OFDM-Autoencoder for End-to-End Learning of Communications Systems
OFDM-Autoencoder for End-to-End Learning of Communications Systems
复制标题
DOI：
10.1109/spawc.2018.8445920
复制
发表时间：
2018-03
期刊：
影响因子：
--
通讯作者：
Alexander Felix;Sebastian Cammerer;Sebastian Dörner;J. Hoydis;S. Brink
中科院分区：
文献类型：
--
作者：
Alexander Felix;Sebastian Cammerer;Sebastian Dörner;J. Hoydis;S. Brink
我们通过基于深度神经网络（NN）的自编码器将通信系统的端到端学习思想扩展到带循环前缀（CP）的正交频分复用（OFDM）。我们的实现具有与传统OFDM系统相同的优点，即单抽头均衡和对采样同步误差的鲁棒性，这是以前单载波实现的主要挑战之一。这使得在多径信道上的可靠通信成为可能，并使通信方案适用于具有不精确振荡器的商用硬件。我们表明，所提出的方案可以用最先进的深度学习软件库来实现，因为发射器和接收器仅由基于梯度的训练所需的可微层组成。我们比较了基于自动编码器的系统在频率选择衰落信道上与最先进的OFDM基线的性能。最后，研究了非线性放大器的影响，并表明自编码器固有地学习如何处理这种硬件损伤。
We extend the idea of end-to-end learning of communications systems through deep neural network (NN)-based autoencoders to orthogonal frequency division multiplexing (OFDM) with cyclic prefix (CP). Our implementation has the same benefits as a conventional OFDM system, namely single-tap equalization and robustness against sampling synchronization errors, which turned out to be one of the major challenges in previous single-carrier implementations. This enables reliable communication over multipath channels and makes the communication scheme suitable for commodity hardware with imprecise oscillators. We show that the proposed scheme can be realized with state-of-the-art deep learning software libraries as transmitter and receiver solely consist of differentiable layers required for gradient-based training. We compare the performance of the autoencoder-based system against that of a state-of-the-art OFDM baseline over frequency-selective fading channels. Finally, the impact of a non-linear amplifier is investigated and we show that the autoencoder inherently learns how to deal with such hardware impairments.