Deep Learning Constellation Design for the AWGN Channel With Additive Radar Interference

Abstract

Radar and wireless communication coexistence is considered in this paper as a possible solution to face the exploding demand and rising congestion in wireless networks. The transmission medium is modeled as an AWGN channel with additive radar interference. Standard constellations are not optimal in this context and an auto-encoder (AE) is used to design proper constellations and corresponding receiver devices. AE is a powerful tool in neural networks that shares strong similarities with communication systems. This technique is particularly relevant in the lack of an analytical expression of the loss function. In the asymptotic region (high interference regime), the optimal constellation shape is known and the AE always converges towards this optimal solution. In the other regions, the AE is able to yield solutions that outperform the standard configurations. Several demapping alternatives are also considered leading to the conclusion that it is possible to maintain the communication link in the presence of radar interference independently of the interference power. This is a step further compared to previous works in which solutions were limited to low or high interference regimes.

Coded Transmission under Non-Cooperative Radar Interference

“…Considering the simplicity and its popularity, a rate-1/2 convolutional encoder [5,7] 8 is employed in the transmitter along with 4-AM, 4-QAM and irregular 64-ary constellations. (10) with Nc terms for (11).…”

“…While this is true for quasi-regular (QR) cases, many systems are in fact irregular; especially for when the encoders are paired with non-uniformly spaced constellations [10]. For the communication systems suffering from non-cooperative radar interference, the optimal irregular constellations have been proposed in [11] for uncoded scenarios by utilizing deep learning techniques. Interestingly, this can be also observed in the cases where a convolutional encoder used with conventional M -QAM and M -PSK constellations [10].…”

Reinforcement Learning-Based Anti-Jamming in Networked UAV Radar Systems

“…Wang Li et al proved that some basic reinforcement learning algorithms could be successfully applied to dynamic detection of multiple-input-multiple-output (MIMO) radar with unknown environment and unknown number of targets [23]. Deep learning was used in [24] to discuss channel selection when wideband radar signals coexist with narrowband communication signals in the communication systems.…”

Autoencoder-bank Based Design for Adaptive Channel-Blind Robust Transmission

“…Owing to these benefits, a number of studies on employing AEs in the physical layer of communication systems has been reported [6,7,8,9,10]. Particularly, the idea of end-to-end learning of communication systems through deep NN-based AEs has been applied to a communication system characterized by an orthogonal frequency division multiplexing with cyclic prefix in [6].…”

“…Furthermore, the authors in [9] develop an AE-based deep learning architecture to model a multiuser single-input multipleoutput communication system. The work in [10] employs an AE to find proper constellations and corresponding receiver devices when a radar systems coexists with interfering wireless systems.…”