Search

This paper simulates the relative performance of various artificial intelligence (AI) techniques when applied to nonlinear distortion compensation in wavelength division multiplexing (WDM) optical communication systems. These procedures are less complex than state-of-the-art compensation methods and do not necessitate prior knowledge about the properties of data in neighboring WDM channels, which can be practically challenging. In this study, Neural Networks (NNs) were integrated into both the transmitter and receiver sections of 3- and 5-channel WDM systems, and the resulting enhancement in performance (Q-factor) was assessed across varying levels of fiber nonlinearities. While the NN stage enhances the system performance, the improvement decreases as expected with the channel number and γ . Next, two-stage architectures that employ a transmitter side NN together with a classifier at the receiver side were modeled. For the systems examined in this paper simple decision tree structures, boosting, forests, extra trees, and multi-layer perceptron (MLP) classifiers all yielded enhanced system performance compared to simple chromatic dispersion compensation (CDC) with the only exception being Ada boosting which decreased the Q-factor for γ = 14 W - 1 k m - 1 . The outcomes of these investigations show that the most effective performance in highly nonlinear WDM systems is attained by employing two-stage systems, with the incorporation of random forest or extra tree AI methods at the receiver side yielding the highest results. [ABSTRACT FROM AUTHOR]

Due to the advancement of high definition, 5G technologies, the Internet of Things, and Artificial Intelligence, the demand for optical networks has increased widely. Optical communication networks offer various metrics, including high transmission capacity, efficient anti-interference, minimum transmission loss and robustness, and so on, that offer opportunities for communication networks. To satisfy the optical network demands, effective network resource utilization is essential. Therefore, developing a tool with improved Quality of Transmission (QoT) accuracy in optical networks is necessary. Recently, Artificial intelligence (AI) approaches have provided various opportunities to resolve these issues and the deep learning (DL) algorithms offer improved performance over the conventional methods. This paper developed a novel DL-based cognitive QoT prediction model for Quantum optical communication networks. This proposed model predicts the QoT for the QoS (Quality of Service) setup using the DL model with the transmission computation. The proposed model utilized an optimized DL model called CNN-LSTM for the prediction process using the signal and link characteristics as input features. The DL model is trained using the transmission equations. The hyperparameters of the neural network are optimized using frog leap optimization to improve the predictive performance. The experimental results highlight the enhanced and improved version of the proposed model, and the results are compared with the conventional systems in terms of performance measures. [ABSTRACT FROM AUTHOR]