Network link adjustment method, network device and communication system

Abstract

The invention discloses a network link adjustment method, network equipment and a communication system, and relates to the technical field of communication. A first network device obtains a service flow between different nodes and a target transmission bandwidth required by the service flow, and re-determines a link group between the different nodes according to a link demand corresponding to the target transmission bandwidth and the link number of the link group between the different nodes. The first network device forwarding the service flow of the first node directly obtains the service flow sent by the first node to the second node, and guarantees the accuracy of the obtained service flow. The re-determined link group can be matched with the target transmission bandwidth of the service flow, so that the accuracy of links between different service nodes is improved; moreover, the re-determined link group can also expand or delete the original link group between different nodes, and when the link demand of the service flow changes, the links between different service nodes are adjusted in time, thereby ensuring the timeliness of the adjustment of the links between the service nodes.

Description

[0001] This application claims priority to the Chinese Patent Application No. 202410750295.8, filed on June 11, 2024, entitled "A communication reconstruction method and device", the content of which is incorporated herein by reference in its entirety. TECHNICAL FIELD

[0002] The present application relates to the field of communication technology, and in particular to a network link adjustment method, a network device and a communication system. BACKGROUND

[0003] The data center network usually includes a network control node, a link adjustment device, a first node and a second node. The first node includes a plurality of service nodes. Generally, each service node in the first node counts the service flow sent to the second node, and sends the counted service flow to the network control node. The network control node receives the service flow sent by each service node in the first node, and obtains the service flow sent by the first node to the second node. The network control node adjusts the link provided by the link adjustment device for forwarding the service flow sent by the first node to the second node according to the service flow sent by the first node to the second node.

[0004] In the above process, the network control node receives the service flow sent by each service node. In the case of a large number of service nodes, the network control node may have a high delay and poor accuracy in receiving the service flow due to bandwidth limitations of the network control node, etc. This causes the network control node to be unable to instruct the link adjustment device to adjust the link for forwarding the service flow of each node in a timely manner according to the service flow between each node, thereby affecting the service flow interaction between each node. SUMMARY

[0005] The present application provides a network link adjustment method, a network device and a communication system, which are used to solve the problem that the data center network cannot accurately adjust the link provided by the link adjustment device for forwarding the service flow of each node, thereby affecting the service flow interaction between each node.

[0006] In a first aspect, this application provides a network link adjustment method. The method is applied to a first network device, which is located at a first node in a data center network. The data center network also includes a network control node, a link adjustment device, a first node, and a second node. The network control node manages the link adjustment device, which adjusts the links of service flows in the data center network. The network link adjustment method provided in the first aspect includes: the first network device acquiring a first link group between the first node and the second node. The first link group includes at least one link. The first network device acquires the service flow sent from the first node to the second node and determines the target transmission bandwidth required by the service flow. If the number of links provided by the first link group is less than the link requirement corresponding to the target transmission bandwidth, the first network device sends a first message to the network control node. The first message requests the network control node to establish a first link between the first node and the second node. The first network device, in response to a first response from the network control node, determines a second link group that the service flow will use. The first response indicates that a first link has been established, and the second link group includes at least one link and the newly added first link.

[0007] In the first aspect of this application, a first network device acquires the service flow between different nodes and the target transmission bandwidth required by the service flow, and redetermines the link groups between the different nodes based on the link requirements corresponding to the target transmission bandwidth and the number of links in the link groups between the different nodes. The first network device, which forwards the service flow of the first node, directly acquires the service flow sent from the first node to the second node, ensuring the accuracy of the acquired service flow. Furthermore, the redetermined link groups not only match the target transmission bandwidth of the service flow, improving the accuracy of links between different service nodes, but also allow for the expansion or reduction of existing link groups between different nodes. When the link requirements of the service flow change, the links between different service nodes are adjusted in a timely manner, ensuring the timeliness of link adjustments between service nodes.

[0008] In one possible implementation, when the number of links provided by the first link group is greater than or equal to the link requirement corresponding to the target transmission bandwidth, the first network device sends a second message to the network control node. The second message requests the network control node to disconnect the second link in the first link group. In response to the network control node's second response, the first network device determines the third link group that the service flow will use. The second response indicates that the second link has been disconnected, and the third link group includes all links in the first link group except the second link. Thus, when the number of links provided by the first link group is greater than or equal to the link requirement corresponding to the target transmission bandwidth, the first network device sends a message instructing the link adjustment device to disconnect the second link, improving the resource utilization of the link adjustment device's link resources.

[0009] In another possible implementation, the first network device acquires the service flow sent from the first node to the second node, including: the first network device acquiring an initial service flow sent from the first node to the second node; the first network device acquiring a compensation value based on the initial service flow; wherein the compensation value is used to indicate the difference obtained by measuring the service flow sent from the first node to the second node using a first frequency and a second frequency, or the compensation value is used to indicate the difference obtained by comparing the initial service flow with historical service flows; and the first network device using the compensation value to compensate the initial service flow to obtain the service flow. Thus, by using the compensation value to compensate the initial service flow, the first network device reduces the inaccuracy of the service flow reflecting the link occupancy of the first node due to uneven duty cycles, thereby improving the accuracy of the target transmission bandwidth of the acquired service flow.

[0010] In another possible implementation, the business flow is f, which satisfies the following formula: f = a * (w * F) a +(1-w)*F m Where a is the proportionality coefficient, w is the weighting coefficient, and F a For the initial business flow, F m The compensation value is obtained by measuring the initial traffic flow using a first frequency, and then by measuring it using a second frequency, provided that a first condition is met. The first condition includes one or more of the following: the initial traffic flow is greater than or equal to a second traffic threshold, the congestion value of each link in the first link group is greater than or equal to a congestion threshold, and the second frequency is greater than the first frequency. Thus, by increasing the measurement frequency when the initial traffic flow is greater than or equal to the second traffic threshold and the congestion value of each link in the first link group is greater than or equal to the congestion threshold, it ensures that the measured traffic flow accurately reflects the target transmission bandwidth required by the first node.

[0011] In another possible implementation, the compensation value is the maximum traffic value of the service flow within a first number of cycles, measured using a second frequency.

[0012] In another possible implementation, the first link group includes a second link. A first network device, responding to a second response from the network control node, determines a third link group from which the service flow will use. This includes: the first network device receiving a third response from the network control node and, based on the third response, switching the service flow forwarded by the second link to other links. The third response is sent by the network control node under the condition that a disconnection condition is met. The disconnection condition includes: the network control node receiving a message from a second network device (configured on the second node) requesting the disconnection of the second link. If the service flow forwarded by the second link is less than or equal to a first traffic threshold, the first network device sends a third message to the network control node. This third message indicates that the service flow forwarded by the second link is less than or equal to the first traffic threshold. The first network device receives the second response from the network control node and determines the third link group based on other links.

[0013] In another possible implementation, the second link is released when the traffic flow forwarded by the second link is less than or equal to the first traffic threshold. In this way, the disconnected link can be reused to transmit traffic, improving the utilization of link resources.

[0014] In another possible implementation, the first and / or second messages include one or more of the following: link information and target transmission bandwidth. The link information includes one or more of the following: information about links to be established and information about links to be reduced. Thus, when the first and second messages include link information, the network control node can determine whether to add or disconnect links based on this link information. And when the first and second messages include target transmission bandwidth, the network control node can determine whether to add or disconnect links based on the number of links in the first link group provided by the link adjustment device and the target transmission bandwidth required by the service flow, thus expanding the application scenarios.

[0015] In another possible implementation, the first node also includes a third network device. The service flow includes: service flows sent from the first node to the second node via the first network device, and / or service flows sent from the first node to the second node via the third network device. Thus, the first node can use one or more network devices to forward service flows as needed for the actual application, ensuring data interaction between nodes.

[0016] Secondly, this application provides a network link adjustment method. This method is applied to a network control node in a data center network. The data center network also includes a link adjustment device, a first node, and a second node. The first node includes a first network device. The network control node manages the link adjustment device. The link adjustment device adjusts the links of service flows in the data center network. The network link adjustment method provided in the second aspect includes: the network control node receiving a first message from the first network device. The first message requests the establishment of a first link between the first node and the second node. The first link is determined based on the target transmission bandwidth required for the service flows transmitted between the first node and the second node. In response to the first message, the network control node determines whether the number of available links provided by the link adjustment device is greater than or equal to the link requirement of the first link. If the number of available links provided by the link adjustment device is greater than or equal to the link requirement of the first link, the network control node sends a link establishment indication message to the link adjustment device. The link establishment indication message indicates the establishment of the first link. The network control node receives a link establishment indication response from the link adjustment device and sends a first response to the first network device. The link establishment indication response indicates that the link adjustment device has established the first link, and the first response indicates that the first link has been established.

[0017] In the second aspect of this application, the network control node, based on the received first message, instructs the link adjustment device to establish the first link if the number of available links provided by the link adjustment device is greater than or equal to the link demand of the first link. This ensures the smooth forwarding of service flows from the first node to the second node.

[0018] In one possible implementation, the method further includes: a network control node receiving a second message from a first network device. The second message requests the disconnection of a second link between the first node and the second node. The second link is a link in a first link group between the first node and the second node. In response to the second message, the network control node determines whether a link adjustment device needs to disconnect the second link. If the link adjustment device disconnects the second link, the network control node instructs the link adjustment device to disconnect the second link and sends a second response to the first node indicating that the second link has been disconnected. Thus, upon receiving a second message indicating the disconnection of the second link, the network control node does not immediately disconnect the second link but instead determines whether it can be disconnected. This ensures the smooth forwarding of service flows from other nodes utilizing the second link for forwarding service flows.

[0019] In another possible implementation, the network control node responds to the second message by determining whether the link adjustment device has disconnected the second link. This includes the network control node sending a third response to the first network device in response to the second message. The third response is sent by the network control node under the condition that a disconnection condition is met. The disconnection condition includes: the network control node receiving a message from the second network device requesting the disconnection of the second link. The second network device is configured on the second node. The third response instructs the first network device to switch the service flow forwarded by the second link to other links. Other links are links in a first link group other than the second link. The first link group includes at least one link that forwards the service flow from the first node to the second node. The network control node receives a third message from the first network device. The third message indicates that the service flow forwarded by the second link is less than or equal to a first traffic threshold. The network control node also responds to the third message by determining whether the link adjustment device has disconnected the second link. Thus, upon receiving the second message indicating the disconnection of the second link, the network control node sends an instruction to the first network device to switch the service flow forwarded by the second link to other links, ensuring the normal forwarding of the service flow.

[0020] Thirdly, this application provides a network link adjustment method. This method can be applied to a data center network. The data center network includes a first network device, a network control node, a link adjustment device, a first node, and a second node. The first network device is located on the first node. The network control node manages the link adjustment device. The link adjustment device adjusts the links of service flows in the data center network. The forwarding method provided in this third aspect includes: the first network device acquiring a first link group between the first node and the second node. The first link group includes at least one link. The first network device acquires the service flow sent from the first node to the second node and determines the target transmission bandwidth required by the service flow. If the number of links provided by the first link group is less than the link requirement corresponding to the target transmission bandwidth, the first network device sends a first message to the network control node. The first message requests the network control node to establish a first link between the first node and the second node, where the first link is a link outside the first link group. The network control node receives the first message and, in response, determines whether the number of available links provided by the link adjustment device is greater than or equal to the link requirement of the first link. If so, the network control node sends a link establishment indication message to the link adjustment device. The link establishment indication message indicates the establishment of the first link. The network control node receives a link establishment indication response from the link adjustment device and sends a first response to the first network device. The link establishment indication response indicates that the link adjustment device has established a first link, and the first response indicates that the first link has been established. In response to the network control node's first response, the first network device determines a second link group that the service flow will use. The second link group includes at least one link and the newly added first link.

[0021] In one possible implementation, the method further includes: if the number of links provided by the first link group is greater than or equal to the link requirement corresponding to the target transmission bandwidth, the first network device sends a second message to the network control node. The second message requests the network control node to disconnect the second link in the first link group. The network control node receives the second message and sends a second response to the first network device. The second response indicates that the second link has been disconnected. In response to the second response, the first network device determines a third link group that the service flow will use. The third link group includes all links in the first link group except the second link.

[0022] Fourthly, this application provides a communication system. The communication system includes a network control node, a link adjustment device, a first node, and a second node. The first node includes a first network device. The network control node manages the link adjustment device. The link adjustment device adjusts the links of service flows in a data center network. The first network device is configured to: acquire a first link group between the first node and the second node. The first link group includes at least one link. The first network device is configured to: acquire the service flow sent from the first node to the second node and determine the target transmission bandwidth required by the service flow. When the number of links provided by the first link group is less than the link requirement corresponding to the target transmission bandwidth, the first network device is configured to: send a first message to the network control node. The first message requests the network control node to establish a first link between the first node and the second node. The first network device is configured to: in response to a first response from the network control node, determine a second link group that the service flow will use. The first response indicates that a first link has been established, and the second link group includes at least one link and the newly added first link.

