ANN LS-based Channel Estimation Algorithm of IM/DD-OFDM/OQAM-PON systems with SDN Mobile Fronthaul Network in 5G

Orthogonal frequency division multiplexing/offset quadrature amplitude modulation (OFDM/OQAM) passive op-tical network (PON) is the key to 5G SDN mobile fronthaul (MFH) due to its super bandwidth and extremely small order of magnitude signal delay. In the transmission process of signal, owing to the combined effect of chromatic dispersion (CD) and polarization (PMD), signal intrinsic imaginary interference (IMI) will be generated, which will make the transmission performance of OFDM/OQAM-PON change to a certain extent. An artificial neural network_least squares channel estimation algorithm (ANN_LS-CEA) is proposed. Firstly, the algorithm fits the time domain waveform by ANN. Secondly, estimates the channel transfer function (TF) in the frequency domain by LS to effectively reduce IMI. Through a series of simulation test data, it can be found that this algorithm can effectively improve the overall performance of the system. Compared with the ANN-CEA, this algorithm can reduce the bit error rate (BER) performance by 50%.