Deep Learning Based Communication Over the Air

By Sebastian Dörner, Sebastian Cammerer, Jakob Hoydis, Stephan ten Brink. 2017

806 citations recorded by the source corpus.

End-to-end learning of communications systems is a fascinating novel concept that has so far only been validated by simulations for block-based transmissions. It allows learning of transmitter and receiver implementations as deep neural networks (NNs) that are optimized for an arbitrary differentiable end-to-end performance metric, e.g., block error rate (BLER). In this paper, we demonstrate that over-the-air transmissions are possible: We build, train, and run a complete communications system solely composed of NNs using unsynchronized off-the-shelf software-defined radios and open-source deep learning software libraries. We extend the existing ideas toward continuous data transmission, which eases their current restriction to short block lengths but also entails the issue of receiver synchronization. We overcome this problem by introducing a frame synchronization module based on another NN. A comparison of the BLER performance of the “learned” system with that of a practical baseline shows competitive performance close to $\text{1}$ dB, even without extensive hyperparameter tuning. We identify several practical challenges of training such a system over actual channels, in particular, the missing channel gradient, and propose a two-step learning procedure based on the idea of transfer learning that circumvents this issue.

Subfields: Aerospace Engineering, Electrical and Electronic Engineering

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

In Electrical and Electronic Engineering

Citations in the corpus

Wireless Network Intelligence at the Edge (2018, methodology): “Toward this vision, at the physical layer, an E2E communication framework was studied under unknown channels using an autoencoder (AE) [19], [20], recurrent NN (RNN) [21], and generative adversarial network (GAN) [22].”
An Interpretable Neural Network for Configuring Programmable Wireless Environments (2019, background): “The idea of backpropagation is to adjust the weights of nodes based on the errors at the output layer [15].”
Thirty Years of Machine Learning: The Road to Pareto-Optimal Wireless Networks (2019, methodology): “[326] also developed a DNN based prototype system solely composed of two unsynchronized”
6G Networks: Beyond Shannon Towards Semantic and Goal-Oriented Communications (2020, background): “Examples of application of machine learning tools to the physical layer of a communication system have been already studied, under unknown channels, using an autoencoder (AE) [58], [59], a recurrent neural network (RNN) [60], and a generative adversarial network (GAN) [61].”
Channel Agnostic End-to-End Learning Based Communication Systems with Conditional GAN (2018, methodology): “In [9], the end-to-end method has been extended to handle various hardware imperfection.”
A Tutorial on Ultrareliable and Low-Latency Communications in 6G: Integrating Domain Knowledge Into Deep Learning (2021, methodology): “Considering that the real-world channel is not available, the autoencoder is ﬁrst trained with a stochastic channel model and then implemented in real hardware for over-the-air transmissions [61].”
Deep Learning-Based End-to-End Wireless Communication Systems With Conditional GANs as Unknown Channels (2019, methodology): “In [15], the end-to-end method has been extended to handle various hardware imperfection.”
Survey on 6G Frontiers: Trends, Applications, Requirements, Technologies and Future Research (2021, background): “For example, the reconﬁgurability and adaptability of radio systems can be obtained via end-to-end learning design [348].”
A Deep Learning Framework for Optimization of MISO Downlink Beamforming (2019, methodology): “Among these efforts, the autoencoder based on unsupervised DL, investigated in [33], [34], is an ambitious attempt to learn an end-to-end communications system [35].”
Machine Learning in the Air (2019, background): “this limitation, [58] proposes a two-phase training approach:”
Deep Learning Enabled Semantic Communication Systems (2020, background): “Reinforcement learning has been exploited in [19] to acquire the channel gradient under an unknown channel model, which achieves better performance than the differential quadrature phase-shift keying (DQPSK) over real channels.”
Deep Learning in Physical Layer Communications (2018, background): “In this section, we will present innovative learning-based communication systems by treating the entire communication system as an end-to-end reconstruction task [4, 14, 15].”
Grant-Free Non-Orthogonal Multiple Access for IoT: A Survey (2019, background): “• Practical channel statistics: Systems with unknown channel models need to be better addressed by these approaches [178] in order for learning algorithms to retain their reputation of ability to tune parameters on the fly.”
Twelve Scientific Challenges for 6G: Rethinking the Foundations of Communications Theory (2022, background): “In these techniques, the combined effect of hardware response and communication channel can be learned and handled by the trained models [38].”