[0023] Fifthly, this application provides a network device. The network device includes: a link acquisition module, a service flow acquisition module, and a processing module. The link acquisition module is used to: acquire a first link group between a first node and a second node. The first link group includes at least one link. The service flow acquisition module is used to: acquire the service flow sent from the first node to the second node and determine the target transmission bandwidth required by the service flow. The processing module is used to: send a first message to a network control node when the number of links provided by the first link group is less than the link requirement corresponding to the target transmission bandwidth. The first message is used to request the network control node to establish a first link between the first node and the second node. The processing module is further used to: in response to a first response from the network control node, determine a second link group that the service flow will use. The first response indicates that a first link has been established, and the second link group includes at least one link and the newly added first link.

[0024] Sixthly, this application provides a network control node. The network control node includes a transceiver module and a processing module. The transceiver module is configured to: receive a first message from a first network device. The first message requests the establishment of a first link between a first node and a second node. The first link is determined based on the target transmission bandwidth required for the service flow transmitted between the first node and the second node. The processing module is configured to: respond to the first message and determine whether the number of available links provided by a link adjustment device is greater than or equal to the link requirement of the first link. If the number of available links provided by the link adjustment device is greater than or equal to the link requirement of the first link, the processing module is further configured to: instruct the link adjustment device to establish the first link and send a first response to the first network device, the first response indicating that the first link has been established.

[0025] In a seventh aspect, this application provides a communication device. The communication device includes a memory and a processor. The memory stores a set of computer instructions. When the processor executes the set of computer instructions, it performs the operation steps of the method described in the first aspect or any possible implementation thereof, or performs the operation steps of the method described in the second aspect or any possible implementation thereof.

[0026] Eighthly, this application provides a computer-readable storage medium. It includes: computer software instructions; when executed in a computing device, the computer software instructions cause the computing device to perform operational steps of the method as described in the first aspect or any possible implementation thereof, or cause the computing device to perform operational steps of the method as described in the second aspect or any possible implementation thereof.

[0027] Ninthly, this application provides a computer program product. When the computer program product is run on a computer, it causes a computing device to perform the operation steps of the method as described in the first aspect or any possible implementation thereof, or causes the computing device to perform the operation steps of the method as described in the second aspect or any possible implementation thereof.

[0028] The beneficial effects of aspects three through nine above can be described with reference to the first aspect or any implementation thereof, and the second aspect or any implementation thereof, and will not be repeated here. Based on the implementations provided in the above aspects, this application can be further combined to provide more implementations. Attached Figure Description

[0029] Figure 1 This is an example diagram of the architecture of the first type of communication system;

[0030] Figure 2 This is an example diagram of the architecture of a forwarding cluster;

[0031] Figure 3 This is an example diagram of the architecture of the second type of communication system;

[0032] Figure 4 This is an example diagram of the architecture of the third type of communication system;

[0033] Figure 5 A flowchart illustrating a network link adjustment method provided in this application;

[0034] Figure 6 An example diagram of a business flow provided in this application;

[0035] Figure 7This application provides a schematic diagram of a process for obtaining compensation values ​​using frequency conversion.

[0036] Figure 8 An example diagram illustrating the establishment of communication between multiple network devices provided in this application;

[0037] Figure 9 A flowchart illustrating the process of obtaining an initial business flow provided in this application;

[0038] Figure 10 An example diagram of a data center network provided in this application;

[0039] Figure 11 A flowchart illustrating the initial business flow for obtaining a node, as provided in this application;

[0040] Figure 12 An interaction model diagram of the business flow of a node is provided in this application;

[0041] Figure 13 This application provides an example diagram showing the correspondence between link requirements and link quantity;

[0042] Figure 14 A schematic diagram of the structure of a network device provided in this application;

[0043] Figure 15 A schematic diagram of the structure of a network control node provided in this application;

[0044] Figure 16 This is a schematic diagram of the structure of a communication device provided in this application. Detailed Implementation

[0045] This application provides a network link adjustment method. A first network device acquires the service flow between different nodes and the target transmission bandwidth required by the service flow, and redetermines the link groups between the different nodes based on the link requirements corresponding to the target transmission bandwidth and the number of links in the link groups between the different nodes. The first network device forwarding the service flow of the first node directly acquires the service flow sent from the first node to the second node, ensuring the accuracy of the acquired service flow. Furthermore, the redetermined link groups not only match the target transmission bandwidth of the service flow, improving the accuracy of links between different service nodes, but also allow for the expansion or reduction of existing link groups between different nodes. When the link requirements of the service flow change, the links between different service nodes are adjusted in a timely manner, ensuring the timeliness of link adjustments between service nodes.

[0046] To ensure clarity and conciseness in the description of the following embodiments, some concepts that may be involved in this application will be briefly introduced first.

[0047] A network control node can refer to a device used to adjust the communication links provided between nodes by the link adjustment device.

[0048] Link adjustment equipment refers to devices used to provide links for forwarding service flows between nodes in a data center network. Link adjustment equipment can be devices that modify the provided links by changing their internal structure. Link adjustment equipment can include, but is not limited to, optical cross-connect (OXC) devices, optical circuit switches (OCS) devices, etc. When the link adjustment equipment is an OXC or OCS device, it can adjust the links used for forwarding service flows between nodes by changing its internal optical paths.

[0049] An OXC device is a multifunctional optical transport network (OTN) device that combines multiplexing, wiring, protection / recovery, monitoring, and network management. OXC devices may include, but are not limited to: fiber-level cross-connect devices and wavelength-level cross-connect devices. For example, wavelength-level cross-connect devices may include, but are not limited to: wavelength selectivity cross-connect (WSXC) and wavelength interchangeable cross-connect (WIXC).

[0050] OCS (Optical Controller System) devices utilize optical fiber as the network transmission medium between the controller and input / output (I / O), replacing the traditionally used copper twisted-pair cables. OCS devices can include, but are not limited to, wavelength selective switches (WSS) or optical branching devices with multiple input and output optical ports, which will not be elaborated upon here. Among these, the WSS is a core component in next-generation reconfigurable optical add-drop multiplexer (ROADM) optical networks.

[0051] A node can refer to a point of delivery (POD) in a data center network. A node can include multiple network devices and service nodes. Service nodes within a node can use the network devices within the node to forward service flows to other nodes.

[0052] Network devices can refer to devices used to forward the service flow of a service node to other nodes.

[0053] A business node can refer to a device that needs to interact with other nodes in terms of business flow, such as a server.

[0054] A service flow can refer to data packets transmitted between nodes. For example, a service flow refers to Internet Protocol version 4 (IPv4) data packets or Internet Protocol version 6 (IPv6) data packets transmitted from a first node to a second node.

[0055] Based on the brief introduction of the concepts that may be involved in this application above, the following section introduces the communication systems that may be applied to the network link adjustment method provided in this application.

[0056] Figure 1 Here is an example diagram of the architecture of the first type of communication system, such as... Figure 1 As shown, the communication system 100 may include: a network control node 110, a link adjustment device 120, and at least one node 130 (such as a first node and a second node). Each node 130 may include: at least one network device and at least one service node. For example, the first node may include at least one first network device and at least one service node, and the second node may include at least one second network device and at least one service node.

[0057] Network control node 110 is used to manage the link adjustment device. Specifically, network control node 110 adjusts the links provided by the link adjustment device for forwarding service flows between nodes based on the service flows forwarded between nodes 130. Network control node 110 can be a server, container, virtual machine, etc.

[0058] Link adjustment device 120 is used to provide communication links for service flow forwarding between nodes 130. Specifically, link adjustment device 120 receives link adjustment commands sent by network control node 110 and, in response to the link adjustment commands, establishes a link between two nodes 130, or, in response to the link adjustment commands, disconnects the link between two nodes 130. If link adjustment device 120 is an optical cross-connect (OXC) device, in this case, link adjustment device 120 can, in response to link adjustment command 1 from network control node 110, disconnect its internal optical path 1 used for service flow forwarding between node 1 and node 2.

[0059] Network devices are used to receive service flows sent by service nodes of their respective nodes (e.g., the first node) and forward these service flows to the destination node (e.g., the second node). Specifically, the first network device receives service flows sent by service nodes of the first node and uses the link adjustment device 120 to forward the service flows from the first node to the second node via the link provided by the first node. Network devices can be devices with data forwarding capabilities, such as switches, routers, etc. Taking a switch as an example, a network device can also be called an aggregation switch.

[0060] Depending on the needs of the actual application, network devices can be a single physical device (such as a single switch, a single router, etc.) or a forwarding cluster composed of multiple physical devices with data forwarding functions. Figure 2 Here is an example diagram of the architecture of a forwarding cluster, such as... Figure 2 As shown in (a), the forwarding cluster includes data forwarding devices 1 to n. Each of data forwarding devices 1 to n can receive the service flow from the service node and forward the service flow to other nodes.

[0061] In some possible examples, a forwarding cluster can include multiple forwarding sublayers. For example... Figure 2 As shown in (b), each forwarding sublayer may include one or more data forwarding devices. A forwarding sublayer may receive service flows forwarded by service nodes or other forwarding sublayers, and forward the service flows to other forwarding sublayers or other nodes.

[0062] For example, the forwarding cluster includes forwarding sublayer 1 and forwarding sublayer 2. Forwarding sublayer 1 includes data forwarding device 11 and data forwarding device 12, and forwarding sublayer 2 includes data forwarding device 21 and data forwarding device 22. Data forwarding devices 11 and 12 in forwarding sublayer 1 can receive service flows from service nodes and forward the received service flows to data forwarding devices 21 and 22 in forwarding sublayer 2. Each data forwarding device in forwarding sublayer 2 forwards the service flows to other nodes.

[0063] In some possible situations, Figure 3 Here is an example diagram of the architecture of the second type of communication system, such as Figure 3 As shown, node 130 of communication system 100 may also include other network devices, such as top-of-rack (TOR) switches. In this case, service nodes of node 130 send service flows to the TOR switch, and the TOR switch forwards the service flows to the node's network devices.

[0064] In some possible situations, Figure 4 Here is an example diagram of the architecture of the third type of communication system, such as Figure 4As shown, the communication system 100 may further include multiple link adjustment devices 120. Each of the multiple link adjustment devices 120 can interact with each node 130 in the communication system 100 to realize service flow interaction.

[0065] In some other possible scenarios, Figure 1 , Figure 3 and Figure 4 The illustrated communication system 100 may also exclude the link adjustment device 120. The network device of the source node can send service flows to the destination node via physical lines. In this case, according to the link adjustment command sent by the network control node 110, the physical line between any two source nodes 130 in the communication system 100 can be disconnected, or a new physical line can be added between any two nodes 130 in the communication system 100. The network link adjustment method provided in this application can be applied to a communication system 100 that includes one or more link adjustment devices 120, or it can be applied to a communication system 100 that does not include the link adjustment device 120. In this application, the communication system can also be referred to as a data center network.

[0066] It is understood that the structure illustrated in this embodiment does not constitute a specific limitation on the communication system. In other embodiments, the communication system may include more or fewer nodes than illustrated, or different node deployment methods. The illustrated network control node, nodes, and service nodes may be implemented in hardware, software, or a combination of software and hardware.

[0067] To ensure the normal forwarding of service flows between nodes in a communication system, the service flows forwarded between nodes can be acquired, and the number of links provided to nodes by the link adjustment device can be adjusted accordingly. Typically, the links used to implement service flow forwarding between nodes can be adjusted as follows: Each service node acquires the service flows it sends to other nodes and forwards these flows to the network control node. The network control node receives the service flows sent by each service node and adjusts the number of links provided to the nodes by the link adjustment device based on the received service flows.

[0068] In the above process, when a large number of service nodes are sending service flows to the network control node, the network control node may be unable to receive the service flows sent by each service node due to bandwidth limitations. This prevents the network control node from adjusting the links provided by the link adjustment equipment for forwarding service flows between nodes based on the service flows between them, thus affecting the interaction of service flows between nodes.

[0069] Based on this, this application provides a network link adjustment method. In this method, a first network device obtains the service flow between different nodes and the target transmission bandwidth required by that service flow. Then, based on the link requirements corresponding to the target transmission bandwidth and the number of links in the link groups between different nodes, it redetermines the link groups between the different nodes. The first network device, which forwards the service flow of the first node, directly obtains the service flow sent from the first node to the second node, ensuring the accuracy of the obtained service flow. Furthermore, the redetermined link groups not only match the target transmission bandwidth of the service flow, improving the accuracy of links between different service nodes, but also allow for the expansion or reduction of existing link groups between different nodes. When the link requirements of the service flow change, the links between different service nodes are adjusted in a timely manner, ensuring the timeliness of link adjustments between service nodes.

