Disclosed is a hardware-based protection group switching method and optical communication equipment. The method includes: transmitting, by a FPGA in equipment when detecting switching triggering information indicating that a local network element possibly has switching triggering situations, the switching triggering information to each protection state machine through a hardware bus; determining, by each protection state machine according to related traffic flow information, one or more related protection groups that are possibly affected by each switching triggering situation, and generating each corresponding switching triggering condition according to each piece of switching triggering information; separately querying, by the protection state machines corresponding to the related protection groups, a pre-stored table for APS protocol operation results; and updating a cross connection table according to the operation results, and configuring the updated cross connection table to a cross connection chip or a packet switching chip through the FPGA.

A method and apparatus for allocating a bandwidth based on machine learning in a passive optical network, the method including generating an inference model to predict a consumed bandwidth required for transmission by learning unstructured data of a PON including an OLT and traffic data corresponding to state information of the PON collected from the PON, predicting a consumed bandwidth with respect to a queue corresponding to a class requiring a low-latency service among classes of ONUS connected to the OLT based on the generated inference model, performing a VBA with respect to the queue corresponding to the class requiring the low-latency service based on the predicted consumed bandwidth, and performing a DBA with respect to a queue corresponding to a class not requiring the low-latency service using a transmission bandwidth which remains after the VBA is performed.

Disclosed is a hardware-based protection group switching method and optical communication equipment. The method includes: transmitting, by a FPGA in equipment when detecting switching triggering information indicating that a local network element possibly has switching triggering situations, the switching triggering information to each protection state machine through a hardware bus; determining, by each protection state machine according to related traffic flow information, one or more related protection groups that are possibly affected by each switching triggering situation, and generating each corresponding switching triggering condition according to each piece of switching triggering information; separately querying, by the protection state machines corresponding to the related protection groups, a pre-stored table for APS protocol operation results; and updating a cross connection table according to the operation results, and configuring the updated cross connection table to a cross connection chip or a packet switching chip through the FPGA.

A method and apparatus for allocating a bandwidth based on machine learning in a passive optical network, the method including generating an inference model to predict a consumed bandwidth required for transmission by learning unstructured data of a PON including an OLT and traffic data corresponding to state information of the PON collected from the PON, predicting a consumed bandwidth with respect to a queue corresponding to a class requiring a low-latency service among classes of ONUS connected to the OLT based on the generated inference model, performing a VBA with respect to the queue corresponding to the class requiring the low-latency service based on the predicted consumed bandwidth, and performing a DBA with respect to a queue corresponding to a class not requiring the low-latency service using a transmission bandwidth which remains after the VBA is performed.