Method, device, equipment and medium for selecting a cloud platform

Abstract

The present application discloses a method, apparatus, device and medium for selecting a cloud platform, which belongs to the field of communications. The method includes: obtaining business information, the business information includes access device information and path requirement information; obtaining a recommendation result of the cloud platform based on the business information, the recommendation result is used to indicate the cloud platform corresponding to each access device in the first device set, the first device set includes a first access device, the first access device corresponds to the first cloud platform, the path requirement evaluation information of the path from the first access device to the first cloud platform meets the path requirement information, the first device set includes M access devices or some of the M access devices, the cloud platform corresponding to each access device belongs to a candidate cloud platform set, and the candidate cloud platform set includes P cloud platforms; the recommendation result is displayed in the first interface. The present application can improve the efficiency of selecting a cloud platform and reduce labor costs.

Description

Technical Field

[0001] The present application relates to the field of communications, and in particular to a method, apparatus, device, and medium for selecting a cloud platform. Background Art

[0002] A cloud platform can provide computing and / or storage services, and customer premises equipment (CPE) can be connected to a cloud platform to use the services provided by the cloud platform.

[0003] Currently, when a CPE needs to be connected to a cloud platform, users can manually select a cloud system for the CPE from a variety of cloud platforms and then connect the terminal device to the cloud system. However, manual cloud platform selection is not only inefficient but also labor-intensive. Summary of the Invention

[0004] This application provides a method, apparatus, device, and medium for selecting a cloud platform. This application obtains a recommendation result for a cloud platform based on business information. Because the recommendation result is used to indicate the cloud platform corresponding to each access device in a first device set, and the path requirement assessment information of the path between each access device and its corresponding cloud platform satisfies the path requirement information, the cloud platform corresponding to each access device indicated by the recommendation result can be directly selected for each access device, thereby improving the efficiency of cloud platform selection and reducing labor costs. The technical solution is as follows:

[0005] In a first aspect, the present application provides a method for selecting a cloud platform, in which business information is obtained, the business information including access device information and path requirement information, the access device information including device identifiers of M access devices, the path requirement information including bandwidth information, and M being an integer greater than 0. A recommendation result for a cloud platform is obtained based on the business information, the recommendation result being used to indicate the cloud platform corresponding to each access device in a first device set, the first device set including a first access device, the first access device corresponding to a first cloud platform, the path requirement assessment information of the path from the first access device to the first cloud platform meeting the path requirement information, the first device set including the M access devices or some of the M access devices, the cloud platform corresponding to each access device belonging to a candidate cloud platform set, the candidate cloud platform set including P cloud platforms, and P being an integer greater than 0. The recommendation result is displayed on the first interface.

[0006] Because a cloud platform recommendation result is obtained based on the business information, the recommendation result is used to indicate the cloud platform corresponding to each access device in the first device set, thereby automatically recommending a cloud platform for each access device in the first device set and displaying the recommendation result on the first interface. For any access device in the first device set, that is, for the first access device, since the path requirement assessment information of the path from the first access device to the first cloud platform meets the path requirement information, when the recommendation result is displayed on the first interface, the cloud platform corresponding to the first access device indicated by the recommendation result can be directly selected for the first access device, allowing the first access device to access the cloud platform corresponding to the first access device indicated by the recommendation result. This improves the efficiency of platform selection and reduces labor costs.

[0007] In one possible implementation, a network topology is displayed on a first interface. The nodes in the network topology include M access devices and P cloud platforms. The network topology includes at least one delay circle corresponding to a root node. The root node is a node in the network topology. The at least one delay circle corresponds one-to-one with at least one delay threshold. The at least one delay circle includes a first delay circle. The minimum delay from each node in the first delay circle to the root node is less than or equal to the first delay threshold. The minimum delay from each node outside the first delay circle to the root node is greater than the first delay threshold. The first delay threshold is the delay threshold corresponding to the first delay circle. This allows for intuitive graphical display, allowing users to intuitively perceive latency.

[0008] In another possible implementation, in the network topology, the path from the first access device to the first cloud platform is displayed in a specified display mode, thereby facilitating the user to identify the path from the network topology.

[0009] In another possible implementation, the specified display mode includes a highlight display mode, a bold display mode, and / or a mode of displaying the path using a color corresponding to the path.

[0010] In another possible implementation, N paths are calculated based on the service information, where N is greater than 0 and less than or equal to M. Each path corresponds to a different access device. The N paths include a first path whose path requirement assessment information satisfies the path requirement information. The first path is a path from an access device in the first device set to a virtual node, where the virtual node is a parent node of the P cloud platforms. Based on the N paths, a cloud platform corresponding to each access device in the first device set is selected to obtain a recommendation result.

[0011] Among them, since a virtual node is created in the network topology, and the virtual node is the parent node of each cloud platform, the virtual node is used as the destination node for each access device, so that the corresponding path can be calculated for each access device in the first device set. In addition, based on N paths, a cloud platform is selected for the access devices in the first device set. In this way, based on the N paths, the required information of each access device in the first access device is comprehensively considered, and cloud platforms can be selected for more access devices to ensure that as many access devices as possible can access the cloud platform. For example, among the M access devices, there may be a part of the access devices that require a large amount of bandwidth resources. Since the bandwidth resources in the network are limited, when selecting a cloud platform based on the N paths, the cloud platform can be preferentially selected for other access devices except for this part of the access devices to ensure that the cloud platform is selected for as many access devices as possible.

[0012] In another possible implementation, the first path corresponds to the first access device. The first path is calculated based on the device identifier of the first access device, the path requirement information, and a network topology. Nodes in the network topology include virtual nodes, M access devices, and P cloud platforms. This ensures that the calculated path requirement assessment information for the first path satisfies the path requirement information.

[0013] In another possible implementation, the network topology further includes link information of a link between two adjacent nodes in the network, where the link information includes available bandwidth of the link.

[0014] In another possible implementation, the link information further includes a delay and / or a routing weight of the link, where the routing weight is used to indicate a routing cost of the link.

[0015] In another possible implementation, the first path is the shortest path from the first access device to the virtual node.

[0016] In another possible implementation, an overloaded link set is obtained based on the path demand information and the N paths. The overloaded link set includes at least one overloaded link, all or some of the links traversed by the N paths, and the load of the overloaded links exceeds the available bandwidth of the overloaded links. A first path set is obtained based on the overloaded link set. The first path set includes some or all of the N paths, and the load of the links traversed by the paths in the first path set does not exceed the available bandwidth of the links. The cloud platform traversed by the second path is selected as the cloud platform corresponding to the second access device. The second path is a path included in the first path set, and the second access device is the access device corresponding to the second path.