[0070] Figure 5 This application provides a flowchart illustrating a network link adjustment method, which can be applied to data center networks, and the data center network can have... Figure 1 , Figure 3 and Figure 4 The architecture of the communication system shown is as follows: The data center network may include a network control node, link adjustment equipment, and at least one node (such as a first node and a second node). The first node is equipped with a first network device, and the second node is equipped with a second network device. The network control node manages the link adjustment equipment. The link adjustment equipment is used to adjust the links of service flows in the data center network. Figure 5 As shown, the method may include the following steps S500 to S5100.

[0071] S500, the first network device acquires the first link group between the first node and the second node.

[0072] The first link group includes at least one link. A first network device on a first node and a second network device on a second node can establish a communication connection and announce to each other to obtain link information between the first and second nodes. For example, the first network device on the first node and the second network device on the second node may establish a connection using the Transmission Control Protocol (TCP) and obtain the ability for mutual announcement between the first and second nodes through Layer 3 forwarding. Based on the acquired mutual announcement capability, the first network device on the first node and the second network device on the second node announce to each other to obtain the first link group between the first and second nodes.

[0073] In some possible scenarios, such as when configuration information is limited, the first node can obtain the first link group between the first and second nodes with the help of the network control node. Specifically, the first network device can send information 1 configured on the first node. Information 1 includes, but is not limited to, the first node's identity (ID) and the Autonomous System Number (ASN) to which the first node belongs to, to the network control node. The second network device can send information 2 configured on the second node. Information 2 includes, but is not limited to, the second node's identity (ID) and the ASN2 to which the first node belongs, to the network control node. The network control node receives information 1 and information 2. The network control node obtains summary information based on information 1 and information 2, and sends the summary information to both the first and second network devices. The summary information includes: the first node's identity, ASN1, the second node's identity, and ASN2.

[0074] The above example uses a data center network including a first node and a second node, where the first node includes a first network device and the second node includes a second network device. In the case where the data center network includes more nodes (such as a third node) or nodes include more network devices (such as a third network device being set on the first node), the method described above can still be used to obtain the link groups between the nodes of the data center network, which will not be elaborated here.

[0075] S510, the first network device obtains the service flow sent from the first node to the second node.

[0076] The service flow can be a service flow sent from the first node to the second node, with the second node as the destination node. Alternatively, the service flow can be a service flow sent from the first node to the second node, with other nodes (such as a third node) as destination nodes; this application does not limit this. The first network device can acquire the service flow sent from the first node to the second node in various ways; examples of two possible methods are given below.

[0077] Example 1: The first network device counts the number of data packets sent from the first node to the second node within a set time period, and obtains the service flow sent from the first node to the second node based on the number of data packets obtained.

[0078] In this example, the first network device counts the number of data packets included in the service flow sent from the first node to the second node within a set time period, and obtains the service flow sent from the first node to the second node based on the counted number of data packets.

[0079] For example, network device 1 in node 1 counts the amount of data packets sent from node 1 to node 2 within a single set period (e.g., 60 seconds) (e.g., 600 megabytes (MB)), and based on the amount of data packets obtained, the service flow sent from node 1 to node 2 is 80 megabits per second (Mbps) (600*8 / 60).

[0080] Example 2: The first network device directly obtains the data packets sent from the first node to the second node, and obtains the service flow sent from the first node to the second node based on the obtained data packets.

[0081] In this example, the first network device can buffer data packets sent from the first node to the second node. The first network device counts the number of buffered data packets and, based on the counted number of data packets, determines the service flow sent from the first node to the second node.

[0082] For example, network device 1 in node 1 caches data packets sent from node 1 to node 2. Network device 1 counts the data packets sent from node 1 to node 2 within a set time period (e.g., 60 seconds), and based on the amount of data packets obtained from the count (e.g., 600MB), it determines that the service flow sent from node 1 to node 2 is 80Mbps (600*8 / 60).

[0083] The preceding text provides examples of two possible methods for the first network device to acquire service flows. Depending on the specific application scenario, the first network device may also acquire service flows using other methods, such as a combination of Examples 1 and 2. This application does not limit this approach. The following section uses the example of the first network device acquiring the service flow sent from the first node to the second node using the method shown in Example 1 to illustrate the network link adjustment method provided in this application.

[0084] In some possible scenarios, a service flow may include: a service flow sent from the first node to the second node via a first network device, and a service flow sent from the first node to the second node via other network devices. The meaning of a service flow can vary depending on the number of first network devices included in the first node. If the first node includes one first network device (e.g., network device 1), then the service flow may refer to the service flow sent from the first node to the second node via network device 1. If the first node includes multiple first network devices (e.g., network device 1 and network device 2), then the service flow may refer to the service flow sent from the first node to the second node via both network device 1 and network device 2.

[0085] In other words, the first node can use one or more network devices to send service flows to the second node. Depending on the number of network devices used by the first node, the way the first network devices obtain the service flows sent from the first node to the second node varies, and these scenarios are described below.

[0086] In scenario A, the first node sends a service flow to the second node using a network device (such as the first network device).

[0087] Taking the example of a first node sending a service flow to a second node using a first network device, the process of the network device obtaining the service flow sent by the first node to the second node is explained. In this case, the first network device can obtain the service flow sent by the first node to the second node using the following (1) to (3).

[0088] (1) The first network device obtains the initial service flow sent from the first node to the second node.

[0089] The first network device can measure the received service flow using a first frequency to obtain multiple measurement results. The first network device then calculates the average of the multiple measurement results and uses this average as the initial service flow.

[0090] For example, a first network device measures the received traffic flow at a rate of f1 (e.g., f1 = 10 times / second), obtaining 10 measurement results. The first network device calculates the average of these 10 measurement results and uses this average as the initial traffic flow.

[0091] In some possible scenarios, the first network device can also process the measurement results to improve the accuracy of the measurement. This processing may include, but is not limited to, removing the maximum value from the measurement results, removing the minimum value from the measurement results, removing values ​​with obvious errors from the measurement results, etc.

[0092] In real-world applications, the first node typically does not send service flows evenly to the second node. Figure 6 An example diagram of a business flow provided for this application, such as Figure 6As shown, within a statistical period, the first node sends service flows to the second node in the first half of the period and does not send any service flows to the second node in the second half of the period. In this scenario, the first network device acquires the service flows for the first half of the period, obtaining a target transmission bandwidth of M gigabits per second (Gbps). The first network device also acquires the service flows for the second half of the period, obtaining a target transmission bandwidth of 0 Gbps. Using the measurement averaging method described above, the first network device obtains a target transmission bandwidth of M / 2 Gbps between the first and second nodes. In this scenario, if M / 2 Gbps of data transmission bandwidth is allocated to the first and second nodes, congestion may occur in the first half of the period, and low bandwidth utilization may exist in the second half of the period.

[0093] In other words, when the first node sends service flows unevenly to the second node, the service flows obtained by the first network device using the measurement average method described above may not accurately describe the target transmission bandwidth required for the service flows between the first and second nodes. In this case, the first network device can use a compensation value to compensate for the initial service flows obtained to obtain the compensated service flows. The first network device can then obtain the service flows sent from the first node to the second node based on the compensated service flows. In this way, the service flows can more accurately describe the target transmission bandwidth required between the first and second nodes. The first network device can perform the following (2) and (3) to obtain the compensated service flows.

[0094] (2) The first network device obtains the compensation value based on the initial service flow.

[0095] The compensation value can refer to the difference in the service flow transmitted from the first node to the second node measured using a frequency conversion method. For example, the compensation value can be used to indicate the difference obtained by measuring the service flow transmitted from the first node to the second node using a first frequency and a second frequency. Alternatively, the compensation value can be used to indicate the difference obtained by comparing historical service flows with initial service flows. In other words, the first network device can obtain the compensation value in different ways. The specific process of obtaining the compensation value using the above two methods is given below.

[0096] Example 1: The first network device uses frequency conversion measurement to obtain the compensation value.

[0097] Figure 7 This application provides a flowchart illustrating a process for obtaining compensation values ​​using frequency conversion, as shown below. Figure 7 As shown, the process by which the first network device obtains the compensation value using frequency conversion measurement may include the following ① to ④.

[0098] ① The first network device detects a congestion event.

[0099] In some possible scenarios, the first network device may consider a congestion event to have occurred if a first condition is met. The first condition includes one or more of the following: the initial traffic flow is greater than or equal to a second traffic threshold; or the congestion value of each link in the first link group is greater than or equal to a congestion threshold. The process by which the network device detects congestion events using the above two methods is described below.

[0100] 1. The first network device detects service flows to detect congestion events.

[0101] In this scenario, the first network device can acquire the initial traffic flow and compare it with the second traffic threshold. If the initial traffic flow is greater than or equal to the second traffic threshold, a congestion event is considered to have occurred. In other words, the first network device can execute step ② if the acquired initial traffic flow is greater than or equal to the second traffic threshold.

[0102] 2. The first network device detects the congestion value of each link in the first link group to detect congestion events.

[0103] A first network device considers a congestion event to have occurred if the congestion value of each link in the first link group is greater than or equal to a congestion threshold. The congestion value can refer to the number of micro-bursts occurring at the port corresponding to the link. A micro-burst is considered to have occurred if the port's buffer usage is greater than or equal to a usage threshold. The first network device can detect the congestion value of each link in the first link group using the following process: The first network device scans the buffer usage of the ports corresponding to each link in the first link group at set intervals. If the buffer usage of the first port is greater than or equal to the usage threshold, a micro-burst is considered to have occurred at the first port. The first network device detects the number of micro-bursts occurring at the first port within a set time period, and if the number of micro-bursts occurring at the first port within the set time period is greater than or equal to the congestion threshold, the link corresponding to the first port is considered to be congested. Similarly, the first network device can detect the congestion status of other links in the first link group besides the first link using the method described above. If the number of links with congestion events in at least one link of the first link group is greater than or equal to a congestion number threshold, a congestion event is considered to have occurred between the first node and the second node.

[0104] The above provides examples of two possible methods for detecting congestion events. Depending on the needs of the actual application, other methods can also be used to detect congestion events, and this application does not limit this. Furthermore, in the event of a congestion event being detected, the first network device can perform ②.

[0105] ②The first network device uses the second frequency to measure the service flow sent from the first node to the second node.

[0106] The second frequency is greater than the first frequency.

[0107] ③ The first network device obtains the maximum value of the service flow measured using the second frequency.

[0108] In this scenario, the compensation value can be obtained in the following way. Specifically, the first network device can use a second frequency to detect a first number of traffic rates of the service flow within a first number of cycles. Furthermore, the first network device can obtain the traffic rate of the service flow within a single set period based on the amount of data added in a single set period and the duration corresponding to that single set period. This first number can be set according to actual needs.

[0109] For example, the first quantity is 5, the set period is Δt, and the initial data volume is M0. In this case, network device 1 can obtain the traffic rate within the first set period in the following manner. Specifically, network device 1 obtains the data volume M1 after the first set period Δt. Network device 1 obtains the difference ΔM1 between M1 and M0, and uses ΔM1 and Δt to calculate the traffic rate s1 of the service flow within the first set period Δt. And network device 1 obtains the data volume M2 after the second set period Δt. Network device 1 obtains the difference ΔM2 between M2 and M1, and uses ΔM2 and Δt to calculate the traffic rate s2 of the service flow within the second set period Δt. Similarly, network device 1 uses the above method to obtain the traffic rates s3 to s5 within the third to fifth set periods.

[0110] ④ The first network device obtains a compensation value based on the first number of traffic rates acquired.

[0111] The first network device can obtain the compensation value based on the first number of traffic rates in various ways. Two possible methods are given below.

[0112] Method 1: The first network device selects a traffic rate that meets the set conditions from a first number of traffic rates as the compensation value.

[0113] For example, the first network device selects the largest traffic rate from a first number of traffic rates as the compensation value. That is, the first network device uses the maximum measured traffic rate within a first number of set periods as the compensation value; the compensation value can be the maximum traffic value of the service flow within the first number of periods measured using a second frequency. In this case, the first network device obtains the maximum value among the first number of traffic rates and uses that maximum traffic rate as the compensation value. The first number can be preset or set according to the needs of the actual application; this application does not limit this.

[0114] For example, the first network device measures the traffic rate over five predetermined periods as s1 to s5. In this case, the first network device uses the maximum value among s1 to s5 as the compensation value.

[0115] For example, the first network device selects the median value from the traffic rates in the first quantity as the compensation value, and so on.

