A Stacked-Autoencoder Based End-To-End Learning Framework For Decode-And-Forward Relay Networks

In this work, we study an end-to-end deep learning (DL)-based constellation design for decode-and-forward (DF) relay network. Firstly, we study both the one-way (OW) and two-way (TW) relaying by interpreting DF relay networks as stacked autoencoders, under Rayleigh fading channels, leading to a performance improvement of 0.5 dB for TWDF networks. Secondly by introducing redundant bits in transmission and reception, we design end-to-end DL-based framework similar to the differential coded modulation for OWDF and coded modulation for TWDF relay networks, under block fading Rayleigh channels and achieve performance gain of 2 dB and 1 dB over conventional method, without using the channel state information knowledge in OWDF networks.