Ghasrizadeh Sadegh, Khare Prasunika, Costa Nelson, Ruiz Marc, Napoli Antonio, Pedro Joao, Velasco Luis
Advanced Broadband Communications Center (CCABA), Universitat Politècnica de Catalunya (UPC), 08034 Barcelona, Spain.
Infinera Unipessoal Lda., Carnaxide, 2790-078 Oeiras, Portugal.
Sensors (Basel). 2024 Dec 17;24(24):8054. doi: 10.3390/s24248054.
Multiband (MB) optical transmission targets increasing the capacity of operators' optical transport networks. However, nonlinear impairments (NLI) affect each optical channel in the C+L+S bands differently, and, therefore, the routing and spectrum assignment (RSA) problem needs to be complemented with fast and accurate tools to consider the quality of transmission (QoT) within the provisioning process. This paper proposes a digital twin-assisted approach for lightpath provisioning to provide a complete solution for the RSA problem that ensures the required QoT in MB optical networks. The OCATA time domain digital twin is proposed, not only to estimate the QoT of a selected path but also to support the QoT-based channel assignment process. OCATA is based on a Deep Neural Network (DNN) to model the propagation of the optical signal. However, because of the different impacts of nonlinear noise on each channel and the large number of channels that need to be considered in C+L+S MB scenarios, OCATA needs to be adapted to make it scalable, while keeping its high accuracy and fast QoT estimation characteristics. In consequence, a complete methodology is proposed in this work that limits the number of channels being modeled to just a few. Moreover, OCATA-MB helps to mitigate NLI noise by programming the receiver at the provisioning time and thus with very little complexity compared to its equivalent implemented during the operation. NLI noise mitigation can be applied in the case when a lightpath cannot be provisioned because none of the available channels can provide the required QoT, making it an advantageous tool for reducing connection blocking. Exhaustive simulation results demonstrate the remarkable accuracy of OCATA-MB in estimating the QoT for any channel. Interestingly, by utilizing the proposed OCATA-MB-assisted lightpath provisioning approach, a reduction of the blocking ratio exceeding 50% when compared to traditional approaches is shown when NLI noise mitigation is not applied. If NLI mitigation is implemented, an additional over 50% blocking reduction is achieved.
多波段（MB）光传输旨在提高运营商光传输网络的容量。然而，非线性损伤（NLI）对C+L+S波段中的每个光信道的影响各不相同，因此，在配置过程中，路由和频谱分配（RSA）问题需要借助快速且准确的工具来考虑传输质量（QoT）。本文提出了一种用于光路配置的数字孪生辅助方法，为RSA问题提供完整解决方案，确保MB光网络中的所需QoT。提出了OCATA时域数字孪生，不仅用于估计所选路径的QoT，还用于支持基于QoT的信道分配过程。OCATA基于深度神经网络（DNN）对光信号的传播进行建模。然而，由于非线性噪声对每个信道的影响不同，以及在C+L+S MB场景中需要考虑大量信道，OCATA需要进行调整以使其具有可扩展性，同时保持其高精度和快速QoT估计特性。因此，本文提出了一种完整的方法，将建模的信道数量限制为仅几个。此外，OCATA-MB通过在配置时对接收器进行编程来帮助减轻NLI噪声，因此与运行期间实现的等效方法相比，其复杂度非常低。当由于没有可用信道能够提供所需的QoT而无法配置光路时，可以应用NLI噪声减轻，这使其成为减少连接阻塞的有利工具。详尽的仿真结果证明了OCATA-MB在估计任何信道的QoT方面具有显著的准确性。有趣的是，通过使用所提出的OCATA-MB辅助光路配置方法，在不应用NLI噪声减轻的情况下，与传统方法相比，阻塞率降低超过50%。如果实施NLI减轻，则可实现额外超过50%的阻塞减少。
