4.7 Article

Reducing Computational Complexity of Neural Networks in Optical Channel Equalization: From Concepts to Implementation

期刊

JOURNAL OF LIGHTWAVE TECHNOLOGY
卷 41, 期 14, 页码 4557-4581

出版社

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/JLT.2023.3234327

关键词

Bayesian optimizer; coherent detection; computational complexity; neural network; nonlinear equalizer; pruning; quantization

向作者/读者索取更多资源

This paper introduces a new method for developing low-complexity neural network (NN) based equalizers for high-speed coherent optical transmission systems. Deep model compression techniques applied to feed-forward and recurrent NN designs are explored and compared, with a focus on their impact on equalizer performance. A Bayesian optimization-assisted compression approach is proposed and evaluated, optimizing hyperparameters to simultaneously enhance performance and reduce complexity. Additionally, metrics are introduced to quantify computing complexity in various compression algorithms, serving as benchmarks for evaluating the effectiveness of NN equalizers with compression. The trade-off between compression complexity and performance is evaluated using simulated and experimental data.
This paper introduces a novel methodology for developing low-complexity neural network (NN) based equalizers to address impairments in high-speed coherent optical transmission systems. We present a comprehensive exploration and comparison of deep model compression techniques applied to feed-forward and recurrent NN designs, assessing their impact on equalizer performance. Our investigation encompasses quantization, weight clustering, pruning, and other cutting-edge compression strategies. We propose and evaluate a Bayesian optimization-assisted compression approach that optimizes hyperparameters to simultaneously enhance performance and reduce complexity. Additionally, we introduce four distinct metrics (RMpS, BoP, NABS, and NLGs) to quantify computing complexity in various compression algorithms. These metrics serve as benchmarks for evaluating the relative effectiveness of NN equalizers when compression approaches are employed. The analysis is completed by evaluating the trade-off between compression complexity and performance using simulated and experimental data. By employing optimal compression techniques, we demonstrate the feasibility of designing a simplified NN-based equalizer surpassing the performance of conventional digital back-propagation (DBP) equalizers with only one step per span. This is achieved by reducing the number of multipliers through weighted clustering and pruning algorithms. Furthermore, we highlight that an NN-based equalizer can achieve better performance than the full electronic chromatic dispersion compensation block while maintaining a similar level of complexity. In conclusion, we outline remaining challenges, unanswered questions, and potential avenues for future research in this field.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

4.7
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据