Potential deep learning approaches for the physical layer
1University of Oulu, Faculty of Information Technology and Electrical Engineering, Communications Engineering
|Online Access:||PDF Full Text (PDF, 1 MB)|
|Persistent link:|| http://urn.fi/URN:NBN:fi:oulu-201908142760
Oulu : N. Rajapakshage,
|Publish Date:|| 2019-08-20
|Thesis type:||Master's thesis (tech)
Wijayakulasooriya, Janaka V.
Deep learning based end-to-end learning of a communications system tries to optimize both transmitter and receiver blocks in a single process in an end-to-end manner, eliminating the need for artificial block structure of the conventional communications systems. Recently proposed concept of autoencoder based end-to-end communications is investigated in this thesis to validate its potential as an alternative to conventional block structured communications systems. A single user scenario in the additive white Gaussian noise (AWGN) channel is considered in this thesis. Autoencoder based systems are implemented equivalent to conventional communications systems and bit error rate (BER) performances of both systems are compared in different system settings.
Simulations show that the autoencoder outperforms equivalent uncoded binary phase shift keying (BPSK) system with a 2 dB margin to BPSK for a BER of 10⁻⁵, and has comparable performance to uncoded quadrature phase shift keying (QPSK) system. Autoencoder implementations equivalent to coded BPSK have shown comparable BER performance to hard decision convolutional coding (CC) with less than 1 dB gap over the 0–10 dB Eb/N0 range. Autoencoder is observed to have close performance to the conventional systems for higher code rates. Newly proposed autoencoder model as an alternative to coded systems with higher order modulations has shown that autoencoder is capable of learning better transmission mechanisms compared to the conventional systems adhering to the system parameters and resource constraints provided. Autoencoder equivalent of half-rate 16-quadrature amplitude modulation (16-QAM) system achieves a better performance with respect to hard decision CC over the 0–10 dB Eb/N0 range, and a comparable performance to soft decision CC with a better BER in 0–4 dB Eb/N0.
Comparable BER performance, lower processing complexity and low latency processing due to inherent parallel processing architecture, flexible structure and higher learning capacity are identified as advantages of the autoencoder based systems which show their potential and feasibility as an alternative to conventional communications systems.
© Nuwanthika Rajapakshage, 2019. This publication is copyrighted. You may download, display and print it for your own personal use. Commercial use is prohibited.