[0017] Since the first path set is obtained based on the overloaded link set, it is ensured that the load of the link passed by the path in the first path set does not exceed its own available bandwidth. Based on the first path set, a cloud platform is selected for the access devices in the first device set, which ensures that the resources occupied by each access device in the first device set does not exceed the overall resources of the network, so that each access device can successfully access its corresponding cloud platform.

[0018] In another possible implementation, based on the path demand information and the N paths, loads of multiple links are obtained, where the multiple links include links through which the N paths pass. The multiple links include a first link, where the load of the first link is equal to the sum of the path bandwidths required by access devices corresponding to at least one path, and the at least one path passes through the first link. Thus, an overloaded link set can be obtained based on the loads of the multiple links.

[0019] In another possible implementation, a second path set is obtained based on an overloaded link set, where each path in the second path set passes through one or more overloaded links in the overloaded link set. A third path that meets specified conditions is selected from the second path set. The load of a target link is reduced based on the path bandwidth required by an access device corresponding to the third path, where the target link is an overloaded link that the third path passes through. A fourth path is migrated from the second path set to the first path set, where the load of each overloaded link that the fourth path passes through does not exceed its respective available bandwidth.

[0020] Since the path bandwidth required by the access device corresponding to the third path reduces the load of the target link, the overloaded link passed by the fourth path in the second path set becomes a non-overloaded link, and the fourth path is migrated from the second path set to the first path set. In this way, when a cloud platform is selected for the access devices in the first device set based on the first path set, it is ensured that the resources occupied by each access device in the first device set will not exceed the overall resources of the network, so that each access device can successfully access its corresponding cloud platform.

[0021] In another possible implementation, the specified conditions satisfied by the third path include one or more of the following: the overload degree of the third path is the largest, the third path includes the largest number of links, and the path bandwidth required by the access device corresponding to the third path is the smallest, where the overload degree of the third path is used to indicate the number of overloaded links passed by the third path.

[0022] In another possible implementation, the third path is migrated from the second path set to the third path set.

[0023] In another possible implementation, the first path set further includes paths in the N paths except for the second path set.

[0024] In another possible implementation, based on the path bandwidth required by the second access device, the available bandwidth of the link through which the second path passes is reduced. This ensures that when cloud platforms are selected for the X access devices corresponding to the X paths in the third path set, the resources occupied by the X access devices do not exceed the overall network resources, allowing each access device to successfully access its corresponding cloud platform.

[0025] In another possible implementation, Y paths are calculated based on the device identifiers of X access devices and the path requirement information. The X access devices include the access device corresponding to each path in the third path set, where X is an integer greater than 0 and Y is greater than 0 and less than or equal to X. Based on the Y paths, corresponding cloud platforms are selected for the access devices in the second device set, where the second device set includes the access device corresponding to each of the Y paths. This allows cloud platforms to be selected for a greater number of access devices.

[0026] In a second aspect, the present application provides a method for displaying information, wherein a first interface is displayed, the first interface being used to input business information, the business information including access device information and path requirement information, the access device information including device identifiers of M access devices, the path requirement information including bandwidth information, where M is an integer greater than 0. Based on the business information, path information of access devices in a first device set is displayed in the first interface, the path information including device information of the access device, platform information of a cloud platform corresponding to the access device, and path requirement assessment information of a path from the access device to the cloud platform, the path requirement assessment information satisfying the path requirement information, and the first device set including M terminal devices or some of the M terminal devices.

[0027] Because the path information of the access devices in the first device set is displayed on the first interface based on the business information, and the path information includes the device information of the access device, the platform information of the cloud platform corresponding to the access device, and the path requirement assessment information of the path from the access device to the cloud platform, a cloud platform can be automatically recommended for each access device in the first device set. For any access device in the first device set, since the path requirement assessment information of the path from the access device to the cloud platform meets the path requirement information, the cloud platform corresponding to the access device displayed on the first interface can be directly selected for the access device, allowing the access device to access the cloud platform. This improves the efficiency of platform selection and reduces labor costs.

[0028] In a third aspect, the present application provides a device for selecting a cloud platform, the device comprising: a processing unit and a display unit. The processing unit is used to obtain business information, the business information including access device information and path requirement information, the access device information including device identifications of M access devices, the path requirement information including bandwidth information, and M being an integer greater than 0. The processing unit is also used to obtain a recommendation result for the cloud platform based on the business information, the recommendation result being used to indicate the cloud platform corresponding to each access device in the first device set, the first device set including a first access device, the first access device corresponding to the first cloud platform, the path requirement evaluation information of the path from the first access device to the first cloud platform meeting the path requirement information, the first device set including the M access devices or some of the M access devices, the cloud platform corresponding to each access device belongs to a candidate cloud platform set, the candidate cloud platform set including P cloud platforms, and P being an integer greater than 0. The display unit is used to display the recommendation result in the first interface.

[0029] Because the processing unit obtains a cloud platform recommendation result based on the business information, the recommendation result is used to indicate the cloud platform corresponding to each access device in the first device set, so that the processing unit can automatically recommend a cloud platform for each access device in the first device set, and the display unit displays the recommendation result on the first interface. For any access device in the first device set, that is, for the first access device, because the path requirement assessment information of the path from the first access device to the first cloud platform meets the path requirement information, when the display unit displays the recommendation result on the first interface, the cloud platform corresponding to the first access device indicated by the recommendation result can be directly selected for the first access device, so that the first access device can access the cloud platform corresponding to the first access device indicated by the recommendation result. This improves the efficiency of platform selection and reduces labor costs.

[0030] In one possible implementation, the display unit is further used to display a network topology in a first interface, where the nodes in the network topology include M access devices and P cloud platforms, and the network topology includes at least one delay circle corresponding to a root node. The root node is a node in the network topology, and the at least one delay circle corresponds one-to-one with at least one delay threshold. The at least one delay circle includes a first delay circle, where the minimum delay from each node in the first delay circle to the root node is less than or equal to the first delay threshold, and the minimum delay from each node outside the first delay circle to the root node is greater than the first delay threshold. The first delay threshold is the delay threshold corresponding to the first delay circle. In this way, an intuitive graphical display can be achieved, and the user can intuitively perceive the delay.

[0031] In another possible implementation, the display unit is further configured to display, in the network topology, a path from the first access device to the first cloud platform in a specified display manner.

