Deep Learning Based Over-the-Air Training of Wireless Communication Systems without Feedback
Article
Davey, Christopher P., Shakeel, Ismail, Deo, Ravinesh C. and Salcedo-sanz, Sancho. 2024. "Deep Learning Based Over-the-Air Training of Wireless Communication Systems without Feedback." Sensors. 24 (10). https://doi.org/10.3390/s24102993
Article Title | Deep Learning Based Over-the-Air Training of Wireless Communication Systems without Feedback |
---|---|
ERA Journal ID | 34304 |
Article Category | Article |
Authors | Davey, Christopher P., Shakeel, Ismail, Deo, Ravinesh C. and Salcedo-sanz, Sancho |
Journal Title | Sensors |
Journal Citation | 24 (10) |
Number of Pages | 21 |
Year | 2024 |
Publisher | MDPI AG |
Place of Publication | Switzerland |
ISSN | 1424-8220 |
1424-8239 | |
Digital Object Identifier (DOI) | https://doi.org/10.3390/s24102993 |
Web Address (URL) | https://www.mdpi.com/1424-8220/24/10/2993 |
Abstract | In trainable wireless communications systems, the use of deep learning for over-the-air training aims to address the discontinuity in backpropagation learning caused by the channel environment. The primary methods supporting this learning procedure either directly approximate the backpropagation gradients using techniques derived from reinforcement learning, or explicitly model the channel environment by training a generative channel model. In both cases, over-the-air training of transmitter and receiver requires a feedback channel to sound the channel environment and obtain measurements of the learning objective. The use of continuous feedback not only demands extra system resources but also makes the training process more susceptible to adversarial attacks. Conversely, opting for a feedback-free approach to train the models over the forward link, exclusively on the receiver side, could pose challenges to reliably end the training process without intermittent testing over the actual channel environment. In this article, we propose a novel method for the over-the-air training of wireless communication systems that does not require a feedback channel to train the transmitter and receiver. Random samples are transmitted through the channel environment to train a mixture density network to approximate the channel distribution on the receiver side of the network. The transmitter and receiver models are trained with the resulting channel model, and the transmitter can be deployed after training. We show that the block error rate measurements obtained with the simulated channel are suitable for monitoring as a stopping criterion during the training process. The resulting method is demonstrated to have equivalent performance to the end-to-end autoencoder training on small message sequences. |
Keywords | deep learning; feedback-free training; trainable wireless communications systems; over-the-air training; neural networks |
Contains Sensitive Content | Does not contain sensitive content |
ANZSRC Field of Research 2020 | 400608. Wireless communication systems and technologies (incl. microwave and millimetrewave) |
Byline Affiliations | School of Mathematics, Physics and Computing |
Defence Science and Technology Group, Australia | |
University of Alcala, Spain |
Permalink -
https://research.usq.edu.au/item/z849x/deep-learning-based-over-the-air-training-of-wireless-communication-systems-without-feedback
Download files
33
total views5
total downloads2
views this month0
downloads this month