[0116] Method 2: The first network device processes a first number of traffic rates and uses the processing result as a compensation value.

[0117] The first network device can process the first number of traffic rates in multiple ways and obtain compensation values.

[0118] For example, network device 1 can obtain the average of a first number of traffic rates and use this average as a compensation value. For instance, network device 1 measures traffic rates s1 to s5 over five predetermined periods. In this case, network device 1 obtains the average of s1 to s5 and uses this average as the compensation value.

[0119] For example, network device 1 can also perform a weighted calculation on a first number of traffic rates to obtain a weighted result. Network device 1 can use this weighted result as a compensation value. For instance, if network device 1 measures the traffic rates s1 to s5 over five set periods, in this case, network device 1 performs a weighted calculation on s1 to s5 and uses the weighted result as a compensation value.

[0120] Depending on the needs of the actual application, the first network device may also use other methods to obtain the compensation value based on the first number of traffic rates, which is not limited in this application.

[0121] The process of obtaining compensation values ​​using frequency conversion in the first network device has been explained above. The process of obtaining compensation values ​​based on historical service flows in the first network device is explained below using Example 2.

[0122] Example 2: The first network device uses historical traffic flows to obtain compensation values.

[0123] In this scenario, the first network device can obtain historical traffic flows between the first and second nodes and use these historical traffic flows to obtain a compensation value. For example, the first network device obtains a compensation coefficient based on the historical traffic flows and a compensation value based on this compensation coefficient. For instance, if the historical traffic flow is greater than or equal to the initial traffic flow, the congestion value is greater than or equal to the congestion threshold, and the actual latency is greater than or equal to the expected latency, the compensation coefficient is set to be greater than 0 and less than 1. Conversely, if the historical traffic flow is less than the initial traffic flow, the congestion value is less than the congestion threshold, and the actual latency is less than the expected latency, the compensation coefficient is set to be greater than 0 and less than 1. Actual latency can refer to the actual duration consumed by each link forwarding traffic flow provided by the adjusted link adjustment device, and expected latency can refer to the expected duration of each link forwarding traffic flow provided by the adjusted link adjustment device.

[0124] (3) The first network device uses the compensation value to compensate the initial service flow and obtain the service flow.

[0125] Depending on how the first network device obtains the compensation value, the computing device can use different methods to obtain the service flow, which will be explained in the following cases.

[0126] In scenario a, the compensation value is obtained by the first network device using frequency conversion measurement.

[0127] In this scenario, the first network device can use the initial service flow and the compensation value to perform a weighted calculation to obtain the service flow. Specifically, the first network device can use the following formula (1) to obtain the service flow.

[0128] f = w * F a +(1-w)*F m Formula (1)

[0129] Where f is the business flow, w is the weighting coefficient, and F a For the initial business flow, F m This is the compensation value. In some possible cases, w∈[0,1].

[0130] For example, w is 0.8, the initial service flow obtained by the first network device is 800Gbps, and the obtained compensation value is 1000Gbps. In this case, the first network device can obtain a service flow of 840Gbps.

[0131] In some possible scenarios, the first network device can adjust the weighted result obtained by weighting the initial service flow and the compensation value, and use the adjusted result as the service flow. The first network device can adjust the weighted result in several ways; examples of two possible methods are given below.

[0132] Example 1: The first network device adjusts the weighted result using a scaling factor.

[0133] The scaling factor can be a constant set by the first network device according to actual application needs, or it can be obtained from historical service flows; this application does not limit this. In this case, the first network device can obtain the service flow using the following formula (2).

[0134] f = a * (w * F a +(1-w)*F m ) Formula (2)

[0135] Where f is the business flow, a is the proportional coefficient, w is the weighting coefficient, and F a For the initial business flow, F m This is a compensation value. 'a' can be any value greater than 0. For example, 'a' can be a number greater than 0 and less than 1, such as 0.5. Or, 'a' can be 1. Or, 'a' can be a number greater than 1, such as 1.5, 2, etc.

[0136] In some possible situations, 'a' can be calculated by using the reciprocal of the set bandwidth utilization rate, depending on the actual application needs, such as to improve the reliability of the link for service flow transmission.

[0137] For example, the data transmission bandwidth capacity of each link is 800Gbps. If network device 1 calculates the target transmission bandwidth of the service flow using formula (1), and the calculated target transmission bandwidth is 1.6TB / s, then two links need to be allocated to realize the transmission of the service flow. The service flow can only be transmitted normally if both links are in normal working condition. If either of the two links is not in normal working condition, the service flow may not be transmitted normally, resulting in low reliability. The set bandwidth utilization rate is 50%. If network device 1 calculates the target transmission bandwidth of the service flow using formula (2), and the calculated target transmission bandwidth is 3.2TB / s, then four links need to be allocated to realize the transmission of the service flow. The normal transmission of the service flow can be guaranteed if two of the four links are in normal working condition, resulting in high reliability. In some possible cases, the data transmission bandwidth capacity of a link can also be called the data transmission bandwidth of the link.

[0138] Example 2: The first network device adjusts the weighted result using an adjustment factor.

[0139] The adjustment coefficient can be a constant set according to actual application needs, or it can be obtained by the first network device based on historical service flows. This application does not limit this. In this case, the first network device can obtain the service flow using the following formula (3).

[0140] f = w * F a +(1-w)*F m+b Formula (3)

[0141] Where f is the business flow, w is the weighting coefficient, and F a For the initial business flow, F m 'b' is the compensation value, and 'b' is the adjustment coefficient.

[0142] Depending on the needs of the actual application, the first network device may also use other methods to adjust the weighting result to obtain the service flow, such as the first network device using both the proportional system and the adjustment coefficient to adjust the weighting result, etc., which is not limited in this application.

[0143] In scenario b, the first network device uses the compensation value obtained from historical service flows.

[0144] In this case, the first network device can obtain the service flow based on the product of the compensation value and the initial service flow. Specifically, the first network device can obtain the service flow using the following formula (4).

[0145] f = m * F a Formula (4)

[0146] Where f is the business flow, m is the compensation value, and F a This is the initial business flow.

[0147] For example, network device 1 acquires an initial service flow of 800Gbps and an acquisition compensation value of 1.2. In this case, network device 1 can obtain a service flow of 960Gbps.

[0148] In some possible scenarios, the first network device can adjust the product of the initial service flow and the compensation value, and use the adjusted result as the service flow. Please refer to the relevant description in scenario a above for the adjustment method; it will not be repeated here.

[0149] In scenario B, the first node uses multiple network devices to send service flows to the second node.

[0150] In this scenario, the following steps ① to ③ can be used to obtain the service flow sent from the first node to the second node.

[0151] ① Multiple network devices establish communication.

[0152] These multiple network devices can use TCP to achieve communication between each other. For details on this process, please refer to the general techniques, which will not be elaborated here. Figure 8 An example diagram illustrating the establishment of communication between multiple network devices provided in this application, such as... Figure 8 As shown, node 1 includes network device 1 to network device n, and each network device among network device 1 to network device n can use TCP to realize mutual communication between network devices.

[0153] ②Each of the multiple network devices obtains the service flow sent from the first node to the second node.

[0154] Each of the multiple network devices can use the method described in scenario A above to obtain the service flow sent from the first node to the second node through each network device.

[0155] For example, the first node sends service flows to the second node via network devices 1 to n. Network devices 1 to n can obtain service flows 1 to n sent by the first node to the second node via network devices 1 to n in the manner described in scenario A above.

[0156] ③ Among multiple network devices, the target network device obtains the service flow sent from the first node to the second node based on the service flow obtained by other network devices.

[0157] The target network device can be some or all of multiple network devices. If the target network device is one of multiple network devices, it can be a target network device that meets preset conditions, or it can be a specified network device. These preset conditions can be network devices with data transmission bandwidth greater than or equal to a bandwidth threshold.

[0158] Taking the example of all network devices among multiple network devices as the target network device, the process of obtaining the service flow sent from the first node to the second node is explained. In this case, each network device notifies the target network device of the service flow sent from the first node to the second node that it has obtained. Each network device receives the service flows notified by other network devices, and each network device summarizes its obtained service flows and the service flows obtained by other network devices to obtain a summary result. Based on the summary result, each network device obtains the service flow sent from the first node to the second node.

[0159] For example, Node 1 sends a service flow to Node 2 using network device 1 and network device 2. Network device 1 obtains a Gbps of the service flow sent from Node 1 to Node 2, and network device 2 obtains b Gbps of the service flow sent from Node 1 to Node 2. In this case, network device 1 and network device 2 mutually announce the service flows they have obtained. Based on its own obtained service flow a Gbps and the received service flow b Gbps announced by network device 2, network device 1 obtains that the service flow sent from Node 1 to Node 2 is (a+b) Gbps. Similarly, network device 1 obtains that the service flow sent from Node 1 to Node 2 is (a+b) Gbps.

[0160] The process of obtaining compensation values ​​by network devices has been explained in detail above. The following section describes how network devices obtain initial service flows. Network devices can obtain the initial service flows sent from the first node to the second node by matching forwarding table entries that match the service flow or by directly matching the destination node.

[0161] The following example illustrates the process of obtaining the initial service flow sent from the first node to the second node by the first network device in a data center network, where each node includes multiple network devices. The process can include the following ① to ④.

[0162] ①The first network device obtains the correspondence between nodes, routing domains, and forwarding table entries.

[0163] Forwarding entries can include multiple path groups used to implement service flow transmission between nodes. A path group can include one or more links used to implement service flow transmission between the source node and the destination node. For example, a forwarding entry can include multiple Equal-Cost Multipath Routing (ECMP) groups. Another example is that a forwarding entry can include multiple Weighted Cost Multiple Path (WCMP) groups. The following explanation uses an example of a forwarding entry including multiple ECMP groups to illustrate the method by which a network device obtains the initial service flow sent from the first node to the second node.

[0164] In some possible scenarios, the first network device can obtain the correspondence between node identifiers, routing domain identifiers (such as Autonomous System (AS) identifiers), and ECMP group identifiers in the forwarding table to obtain the correspondence between nodes, routing domains, and forwarding table entries. Node identifiers may include, but are not limited to, node names, node numbers, etc. Routing domain identifiers may include, but are not limited to, routing domain names and routing domain numbers (such as Autonomous System Numbers (ASN)). ECMP group identifiers may also include, but are not limited to, ECMP group names and ECMP group numbers. In some possible scenarios, this correspondence may also be referred to as a mapping relationship.

[0165] ② The first network device acquires the service flow transmitted using the first ECMP group.

[0166] The first network device sends service flows to multiple nodes using multiple ECMP groups. Based on the correspondence, the first network device determines the ECMP group (e.g., the first ECMP group) corresponding to the second node. The first network device obtains the service flows sent by each link in the first ECMP group, and based on the service flows sent by each link, obtains the service flows transmitted in the first ECMP group.

[0167] ③ The first network device obtains the service flow sent from the first ASN to the second ASN based on the correspondence and the service flow transmitted in the first ECMP group.

[0168] ④ Based on the correspondence, the first network device obtains the service flow sent by node 1 according to the service flow transmitted by the first ASN.

[0169] Figure 9 A flowchart illustrating the process of obtaining an initial business flow is provided in this application, such as... Figure 9 As shown, the data center network includes nodes 1 to 3. Each of nodes 1 to 3 uses two network devices (e.g., network device 1 and network device 2) to implement service flow transmission between nodes. The two network devices in node 1 constitute ASN1, the two network devices in node 2 constitute ASN2, and the two network devices in node 3 constitute ASN3. ECMP group 1 corresponds to ASN2, and ECMP group 2 corresponds to ASN3. Network device 1 of node 1 obtains the service flows sent by ECMP group 1 and ECMP group 2. Network device 1 determines the correspondence between ECMP group 1 and ASN2 based on the correspondence between ECMP groups and ASNs. Network device 1 obtains the service flows sent from ASN1 to ASN2. Based on the service flows sent from ASN1 to ASN2, network device 1 obtains the service flows sent from node 1 to node 2.

[0170] The above example of obtaining service flows sent from the first node to the second node illustrates how a network device can obtain service flows sent from a single node to another single node. In some possible scenarios, the above method can also be used to obtain service flows sent from a single node to one or more nodes, or to obtain service flows sent from multiple nodes to one or more nodes.

[0171] Figure 10 An example diagram of a data center network provided in this application, such as Figure 10As shown, the data center network includes nodes 1 to 3. Node 1 includes network device 1, network device 2, TOR1 to TORm, and multiple service nodes. TORi receives service flows from service nodes i1 to ij and sends these service flows to either network device 1 or network device 2. i is a positive integer greater than or equal to 1 and less than or equal to m. j is a positive integer greater than or equal to 2. Node 1 sends a service flow of 500Gbps to node 2 using network device 1, and a service flow of 300Gbps to node 2 using network device 2. Node 1 sends a service flow of 600Gbps to node 3 using network device 1, and a service flow of 1000Gbps to node 3 using network device 2.