[0032] In another possible implementation, the specified display mode includes a highlight display mode, a bold display mode, and / or a mode of displaying the path using a color corresponding to the path.

[0033] In another possible implementation, the processing unit is used to calculate N paths based on the business information, where N is greater than 0 and less than or equal to M, each path corresponds to a different access device, the N paths include a first path, the path requirement assessment information of the first path satisfies the path requirement information, the first path is a path from an access device in the first device set to a virtual node, and the virtual node is the parent node of the P cloud platforms; based on the N paths, the cloud platform corresponding to each access device in the first device set is selected to obtain a recommendation result.

[0034] Among them, since a virtual node is created in the network topology, and the virtual node is the parent node of each cloud platform, the virtual node is used as the destination node for each access device, so that the corresponding path can be calculated for each access device in the first device set. In addition, based on N paths, a cloud platform is selected for the access devices in the first device set. In this way, based on the N paths, the required information of each access device in the first access device is comprehensively considered, and cloud platforms can be selected for more access devices to ensure that as many access devices as possible can access the cloud platform. For example, among the M access devices, there may be a part of the access devices that require a large amount of bandwidth resources. Since the bandwidth resources in the network are limited, when selecting a cloud platform based on the N paths, the cloud platform can be preferentially selected for other access devices except for this part of the access devices to ensure that the cloud platform is selected for as many access devices as possible.

[0035] In another possible implementation, the first path corresponds to a first access device, and the processing unit is configured to calculate the first path based on a device identifier of the first access device, the path requirement information, and a network topology, where nodes in the network topology include virtual nodes, M access devices, and P cloud platforms. This ensures that the calculated path requirement assessment information of the first path satisfies the path requirement information.

[0036] In another possible implementation, the network topology further includes link information of a link between two adjacent nodes in the network, where the link information includes available bandwidth of the link.

[0037] In another possible implementation, the link information further includes a delay and / or a routing weight of the link, where the routing weight is used to indicate a routing cost of the link.

[0038] In another possible implementation, the first path is the shortest path from the first access device to the virtual node.

[0039] In another possible implementation, the processing unit is configured to obtain an overloaded link set based on the path demand information and the N paths, the overloaded link set including at least one overloaded link, including all or some of the links traversed by the N paths, with the load of the overloaded links exceeding the available bandwidth of the overloaded links. A first path set is obtained based on the overloaded link set, the first path set including some or all of the N paths, with the load of the links traversed by the paths in the first path set not exceeding the available bandwidth of the links. The cloud platform traversed by the second path is selected as the cloud platform corresponding to the second access device, the second path being a path included in the first path set, and the second access device being the access device corresponding to the second path.

[0040] Since the first path set is obtained based on the overloaded link set, it is ensured that the load of the link passed by the path in the first path set does not exceed its own available bandwidth. Based on the first path set, a cloud platform is selected for the access devices in the first device set, which ensures that the resources occupied by each access device in the first device set does not exceed the overall resources of the network, so that each access device can successfully access its corresponding cloud platform.

[0041] In another possible implementation, a processing unit is configured to obtain loads of multiple links based on the path demand information and N paths, where the multiple links include links through which the N paths pass, and the multiple links include a first link, where the load of the first link is equal to the sum of the path bandwidths required by access devices corresponding to at least one path, and at least one path passes through the first link; thereby, an overloaded link set can be obtained based on the loads of the multiple links.

[0042] In another possible implementation, the processing unit is configured to obtain a second path set based on the overloaded link set, where each path in the second path set passes through one or more overloaded links in the overloaded link set; select a third path that meets specified conditions from the second path set; reduce the load of a target link based on the path bandwidth required by an access device corresponding to the third path, where the target link is the overloaded link passed by the third path; and migrate a fourth path from the second path set to the first path set, where the load of each overloaded link passed by the fourth path does not exceed its respective available bandwidth.

[0043] Since the path bandwidth required by the access device corresponding to the third path reduces the load of the target link, the overloaded link passed by the fourth path in the second path set becomes a non-overloaded link, and the fourth path is migrated from the second path set to the first path set. In this way, when a cloud platform is selected for the access devices in the first device set based on the first path set, it is ensured that the resources occupied by each access device in the first device set will not exceed the overall resources of the network, so that each access device can successfully access its corresponding cloud platform.

[0044] In another possible implementation, the specified conditions satisfied by the third path include one or more of the following: the overload degree of the third path is the largest, the third path includes the largest number of links, and the path bandwidth required by the access device corresponding to the third path is the smallest, where the overload degree of the third path is used to indicate the number of overloaded links passed by the third path.

[0045] In another possible implementation manner, the processing unit is further configured to migrate the third path from the second path set to the third path set.

[0046] In another possible implementation, the first path set further includes paths in the N paths except for the second path set.

[0047] In another possible implementation, the processing unit is further configured to reduce the available bandwidth of the link through which the second path passes, based on the path bandwidth required by the second access device. This ensures that, when selecting a cloud platform for X access devices corresponding to X paths in the third path set, the resources occupied by the X access devices do not exceed the overall network resources, enabling each access device to successfully access its corresponding cloud platform.

[0048] In another possible implementation, the processing unit is further configured to calculate Y paths based on device identifiers and path requirement information of X access devices, where the X access devices include an access device corresponding to each path in the third path set, X is an integer greater than 0, and Y is greater than 0 and less than or equal to X; and select corresponding cloud platforms for access devices in a second device set based on the Y paths, where the second device set includes an access device corresponding to each path in the Y paths. This allows cloud platforms to be selected for a greater number of access devices.

[0049] In a fourth aspect, the present application provides a device for selecting a cloud platform, the device comprising a processor and a computer program, the processor being used to execute the computer program in the memory so that the device completes the method in the first aspect, the second aspect or any possible implementation of the first aspect.

[0050] In a fifth aspect, the present application provides a computer program product, which includes a computer program, and the computer program is loaded through a computer to implement the method of the above-mentioned first aspect, second aspect or any possible implementation method of the first aspect.

[0051] In a sixth aspect, the present application provides a computer-readable storage medium for storing a computer program, which is loaded by a processor to execute the method of the above-mentioned first aspect, second aspect or any possible implementation of the first aspect.

[0052] In the seventh aspect, the present application provides a chip comprising a memory and a processor, wherein the memory is used to store computer instructions, and the processor is used to call and run the computer instructions from the memory to execute the method of the above-mentioned first aspect, second aspect or any possible implementation of the first aspect.

