the output of the matched filter receiver in filter bank multi-carrier with offset quadrature amplitude modulation (FBMC-OQAM) systems complicates the task of channel estimation (CE). The conventional approach is to use a pilot symbol preamble structure, such as in the interference approximation/cancellation methods (IAM/ICM), together with a simple virtual symbol (VS) based CE scheme. However, this virtual symbol approach ignores the residual interference from the data portion of the FMBC burst as well as the correlation of the noise across the sub-carriers; both of these factors ultimately limit the performance. In this paper, we propose a generalized least squares (GLS) based CE scheme which, when applied to the IAM/ICM pilot structures, takes into account both the correlated noise and data interference effects. Closed-form expressions are derived for the channel estimation mean-squared error (CE-MSE) of the proposed GLS method and for the conventional VS method, and it is shown that the proposed method leads to a significant reduction of the CE-MSE by up to 6 dB when compared with the VS based method. This is demonstrated to result in improved bit error rate (BER) performance, especially when higher-order modulation is employed, making it an attractive channel estimation method for many modern deployment scenarios. The proposed GLS-based channel estimation scheme is parameterized allowing a flexible trade-off between channel frequency selectivity, estimation complexity and CE-MSE gain. Finally, symmetry properties of the intrinsic interference coefficients for a general FBMC-OQAM system are also proved, which facilitate the computation of the noise and interference autocorrelation matrices required by the proposed algorithm.