Method, system, and storage medium for multi-granularity virtual network topology configuration in SDM optical networks utilizing MAML and transfer learning

A method for providing virtual network topology configuration services based on model-agnostic meta-learning (MAML) and transfer learning, executed by a processor, characterized by comprising:

• step S1:
• building a network architecture using a software-defined network, wherein the network architecture comprises a network orchestrator, a virtual network topology and a physical base, the physical base comprises a space division multiplexing controller and a multi-granularity node structure,
• the multi-granularity node structure comprises a multi-core optical fiber, an optical switch and a wavelength selection switch, a fan-in and fan-out device of the multi-core optical fiber and the wavelength selection switch are connected to the optical switch to realize multi-granularity switching performed by space division multiplexing network nodes in core and spectrum dimensions,
• the network orchestrator is configured to receive configuration information comprising first information and second information sent by a user, the first information is a virtual network and machine learning services required by the user, and the second information is a quality of transmission requirement of the user under a specific baud rate and modulation format,
• the space division multiplexing controller is configured to receive a request sent by the network orchestrator to acquire current space division multiplexing network topology information, and send a space division multiplexing network topology to the network orchestrator;
• step S2:
• configuring, by the network orchestrator, the virtual network topology based on the configuration information, to map the virtual network topology to a lightpath of the physical base;
• and
• step S3:
• calling, by the network architecture, an intelligent machine learning service providing module to execute an MAML algorithm and a transfer learning algorithm to provide the user with the machine learning services, the machine learning services comprising quality of transmission estimation, fault management, and resource allocation.