[0053] In an eighth aspect, the present application provides a system for selecting a cloud platform, the system comprising: an information acquisition module, a result acquisition module, and a display module. The information acquisition module is used to acquire business information, the business information including access device information and path requirement information, the access device information including device identifications of M access devices, the path requirement information including bandwidth information, and M being an integer greater than 0. The result acquisition module is used to acquire a recommendation result of the cloud platform based on the business information, the recommendation result being used to indicate the cloud platform corresponding to each access device in the first device set, the first device set including the first access device, the first access device corresponding to the first cloud platform, the path requirement evaluation information of the path from the first access device to the first cloud platform meeting the path requirement information, the first device set including the M access devices or some of the M access devices, the cloud platform corresponding to each access device belongs to the candidate cloud platform set, the candidate cloud platform set including P cloud platforms, and P being an integer greater than 0. The display module is used to display the recommendation result in the first interface.

[0054] Because the result acquisition module obtains a cloud platform recommendation result based on the business information, the recommendation result is used to indicate the cloud platform corresponding to each access device in the first device set, thereby automatically recommending a cloud platform for each access device in the first device set and displaying the recommendation result on the first interface. For any access device in the first device set, that is, for the first access device, because the path requirement assessment information of the path from the first access device to the first cloud platform meets the path requirement information, when the display module displays the recommendation result on the first interface, the user can directly select the cloud platform corresponding to the first access device indicated by the recommendation result for the first access device, so that the first access device can access the cloud platform corresponding to the first access device indicated by the recommendation result. This improves the efficiency of platform selection and reduces labor costs.

[0055] In one possible implementation, the display module is also used to display the network topology in the first interface, where the nodes in the network topology include M access devices and P cloud platforms, and the network topology includes at least one delay circle corresponding to the root node. The root node is a node in the network topology, and at least one delay circle corresponds one-to-one to at least one delay threshold. At least one delay circle includes a first delay circle, and the minimum delay from each node in the first delay circle to the root node is less than or equal to the first delay threshold. The minimum delay from each node outside the first delay circle to the root node is greater than the first delay threshold. The first delay threshold is the delay threshold corresponding to the first delay circle.

[0056] In another possible implementation, the display module is further configured to display the path from the first access device to the first cloud platform in the network topology in a specified display mode, thereby facilitating the user to identify the path from the network topology.

[0057] In another possible implementation, the specified display mode includes a highlight display mode, a bold display mode, and / or a mode of displaying the path using a color corresponding to the path.

[0058] In another possible implementation, the result acquisition module is configured to calculate N paths based on the service information, where N is greater than 0 and less than or equal to M, each path corresponding to a different access device, and the N paths including a first path, wherein the path requirement assessment information of the first path satisfies the path requirement information, and the first path is a path from an access device in the first device set to a virtual node, where the virtual node is a parent node of P cloud platforms. Based on the N paths, a cloud platform corresponding to each access device in the first device set is selected to obtain a recommendation result.

[0059] Among them, since a virtual node is created in the network topology, and the virtual node is the parent node of each cloud platform, the virtual node is used as the destination node for each access device, so that the corresponding path can be calculated for each access device in the first device set. In addition, based on N paths, a cloud platform is selected for the access devices in the first device set. In this way, based on the N paths, the required information of each access device in the first access device is comprehensively considered, and cloud platforms can be selected for more access devices to ensure that as many access devices as possible can access the cloud platform. For example, among the M access devices, there may be a part of the access devices that require a large amount of bandwidth resources. Since the bandwidth resources in the network are limited, when selecting a cloud platform based on the N paths, the cloud platform can be preferentially selected for other access devices except for this part of the access devices to ensure that the cloud platform is selected for as many access devices as possible.

[0060] In another possible implementation, the first path corresponds to a first access device, and the result acquisition module is configured to calculate the first path based on a device identifier of the first access device, the path requirement information, and a network topology, where nodes in the network topology include virtual nodes, M access devices, and P cloud platforms. This ensures that the calculated path requirement assessment information for the first path satisfies the path requirement information.

[0061] In another possible implementation, the network topology further includes link information of a link between two adjacent nodes in the network, where the link information includes available bandwidth of the link.

[0062] In another possible implementation, the link information further includes a delay and / or a routing weight of the link, where the routing weight is used to indicate a routing cost of the link.

[0063] In another possible implementation, the first path is the shortest path from the first access device to the virtual node.

[0064] In another possible implementation, the result acquisition module is configured to acquire an overloaded link set based on the path demand information and the N paths, the overloaded link set including at least one overloaded link, including all or some of the links traversed by the N paths, the overloaded links having a load exceeding the available bandwidth of the overloaded links. A first path set is acquired based on the overloaded link set, the first path set including some or all of the N paths, the load of the links traversed by the paths in the first path set not exceeding their own available bandwidth. The cloud platform traversed by the second path is selected as the cloud platform corresponding to the second access device, the second path being the path included in the first path set, and the second access device being the access device corresponding to the second path. Since the first path set is acquired based on the overloaded link set, this ensures that the load of the links traversed by the paths in the first path set does not exceed their own available bandwidth. Selecting a cloud platform for the access devices in the first device set based on the first path set ensures that the resources occupied by each access device in the first device set do not exceed the overall network resources, enabling each access device to successfully access its corresponding cloud platform.

[0065] In another possible implementation, the result acquisition module is configured to acquire loads of multiple links based on the path demand information and the N paths, the multiple links including links through which the N paths pass, the multiple links including a first link, the load of the first link being equal to the sum of path bandwidths required by access devices corresponding to at least one path, and the at least one path passing through the first link. An overloaded link set is acquired based on the loads of the multiple links.

[0066] In another possible implementation, the result acquisition module is used to obtain a second path set based on the overloaded link set, where each path in the second path set passes through one or more overloaded links in the overloaded link set. A third path that meets specified conditions is selected from the second path set. The load of the target link is reduced based on the path bandwidth required by the access device corresponding to the third path, where the target link is the overloaded link passed by the third path. The fourth path is migrated from the second path set to the first path set, where the load of each overloaded link passed by the fourth path does not exceed the respective available bandwidth. Since the load of the target link is reduced based on the path bandwidth required by the access device corresponding to the third path, the overloaded link passed by the fourth path in the second path set becomes a non-overloaded link, and the fourth path is migrated from the second path set to the first path set. In this way, when a cloud platform is selected for the access devices in the first device set based on the first path set, it is ensured that the resources occupied by each access device in the first device set do not exceed the overall resources of the network, so that each access device can successfully access its corresponding cloud platform.