[0172] The following is based on Figure 10 The data center network shown illustrates the process of acquiring service flows. Network devices can acquire service flows from node 1 using the following methods ① and ②.

[0173] ① Network device 1 and network device 2 respectively obtain the initial service flow sent by node 1.

[0174] Network device 1 can use the method described above to obtain the initial service flow 1 sent by node 1. The obtained initial service flow 1 is shown in Table 1 below.

[0175] Table 1. Network device 1 obtains the initial service flow 1 sent by node 1.

[0176]

[0177] Network device 2 can use the method described above to obtain the initial service flow 2 sent by node 1 to node 2 and node 3. The obtained initial service flow 2 is shown in Table 2 below.

[0178] Table 2. Network device 2 obtains the initial service flow 2 sent by node 1.

[0179]

[0180] ② The network device obtains the initial service flow sent by node 1 based on initial service flow 1 and initial service flow 2.

[0181] Network device 1 and network device 2 mutually announce their acquired initial service flows. Network device 1 receives the initial service flow 2 announced by network device 2, and based on its own acquired initial service flow 1 and the received initial service flow 2 announced by network device 2, it obtains the initial service flows shown in Table 3 below. Similarly, network device 2 can also obtain the initial service flows shown in Table 3 below.

[0182] Table 3 Initial service flow of node 1 obtained by network device 1

[0183]

[0184] Figure 11 A flowchart illustrating the initial business flow for obtaining a node is provided in this application, as shown below. Figure 11 As shown, the initial service flow 1 obtained by network device 1 and the initial service flow 2 obtained by network device 2 are as follows: Figure 11 As shown in the announcement, and the initial service flow of node 1 obtained by network device 1 and network device 2. Figure 11 As shown in the announcement.

[0185] ③ The network device uses the compensation value to compensate the initial service flow and obtain the service flow.

[0186] Network devices can compensate for the initial service flow using compensation values ​​obtained through frequency conversion measurement, or they can compensate for the initial service flow using compensation values ​​obtained from historical service flows. The following are exemplary descriptions of the process of compensating for the initial service flow using the above two compensation values.

[0187] Method 1: The network device uses the compensation value obtained by frequency conversion measurement to compensate the initial service flow, thus obtaining the service flow.

[0188] Using the method described above, network devices 1 and 2 measured the peak values ​​of the service flows sent from node 1 to node 2 and node 3, as shown in Table 4.

[0189] Table 4 shows the peak values ​​of service flows sent from Node 1 to Nodes 2 and 3.

[0190]

[0191] Network device 1 and network device 2 respectively use formula (1) above to calculate the service flow. If w in formula (1) is 0.8, the service flow shown in Table 5 can be calculated.

[0192] Table 5 shows the service flows sent from Node 1 to Nodes 2 and 3.

[0193]

[0194] Method 2: The network device compensates the initial service flow with the compensation value obtained from the historical service flow to obtain the service flow.

[0195] If the compensation value obtained based on the historical service flow is 1.2, in this case, the network device uses the formula (4) above to calculate the service flow shown in Table 6 below.

[0196] Table 6 shows the service flows sent from Node 1 to Nodes 2 and 3.

[0197]

[0198] Network devices acquire the service flows sent by nodes. Each node in the data center network uses network devices to count the service flows sent by its own node. Based on the service flows obtained by each node, the target transmission bandwidth required between the nodes in the data center network can be obtained. Figure 12 This application provides an interaction model diagram of a node's business flow, based on... Figure 12 The interaction model shown is such that node 1 counts the business flows it sends to nodes 2 and 3, node 2 counts the business flows it sends to nodes 1 and 3, and node 3 counts the business flows it sends to nodes 1 and 2.

[0199] The above example illustrates the process by which a network device acquires the service flow (i.e., uplink traffic) sent by a first node. In some possible scenarios, the network device may also acquire the service flow received by the node (i.e., downlink traffic). Alternatively, the network device may acquire both the service flow sent and received by the node (i.e., uplink and downlink traffic) to acquire the node's service flow; this application does not limit this approach.

[0200] S520, the first network device obtains the first target transmission bandwidth required for the service flow.

[0201] The first network device directly uses the bandwidth required for transmitting services as the primary target transmission bandwidth.

[0202] For example, when the acquired service flow is as shown in Table 5, network device 1 acquires a target transmission bandwidth of 840Gbps between node 1 and node 2, and a target transmission bandwidth of 1760Gbps between node 1 and node 3. When the acquired service flow is as shown in Table 6, network device 1 acquires a target transmission bandwidth of 960Gbps between node 1 and node 2, and a target transmission bandwidth of 1920Gbps between node 1 and node 3.

[0203] S530, when the link demand corresponding to the first target transmission bandwidth is greater than the number of links provided by the first link group, the first network device sends a first message to the network control node.

[0204] The first message is used to request the network control node to establish a first link between the first node and the second node. The first network device can implement S530 using the following (1) to (3).

[0205] (1) The first network device determines the number of links provided by the first link group.

[0206] Depending on the needs of the actual application, the data transmission bandwidth capabilities of each link in the first link group may be the same or different. This application does not limit this. The following is an example of the network link adjustment method provided in this application, with the example of each link in the first link group having the same data transmission bandwidth capability.

[0207] For example, Link Group 1 includes Links 1 to 5 for transmitting service flows between Node 1 and Node 2. The data transmission bandwidth capacity of Links 1 to 5 is 100 Mbps.

[0208] (2) The first network device generates a link adjustment strategy based on the number of links provided by the first link group and the link requirements corresponding to the target transmission bandwidth.

[0209] The link adjustment policy is used to instruct the link adjustment device to add at least one link (such as the first link) or disconnect at least one link (such as the second link).

[0210] The link requirement corresponding to the first target transmission bandwidth can refer to the required number of links corresponding to the first target transmission bandwidth (hereinafter referred to as the required links). Depending on the actual application needs, the data transmission bandwidth capacity provided by a single required link can be the same as the data transmission bandwidth capacity of each link in the first link group, or it can be different from the data transmission bandwidth capacity of each link in the first link group. The process of the first network device generating link adjustment strategies under these two different scenarios is explained below.

[0211] Scenario 1: The data transmission bandwidth capacity provided by a single demand link is the same as the data transmission bandwidth capacity of each link in the first link group.

[0212] In this scenario, the first network device can compare the number of links in the first link with the number of links corresponding to the first target transmission bandwidth, and generate different link adjustment strategies based on the comparison results, which will be described below.

[0213] ① The number of links in the first link is less than the number of links corresponding to the first target transmission bandwidth.

[0214] If the number of links in the first link is n fewer than the number of links corresponding to the first target transmission bandwidth, the first network device can generate a link adjustment strategy to establish n links.

[0215] ② The number of links in the first link is greater than the number of links corresponding to the first target transmission bandwidth.

[0216] If the number of links in the first link is m more than the number of links corresponding to the first target transmission bandwidth, the first network device can generate a link adjustment strategy to disconnect m links.

[0217] ③ The number of links in the first link is equal to the number of links corresponding to the first target transmission bandwidth.

[0218] When the number of links in the first link is equal to the number of links corresponding to the first target transmission bandwidth, the first network device can generate a link adjustment strategy that does not adjust the links.

[0219] Scenario 2: The data transmission bandwidth capacity provided by a single demand link is different from the data transmission bandwidth capacity of each link in the first link group.

[0220] In this scenario, the first network device can determine the existing data transmission bandwidth capacity based on the number of links in the first link group and the data transmission bandwidth capacity provided by each link in the first link group. The first network device then determines the required data transmission bandwidth capacity based on the number of required links corresponding to the target transmission bandwidth and the data transmission bandwidth capacity provided by the required links. Finally, the first network device generates a link adjustment strategy based on the difference between the required data transmission bandwidth capacity and the existing data transmission bandwidth capacity, and the data transmission bandwidth capacity that a single link of the link adjustment device can provide. Depending on the different differences between the required data transmission bandwidth capacity and the existing data transmission bandwidth capacity, the first network device can generate different link adjustment strategies, which are described below.

[0221] ① The required data transmission bandwidth capacity is greater than the existing data transmission bandwidth capacity.

[0222] In this scenario, the first network device can obtain the difference between the required data transmission bandwidth capacity and the existing data transmission bandwidth capacity. Based on this difference and the data transmission bandwidth capacity that a single link of the link adjustment device can provide, the first network device generates a link adjustment strategy. The link adjustment strategy indicates the number of links that the link adjustment device needs to add and the data transmission capacity of each new link.

[0223] Depending on the needs of the actual application, the data transmission bandwidth capabilities that the link adjustment device can provide for the links may be the same or different, and this application does not limit this. Depending on whether the data transmission bandwidth capabilities provided by the link adjustment device are the same, the first network device can use different methods to obtain the number of links to be added and the data transmission capacity of each new link, which will be explained below.

[0224] 1. The data transmission bandwidth capacity of the links provided by the link adjustment equipment is the same.

[0225] In this scenario, the first network device can perform a division operation between the difference and the data transmission bandwidth capability provided by a single link of the link adjustment device to obtain the number of links that need to be added. Based on the obtained number of new links, the first network device generates a link adjustment strategy. For example, if the difference is 300Gbps and the data transmission bandwidth provided by a single link is 100Gbps, the first network device can generate link adjustment strategy 1 based on 400Gbps and 100Gbps. Link adjustment strategy 1 indicates that 4 (400Gbps / 100Gbps) links need to be added, and each link has a data transmission bandwidth of 100Gbps.

[0226] 2. The data transmission bandwidth capabilities of the links provided by the link adjustment devices are not the same.

[0227] In this scenario, the first network device needs to generate a link adjustment strategy based on the difference and the data transmission bandwidth capacity of each link provided by the link adjustment device. This link adjustment strategy includes: the number of links to be added and the data transmission bandwidth capacity of each added link. For example, if the difference is 400Gbps, and the link adjustment device provides links 1 to 5, where links 1 to 4 provide a data transmission bandwidth capacity of 100Gbps, and link 5 provides a data transmission bandwidth capacity of 400Gbps, the first network device can generate either link adjustment strategy 1 or link adjustment strategy 2. Link adjustment strategy 1 indicates that the link adjustment device adds 4 links, each with a data transmission bandwidth capacity of 100Gbps. Link adjustment strategy 2 indicates that the link adjustment device adds 1 link, each with a data transmission bandwidth capacity of 400Gbps.

[0228] ② The required data transmission bandwidth capacity is less than the existing data transmission bandwidth capacity.

[0229] Similar to ① above, the first network device can determine the number of links to be disconnected and the data transmission bandwidth capacity of the links to be disconnected using the method described in ① above, and the first network device can generate a link adjustment strategy based on the number of links to be disconnected and the data transmission bandwidth capacity of the links to be disconnected. Please refer to the description in ① above for related details, which will not be repeated here.

[0230] ③ The required data transmission bandwidth capacity is equal to the existing data transmission bandwidth capacity.

[0231] In this scenario, the first network device can generate a link adjustment policy that indicates no link adjustment.

[0232] In some possible scenarios, a difference threshold can also be set. If the difference between the number of links in the first link group and the link demand corresponding to the first target transmission bandwidth is greater than the difference threshold, the first network device generates a link adjustment strategy using the method described above. Conversely, if the difference between the number of links in the first link group and the link demand corresponding to the first target transmission bandwidth is less than or equal to the difference threshold, the first network device does not generate a link adjustment strategy.

[0233] (3) The first network device sends a first message to the network control node based on the link adjustment strategy.

[0234] Depending on the content of the link adjustment policy instruction, the first network device may send a message to the network control node or may not send a message to the network control node.

[0235] For example, in a link adjustment policy that instructs the addition of at least one new link (such as a first link), the first network device sends a first message to the network control node. This first message requests the network control node to establish a first link between the first node and the second node.

[0236] For example, when a link adjustment policy is used to instruct the disconnection of at least one link (such as a second link), the first network device sends a second message to the network control node. This second message requests the network control node to disconnect the second link in the first link group.

[0237] For example, if the link adjustment policy indicates that no link should be adjusted, the first network device will not send a message to the network control node.

