Xu, T;
Darwazeh, I;
(2021)
Faster URLLC: Deep Learning Waveform Fingerprinting.
In:
2021 IEEE International Conference on Communications Workshops (ICC Workshops).
IEEE: Montreal, QC, Canada.
Preview |
Text
ICC_Faster_URLLC_2021.pdf - Accepted Version Download (419kB) | Preview |
Abstract
Ultra-reliable low-latency communication (URLLC) is becoming an important research topic since it can boost mission-critical applications to serve 5G and its beyond. Traditionally, communication latency is determined by multiple factors such as transmission distance, signal duration and signal processing complexity. Among them, receiver side signal processing is the most critical factor. Firstly, a traditional 5G receiver will rely on independent signal processing blocks to decode a message, which is not optimal and would introduce unnecessary processing delay. Secondly, unsuccessful signal decoding will trigger retransmission and extra latency will be caused. This work proposes a waveform fingerprinting (WF) framework, which can easily identify users and resource assignment information based on signal patterns. More importantly, the WF scheme removes the block based 5G signal processing mechanism leading to a faster signal identification. A deep learning based intelligent identifier is integrated to assist the faster signal identification. Simulation results reveal that the proposed WF scheme enables higher reliability than the traditional 5G block based processing especially when noise power is higher than signal power. In addition, the processing latency of the WF scheme is two orders of magnitude shorter than the traditional 5G block based scheme.
| Type: | Proceedings paper |
|---|---|
| Title: | Faster URLLC: Deep Learning Waveform Fingerprinting |
| Event: | 2021 IEEE International Conference on Communications Workshops (ICC Workshops) |
| ISBN-13: | 9781728194417 |
| Open access status: | An open access version is available from UCL Discovery |
| DOI: | 10.1109/ICCWorkshops50388.2021.9473878 |
| Publisher version: | https://doi.org/10.1109/ICCWorkshops50388.2021.947... |
| Language: | English |
| Additional information: | This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions. |
| Keywords: | URLLC, waveform, fingerprinting, deep learning, signal classification, SEFDM, non-orthogonal |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Electronic and Electrical Eng |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10134573 |
Archive Staff Only
 |
View Item |
