Low complexity iterative MLSE equalization of M-QAM signals in extremely long Rayleigh fading channels

This work proposes a neural network based iterative maximum likelihood sequence estimation (MLSE) equalizer, able to equalize signals in m-array quadrature amplitude modulation (M-QAM) modulated systems in a mobile fading environment with extremely long channels. Its computational complexity is linear in the data block length and approximately independent of the channel memory length, whereas conventional equalization algorithms have computational complexity linear in the data block length but exponential in the channel memory length. Its performance is compared to the Viterbi MLSE equalizer for short channels and it is shown that the proposed equalizer has the ability to equalize M-QAM signals in systems with hundreds of memory elements, achieving matched filter bound performance with perfect channel state information (CSI) knowledge in uncoded systems. The proposed equalizer is evaluated in a frequency selective Rayleigh fading environment.