US 12,278,692 B2
System and method for determining launch energy, power and efficiency for a smart channel in a DWDM network using machine learning
Mritunjay Pandey, Bangalore (IN); and Karunakar Revuri, Telangana (IN)
Assigned to AT&T Communications Services India Private Limited, Bangalore (IN)
Filed by AT&T Communications Services India Private Limited, Karnataka (IN)
Filed on Dec. 6, 2022, as Appl. No. 18/076,122.
Prior Publication US 2024/0187122 A1, Jun. 6, 2024
Int. Cl. H04J 14/02 (2006.01); H04L 41/12 (2022.01); H04L 41/147 (2022.01); H04L 41/16 (2022.01)
CPC H04J 14/0227 (2013.01) [H04J 14/02219 (2023.08); H04L 41/12 (2013.01); H04L 41/147 (2013.01); H04L 41/16 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A device, comprising:
a processing system including a processor; and
a memory that stores executable instructions that, when executed by the processing system, facilitate performance of operations, the operations comprising:
determining a network topology in a fiber optic network, wherein the network topology comprises a plurality of network elements joined by fiber optic links;
selecting parameter values of a set of parameters to obtain selected parameter values for a channel between a first network element and a second network element in the plurality of network elements;
applying the selected parameter values to the network topology to create parameterized dense wavelength division multiplexing (DWDM) signals between the first network element and the second network element;
responsive to the applying the selected parameter values, determining characteristics of the channel in the fiber optic network;
repeating the selecting and applying of the parameter values to obtain selected parameter values to determine different characteristics of the channel using different selected parameter values;
training a machine learning (ML) model through application of the selected parameter values and the characteristics of the channel and the different selected parameter values and the different characteristics of the channel in the fiber optic network to the ML model and evaluation of performance of the ML model; and
predicting a target launch energy, power and efficiency using the ML model for the channel in the fiber optic network, wherein the characteristics of the fiber optic network include spectral efficiency, asymptotic power efficiency, average energy per bit, stimulated Brillouin scattering, stimulated Raman scattering, Rayleigh scattering, or any combination thereof.