公开(公告)号：US20230111693A1

公开(公告)日：2023-04-13

申请号：US17885040

申请日：2022-08-10

Applicant: Infinera Corp.

Inventor： Juraj Slovak ,  Ankur Neog

IPC: H04J14/02 ,  H01S3/30 ,  G06N3/04

Abstract: Disclosed herein are methods and systems configuring a raman amplifier. One exemplary system may be provided with an optical amplifier deployed in an optical network, the optical amplifier having a plurality of raman pumps configured to obtain a desired gain profile. An actual gain profile and a raman pump configuration of each of the plurality of raman pumps may be processed by a network administration device using a first machine learning model to produce a combined optical transmission segment attribute representing attributes of an optical segment of the optical network. The combined optical transmission segment attribute and the desired gain profile may be processed with a second machine learning model to produce corrected raman pump configurations for each of the plurality of raman pumps of the raman amplifier. The corrected raman pump configurations may be used to configure each of the plurality of raman pumps of the raman amplifier.

公开(公告)号：US11979186B2

公开(公告)日：2024-05-07

申请号：US17929170

申请日：2022-09-01

Applicant: Infinera Corp.

Inventor： Ankur Neog ,  Zhong Pan ,  Baranidhar Ramanathan

IPC: H04B10/079 ,  G06N3/082

CPC classification number: H04B10/07953 ,  G06N3/082

Abstract: Disclosed herein are methods and systems for computing a launch power for an optical node by collecting data for an optical network segment and inputting the collected data and first power spectral density values into a machine learning model which are used to compute a first non-linear interference value. A first generalized-optical signal-to-noise ratio value is computed using the computed first non-linear interference value and amplified spontaneous emission values. At least one second generalized-optical signal-to-noise ratio value is computed using at least one second non-linear interference value, computed using at least one second power spectral density values, and the amplified spontaneous emission values. A highest generalized-optical signal-to-noise ratio value is determined by comparing the first generalized-optical signal-to-noise ratio value and the at least one second generalized-optical signal-to-noise ratio value. A launch power is computed using the power spectral density values associated with the highest generalized-optical signal-to-noise ratio.

公开(公告)号：US20230085524A1

公开(公告)日：2023-03-16

申请号：US17816252

申请日：2022-07-29

Applicant: Infinera Corp.

Inventor： Ankur Neog ,  Baranidhar Ramanathan ,  Wolfgang Schairer

IPC: G05B13/02 ,  H01S3/30 ,  H01S3/091 ,  G06N3/08 ,  G06N3/04

Abstract: Disclosed herein are methods and systems for configuring a raman amplifier. One exemplary system may be provided with a raman amplifier having a plurality of raman pumps and a controller, and a network administration device. The network administration device generates and deploys a first machine learning model and a second machine learning model to the controller of the raman amplifier. A desired gain profile may be automatically assessed using the first machine learning model to determine raman pump configurations for each of the plurality of raman pumps of the raman amplifier. The raman pump configurations for each of the plurality of raman pumps of the raman amplifier may be processed with the second machine learning model to produce an output gain profile. The determined raman pump configurations are deployed only if the output gain profile and the desired gain profile match to within a margin of error.

公开(公告)号：US20230079797A1

公开(公告)日：2023-03-16

申请号：US17929170

申请日：2022-09-01

Applicant: Infinera Corp.

Inventor： Ankur Neog ,  Zhong Pan ,  Baranidhar Ramanathan

IPC: H04B10/079 ,  G06N3/08

Abstract: Disclosed herein are methods and systems for computing a launch power for an optical node by collecting data for an optical network segment and inputting the collected data and first power spectral density values into a machine learning model which are used to compute a first non-linear interference value. A first generalized-optical signal-to-noise ratio value is computed using the computed first non-linear interference value and amplified spontaneous emission values. At least one second generalized-optical signal-to-noise ratio value is computed using at least one second non-linear interference value, computed using at least one second power spectral density values, and the amplified spontaneous emission values. A highest generalized-optical signal-to-noise ratio value is determined by comparing the first generalized-optical signal-to-noise ratio value and the at least one second generalized-optical signal-to-noise ratio value. A launch power is computed using the power spectral density values associated with the highest generalized-optical signal-to-noise ratio.

公开(公告)号：US20220416495A1

公开(公告)日：2022-12-29

申请号：US17841233

申请日：2022-06-15

Applicant: Infinera Corp.

Inventor： Ankur Neog ,  Zhong Pan ,  Baranidhar Ramanathan

IPC: H01S3/091 ,  H01S3/30 ,  H01S3/10 ,  G05B13/02

Abstract: Disclosed herein are methods and systems for automatically configuring a raman amplifier. One exemplary system may be provided with the raman amplifier, a user device, and a network administration device. A processor of the network administration device executes instructions that cause the network administration device to generate a machine learning model using machine learning techniques and deploy the machine learning model to a controller of the raman amplifier. When a desired gain profile is communicated from the user device to the controller of the raman amplifier, instructions stored in non-transitory computer readable memory cause a processor of the controller to automatically assess the desired gain profile using the machine learning model to determine raman pump configurations for each of a plurality of raman pumps of the raman amplifier and send the determined raman pump configurations to each of the plurality of raman pumps of the raman amplifier.