Abstract: A method for distributing an equity reward for federated learning based on an equity theory includes the following steps: applying Adams' equity theory to federated learning, analyzing, by a participant, all factors invested in a federated task comprehensively, then giving an expected reward for this task, calculating, by the task publisher, the reputation of the participant; participating, by the participant, in each round of a training task using a local data to evaluate data contribution, model contribution, and a waiting-time allowance of the participant, then combining contribution results of the three factors to evaluate the contribution of the participant; after a global model converges, dynamically adjusting weights of the three factors according to an objective function of the equity reward, with a goal that an actual reward of the participant is as close as possible to the expected reward, and obtaining and distributing the actual reward of the participant.

Abstract: A method of configuring a forwarding policy, a cloud management platform and an intelligent network management center are provided in the present disclosure. In an examples, the cloud management platform obtains a first mapping between a virtual machine and a network device, and transmits a first notification message to an intelligent network management center associated with the network device in a way that the intelligent network management center configures a forwarding policy associated with the virtual machine for the network device according to the first notification message, wherein the first notification message comprises virtual machine information of the virtual machine and network device information of the network device, and the forwarding policy instructs the network device to perform processing for a packet associated with the virtual machine.

Abstract: A method of transmitting a packet, a controller and a cloud management platform are provided. According to an example of the method, the controller may receive a packet from a virtual switch; obtain a forwarding priority corresponding to the packet; and generate a flow entry corresponding to the packet, wherein the flow entry is used to perform encapsulation of a specified type on a packet matching the flow entry and add the forwarding priority into the encapsulated packet; and distribute the flow entry to the virtual switch so that the virtual switch is capable of sending the packet using the flow entry.

Abstract: There is a service providing method applicable to a server, comprises: receiving a service request message of a client; allocating queuing information for the client, recording a correspondence relationship between the queuing information and a source address of the service request message, and transmitting the queuing information to the client, if the service request message carries no queuing information; and verifying a correspondence relationship between the queuing information and the source address of the service request message if the service request message carries the queuing information, and determining a service priority of the client according to the queuing information if the client passes the verification.

Abstract: In an example, a SDN controller may acquire a path maximum transmission unit (PMTU) of a Virtual Extensible Local Area Network (VXLAN) tunnel from a source VXLAN tunnel end point (VTEP) to a destination VTEP of a data packet, and may transmit a control entry to the source VTEP in such a way that an individual VXLAN packet has a length within the packet length corresponding to the PMTU.

Abstract: A method of transmitting a packet, a controller and a cloud management platform are provided. According to an example of the method, the controller may receive a packet from a virtual switch; obtain a forwarding priority corresponding to the packet; and generate a flow entry corresponding to the packet, wherein the flow entry is used to perform encapsulation of a specified type on a packet matching the flow entry and add the forwarding priority into the encapsulated packet; and distribute the flow entry to the virtual switch so that the virtual switch is capable of sending the packet using the flow entry.

Abstract: A method of configuring a forwarding policy, a cloud management platform and an intelligent network management center are provided in the present disclosure. In an examples, the cloud management platform obtains a first mapping between a virtual machine and a network device, and transmits a first notification message to an intelligent network management center associated with the network device in a way that the intelligent network management center configures a forwarding policy associated with the virtual machine for the network device according to the first notification message, wherein the first notification message comprises virtual machine information of the virtual machine and network device information of the network device, and the forwarding policy instructs the network device to perform processing for a packet associated with the virtual machine.

Abstract: In an example, a SDN controller may acquire a path maximum transmission unit (PMTU) of a Virtual Extensible Local Area Network (VXLAN) tunnel from a source VXLAN tunnel end point (VTEP) to a destination VTEP of a data packet, and may transmit a control entry to the source VTEP in such a way that an individual VXLAN packet has a length within the packet length corresponding to the PMTU.

Abstract: There is a service providing method applicable to a server, comprises: receiving a service request message of a client; allocating queuing information for the client, recording a correspondence relationship between the queuing information and a source address of the service request message, and transmitting the queuing information to the client, if the service request message carries no queuing information; and verifying a correspondence relationship between the queuing information and the source address of the service request message if the service request message carries the queuing information, and determining a service priority of the client according to the queuing information if the client passes the verification.