Machine learning techniques for selecting paths in multi-vendor reconfigurable optical add/drop multiplexer networks

A non-transitory computer-readable medium storing instructions which, when executed by a processing system including at least one processor, cause the processing system to perform operations, the operations comprising:

• defining a feature set for a proposed path through a wavelength division multiplexing network, wherein the proposed path traverses at least one link in the wavelength division multiplexing network, and wherein the at least one link connects a pair of reconfigurable optical add/drop multiplexers. wherein the network includes a plurality of reconfigurable optical add/drop multiplexers including the pair of reconfigurable optical add/drop multiplexers, and wherein the plurality of reconfigurable optical add/drop multiplexers comprising at least one reconfigurable optical add/drop multiplexer manufactured from a first vendor and at least one reconfigurable optical add/drop multiplexer manufactured from a second vendor different from the first vendor;
• predicting an optical performance of the proposed path, wherein the predicting employs a machine learning model that takes the feature set as an input and outputs a metric that quantifies a predicted optical performance of the proposed path;
• and
• determining whether to deploy a new wavelength on the proposed path based on the predicted optical performance of the proposed path.

A system, comprising:

• a processor;
• and
• a non-transitory computer-readable medium storing instructions which, when executed by the processor, cause the processor to perform operations, the operations comprising:
• defining a feature set for a proposed path through a wavelength division multiplexing network, wherein the proposed path traverses at least one link in the wavelength division multiplexing network, and wherein the at least one link connects a pair of reconfigurable optical add/drop multiplexers, wherein the network includes a plurality of reconfigurable optical add/drop multiplexers including the pair of reconfigurable optical add/drop multiplexers, and wherein the plurality of reconfigurable optical add/drop multiplexers comprising at least one reconfigurable optical add/drop multiplexer manufactured from a first vendor and at least one reconfigurable optical add/drop multiplexer manufactured from a second vendor different from the first vendor;
• predicting an optical performance of the proposed path, wherein the predicting employs a machine learning model that takes the feature set as an input and outputs a metric that quantifies a predicted optical performance of the proposed path;
• and
• determining whether to deploy a new wavelength on the proposed path based on the predicted optical performance of the proposed path.