Neural Network-Based Successive Interference Cancellation for Non-Linear Bandlimited Channels
Open Access
- 3 September 2024
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Communications
- Vol. 73 (3) , 1847-1861
Abstract
Reliable communication over bandlimited and non-linear channels usually requires equalization to simplify receiver processing. Equalizers that perform joint detection and decoding (JDD) achieve the highest information rates but are often too complex to implement. To address this challenge, model-based neural network (NN) equalizers that perform successive interference cancellation (SIC) are shown to approach JDD information rates for bandlimited channels with a memoryless nonlinearity and additive white Gaussian noise. The NNs are chosen to have a periodically time-varying and recurrent structure that imitates the forward-backward algorithm (FBA) in every SIC stage. Simulations for short-haul fiber-optic links with square-law detection show that NN-SIC nearly doubles current spectral efficiencies, and bipolar or complex-valued modulations achieve energy gains of up to 3 dB compared to state-of-the-art intensity modulation. Moreover, NN-SIC is considerably less complex than equalizers that perform JDD, mismatched FBA processing, and Gibbs sampling.Keywords
All Related Versions
This publication has 77 references indexed in Scilit:
- Nonlinear Effects of Wireless Transceivers2019
- Fundamentals of Wireless Communication2005
- Nonlinear Optics in Telecommunications2004
- Factor graphs and the sum-product algorithmIEEE Transactions on Information Theory, 2001
- Multilevel codes: theoretical concepts and practical design rulesIEEE Transactions on Information Theory, 1999
- Iterative detection in code‐division multiple‐access with error control codingEuropean Transactions on Telecommunications, 1998
- OFDM performance in amplifier nonlinearityIEEE Transactions on Broadcasting, 1998
- Iterative correction of intersymbol interference: Turbo‐equalizationEuropean Transactions on Telecommunications, 1995
- Trelliscodierte digitale Übertragungsverfahren1992
- Neural networks, error-correcting codes, and polynomials over the binary n-cubeIEEE Transactions on Information Theory, 1989