[0067] In another possible implementation, the specified conditions satisfied by the third path include one or more of the following: the overload degree of the third path is the largest, the third path includes the largest number of links, and the path bandwidth required by the access device corresponding to the third path is the smallest, where the overload degree of the third path is used to indicate the number of overloaded links passed by the third path.

[0068] In another possible implementation, the system further includes: a path migration module, configured to migrate the third path from the second path set to the third path set.

[0069] In another possible implementation, the first path set further includes paths in the N paths except for the second path set.

[0070] In another possible implementation, the system further includes a bandwidth reduction module configured to reduce the available bandwidth of the link traversed by the second path based on the path bandwidth required by the second access device. This ensures that when selecting a cloud platform for the X access devices corresponding to the X paths in the third path set, the resources occupied by the X access devices do not exceed the overall network resources, enabling each access device to successfully access its corresponding cloud platform.

[0071] In another possible implementation, the result acquisition module is further configured to calculate Y paths based on the device identifiers of X access devices and the path requirement information, where the X access devices include an access device corresponding to each path in the third path set, X is an integer greater than 0, and Y is greater than 0 and less than or equal to X. Based on the Y paths, a corresponding cloud platform is selected for the access devices in the second device set, where the second device set includes an access device corresponding to each of the Y paths. This allows cloud platforms to be selected for a greater number of access devices. BRIEF DESCRIPTION OF THE DRAWINGS

[0072] Figure 1 This is a schematic diagram of a network architecture provided by an embodiment of the present application;

[0073] Figure 2 This is a schematic diagram of another network architecture provided by an embodiment of the present application;

[0074] Figure 3 This is a schematic diagram of a network topology provided in an embodiment of the present application;

[0075] Figure 4 This is a flow chart of a method for selecting a cloud platform provided in an embodiment of the present application;

[0076] Figure 5 This is a schematic diagram of the first interface provided in an embodiment of the present application;

[0077] Figure 6 This is a flowchart of selecting a cloud platform corresponding to each access device in a first device set provided by an embodiment of the present application;

[0078] Figure 7 This is another schematic diagram of the first interface provided in an embodiment of the present application;

[0079] Figure 8 This is a schematic diagram of the structure of a device for selecting a cloud platform provided in an embodiment of the present application;

[0080] Figure 9 This is a schematic diagram of a system structure for selecting a cloud platform provided in an embodiment of the present application;

[0081] Figure 10 This is a schematic diagram of the device structure for selecting a cloud platform provided in an embodiment of the present application. DETAILED DESCRIPTION

[0082] The embodiments of the present application will be described in further detail below with reference to the accompanying drawings.

[0083] See also Figure 1 , an embodiment of the present application provides a network architecture 100, including:

[0084] Multiple cloud platforms 1 and multiple access devices 2, access device 2 serves as a customer terminal device CPE, and users can access one or more cloud platforms among the multiple cloud platforms 1 through access device 2 and use the services provided by the above cloud platforms. Each cloud platform 1 and each access device 2 are connected to network 3.

[0085] For any access device 2, a path between the access device 2 and the cloud platform 1 can be established in the network 3, so that the access device 2 can access the cloud platform 1 through the path.

[0086] For example, see Figure 1 The multiple access devices 2 include access devices 21, 22, 23, and 24, and the multiple cloud platforms include cloud platforms 11, 12, and 13. The access devices 21, 22, 23, and 24, and the cloud platforms 11, 12, and 13 are all connected to the network 3.

[0087] Taking access device 21 as an example, a path is established between access device 21 and a cloud platform in network 3. Assuming the cloud platform is cloud platform 11, access device 21 accesses cloud platform 11 through this path. Also taking access device 22 as an example, a path is established between access device 22 and a cloud platform in network 3. Assuming the cloud platform is cloud platform 12, access device 22 accesses cloud platform 12 through this path. Other access devices are not listed here.

[0088] See also Figure 2 , network 3 includes multiple forwarding nodes, and the path between the access device 2 and the cloud platform 1 often passes through one or more forwarding nodes in network 3.

[0089] For example, see Figure 2 , taking the path between the access device 21 and the cloud platform 11 as an example, the path passes through forwarding nodes 30, 34 and 38. For another example, see Figure 2 , taking the path between the access device 22 and the cloud platform 12 as an example, the path passes through forwarding nodes 31 , 35 and 39 .

[0090] In some embodiments, the plurality of forwarding nodes include one or more of routers, switches, base stations, and the like.

[0091] See also Figure 1 The network architecture 100 also includes a network management device 4, which is connected to the network 3.

[0092] In some embodiments, the network management device 4 communicates with the multiple cloud platforms 1 through the network 3, and / or communicates with the multiple access devices 2 through the network 3.

[0093] In some embodiments, the network management device 4 is used to manage the multiple cloud platforms 1 , the multiple access devices 2 and / or forwarding nodes in the network 3 .

[0094] For the above network architecture 100, the network management device 4 also includes the network topology of the network architecture 100, see Figure 3 , the nodes in the network topology include the multiple cloud platforms 1 and the multiple access devices 2. For example, Figure 3 Nodes 11, 12, and 13 in the are cloud platforms 11, 12, and 13, respectively. Figure 3 The nodes 21, 22, 23 and 24 in FIG are access devices 21, 22, 23 and 24 respectively.

[0095] The nodes in the network topology also include the various forwarding nodes in the network 3. For example, Figure 3 The nodes 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 301 and 302 in the network 3 are forwarding nodes 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 301 and 302 in the network 3 respectively.

[0096] See also Figure 3 The network management device 4 also establishes a virtual node 0 in the network topology. The virtual node 0 is the parent node of each cloud platform 1.

[0097] For a link between any two adjacent nodes in the network topology, the network topology further includes link information of the link, and the link information at least includes the available bandwidth of the link.

[0098] In some embodiments, the link information of the link further includes information such as the link delay and / or routing weight, etc. The routing weight is used to indicate the routing cost of the link.

[0099] In some embodiments, the routing weight is determined based on the link bandwidth of the link. The larger the link bandwidth of the link, the smaller the routing weight, indicating that the routing cost of the link is smaller. The smaller the link bandwidth of the link, the larger the routing weight, indicating that the routing cost of the link is greater.

[0100] The larger the link bandwidth, the shorter the latency required to transmit data over the link, resulting in a lower routing cost for the link. Conversely, the smaller the link bandwidth, the longer the latency required to transmit data over the link, resulting in a higher routing cost for the link.

