Machine Learning Control of Nonlinear Optical Chaos in 6G Data Transmission

View at publisher Summarise with VIRAT
Authors: Guodong Wang
Cited by: 0

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

The upcoming 6G network aims to deliver ultra-high data rates, sub-millisecond latency, massive connectivity, and intelligent automation. However, achieving these capabilities depends on optical fiber systems, where nonlinear optical chaos from effects like self-phase and cross-phase modulation significantly degrades signal quality and stability. To overcome these limitations, this research introduces a Digital Twin–Enabled Machine Learning Control (DT-MLC) framework for managing nonlinear optical behavior in 6G data transmission. The proposed DT acts as a real-time virtual replica of the physical optical system, continuously synchronized through live network feedback. By combining Wingsuit Flying Search-driven Least Squares-Support Vector Regression (WFS-LS-SVR) to recognize early signs of optical chaos and automatically adjust network parameters. To effectively describe complicated optical distortions and improve early chaos prediction, LS-SVR offers a strong foundation for nonlinear regression. A WFSO and adaptive controller are integrated to dynamically optimize system parameters, effectively stabilizing chaotic signal fluctuations under varying transmission loads. The model employs a multimodal 6G optical-network dataset with DT feedback, power, dispersion, and chaos indicators. Z-score normalization standardizes features, improving chaos detection accuracy and ensuring stable learning across conditions. The model evaluations were executed using Python 3.11. Experimental evaluation demonstrates that the proposed model outperforms existing approaches with consistently lower values across all chaotic systems: Lorenz: 0.31s, Rössler: 0.34s, Chen: 0.29s, and Qi: 0.32s, indicating faster convergence and superior stability. The DT-MLC framework improves signal stability, boosts throughput, and enables self-optimizing intelligent control, creating predictive, adaptive, and resilient autonomous 6G optical networks.

Fields of Study & Subjects

Optical Network Technologies Chaos control and synchronization Neural Networks and Reservoir Computing

Publication details

Journal / source
IEEE Communications Standards Magazine
Pages
1–9
Publication date
1 January 2026
Language
EN