RNN-LSTM model for reliable optical transmission in flexible switching network systems

• Published in: Wireless networks Vol. 30; no. 3; pp. 1575 - 1589
• Main Author: Almawgani, Abdulkarem H. M.
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.04.2024; Springer Nature B.V
• Subjects: Algorithms; Communication; Communication networks; Communications Engineering; Communications networks; Communications traffic; Computer Communication Networks; Data communication; Data transmission; Datasets; Efficiency; Electrical Engineering; Engineering; Gaussian process; IT in Business; Machine learning; Network topologies; Networks; Optical communication; Original Paper; Parameters; Provisioning; Quadrature amplitude modulation; Recurrent neural networks; Signal to noise ratio; Trajectory planning; Transmission efficiency; RNN; LSTM; Quality of transmission; Optical communication network; Deep learning algorithm
• ISSN: 1022-0038; 1572-8196
• DOI: 10.1007/s11276-023-03599-9

Data traffic is rapidly growing due to e-commerce, digital communication, and the digital world. Optical networks must provide a better solution to enhance transmission and improve service with cost efficiency. Considerable investigations of the 64QAM (Quadrature Amplitude Modulation) model have been conducted on wireless and optical communication to improve transmission efficiency. The next generation 400Gb/s systems are now widely recognized to be commercially accessible. At the same time, optical communication networks need a superior method to provide the best Quality of Transmission with improved data transmission efficiency. This paper aims to improve the Quality of Transmission in Optical Communication Networks (OCN). Therefore, a simple and fast reconfigurable network model is essentially required. However, there is a problem primarily related to configuring the network parameters to improve the Quality of Transmission (QoT). Research has shown that deep learning algorithms can improve QoT. Recurrent Neural Networks and Long-Short-Term-Memory (RNN-LSTM) algorithms are employed to leverage the factors of QoT in OCN. The RNN model analyzes the physical network parameters, and LSTM analyzes the dynamic data parameters and data from OCN. The Gaussian processes and path computation elements are utilized to obtain a mean absolute Signal Noise Ratio error of merely 0.1dB as a better result by the Gaussian process. The proposed model can provide high flexibility in changing the network topologies, planning, and period with less complexity by including a dataset evolution, adjusting the parameters, and examining output. A real-time dataset is analyzed using RNN-LSTM, implemented in Python, and experimented with. The throughput, bandwidth, and modulation path following light paths are calculated in the experiment to estimate the QoT. The experimental results showed that the proposed RNN-LSTM model provides better QoT. From the comparison, the proposed model provides a better throughput of 1 to 2 Gbps and Under Provisioning Ratio of 0.5 Hz over the existing models.