[0101] The available bandwidth of the link is less than or equal to the link bandwidth of the link.

[0102] In some embodiments, the access device 2 is a CPE such as a switch, router, firewall or gateway device. The network management device 4 is used to perform device management and policy control on the access device 2. It can be a controller, a network management system or a network management platform. It can be deployed on a server or a terminal device, or on a public cloud platform. Alternatively, the network management device 4 is a device cluster including multiple devices, which are servers or terminal devices, etc.

[0103] In some embodiments, when network management device 4 is a server or terminal device, network management device 4 includes one or more processors. When network management device 4 is a device cluster including multiple devices, each device includes one or more processors, so network management device 4 includes multiple processors. In summary, in both cases, network management device 4 includes one or more processors.

[0104] In some embodiments, when the network management device 4 includes multiple processors, the multiple processors include a master processor and at least one slave processor, and the master processor is used to manage the at least one slave processor.

[0105] See also Figure 4 , the embodiment of the present application provides a method 400 for selecting a cloud platform, the method 400 is applied to Figure 1 or Figure 2 In the network architecture 100 shown, the execution subject of the method 400 may be a network management device of the network architecture 100, including:

[0106] Step 401: Acquire service information, which includes access device information and path requirement information. The access device information includes device identifiers of M access devices, and the path requirement information includes bandwidth information, where M is an integer greater than 0.

[0107] In some embodiments, service information is entered by users into a network service subscription platform based on their service needs, or by network service providers into a service management system based on a service purchase agreement signed with the user. For example, a user purchases network services so that terminal devices on the user's network, such as personal computers or servers, can access cloud services, such as enterprise employee management services, on cloud platform B provided by the cloud service provider through CPE A on the user's network. Furthermore, the data transmission path from the user's CPEA to cloud platform B must meet certain path requirements, such as a bandwidth of 100 Mbps and a path latency of less than 100 ms. In some embodiments, this path requirement information also includes latency information.

[0108] The path requirement information includes requirement information of each access device in the M access devices. For the requirement information of any access device, the requirement information includes the path bandwidth required by the access device, or the requirement information includes the path bandwidth and delay required by the access device.

[0109] Among them, with respect to the bandwidth information and / or delay information included in the path requirement information, the bandwidth information includes the path bandwidth required by each access device, and the delay information includes the delay required by each access device.

[0110] If the path bandwidth required by each access device is the same, the bandwidth information includes a path bandwidth; or if the path bandwidth required by each access device is different, the bandwidth information includes the path bandwidth required by each access device. If the delay required by each access device is the same, the delay information includes a delay; or if the delay required by each access device is different, the delay information includes the delay required by each access device.

[0111] In some embodiments, the network management device displays a first interface, so that the user enters the access device information and the path requirement information in the first interface, and then the network management device obtains the access device information and the path requirement information from the first interface.

[0112] The first interface includes at least one first input element and at least one second input element. A user inputs the access device information into the at least one first input element and inputs the path requirement information into the at least one second input element. The first interface also includes a button. When the network management device receives a command triggered by a user clicking the button, the network management device obtains the access device information from the at least one first input element and obtains the path requirement information from the at least one second input element.

[0113] The ways in which a user inputs information into the input elements of the first interface include one or more of the following: the user can use the keyboard to input information into the input elements of the first interface, the user can paste information copied and / or cut by the user into the input elements of the first interface, and the user can input information into the input elements of the first interface by voice.

[0114] The first input element and the second input element are both input boxes. The first interface includes M first input boxes and at least one second input box. The M first input boxes are used to input the device identifications of M access devices, and the at least one second input box is used to input the path requirement information.

[0115] For example, see Figure 5The first interface shown in the figure includes four first input boxes and two second input boxes. The user enters the device identifiers of four access devices into the four first input boxes, namely CPE1, CPE2, CPE3 and CPE4, or the first input box contains the device information of the user's access device, such as the access device identifiers CPE1 and CPE2. The user can click or check the device information of the access device as the input of the first input box, enter the delay information (10ms) into one of the second input boxes, and enter the bandwidth information (100M) into the other second input box. CPE1, CPE2, CPE3 and CPE4 are respectively Figure 2 The device identification of access device 21, the device identification of access device 22, the device identification of access device 23 and the device identification of access device 24 in the network architecture 100 shown. Figure 5 The first interface shown also includes a "recommendation button". When the network management device receives a command triggered by the user clicking the "recommendation button", it obtains the device identifiers of the four access devices from the four first input boxes and obtains the path requirement information from the two second input elements.

[0116] The device identification of the access device includes one or more of the following information: the address of the access device, the name of the access device, the serial number of the access device, etc.

[0117] In some embodiments, the network management device further obtains platform information of P cloud platforms, where P is an integer greater than 0. The P cloud platforms are candidate cloud platforms, and the network management device can select a cloud platform for the M access devices from the candidate cloud platform set, where the candidate cloud platform set includes the P candidate cloud platforms.

[0118] In some embodiments, the first interface further includes at least one third input element, into which the user inputs platform information of the P cloud platforms. When the network management device receives a command triggered by the user clicking the button, the network management device obtains the platform information of the P cloud platforms from the at least one third input element.

[0119] The third input element is the input box. For example, see Figure 5The first interface shown includes three third input boxes, and the user inputs the platform information of the three cloud platforms into the three third input boxes, such as the name of the cloud platform, cloud platform 11; or, the third input box has built-in platform information of the candidate cloud platforms that can be selected, such as the icon of the cloud platform, and the user can click or check the icon of the cloud platform or the platform information of the cloud platform as input for the third input box. When the network management device receives the command triggered by the user clicking the "recommendation button", the network management device obtains the platform information of the three cloud platforms from the three third input boxes. The platform information of the three cloud platforms includes the platform identifiers of the three cloud platforms, and the platform identifiers of the three cloud platforms are Cloud1, Cloud2 and Cloud3. Cloud1, Cloud2 and Cloud3 are respectively Figure 2 The device identifiers of the cloud platform 11, the cloud platform 12, and the cloud platform 13 in the network architecture 100 are shown.

[0120] The platform information of the cloud platform includes information such as the platform identification, remaining capacity and / or cost of the cloud platform.

[0121] Step 402: Calculate N paths based on the service information, where N is greater than 0 and less than or equal to M.

[0122] The service information includes access device information and path requirement information. That is, in step 402, N paths are calculated based on the access device information and the path requirement information.

[0123] Each of the N paths corresponds to a different access device. Since N is less than or equal to M, the N access devices corresponding to the N paths are the M access devices, or some of the M access devices.

