Abstract
Equalization methods are used to recover the signal attenuated by channel loss. Different optimization algorithms are applied to find the best tap coefficients for each equalization that will improve eye opening and reduce bit error rate. The goal function for most equalization optimization algorithms is to reduce the difference between input and output signals, which is a linear optimization problem and can be solved relatively easily. This indirectly will increase eye height and improve eye diagram. Directly optimizing eye height is a non-linear problem and cannot be solved with analytical method. We are proposing FFE and DFE combined equalization optimization algorithm that optimizes directly eye height using Bayesian Optimization (BO). The proposed algorithm can be generalized for multi-level signals.
Recommended Citation
Z. Kiguradze et al., "Bayesian Optimization for High-Speed Channel Equalization," IEEE Electrical Design of Advanced Packaging and Systems Symposium, article no. 9011654, Institute of Electrical and Electronics Engineers, Dec 2019.
The definitive version is available at https://doi.org/10.1109/EDAPS47854.2019.9011654
Department(s)
Electrical and Computer Engineering
Keywords and Phrases
Bayesian Optimization; Channel Response; DFE; Equalization; FFE; Joint optimization; Tap coefficients
International Standard Book Number (ISBN)
978-172812432-2
International Standard Serial Number (ISSN)
2151-1233; 2151-1225
Document Type
Article - Conference proceedings
Document Version
Citation
File Type
text
Language(s)
English
Rights
© 2024 Institute of Electrical and Electronics Engineers, All rights reserved.
Publication Date
01 Dec 2019
Comments
National Science Foundation, Grant IIP-1440110