RAMAN PUMP DESIGN USING MACHINE-LEARNING APPROACHES

1 . A method, comprising:

generating training data corresponding to operation of a Raman pump system, the training data including:

training input parameters specifying Raman pump parameters and one or more channel launch powers corresponding to respective transmission band channels; and

a training output parameter specifying a Raman pump gain profile of the transmission band channels of the Raman pump system; and

training a neural network using the training data such that the neural network is configured to output inferred input parameters for the Raman pump system given a specified Raman pump gain profile.

2 . The method of claim 1 , wherein the neural network includes an auto-encoder that comprises:

an input layer having input nodes representing the Raman pump gain profile and the channel launch powers;

one or more intermediate layers having intermediate nodes representing the Raman pump parameters and the channel launch powers; and

an output layer having output nodes representing the Raman pump gain profile and the channel launch powers.

3 . The method of claim 2 , wherein the auto-encoder of the neural network includes an encoding function between the input layer and the intermediate layer and a decoding function between the intermediate layer and the output layer and is trained using a backpropagation process that involves:

setting decoding weights associated with the decoding function and the one or more intermediate layers based on the Raman pump gain profile of the output layer; and

setting encoding weights associated with the encoding function and the one or more intermediate layers based on the decoding weights.

4 . The method of claim 2 , further comprising comparing a first Raman pump gain profile corresponding to a simulated Raman pump system having the inferred input parameters output by the neural network to a second Raman pump gain profile output by the neural network alongside the inferred input parameters, the comparing the first Raman pump gain profile to the second Raman pump gain profile being based on a root mean square error between the first Raman pump gain profile and the second Raman pump gain profile.

5 . The method of claim 4 , further comprising adjusting weights associated with the input nodes, the intermediate nodes, or the output nodes responsive to the first Raman pump gain profile and the second Raman pump gain profile differing by a threshold value.

6 . The method of claim 1 , further comprising:

obtaining, by the trained neural network, an output parameter indicating a targeted Raman pump gain profile; and

outputting, by the trained neural network, the inferred input parameters that result in the Raman pump system exhibiting behavior corresponding to the targeted Raman pump gain profile indicated by the obtained output parameter.

7 . The method of claim 1 , wherein the Raman pump parameters include a Raman pump wavelength and a Raman pump power.

8 . The method of claim 1 , wherein:

the training data is randomly generated; and

the Raman pump gain profile is computed by solving coupled differential equations associated with the input parameters.

9 . The method of claim 1 , wherein:

the training data is generated in a test bed that:

generates random values of the training input parameters; and

measures the Raman pump gain profile based on the Raman pump system being designed with the random values; and

the test bed repeatedly generates the random values of the training input parameters and measures the Raman pump gain profile for a particular number of times.

10 . A method, comprising:

obtaining, by a neural network, an output parameter indicating a targeted Raman pump gain profile corresponding to a Raman pump system; and

outputting, by the neural network, inferred input parameters that result in the Raman pump system exhibiting behavior corresponding to the targeted Raman pump gain profile indicated by the obtained output parameter, the inferred input parameters including Raman pump parameters and one or more channel launch powers corresponding to respective transmission band channels of the Raman pump system.

11 . The method of claim 10 , wherein the neural network includes an auto-encoder that comprises:

an input layer having input nodes representing the Raman pump gain profile and the channel launch powers;

one or more intermediate layers having intermediate nodes representing the Raman pump parameters and the channel launch powers; and

an output layer having output nodes representing the Raman pump gain profile and the channel launch powers.

12 . The method of claim 11 , wherein the auto-encoder of the neural network includes an encoding function between the input layer and the intermediate layer and a decoding function between the intermediate layer and the output layer and is trained using a backpropagation process that involves:

setting decoding weights associated with the decoding function and the one or more intermediate layers based on the Raman pump gain profile of the output layer; and

setting encoding weights associated with the encoding function and the one or more intermediate layers based on the decoding weights.

13 . The method of claim 11 , further comprising comparing a first Raman pump gain profile corresponding to a simulated Raman pump system having the inferred input parameters output by the neural network to a second Raman pump gain profile output by the neural network alongside the inferred input parameters, the comparing the first Raman pump gain profile to the second Raman pump gain profile being based on a root mean square error between the first Raman pump gain profile and the second Raman pump gain profile.

14 . The method of claim 13 , further comprising adjusting weights associated with the input nodes, the intermediate nodes, or the output nodes responsive to the first Raman pump gain profile and the second Raman pump gain profile differing by a threshold value.

15 . The method of claim 10 , wherein the Raman pump parameters include a Raman pump wavelength and a Raman pump power.

16 . A system, comprising:

a neural network configured to output inferred input parameters for a Raman pump system given a specified Raman pump gain profile, the neural network including an auto-encoder that includes:

an input layer having input nodes representing the Raman pump gain profile and channel launch powers;

one or more intermediate layers having intermediate nodes representing the Raman pump parameters and the channel launch powers; and

an output layer having output nodes representing the Raman pump gain profile and the channel launch powers;

one or more processors; and

one or more non-transitory computer-readable storage media configured to store instructions that, in response to being executed, cause the system to perform operations, the operations comprising:

generating training data corresponding to operation of the Raman pump system, the training data including:

training input parameters specifying Raman pump parameters and one or more channel launch powers corresponding to transmission band channels; and

a training output parameter specifying a Raman pump gain profile of the transmission band channels of the Raman pump system; and

training a neural network using the training data such that the neural network is configured to output inferred input parameters for the Raman pump system given a specified Raman pump gain profile.

17 . The system of claim 16 , wherein the auto-encoder of the neural network includes an encoding function between the input layer and the intermediate layer and a decoding function between the intermediate layer and the output layer and is trained using a backpropagation process that involves:

setting decoding weights associated with the decoding function and the one or more intermediate layers based on the specified Raman pump gain profile of the output layer; and

setting encoding weights associated with the encoding function and the one or more intermediate layers based on the decoding weights.

18 . The system of claim 17 , further comprising comparing a first Raman pump gain profile corresponding to a simulated Raman pump system having the inferred input parameters output by the neural network to a second Raman pump gain profile output by the neural network alongside the inferred input parameters, the comparing the first Raman pump gain profile to the second Raman pump gain profile being based on a root mean square error between the first Raman pump gain profile and the second Raman pump gain profile.

19 . The system of claim 18 , further comprising adjusting weights associated with the input nodes, the intermediate nodes, or the output nodes responsive to the first Raman pump gain profile and the second Raman pump gain profile differing by a threshold value.

20 . The system of claim 16 , wherein the Raman pump parameters include Raman pump wavelength and a Raman pump power.

21 . The system of claim 16 , wherein:

the training data is randomly generated; and

the Raman pump gain profile is computed by solving coupled differential equations associated with the input parameters.