[0238] The preceding text describes the process of a first network device sending a first message to a network control node, using the example of a first network device generating a link adjustment strategy based on the number of links provided by a first link group and the link requirements corresponding to a first target transmission bandwidth, and sending a first message instructing the link adjustment device to add at least one link (such as the first link) or disconnect at least one link (such as the second link). In some possible examples, the first network device may not generate a link adjustment strategy based on the number of links provided by the first link group and the link requirements corresponding to the target transmission bandwidth, but instead directly use the first message carrying the target transmission bandwidth and send this first message carrying the target transmission bandwidth to the network control node. The network control node receives the first message and obtains the link requirements corresponding to the target transmission bandwidth based on the target transmission bandwidth carried in the first message. This application does not limit the network control node to generating a link adjustment strategy based on the number of links provided by the first link group and the link requirements corresponding to the target transmission bandwidth.

[0239] S540, the network control node receives the first message and sends the first response to the first network device.

[0240] The first message received by the network control node is a request to add at least one new link (such as a first link). The first link is a link other than those included in the first link group. The first response indicates that the first link has been established.

[0241] In some possible scenarios, the first message may include one or more of the following: link information, target transmission bandwidth.

[0242] When the first message includes link information, this link information may refer to the link information of the newly added first link. This link information may include, but is not limited to: the number of newly added first links, the source and destination nodes of the newly added first links, and the data transmission bandwidth capacity supported by the newly added first links. If the newly added links include at least one, the first message may also include: the total data transmission bandwidth capacity supported by all the newly added links, etc. In this case, the network control node can receive and parse the first message to obtain the link information of the first link to be added. The network control node can also adjust the available link resources of the link adjustment device to determine whether to add a first link; for details, please refer to ① to ③ below.

[0243] Available link resources may include, but are not limited to, the number of available links and the data transmission capacity and available bandwidth resources supported by each available link. Available link resources may be actively reported by the link adjustment device to the network control node, or they may be reported to the network control node based on an available resource acquisition request sent by the network control node to the link adjustment device. This application does not limit this.

[0244] If the first message includes a first target transmission bandwidth, the network control node determines the number of new links to be added, the data transmission bandwidth capacity of each link in the available link resources, and so on, based on the received first target transmission bandwidth and the data transmission bandwidth capacity supported by each link. Thus, when the data transmission bandwidth capacity supported by each link in the available link resources differs, the network control node can flexibly select links from the available resources as new links according to the actual application needs, expanding the application scenarios. In some possible situations, available link resources may include, but are not limited to: idle link resources, and link resources generated by disconnecting other links. Link resources may include one or more links.

[0245] After receiving the first message, the network control node can execute the following steps ① to ③ to determine whether to add a new first link.

[0246] ① The network control node determines whether there are available link resources.

[0247] Depending on the architecture of the data center network used in this application, the network control node can determine whether there are available link resources for different network devices.

[0248] For example, if the network link adjustment method provided in this application is applied to Figure 1 In the communication system shown, the network control node determines whether the link adjustment device 120 in the communication system 100 has available link resources. Taking the link adjustment device 120 as an OXC device as an example, the network control node determines whether the OXC device has idle link resources, and if the OXC device does not have idle link resources, the network control node determines whether there is a link to be disconnected. If there is a link to be disconnected, the network control node disconnects the link to be disconnected to obtain link resources generated by disconnecting other links. Furthermore, if the OXC device has idle link resources or link resources generated by disconnecting other links, then available link resources can be considered to exist.

[0249] Depending on the availability of link resources, the network control node can perform different actions. If available link resources exist, the network control node can perform the following action ②. And if no available link resources exist, the network control node can perform the following action ③.

[0250] ② The network control node adds a first link using available link resources and sends a first response to the first network device.

[0251] The network control node sends a link establishment indication message to the link adjustment device, instructing the link adjustment device to establish a first link. The network control node receives the link establishment indication response from the link adjustment device and sends a first response to the first network device. The link establishment indication response indicates that the link adjustment device has established the first link. The first response indicates that the first link has been established.

[0252] Depending on the content of the first message, the process by which the network control node uses available link resources to determine the addition of a first link and sends a first response to the first network device differs. These scenarios are described below.

[0253] In scenario (1), the first message includes link information.

[0254] Taking link information including the number of links, the source node and destination node of the newly added link as an example, in this case, the network control node directly parses the first message to obtain the number of links to be added, the source node and destination node of the newly added link. Furthermore, if available link resources exist, the network control node can send a link establishment indication response to the link adjustment device (such as an OXC device) to instruct the addition of a first link using available link resources. After the link adjustment device adds the first link, it sets the port of the first link to UP and sends a link establishment indication response to the network control node to indicate that the first link has been established. The network control node receives the link establishment indication response, generates and sends a first response to the first network device. The first response indicates that the first link has been established. The second link group includes at least one link in the first link group and the newly added first link.

[0255] In some possible scenarios, the link information may also include: the data transmission bandwidth capacity (or target data transmission bandwidth capacity) supported by the newly added first link. In this case, if available link resources exist, the network control node can use the method described above to add at least one link that supports providing the target data transmission bandwidth capacity.

[0256] In scenario (2), the first message includes the first target transmission bandwidth.

[0257] In this scenario, the network control node determines the number and identifiers of the new links to be added based on the data transmission bandwidth capacity supported by the available link resources and the first target transmission bandwidth. The network control node can then instruct the OXC device to add new links based on the determined number and identifiers. In some possible cases, the network control node can determine the data transmission capacity supported by the available link resources based on the data transmission bandwidth capacity supported by each of the one or more links included in the available link resources.

[0258] For example, the first message includes a target transmission bandwidth of 1.6 TB / s. Available link resources include available links 1 to 8. Specifically, available links 1 to 4 each support a data transmission capacity of 800 Gbps, and available links 5 to 8 support a data transmission capacity of 400 Gbps. In this scenario, the network control node can determine multiple links from available links 1 to 8 as new links based on the actual application needs. For example, the network control node can determine any two available links from 1 to 4 as new links. Similarly, the network control node can determine available links 5 to 8 as new links. Furthermore, the network control node can determine available links 1, 5, and 6 as new links, and so on.

[0259] ③ The network control node sends a fourth response to the first network device.

[0260] If no available link resources exist, the network control node generates and sends a fourth response to the first network device. This fourth response indicates that at least one link in the first link group should be used to forward the service flow. Upon receiving the fourth response, the first network device reacquires the service flow sent from node 1 to node 2, and if the link requirement corresponding to the first target transmission bandwidth required by this service flow is greater than the number of links in the first link group, and the first duration is greater than or equal to a set duration, it resends the message to the network control node. This message indicates the addition of at least one new link. The first duration refers to the time difference between the time when the first network device last sent the first message to the network control node and the current time.

[0261] S550, the first network device receives the first response and determines the second link group that the service flow will use.

[0262] The first response indicates that at least one link has been established (such as the first link). The second link group includes at least one existing link and at least one newly added link (such as the first link).

[0263] The first network device can determine the second link group in several ways. Examples of two possible methods are given below.

[0264] Example 1: After receiving the first response, the first network device can determine the second link group based on the first response.

[0265] For example, the first link group includes links 1 to n. At least one new link is added, including links i to j. A first response indicates that links i to j have been established. Based on the received first response, the first network device can determine a second link group including links 1 to n and links i to j.

[0266] Example 2: The first network device can detect the working status of the port and determine the second link group when the port is up.

[0267] For example, the first link group includes links 1 to n. The newly added link includes links i to j. The first network device can detect the working status of the ports corresponding to each link in links i to j. If the working status of the ports corresponding to each link in links i to j is up, the first network device determines a second link group including links 1 to n and links i to j.

[0268] S560, if the link requirement corresponding to the first target transmission bandwidth is less than or equal to the number of links provided by the first link group, the first network device sends a second message to the network control node.

[0269] The second message is used to request the network control node to disconnect at least one link (such as the second link). Please refer to the relevant content in S530 above for details on this part; it will not be repeated here.

[0270] S570, the network control node receives the second message and sends a third response to the first network device.

[0271] The third response is used to instruct the first network device to switch the service flow forwarded by the second link to other links.

[0272] After receiving the second message, before sending the third response to the first network device, to prevent the link adjustment strategy generated by the first network device from failing to accurately reflect the link requirements between the first and second nodes, the network control node can determine whether the disconnection conditions are met. The disconnection conditions include the network control node receiving a message (e.g., a fourth message) from the peer node (e.g., the second node) of the first node's service flow, indicating a reduction in the second link. For example, the network control node can determine whether it has received the second message and a fourth message from the second node's network device (e.g., the second network device) indicating the disconnection of at least one link (e.g., the second link). After receiving the second and fourth messages, the network control node instructs the link adjustment device to disconnect the second link and sends a second response to the first network device indicating that the second link has been disconnected. This process may include the following ① to ③.

[0273] ① The network control node determines whether it has received the fourth message.

[0274] The fourth message is sent when the second target transmission bandwidth meets the second condition. The second target transmission bandwidth is the target transmission bandwidth required between the second node and the first node, detected by the second network device. The second network device is a network device that receives service flows from each service node in the second node and sends the received service flows to the first node. Specifically, the second network device receives service flows sent by each service node in the second node and sends the service flows to the first network device, which then receives and sends the service flows to each service node in the first node. The second condition includes: the link requirement corresponding to the second target transmission bandwidth is less than or equal to the number of links provided by the first link group. The first link group includes at least one link provided by the link adjustment device for the second node to send service flows to the first node.

[0275] In some possible scenarios, the fourth message may be sent proactively by the second network device to the network control node when it detects that the second condition is met, or it may be sent by the second network device based on a bandwidth acquisition request sent by the network control node. The bandwidth acquisition request may be sent by the network control node to the second node after receiving the second message from the first node.

[0276] ②If the network control node receives the fourth message, it sends a third response to the first network device.

[0277] If the network control node receives the fourth message, it indicates that both nodes using the second link have a need to disconnect the second link. In this case, the network control node sends a third response to the first network device.

[0278] ③ If the network control node does not receive the fourth message, it will not send a response to the first network device indicating that the second link should be disconnected.

[0279] If the network control node detects that both the first node and the second node indicate that the second link needs to be disconnected, the network control node may execute the following steps S580 and S590 to disconnect the second link and send a second response to the first network device indicating that the second link has been disconnected. Upon receiving the second response, the first network device executes step S5100 to determine the third link group.

[0280] S580, the first network device receives the third response and sends a third message to the network control node based on the third response.

[0281] After receiving the third response, the first network device will switch the service flow forwarded by the second link to other links. Other links refer to links in the first link group other than the second link. The first network device can use various methods to switch the service flow forwarded by the second link to other links; examples of two possible methods are given below.

[0282] Example 1: The first network device (such as a switch) can use adaptive routing technology to update the quality of the port corresponding to the second link to the worst possible value, without causing the port to go down. The first network device then advertises the information of the port corresponding to the second link to other network devices (such as switches). Other network devices can then use flow table technology, etc., to avoid forwarding traffic through the second link. For more information on adaptive routing and flow table technologies, please refer to the general techniques section; they will not be elaborated upon here.

[0283] Example 2: The first network device can trigger Border Gateway Protocol (BGP) route convergence, but the port corresponding to the second link is not down. The network uses route advertisements and potentially consistent hashing techniques to remove the relevant paths for the port corresponding to the second link. For information on route advertisements and potentially consistent hashing, please refer to the general techniques section; they will not be elaborated upon here.

[0284] If the traffic flow forwarded by the second link is less than or equal to the first traffic threshold, the first network device sends a third message to the network control node. This third message indicates that the traffic flow forwarded by the second link is less than or equal to the first traffic threshold. The first traffic threshold can be set according to the needs of the actual application.

[0285] In some possible scenarios, if the traffic flow forwarded by the second link is less than or equal to the first traffic threshold, the network control node can also control the link adjustment device to release the second link, placing it in a released state. The released second link can then be used to transmit other traffic flows. These other traffic flows can refer to traffic flows sent from the first node to other nodes (such as a third node). Depending on whether the data center network uses OXC or OCS devices for traffic transmission, the process of using the second link to transmit other traffic flows differs, and will be described separately below.

[0286] (1) Data center networks use OXC or OCS devices to transmit service flows.

[0287] Taking the use of OXC equipment in a data center network to transmit service flows as an example, the process of using a second link to transmit other service flows is explained. The second link includes optical path 1 provided by the OXC equipment for forwarding service flows between the first and second nodes. In this scenario, the network control node controls the OXC equipment to disconnect optical path 1 to acquire communication resources. After receiving a message indicating the addition of a link between the first and third nodes, the network control node uses the communication resources acquired by disconnecting optical path 1 to establish optical path 2, and uses optical path 2 to establish link 2, which is used to enable the first node to send service flows to the third node.

[0288] (2) Data center networks do not use OXC or OCS devices to transmit service flows.

