SYSTEM AND METHOD FOR OPTICAL SYSTEM MARGIN ALLOCATION

• US 20200136723A1
• Filed: 07/08/2019
• Published: 04/30/2020
• Est. Priority Date: 10/31/2018
• Status: Active Grant

• Current Assignee: Fujitsu Limited
• Original Assignee: Fujitsu Limited
• Inventors: Bouda, Martin
• Granted Patent: US 10,771,152 B2
• Time in Patent Office: Days
• CPC Class Codes: G06N 3/044 Recurrent networks, e.g. Hopfield networks
• CPC Class Codes: G06N 3/08 Learning methods
• CPC Class Codes: H04B 10/0793 Network aspects, e.g. central monitoring of transmission parameters
• CPC Class Codes: H04B 10/07953 Monitoring or measuring OSNR, BER or Q
• CPC Class Codes: H04B 10/27 Arrangements for networking
• CPC Class Codes: H04J 14/021 Reconfigurable arrangements, e.g. reconfigurable optical add/drop multiplexers [ROADM] or tunable optical add/drop multiplexers [TOADM]
• CPC Class Codes: H04J 14/0241 Wavelength allocation for communications one-to-one, e.g. unicasting wavelengths
• CPC Class Codes: H04J 14/0284 WDM mesh architectures
• CPC Class Codes: H04L 1/0001 Systems modifying transmission characteristics according to link quality, e.g. power backoff adaptive data allocation for multicarrier modulation H04L5/0044; controlling transmission power for radio systems H04W52/04
• CPC Class Codes: H04L 1/0026 Transmission of channel quality indication
• CPC Class Codes: H04L 1/0061 Error detection codes

Abstract

A system and method for generating, based on optical network topology information, an optical model to represent an optical network; provisioning a new optical connection within the optical network: determining, using the optical model, a first bit error rate (BER) of the new optical connection; determining, using the optical network providing the new optical connection, a second BER of the new optical connection; determining, based on the first and the second BER, a BER excursion parameter of the new optical connection; training a margin allocator based on the BER excursion parameter of the new optical connection, and the first BER of the new optical connection; comparing the first BER of the new connection and a required optical margin to a threshold to determine a reliability of the new optical connection; and allocating, using the margin allocator, the required optical margin for additional optical connections of the optical network.

Claims

1. A computer-implemented method, comprising:

obtaining optical network topology information of an optical network;

generating, based on the optical network topology information, an optical model to represent the optical network;

provisioning a new optical connection within the optical network;

in response to provisioning the new optical connection;

determining, using the optical model, a first bit error rate (BER) of the new optical connection of the optical network;

determining, using the optical network providing the new optical connection, a second BER of the new optical connection;

determining, based on the first BER and the second BER, a BER excursion parameter of the new optical connection;

training a margin allocator comprising a recurrent neural network (RNN) based on the BER excursion parameter of the new optical connection, and the first BER of the new optical connection;

comparing the first BER of the new connection and a required optical margin to a threshold to determine a reliability of the new optical connection; and

allocating, using the margin allocator, the required optical margin for additional optical connections of the optical network.

2. The computer-implemented method of claim 1, further comprising updating one or more parameters of the optical model based on the new optical connection and the second BER of the new optical connection.

3. The computer-implemented method of claim 2, wherein updating the parameters of the optical model further comprises:

updating each optical model block of the optical model based on a wavelength, a spectral width, and a power level of the new optical connection.

4. The computer-implemented method of claim 1, wherein the threshold is a forward error correction (FEC) error correction limit.

5. The computer-implemented method of claim 1, wherein obtaining the optical network topology information of the optical network includes obtaining topology information of one or more reconfigurable optical add-drop multiplexers (ROADMs) of the optical network and optical connections between the ROADMs of the optical network.

6. The computer-implemented method of claim 1, further comprising:

determining a reachability of the new optical connection based on the signal quality of the new optical connection and the optical margin of the new optical connection.

7. The computer-implemented method of claim 1, wherein determining the BER excursion parameter of the optical connection further comprises:

identifying a largest BER deviation within a time period shorter than a time period of an averaged BER.

8. The computer-implemented method of claim 1, wherein determining the BER excursion parameter of the optical connection comprises:

identifying a largest SNR deviation within a time period shorter than a transmission frame from a predicted SNR value obtained using an optical model with associated parameters that are adjusted substantially less frequently than the time period.

9. The computer-implemented method of claim 1, further comprising:

determining a BER of an existing optical connection of the optical network;

determining, by the optical model, a signal quality of the existing optical connection;

determining, based on the BER of the existing optical connection, a BER excursion parameter of the existing optical connection; and

training the margin allocator RNN based on the BER excursion parameter of the existing connection and the signal quality of the existing connection.

10. The computer-implemented method of claim 9, further comprising:

updating or more parameters of the optical model based on the BER of the existing optical connection.

11. The computer-implemented method of claim 1, further comprising:

identifying a signal-to-noise ratio (SNR) of at least one other optical connection of the optical network;

determining a signal quality metric using the optical model and one or more parameters of the optical model that are based on the SNR of the at least one other optical connection of the optical network; and

replacing the first BER with the determined signal quality metric.

12. The computer-implemented method of claim 11, wherein the BER excursion parameter of the new optical connection is based on the determined signal quality metric over a time window that is substantially greater than a window used to determine the second BER.

13. A system comprising a processor having access to memory media storing operations executable by the processor to:

obtaining optical network topology information of an optical network;

generating, based on the optical network topology information, an optical model to represent the optical network;

provisioning a new optical connection within the optical network;

in response to provisioning the new optical connection;

determining, using the optical model, a first bit error rate (BER) of the new optical connection of the optical network;

determining, using the optical network providing the new optical connection, a second BER of the new optical connection;

determining, based on the first BER and the second BER, a BER excursion parameter of the new optical connection;

training a margin allocator comprising a recurrent neural network (RNN) based on the BER excursion parameter of the new optical connection, and the first BER of the new optical connection;

comparing the first BER of the new connection and a required optical margin to a threshold to determine a reliability of the new optical connection; and

allocating, using the margin allocator, the required optical margin for additional optical connections of the optical network.

14. The system of claim 13, the operations further comprising updating one or more parameters of the optical model based on the new optical connection and the second BER of the new optical connection.

15. The system of claim 14, wherein updating the parameters of the optical model further comprises:

updating each optical model block of the optical model based on a wavelength, a spectral width, and a power level of the new optical connection.

16. The system of claim 13, wherein the threshold is a forward error correction (FEC) error correction limit.

17. The system of claim 13, wherein obtaining the optical network topology information of the optical network includes obtaining topology information of one or more reconfigurable optical add-drop multiplexers (ROADMs) of the optical network and optical connections between the ROADMs of the optical network.

18. The system of claim 13, the operations further comprising:

determining a reachability of the new optical connection based on the signal quality of the new optical connection and the optical margin of the new optical connection.

19. The system of claim 13, wherein determining the BER excursion parameter of the optical connection further comprises:

identifying a largest BER deviation within a time period shorter than a time period of an averaged BER.

20. The system of claim 13, wherein determining the BER excursion parameter of the optical connection comprises:

identifying a largest SNR deviation within a time period shorter than a transmission frame from a predicted SNR value obtained using an optical model with associated parameters that are adjusted substantially less frequently than the time period.