Our site saves small pieces of text information (cookies) on your device in order to deliver better content and for statistical purposes. You can disable the usage of cookies by changing the settings of your browser. By browsing our site without changing the browser settings you grant us permission to store that information on your device.
SIMRANJIT SINGH1,* , JAGROOP KAUR2, HARPREET KAUR2,3, RAJANDEEP SINGH4
Study offers the idea of utilizing machine-learning (ML) to forecast performance of a 50G-WDM-PON based on dual-parallel Mach-Zehnder-Modulator. Millimeter wave-over-fiber is also introduced with dual-parallel MZM based 50G-WDM-PON network by combining the benefits of millimeter wave and fiber-optic. Machine learning uses data-driven algorithms to extract patterns and relationships from previous network performance data. The numerical simulation is investigated with machine learning model to predict the performance of the signal in terms of Q-factor and error rate. ML model provides good accuracy of greater than 75%. Only one logistic model offers less than 90%. Findings show successful performance parameters using ML.
5G, 50G-Passive Optical Network, Dual-Parallel Mach–Zehnder Modulator, Wavelength Division Multiplexing and Machine Learning.
SIMRANJIT SINGH, JAGROOP KAUR, HARPREET KAUR, RAJANDEEP SINGH, Performance estimation of next generation passive optical networks stage 2 with machine learning techniques for 5G and beyond, Optoelectronics and Advanced Materials - Rapid Communications, 18, 9-10, September-October 2024, pp.440-454 (2024).
Submitted at: Nov. 12, 2023
Accepted at: Oct. 2, 2024
Optoelectronics and Advanced Materials - Rapid Communications
(2023): 0.5 - 2023 Journal Citation Reports (Clarivate Analytics, 2024)
Active accounts were imported to the new platform and assigned a random password by default. In order to access your account you need to access the login page and go through the Lost Password dialog (involves the system sending you an email with instructions) in order to reset your password. This step is necessary as passwords are kept in hashed form and the new platform uses modern hashing algorithms incompatible with the previous ones.