[0289] In this scenario, communication devices can use physical lines (such as twisted-pair cables) to transmit service flows between nodes. Specifically, after the network control node receives a message indicating the addition of a link between the first node and the third node, it can disconnect one end of the first link connected to the second node and connect that end to the third node to achieve service flow transmission between the first node and the third node. The above example of a first network device forwarding a service flow sent from the first node to the second node illustrates the network link adjustment method provided in this application. Depending on the needs of the actual application, the first network device can also use the method described above to forward service flows from multiple nodes (such as the first node, the third node, etc.) to the second node. Similarly, the first network device can also use the method described above to forward the service flow from the first node to multiple nodes (such as the second node, the fourth node, etc.). Furthermore, the first network device can also use the method described above to forward the service flow from multiple nodes (such as the first node, the third node, etc.) to multiple nodes (such as the second node, the fourth node, etc.).

[0290] Correspondingly, the network control node can execute S590.

[0291] S590, the network control node receives the third message and determines, based on the third message, to send a second response to the first network device.

[0292] The network control node receives a third message. Based on the third message, the network control node configures the link adjustment device to disconnect the second link and sends a second response to the first network device. The second response indicates that the second link has been disconnected.

[0293] In S5100, the first network device receives the second response and determines the third link group based on the other links.

[0294] After receiving a second response indicating that the second link has been disconnected, the first network device can identify the other links in the first link group besides the second link as links in the third link group.

[0295] The network link adjustment method provided in this application will be explained below with specific examples.

[0296] Node 1 in data center network 1 needs to send service flows to nodes 2 through 11. The number of links provided by data center network 1 for node 1 and nodes 2 through 11 are 2 to 11, respectively. Node 1 includes network devices 1 through n.

[0297] The target network device in Node 1 acquires the service flows sent from Node 1 to each of Nodes 2 through 11. The target network device can be all or some of the network devices in Node 1. These network devices can be network devices that meet certain set conditions, or they can be specific network devices. The following explanation uses Network Device 1 as the target network device. In this scenario, each network device in Node 1 can acquire the sub-service flows sent from Node 1 to each of Nodes 2 through 11. Additionally, Network Device 1 can count the sub-service flows that have the same destination node and acquire the service flows sent from Node 1 to that destination node.

[0298] For example, Node 1 sends a service flow to Node 2 using network device 1 and network device 2. In this case, network device 1 obtains service flow 11 sent from Node 1 to Node 2, and network device 2 obtains service flow 12 sent from Node 1 to Node 3. Network device 1 and network device 2 obtain service flow 1 sent from Node 1 to Node 2 based on service flow 11 and service flow 12. Similarly, network device 1 in Node 1 obtains service flows 2 to 10 sent from Node 1 to Node 3 to Node 11.

[0299] Network device 1 obtains the target transmission bandwidth required for the service flows sent by node 1 to each node, and obtains the link requirements corresponding to each target transmission bandwidth. For example, network device 1 obtains the target bandwidths 2 to 10 for service flows 2 to 10, and obtains the link requirements 2 to 10 corresponding to each target bandwidth. One service flow corresponds to one target bandwidth. One target bandwidth corresponds to one link requirement. For example, service flow 2 corresponds to target bandwidth 2, and target bandwidth 2 corresponds to link requirement 2.

[0300] Network device 1 obtains the links to be adjusted based on link requirements 2 to 10 and the number of links 2 to 10. Taking the example that the links provided by the link adjustment device have the same data transmission bandwidth capability, and the newly added links also have the same data transmission bandwidth capability, network device 1 compares link requirements 2 to 10 and the number of links 2 to 10 to determine the links to be adjusted. For example, network device 1 compares link requirements 2 and the number of links 2 to determine the link between node 1 and node 2 that needs to be adjusted.

[0301] Figure 13 This application provides an example diagram showing the correspondence between link requirements and link quantity, such as... Figure 13 As shown, network device 1 obtains the links to be adjusted based on the requirements of each link and the number of links provided. Specifically, network device 1 determines that one link needs to be added between node 1 and node 2, one link needs to be removed between node 1 and node 6, and one link needs to be removed between node 1 and node 10.

[0302] Node 1 sends service flows to Node 2 using the newly added link and existing links. Data center network 1 removes one link from its existing links (e.g., link 1 to link 3), and Node 1 uses links 2 and 3 (after removing link 1) to send service flows to Node 6. Data center network 1 also removes one link from its existing links (e.g., link 4 to link 8), and Node 1 uses links 5 to 8 (after removing link 4) to send service flows to Node 10.

[0303] In this embodiment, the first network device acquires the service flow between different nodes and the target transmission bandwidth required by the service flow. Based on the link requirements corresponding to the target transmission bandwidth and the number of links in the link groups between different nodes, it redetermines the link groups between the different nodes. The first network device, which forwards the service flow of the first node, directly acquires the service flow sent from the first node to the second node, ensuring the accuracy of the acquired service flow. Furthermore, the redetermined link groups not only match the target transmission bandwidth of the service flow, improving the accuracy of links between different service nodes, but also allow for the expansion or reduction of existing link groups between different nodes. When the link requirements of the service flow change, the links between different service nodes are adjusted in a timely manner, ensuring the timeliness of link adjustments between service nodes.

[0304] It is understood that, in order to achieve the functions in the above embodiments, the computing device includes hardware structures and / or software modules corresponding to the execution of each function. Those skilled in the art should readily recognize that, based on the units and method steps described in conjunction with the embodiments disclosed in this application, this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed in hardware or by computer software driving hardware depends on the specific application scenario and design constraints of the technical solution.

[0305] The above text combines Figures 5 to 13 The network link adjustment method provided according to the embodiments of this application is described in detail below. Figure 14 This application describes a network device provided according to an embodiment of the present application.

[0306] Figure 14 This is a schematic diagram of a network device provided in this application. The network device can be used to implement the function of the first network device in the above-described network link adjustment method embodiments, to forward the service flow sent by the first node to the second node, thus achieving the beneficial effects of the above-described method embodiments. In this embodiment, the network device can be as follows: Figure 16 The device shown.

[0307] like Figure 14As shown, network device 1400 includes: a link acquisition module 1410, a service flow acquisition module 1420, and a processing module 1430. The link acquisition module 1410 is used to: acquire a first link group between a first node and a second node. The first link group includes at least one link. The service flow acquisition module 1420 is used to: acquire the service flow sent from the first node to the second node and determine the target transmission bandwidth required by the service flow. The processing module 1430 is used to: send a first message to a network control node if the number of links provided by the first link group is less than the link requirement corresponding to the target transmission bandwidth. The first message is used to request the network control node to establish the first link between the first node and the second node. The processing module 1430 is also used to: in response to the first response from the network control node, determine a second link group that the service flow will use.

[0308] The first response is used to indicate that a first link has been established, and the second link group includes at least one link and the newly added first link.

[0309] In some possible scenarios, processing module 1430 is further configured to: send a second message to the network control node if the number of links provided by the first link group is greater than or equal to the link requirement corresponding to the target transmission bandwidth. The second message is used to request the network control node to disconnect the second link in the first link group. Processing module 1430 is further configured to: determine the third link group to be used by the service flow in response to a second response from the network control node. The second response is used to indicate that the second link has been disconnected, and the third link group includes all links in the first link group except the second link.

[0310] In some possible scenarios, the service flow acquisition module 1420 is specifically used to: acquire the initial service flow sent from the first node to the second node. The service flow acquisition module 1420 is also specifically used to: acquire a compensation value based on the initial service flow. The compensation value is used to indicate the difference obtained by measuring the service flow sent from the first node to the second node using a first frequency and a second frequency, or the compensation value is used to indicate the difference obtained by comparing the initial service flow with historical service flows. The service flow acquisition module 1420 is also specifically used to: compensate the initial service flow using the compensation value to obtain the service flow.

[0311] In some possible cases, the compensation value is the maximum traffic value of the service flow within a first number of cycles, measured using a second frequency.

[0312] In some possible scenarios, the first link group includes the second link. Processing module 1430 is specifically configured to: receive a third response sent by the network control node, and switch the service flow forwarded by the second link to other links based on the third response. The third response is sent by the network control node when a disconnection condition is met, including: the network control node receiving a message from a second network device requesting the disconnection of the second link, the second network device being configured on the second node. Processing module 1430 is also specifically configured to: send a third message to the network control node when the service flow forwarded by the second link is less than or equal to a first traffic threshold. The third message indicates that the service flow forwarded by the second link is less than or equal to the first traffic threshold. Processing module 1430 is also specifically configured to: receive a second response sent by the network control node, and determine a third link group based on other links.

[0313] In some possible scenarios, the second link is in a released state if the traffic flow forwarded by the second link is less than or equal to the first traffic threshold.

[0314] In some possible scenarios, the first message and / or the second message may include one or more of the following: link information, target transmission bandwidth, and the link information may include one or more of the following: information about the link to be established, information about the link to be reduced.

[0315] In some possible scenarios, the first node may also include a third network device. The service flow includes: service flows sent from the first node to the second node via the first network device, and / or, service flows sent from the first node to the second node via the third network device.

[0316] For more information on the functions of the link acquisition module 1410, the service flow acquisition module 1420, and the processing module 1430, please refer to the description of the network link adjustment method above; it will not be repeated here.

[0317] Figure 15 This is a schematic diagram of a network control node provided in this application. The network control node can be used to implement the functions of the network control node in the above-described network link adjustment method embodiments. In this embodiment, the network control node can be as follows: Figure 16 The device shown.

[0318] like Figure 15As shown, the network control node 1500 includes a transceiver module 1510 and a processing module 1520. The transceiver module 1510 is configured to: receive a first message from a first network device. The first message requests the establishment of a first link between the first node and a second node, the first link being determined based on the target transmission bandwidth required for the service flow transmitted between the first node and the second node. The processing module 1520 is configured to: in response to the first message, determine whether the number of available links provided by the link adjustment device is greater than or equal to the link requirement of the first link. The processing module 1520 is further configured to: if the number of available links provided by the link adjustment device is greater than or equal to the link requirement of the first link, instruct the link adjustment device to establish the first link. The transceiver module 1510 is further configured to: send a first response to the first network device, the first response indicating that the first link has been established.

[0319] In some possible scenarios, the transceiver module 1510 is further configured to: receive a second message from the first network device. The second message requests the disconnection of a second link between the first node and the second node, the second link being determined based on the target transmission bandwidth required for the service flow transmitted between the first node and the second node. The processing module 1520 is further configured to: determine, in response to the second message, whether the link adjustment device needs to disconnect the second link. The processing module 1520 is further configured to: if the second link needs to be disconnected, instruct the link adjustment device to disconnect the second link. The transceiver module 1510 is further configured to: send a second response to the first node indicating that the second link has been disconnected.

[0320] In some possible scenarios, the processing module 1520 is specifically used to: send a third response to the first network device in response to the second message.

[0321] The third response is sent when the disconnection conditions are met. These conditions include receiving a message from a second network device (located on the second node) requesting the disconnection of the second link. The third response instructs the first network device to switch the service flow forwarded by the second link to another link. The other links are links in the first link group other than the second link, and the first link group includes at least one link that forwards the service flow from the first node to the second node. The transceiver module 1510 is configured to receive the third message from the first network device. The third message indicates that the service flow forwarded by the second link is less than or equal to a first traffic threshold indicating support for disconnecting the link. The processing module 1520 is further configured to, in response to the third message, determine whether the link adjustment device has disconnected the second link.

[0322] For more information on the functions of the transceiver module 1510 and the processing module 1520, please refer to the description of the network link adjustment method above, which will not be repeated here.

[0323] The network device 1400 of this application embodiment can be implemented by software modules. The network device 1400 of this application embodiment can correspond to the function of the first network device in the network link adjustment method described in this application embodiment, and the above and other operations and / or functions of each module in the network device 1400 are respectively for implementing the flow of the network link adjustment method in the foregoing figures. For the sake of brevity, they will not be described in detail here.

[0324] Similarly, the network control node 1500 can be implemented through software modules. The network control node 1500 in this embodiment can correspond to the function of the network control node in the network link adjustment method described in this embodiment, and the above and other operations and / or functions of each module in the network control node 1500 are respectively for implementing the flow of the network link adjustment method in the foregoing figures. For simplicity, they will not be described in detail here.

[0325] It is worth noting that if the network device 1400 and the network control node 1500 are implemented through software modules, for example, these software modules can be provided to users through a cloud service subscription model, allowing users to choose different subscription tiers according to their needs. Alternatively, these software modules can also provide enterprise-level customized services with professional domain customization, interface personalization, and extended functions according to the needs of users or enterprises.

[0326] When the network device 1400 and the network control node 1500 are implemented in hardware, this hardware can be implemented using a processor or a chip. The chip includes interface circuitry and control circuitry. The interface circuitry is used to receive data from other devices besides the processor and transmit it to the control circuitry, or to send data from the control circuitry to other devices besides the processor.

