On deep learning-based communication over the air

Abstract

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 offthe-shelf software-defined radios (SDRs) and open-source deep learning (DL) software libraries. We extend the existing ideas towards 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 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.S. Dörner, S. Cammerer, and S. ten Brink are with the Institute

Deep Learning Design for Joint Antenna Selection and Hybrid Beamforming in Massive MIMO

“…This has been demonstrated in several successful applications of DL in wireless communications problems such as channel estimation [31], [32], analog beam selection [33], [34], and also hybrid beamforming [33], [35]- [39]. In particular, DL-based techniques have been shown [32], [37], [38], [40], [41] to be computationally efficient in searching for optimum beamformers and tolerant to imperfect channel inputs when compared with the conventional methods,. However, these works investigated only narrow-band channels [35]- [38].…”

Deep Energy Autoencoder for Noncoherent Multicarrier MU-SIMO Systems

“…This data-driven system enables a joint optimization of both the transmitter and receiver via training, leading to better performance than conventional block-based systems. The AEbased system was implemented under real-world environments in [22]. The AE concept was also applied to OFDM and noncoherent MU-SIMO systems in [23] and [24], respectively.…”

Deep Learning Enabled Optimization of Downlink Beamforming Under Per-Antenna Power Constraints: Algorithms and Experimental Demonstration

“…In these situations, DL based detection has been proposed to tackle the underlying unknown nonlinearities [28]. Another area of interest is to optimize the end-to-end system performance [29], [30]. Conventional communication systems are based on the modular design and each block (e.g., coding, modulation) is optimized independently, which can not guarantee the optimal overall performance.…”