Abstract: A federated learning method includes: each second device in a plurality of second devices first obtains data distribution information and sends the data distribution information to a first device. The first device receives the data distribution information from the plurality of second devices participating in federated learning. The first device selects a matched federated learning policy based on the data distribution information. The first device sends a parameter reporting policy corresponding to the federated learning to at least one second device in the plurality of second devices. A second device that receives the parameter reporting policy is configured to obtain second gain information based on the parameter reporting policy and a current training sample, and the second gain information is for obtaining a second model of the second device.

Abstract: A controller groups a plurality of service application types into a plurality of application type groups based on link quality requirements of the plurality of service application types in a network; determines sending priorities based on the plurality of application type groups; separately determines at least one link for the plurality of application type groups based on link quality requirements of the plurality of application type groups and link quality information of a plurality of links in the network; separately determines network configurations for the plurality of application type groups based on the at least one link separately determined for the plurality of application type groups, the sending priorities of the plurality of application type groups, the link quality requirements of the plurality of application type groups, and a policy recommendation engine; and delivers the network configurations to a policy execution point device.