Loading [a11y]/accessibility-menu.js
End-to-End Learned Self-Interference Cancellation | IEEE Conference Publication | IEEE Xplore

End-to-End Learned Self-Interference Cancellation


Abstract:

Full-duplex communications systems can transmit and received information at the same time and on the same frequency band. However, they require strong self-interference (...Show More

Abstract:

Full-duplex communications systems can transmit and received information at the same time and on the same frequency band. However, they require strong self-interference (SI) cancellation. While a part of this SI cancellation is carried out in the analog domain, in most cases digital SI cancelation is required as well. In this work, we examine various digital SI cancellation methods for a full-duplex system with high-order QAM constelations and 5G low-density parity-check (LDPC) based error-correction. Our results show that an end-to-end trained neural network joint SI canceller and demodulator can lead to significant bit error rate performance gains over a range of constellation sizes and LDPC code blocklengths.
Date of Conference: 31 October 2022 - 02 November 2022
Date Added to IEEE Xplore: 07 March 2023
ISBN Information:

ISSN Information:

Conference Location: Pacific Grove, CA, USA

References

References is not available for this document.