No abstract

No abstract

In this paper, we devise a highly efficient machine learning-based channel estimation for orthogonal frequency division multiplexing (OFDM) systems, in which the training of the estimator is performed online. A simple learning module is employed for the proposed learning-based estimator. The training process is thus much faster and the required training data is reduced significantly. Besides, a training data construction approach utilizing least square (LS) estimation results is proposed so that the training data can be collected during the data transmission. The feasibility of this novel construction approach is verified by theoretical analysis and simulations. Based on this construction approach, two alternative training data generation schemes are proposed. One scheme transmits additional block pilot symbols to create training data, while the other scheme adopts a decision-directed method and does not require extra pilot overhead. Simulation results show the robustness of the proposed channel estimation method. Furthermore, the proposed method shows better adaptation to practical imperfections compared with the conventional minimum mean-square error (MMSE) channel estimation. It outperforms the existing machine learning-based channel estimation techniques under varying channel conditions.

In the linear minimum mean square error (LMMSE) estimation for orthogonal frequency division multiplexing (OFDM) systems, the channel correlation function (CCF) is required. Some methods have been proposed to calculate the CCF. Instead of providing a novel method to obtain the CCF, a scheme is developed for the estimator to select among different CCFs. In this paper, an enhanced LMMSE estimation is proposed that is able to select the best-matched CCF within a candidate set. To this end, a parameter comparison scheme is proposed, in which the possible channel statistics for the LMMSE estimation can be evaluated using the sampled noise MSE. Analytical expressions are thus derived to indicate the accuracy of the proposed scheme. Furthermore, fuzzy bound is provided as the performance metric, which reflects the resolution of the parameter comparison scheme. As an example of application, the enhanced LMMSE method is used with the block pilot pattern in the OFDM systems, and the possible CCF candidates for typical scenarios are presented. The complexity of the estimator is also analyzed and a simplified parameter comparison algorithm is proposed to reduce the complexity. Finally, the theoretical analysis and performance comparison are demonstrated by simulation experiments.This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.

This paper devises a robust receiver for OFDM systems in the presence of residual timing offsets and unknown channel prior information. The proposed receiver constructs typical receiver models and resorts to the model selection technique to choose the best-matched receiver model to improve the channel estimation and signal detection. The typical receiver models are classified by considering the channel delay spread and the level of timing offset. Based on the receiver model selected by the Bayesian model selection algorithm, the channel length and timing offset parameters in the receiver model can provide the effective channel statistical information to make the channel estimator adapt to the altered circumstances and thus more accurate. Furthermore, the effective interference variance parameters in the selected receiver model are used to enhance the channel estimation and refine the soft symbol detection. The simulation results show that the proposed receiver achieves a significant performance gain compared to the existing methods. It is also shown that the proposed scheme makes the receiver robust to the diverse channel conditions and the timing offset states at a cost of the only a moderate increase in complexity. INDEX TERMSOrthogonal frequency-division multiplexing (OFDM), channel estimation, symbol timing offset, model selection.