[0327] The control circuit uses logic circuits or executed code instructions to implement any of the possible implementation methods in the above embodiments. The beneficial effects can be found in the descriptions of any aspect of the above embodiments, and will not be repeated here.

[0328] For example, network device 1400 and network control node 1500 can also be implemented through network devices, such as... Figure 16 As shown, Figure 16 This application provides a schematic diagram of a communication device 1600, which includes a communication interface 1610 and a processor 1620. It is understood that the communication interface 1610 can be a transceiver or an input / output (I / O) interface. Optionally, the communication device 1600 may further include a memory 1630 for storing instructions executed by the processor 1620, or storing input data required by the processor 1620 to execute instructions, or storing data generated after the processor 1620 executes instructions. The communication device 1600 may refer to the aforementioned...Figure 1 , Figure 3 and Figure 4 The network devices shown, etc.

[0329] When the communication device 1600 is used to implement the embodiments shown in the foregoing figures, the processor 1620, communication interface 1610, and memory 1630 can also collaboratively implement various operational steps in the network link adjustment method executed by each network device and network control node in the data center network. The communication device 1600 can also execute... Figure 14 The functions and execution of the network device 1400 shown are as follows. Figure 15 The functions of the network control node 1500 shown are not described in detail here.

[0330] The specific connection method between the communication interface 1610, processor 1620 and memory 1630 is not limited in the embodiments of this application.

[0331] The memory 1630 can be used to store software programs and modules, such as the program instructions / modules corresponding to the network link adjustment method provided in this application embodiment. The processor 1620 executes various functional applications and data processing by executing the software programs and modules stored in the memory 1630. The communication interface 1610 can be used to communicate with other devices for signaling or data. In this application, the communication device 1600 may have multiple communication interfaces 1610.

[0332] Communication interface 1610 can be used to receive service flows sent from the first node to the second node. Processor 1620 can be used to obtain the link requirements corresponding to the target transmission bandwidth required by the service flow, and adjust the links provided by the link adjustment device of the data center network according to the link requirements corresponding to the target transmission bandwidth and the number of links in the first link group, using the method described above.

[0333] It is understood that the processor 1620 in the embodiments of this application can be a CPU, or other general-purpose processors, digital signal processors (DSPs), ASICs, FPGAs, or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. A general-purpose processor can be a microprocessor or any conventional processor.

[0334] The method steps in the embodiments of this application can be implemented in hardware or by a processor executing software instructions. The software instructions can consist of corresponding software modules, which can be stored in random access memory (RAM), flash memory, read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), registers, hard disks, portable hard disks, CD-ROMs, or any other form of storage medium known in the art. An exemplary storage medium is coupled to a processor, enabling the processor to read information from and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and storage medium can reside in an ASIC. Additionally, the ASIC can reside in a network device or a terminal device. Alternatively, the processor and storage medium can exist as discrete components in the network device or terminal device.

[0335] This application also provides a computer program product containing instructions. The computer program product may be a software or program product containing instructions capable of running on a computing device or stored on any available medium. When the computer program product is run on at least one computing device, it causes the at least one computing device to perform a network link adjustment method.

[0336] This application also provides a computer-readable storage medium. The computer-readable storage medium can be any available medium that a computing device can store, or a data storage device such as a data center network that includes one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid-state drive). The computer-readable storage medium includes instructions that instruct a computing device to perform a network link adjustment method.

[0337] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this application, and these modifications or substitutions should all be covered within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A network link adjustment method, characterized in that, The method is applied to a first network device, which is located at a first node in a data center network. The data center network further includes a network control node, a link adjustment device, the first node, and a second node. The network control node manages the link adjustment device, and the link adjustment device adjusts the links of service flows in the data center network. The method includes: Obtain a first link group between the first node and the second node, wherein the first link group includes at least one link; Obtain the service flow sent from the first node to the second node, and determine the target transmission bandwidth required by the service flow; If the number of links provided by the first link group is less than the link requirement corresponding to the target transmission bandwidth, a first message is sent to the network control node; the first message is used to request the network control node to establish a first link between the first node and the second node. In response to a first response from the network control node, a second link group to be used by the service flow is determined; the first response indicates that the first link has been established, and the second link group includes the at least one link and the newly added first link.

2. The method according to claim 1, characterized in that, The method further includes: If the number of links provided by the first link group is greater than or equal to the link requirement corresponding to the target transmission bandwidth, a second message is sent to the network control node; the second message is used to request the network control node to disconnect the second link in the first link group. In response to a second response from the network control node, a third link group to be used by the service flow is determined; the second response indicates that the second link has been disconnected, and the third link group includes other links in the first link group besides the second link.

3. The method according to claim 1 or 2, characterized in that, The step of obtaining the service flow sent from the first node to the second node includes: Obtain the initial service flow sent from the first node to the second node; Based on the initial service flow, a compensation value is obtained; the compensation value is used to indicate the difference obtained by measuring the service flow sent from the first node to the second node using a first frequency and a second frequency, or the compensation value is used to indicate the difference obtained by comparing the historical service flow with the initial service flow; The initial service flow is compensated using the compensation value to obtain the service flow.

4. The method according to claim 3, characterized in that, The compensation value is the maximum traffic value of the service flow within a first number of cycles, measured using the second frequency.

5. The method according to any one of claims 2-4, characterized in that, The first link group includes the second link. The second response to the network control node, determining the third link group to be used by the service flow, includes: The network control node receives a third response from the network control node and switches the service flow forwarded by the second link to the other link according to the third response. The third response is sent by the network control node when a disconnection condition is met. The disconnection condition includes: the network control node receives a message from a second network device requesting to disconnect the second link. The second network device is set on the second node. If the traffic flow forwarded by the second link is less than or equal to the first traffic threshold, a third message is sent to the network control node; the third message indicates that the traffic flow forwarded by the second link is less than or equal to the first traffic threshold. The system receives the second response sent by the network control node and determines the third link group based on the other links.

6. The method according to claim 5, characterized in that, If the traffic flow forwarded by the second link is less than or equal to the first traffic threshold, the second link is in a released state.

7. The method according to any one of claims 1-6, characterized in that, The first message and / or the second message includes one or more of the following: link information, the target transmission bandwidth, and the link information includes one or more of the following: information on the links to be established, and information on the links to be reduced.

8. The method according to any one of claims 1-7, characterized in that, The first node also includes a third network device. The service flow includes: the service flow sent by the first node to the second node via the first network device, and / or the service flow sent by the first node to the second node via the third network device.

9. A network link adjustment method, characterized in that, The method is applied to a network control node in a data center network, which further includes a link adjustment device, a first node, and a second node. The first node includes a first network device. The network control node manages the link adjustment device, which adjusts the links of service flows in the data center network. The method includes: Receive a first message from the first network device; the first message is used to request the establishment of a first link between the first node and the second node, wherein the first link is a link outside the first link group between the first node and the second node; In response to the first message, determine whether the number of available links provided by the link adjustment device is greater than or equal to the link demand of the first link; If so, a link establishment indication message is sent to the link adjustment device; the link establishment indication message is used to indicate the establishment of the first link; The link adjustment device receives a link establishment indication response and sends a first response to the first network device; the link establishment indication response is used to indicate that the link adjustment device has established the first link, and the first response is used to indicate that the first link has been established.

10. The method according to claim 9, characterized in that, The method further includes: The system receives a second message from the first network device; the second message is used to request the disconnection of the second link between the first node and the second node, wherein the second link is a link in the first link group between the first node and the second node. In response to the second message, determine whether the link adjustment device needs to disconnect the second link; If so, the link adjustment device is instructed to disconnect the second link, and the second response is sent to the first node to indicate that the second link has been disconnected.

11. The method according to claim 10, characterized in that, The step of responding to the second message and determining whether the link adjustment device needs to disconnect the second link includes: In response to the second message, a third response is sent to the first network device; The third response is sent when a disconnection condition is met, which includes: receiving a message from a second network device requesting the disconnection of the second link, the second network device being located on the second node; the third response instructs the first network device to switch the service flow forwarded by the second link to another link; the other link is a link in a first link group other than the second link, the first link group including at least one link that forwards the service flow of the first node to the second node; Receive a third message from the first network device; the third message indicates that the service flow forwarded by the second link is less than or equal to a first traffic threshold used to indicate support for disconnecting the link. In response to the third message, determine whether the link adjustment device disconnects the second link.

12. A network link adjustment method, characterized in that, The method is applied to a data center network, which includes a first network device, a network control node, a link adjustment device, a first node, and a second node. The first network device is disposed on the first node. The network control node manages the link adjustment device, and the link adjustment device adjusts the links of service flows in the data center network. The method includes: The first network device acquires a first link group between the first node and the second node, the first link group including at least one link; The first network device acquires the service flow sent from the first node to the second node and determines the target transmission bandwidth required by the service flow; If the number of links provided by the first link group is less than the link requirement corresponding to the target transmission bandwidth, the first network device sends a first message to the network control node; the first message is used to request the network control node to establish a first link between the first node and the second node, and the first link is a link other than the links included in the first link group; The network control node receives the first message and, in response to the first message, determines whether the number of available links provided by the link adjustment device is greater than or equal to the link demand of the first link. If so, the network control node sends a link establishment indication message to the link adjustment device; the link establishment indication message is used to indicate the establishment of the first link; The network control node receives a link establishment indication response sent by the link adjustment device and sends a first response to the first network device; the link establishment indication response is used to indicate that the link adjustment device has established the first link, and the first response is used to indicate that the first link has been established; In response to the first response from the network control node, the first network device determines a second link group to be used by the service flow; the second link group includes the at least one link and the newly added first link.

13. The method according to claim 12, characterized in that, The method further includes: If the number of links provided by the first link group is greater than or equal to the link requirement corresponding to the target transmission bandwidth, the first network device sends a second message to the network control node; the second message is used to request the network control node to disconnect the second link in the first link group. The network control node receives the second message and sends a second response to the first network device; the second response indicates that the second link has been disconnected. The first network device responds to the second response by determining a third link group to be used by the service flow; the third link group includes the other links in the first link group other than the second link.

14. A communication system, characterized in that, The communication system includes a network control node, a link adjustment device, a first node, and a second node. The first node includes a first network device. The network control node manages the link adjustment device, which adjusts the links of service flows in the data center network. The first network device is configured to: acquire a first link group between the first node and the second node, wherein the first link group includes at least one link; The first network device is configured to: acquire the service flow sent by the first node to the second node, and determine the target transmission bandwidth required by the service flow; When the number of links provided by the first link group is less than the link requirement corresponding to the target transmission bandwidth, the first network device is configured to: send a first message to the network control node; the first message is configured to request the network control node to establish a first link between the first node and the second node; The first network device is configured to: in response to a first response from the network control node, determine a second link group that the service flow will use; The first response indicates that the first link has been established, and the second link group includes the at least one link and the newly added first link.

15. A network device, characterized in that, The network device includes: The link acquisition module is used to: acquire a first link group between the first node and the second node, wherein the first link group includes at least one link; The service flow acquisition module is used to: acquire the service flow sent from the first node to the second node, and determine the target transmission bandwidth required by the service flow; The processing module is configured to: send a first message to the network control node when the number of links provided by the first link group is less than the link requirement corresponding to the target transmission bandwidth; the first message is configured to request the network control node to: establish a first link between the first node and the second node; The processing module is further configured to: in response to a first response from the network control node, determine a second link group to be used by the service flow; the first response is used to indicate that the first link has been established, and the second link group includes the at least one link and the newly added first link.

16. A network control node, characterized in that, The network control node includes: The transceiver module is configured to: receive a first message from the first network device; the first message is used to request the establishment of a first link between the first node and the second node, wherein the first link is a link outside the first link group between the first node and the second node; The processing module is configured to: in response to the first message, determine whether the number of available links provided by the link adjustment device is greater than or equal to the link demand of the first link; The processing module is further configured to: if so, send a link establishment indication message to the link adjustment device; the link establishment indication message is used to indicate the establishment of the first link; The transceiver module is further configured to: receive a link establishment indication response sent by the link adjustment device; The processing module is further configured to: send a first response to the first network device; the link establishment indication response is used to indicate that the link adjustment device has established the first link, and the first response is used to indicate that the first link has been established.

17. A communication device, characterized in that, The system includes a memory and a processor, wherein: the memory is used to store program code; the processor is used to call the program code to implement the method of any one of claims 1-8, or the processor is used to call the program code to implement the method of any one of claims 9-11.

18. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes computer instructions; when the computer instructions are executed in a computing device, the computing device performs the method of any one of claims 1-8, or the computing device performs the method of any one of claims 9-11.

19. A computer program product, characterized in that, When the computer program product is run in a computing device, the computing device performs the method of any one of claims 1-8, or the computing device performs the method of any one of claims 9-11.

Images