Quantum machine learning for demappers of low order modulations of 5G and beyond


Anwar, Khoirul and Alias, Mohamad Yusoff (2023) Quantum machine learning for demappers of low order modulations of 5G and beyond. In: The 1st Conference on Quantum Sciences and Technology (ConQuest2022), 22–24 November 2022, South Tangerang, Indonesia.

Full text not available from this repository.


This paper proposes quantum machine learning (QML) to assist fast demapping of low order modulations of future wireless communications beyond the fifth generation (5G), where the 5G new radio (NR) demappers are used as examples since standards for 5G-Advanced and the sixth generation (6G) are still unavailable. We demonstrate that QML circuit can be constructed to solve the problem of demapping involving many points, which is in general difficult and intractable, especially when the number of modulation constellation points are significantly large. In this paper, we use an amplitude encoding technique to map the received signal constellations, followed by data processing prior to the measurement, for further processing. The proposed QML circuit is confirmed to be able to demap successfully the signals of 5G NR, i.e., complex binary phase shift keying (C-BPSK) modulations with the training data of only the four complex symbols. These results are expected to stimulate other variational quantum algorithms (VQA) for higher order modulations of 5G-Advanced or 6G communications.

Item Type: Conference or Workshop Item (Paper)
Uncontrolled Keywords: 5G, wireless communications.
Subjects: T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK5101-6720 Telecommunication. Including telegraphy, telephone, radio, radar, television
Divisions: Faculty of Engineering (FOE)
Depositing User: Ms Nurul Iqtiani Ahmad
Date Deposited: 03 Jan 2024 03:51
Last Modified: 03 Jan 2024 03:51
URII: http://shdl.mmu.edu.my/id/eprint/11997


Downloads per month over past year

View ItemEdit (login required)