Pre-DFT processing using eigenanalysis for coded OFDM with multiple receive antennas

In broadband wireless communications, coded orthogonal frequency-division multiplexing (OFDM) can be used with multiple receive antennas to achieve both frequency diversity and space diversity. In this scenario, the optimal approach is subcarrier-based space combining. However, such an approach is quite complex, because multiple discrete Fourier transform (DFT) blocks, each per receive antenna, are used. In this paper, we propose a pre-DFT processing scheme based upon eigenanalysis. In the proposed scheme, the received signals are weighted and combined both before and after the DFT processing. As a result, the required number of DFT blocks can be significantly reduced. With perfect weighting coefficients, the margin of the performance improvement decreases along with the increase of the number of DFT blocks, thus enabling effective performance and complexity tradeoff. To achieve a maximum average pairwise codeword distance, it will be shown that the maximum number of DFT blocks required is equal to the minimum of the number of receive antennas and the number of distinct paths in the channel. When the number of distinct paths is larger than the number of receive antennas and with a smaller number of DFT blocks, extensive simulation results will also show that near-optimal performance can still be achieved for most channels. Finally, in an OFDM system with differential modulation, we use a signal covariance matrix to obtain the weighting coefficients before the DFT processing. In this case, simulation results will demonstrate that the performance of the proposed scheme can be better than subcarrier-based space combining, but with much lower complexity.