CNN-based Algorithm for Joint Channel and Phase Noise Estimation in OFDM Relay Systems

In this paper, it is proposed a convolutional neural network (CNN)-based algorithm for joint estimation of the channel and phase noise in orthogonal frequency-division multiplexing (OFDM) relay systems. Due to the time-varying nature of the oscillator phase noise in higher frequency bands, this impairment can no longer be treated as additive white gaussian noise leading to the deterioration in the overall performance of wireless communication systems. Thus, jointly with the channel frequency response, the proposed algorithm infers the intercarrier interference in the received baseband signal introduced by the phase noise of the transmitter and receiver oscillators. The impact of the number of cascaded channels between the source and the destination of the relay system is also studied. The proposed CNN-based approach has the potential to deal with the challenging phase noise problem, which is still an open issue for the cascaded channels. The obtained results show that due to the relevant intercarrier interference mitigation, the CNN-based approach outperforms the least square practical estimation and presents a considerable improvement in the bit error rate (BER). To the best of author's knowledge, this is the first work that unifies the relay cascaded channel and phase noise estimation in the frequency domain using a CNN-based algorithm.

Automated summary

This paper proposes a CNN-based algorithm for joint estimation of channel and phase noise in OFDM relay systems. The algorithm infers intercarrier interference caused by phase noise and investigates the impact of cascaded channels. The results show that the CNN-based approach outperforms practical estimation methods and significantly improves the bit error rate.