[0124] The N paths include a first path, the path requirement evaluation information of the first path meets the path requirement information, the first path is a path from an access device in the first device set to the virtual node, and the first device set includes the M access devices or some of the M access devices.

[0125] For ease of explanation, the access device corresponding to the first path is referred to as the first access device. That is, the first path is the path from the first access device to the virtual node, and the first path passes through a cloud platform. In some embodiments, the cloud platform passed through by the first path is one of the P candidate cloud platforms, or the cloud platform passed through by the first path is a cloud platform in the network.

[0126] The path demand assessment information of the first path includes the bandwidth of the first path, and may also include information such as the delay of the first path.

[0127] For example, the path demand assessment information for a first path includes the bandwidth of the first path, and the path demand information includes the path bandwidth required by the first access device. If the bandwidth of the first path is greater than or equal to the path bandwidth required by the first access device, the path demand assessment information for the first path satisfies the path demand information. For another example, the path demand assessment information for a first path includes the bandwidth and delay of the first path, and the path demand information includes the path bandwidth and delay required by the first access device. If the bandwidth of the first path is greater than or equal to the path bandwidth required by the first access device and the delay of the first path is less than or equal to the delay required by the first access device, the path demand assessment information for the first path satisfies the path demand information.

[0128] The network management device includes a network topology of the network. For a first path, the first path is calculated based on a device identifier of the first access device, the path requirement information, and the network topology.

[0129] In some embodiments, based on the device identification of the first access device, the demand information of the first access device and the network topology, it is calculated whether there is a path whose path demand assessment information meets the demand information of the first access device. If such a path exists, the path is used as the first path corresponding to the first access device. If such a path does not exist, the calculation of the path for the first access device is stopped.

[0130] In some embodiments, the first path is the shortest path from the first access device to the virtual node.

[0131] In some embodiments, the so-called shortest path means that in the path from the first access device to the virtual node, the sum of the routing weights corresponding to the first path is the smallest, and the sum of the routing weights of the first path is equal to the cumulative value of the routing weights of each link passed by the first path.

[0132] For the other M-1 access devices, similar to the first access device, the path corresponding to each of the other access devices is calculated.

[0133] For example, for the device identifier CPE1 of the access device 21, based on the device identifier CPE1 of the access device 21, the demand information of the access device 21 and the Figure 3 The network topology shown calculates path 1 from the access device 21 to the cloud platform 11. The links passed by path 1 include link <21,30> between the access device 21 and the forwarding node 30, link <30,34> between the forwarding node 30 and the forwarding node 34, link <34,38> between the forwarding node 34 and the forwarding node 38, and link <38,11> between the forwarding node 38 and the cloud platform 11.

[0134] For the device identifier CPE2 of the access device 22, based on the device identifier CPE2 of the access device 22, the demand information of the access device 22 and the Figure 3 The network topology shown calculates path 2 from the access device 22 to the cloud platform 12. The links passed by path 2 include link <22,31> between the access device 22 and the forwarding node 31, link <31,35> between the forwarding node 31 and the forwarding node 35, link <35,39> between the forwarding node 35 and the forwarding node 39, and link <39,12> between the forwarding node 39 and the cloud platform 12.

[0135] For the device identifier CPE3 of the access device 23, based on the device identifier CPE3 of the access device 23, the demand information of the access device 23 and the Figure 3 The network topology shown calculates the path 3 from the access device 23 to the cloud platform 12. The links passed by the path 3 include the link <23, 32> between the access device 23 and the forwarding node 32, the link <32, 36> between the forwarding node 32 and the forwarding node 36, the link <36, 35> between the forwarding node 36 and the forwarding node 35, the link <35, 39> between the forwarding node 35 and the forwarding node 39, and the link <39, 12> between the forwarding node 39 and the cloud platform 12.

[0136] For the device identifier CPE4 of the access device 24, based on the device identifier CPE4 of the access device 24, the demand information of the access device 24 and the Figure 3 The network topology shown calculates path 4 from the access device 24 to the cloud platform 13. The links passed by path 4 include link <24,33> between the access device 24 and the forwarding node 33, link <33,37> between the forwarding node 33 and the forwarding node 37, link <37,302> between the forwarding node 37 and the forwarding node 302, and link <302,13> between the forwarding node 302 and the cloud platform 13.

[0137] In some embodiments, the network management device includes multiple processors. Assume that the network management device includes Q processors, where Q is an integer greater than 1, one of the processors is a master processor, and the other Q-1 processors are slave processors.

[0138] The main processor of the network management device divides the M access devices into Q device sets, each of which corresponds to the Q processors. For each processor and its corresponding device set, the processor calculates paths for the access devices in that device set. The main processor obtains the paths calculated by each slave processor, resulting in a total of N paths. This parallel path calculation by the Q processors improves path calculation efficiency.

[0139] It should be noted that when each processor calculates a path, it does not update the link information of each link in the network topology, that is, it does not update the available bandwidth, delay, and / or routing weight of each link.

[0140] Step 403: Based on the N paths, a cloud platform corresponding to each access device in the first device set is selected to obtain a recommendation result.

[0141] The first device set includes the M access devices or some of the M access devices. The recommendation result is used to indicate the cloud platform corresponding to each access device in the first device set.

[0142] In some embodiments, the recommendation result includes path information of each access device in the first device set. For the path information of any access device in the first device set, the path information includes device information of the access device, platform information of the cloud platform corresponding to the access device, and path requirement assessment information of the path from the access device to the cloud platform.

[0143] In step 403, see Figure 6 , the cloud platform corresponding to each access device in the first device set can be selected through the following operations 4031 to 4036. The operations 4031-4036 are respectively:

[0144] 4031: Based on the path demand information and the N paths, an overloaded link set is obtained. The overloaded link set includes at least one overloaded link. The overloaded link set includes all or part of the links passed by the N paths. The load of the overloaded link exceeds the available bandwidth of the overloaded link.

[0145] In 4031, the overload link set is obtained through the following operations (1) and (2). The operations (1) and (2) are respectively:

[0146] (1): Based on the path demand information and the N paths, loads of multiple links are obtained, where the multiple links include links through which the N paths pass, and the multiple links include a first link, where the load of the first link is equal to the sum of path bandwidths required by access devices corresponding to at least one path, and the at least one path is a path passing through the first link.

[0147] In operation (1), for each of the N paths, the links that each path passes through are determined, resulting in multiple links. That is, the multiple links include the links that the N paths pass through. For any link in the multiple links, for ease of explanation, this link is referred to as the first link. At least one path that passes through the first link is determined. For each of the at least one path, the path bandwidth required by the access device corresponding to each path is obtained from the path demand information. The obtained path bandwidths are accumulated to obtain the load of the first link. The load of each link in the multiple links is obtained in the same manner as the load of the first link described above.

[0148] For example, the N paths include the aforementioned acquired paths 1, 2, 3, and 4. The path requirement information includes that the required path bandwidths for access devices 21, 22, 23, and 24 are all "100M." It is determined that the links traversed by path 1 include link <21, 30>, link <30, 34>, link <34, 38>, and link <38, 11>. It is determined that the links traversed by path 2 include link <22, 31>, link <31, 35>, link <35, 39>, and link <39, 12>. It is determined that the links traversed by path 3 include link <23, 32>, link <32, 36>, link <36, 35>, link <35, 39>, and link <39, 12>. It is determined that the links traversed by path 4 include link <24, 33>, link <33, 37>, link <37, 302>, and link <302, 13>.

[0149] For link <21,30>, the path passing through link <21,30> includes path 1. Therefore, the load of link <21,30> is equal to the path bandwidth (100M) required by access device 21 corresponding to path 1. For link <35,39>, the path passing through link <35,39> includes path 2 and path 3. Therefore, the load of link <35,39> is equal to the sum of the path bandwidth (100) required by access device 22 corresponding to path 2 and the path bandwidth (100M) required by access device 23 corresponding to path 3. In other words, the load of link <35,39> is equal to "200M".

[0150] The loads of other links are obtained in the same manner as above. For example, the loads of link <30,34>, link <34,38>, link <38,11>, link <22,31>, link <31,35>, link <23,32>, link <32,36>, link <36,35>, link <24,33>, link <33,37>, link <37,302>, and link <302,13> are all "100M", and the load of link <39,12> is "200M".

[0151] (2): Obtain an overloaded link set based on the loads of the multiple links.

[0152] In operation (2), the available bandwidth of each link is obtained from the network topology of the network. Based on the available bandwidth and load of each link, a link whose load exceeds its available bandwidth is selected from the multiple links as an overloaded link, thereby obtaining an overloaded link set.

[0153] For example, if the load of link <35,39> (200M) exceeds its available bandwidth (150M), link <35,39> is considered an overloaded link. Also, if the load of link <39,12> (200M) exceeds its available bandwidth (160M), link <39,12> is considered an overloaded link. Therefore, the overloaded link set includes overloaded link <35,39> and overloaded link <39,12>.

[0154] Next, a first path set is obtained based on the overloaded link set. The first path set includes some or all of the N paths, and the load of the links traversed by the paths in the first path set does not exceed the available bandwidth of the links. In implementation, the first path set can be obtained through the following operations 4032 to 4036.

[0155] 4032: Acquire a second path set based on the overloaded link set, where each path in the second path set passes through one or more overloaded links in the overloaded link set.

[0156] In step 4032, an overloaded link is selected from the overloaded link set, one or more paths passing through the overloaded link are selected from the N paths, and the one or more paths are added to the second path set. The above steps are repeated until all paths in the N paths that include the overloaded link are added to the second path set.

[0157] For the other paths in the N paths except the second path set, the link passed by each other path is not an overloaded link, so each other path is added to the first path set.

[0158] For example, the overloaded link set includes overloaded link <35,39> and overloaded link <39,12>. Path 2 and path 3 pass through these two overloaded links, so the second path set includes path 2 and path 3, and the first path set includes path 1 and path 4 except path 2 and path 3.

[0159] 4033: Select a third path that meets a specified condition from the second path set, and migrate the third path from the second path set to the third path set.

[0160] The specified conditions satisfied by the third path include one or more of the following: the third path has the largest overload degree, the third path includes the largest number of links, and the access device corresponding to the third path requires the smallest path bandwidth, where the overload degree of the third path is used to indicate the number of overloaded links passed by the third path.

[0161] The following is an example of an implementation of selecting the third path. Of course, there are other implementations of selecting the third path, which will not be detailed here. This implementation example is:

[0162] For any path in the second path set, count the number of overloaded links it passes through. Based on this number of overloaded links, calculate the overload degree of the path. The overload degree of each path in the second path set is calculated in the same manner as described above. Select the path with the highest overload degree from the second path set. If only one path is selected, use that selected path as the third path.

[0163] If multiple paths are selected, the number of links in each of the multiple paths is counted, and the path with the largest number of links is selected from the multiple paths. If there is only one path with the largest number of links, the path with the largest number of links is used as the third path.

[0164] If there are multiple paths with the largest number of links, the path bandwidth required by the access device corresponding to each link in the multiple links is obtained from the path demand information, the access device with the smallest required path bandwidth is selected, and the path corresponding to the selected access device is used as the third path.

[0165] In some embodiments, for the above operation of obtaining the overload degree of the path, the number of overloaded links is used as the overload degree of the path, or the product of the number of overloaded links and a specified coefficient is used as the overload degree of the path.

[0166] For example, for paths 2 and 3 in the second path set, both include two overloaded links, so the overload degree of both paths 2 and 3 is 2. The paths with the highest overload degree selected from the second path set include paths 2 and 3. However, path 2 includes 4 links, and path 3 includes 5 links. From these two paths, path 3, with the largest number of links, is selected as the third path. Path 3 is moved from the second path set to the third path set, and the remaining paths in the second path set include path 2.

[0167] 4034: Reduce the load of a target link based on the path bandwidth required by the access device corresponding to the third path, where the target link is an overloaded link through which the third path passes.

[0168] In step 4034, each overloaded link along the third path is determined to obtain a target link. The path bandwidth required by the access device corresponding to the third path is subtracted from the target link's load. If the reduced target link load is less than or equal to the target link's available bandwidth, the target link is changed from an overloaded link to a non-overloaded link and removed from the overloaded link set. If the reduced target link load is greater than the target link's available bandwidth, the target link remains in the overloaded link set.

[0169] When the target link is changed to a non-overloaded link, a path passing through the target link is obtained from the second path set, and the overload degree of the path is reduced based on the number of target links. The reduced overload degree of the path may be 0, meaning that the load on each overloaded link passed by the path does not exceed the available bandwidth of each link, thereby ensuring that the load on each link passed by the path does not exceed the available bandwidth of each link. Alternatively, the reduced overload degree of the path may still be greater than 0, meaning that the path still passes through an overloaded link whose load exceeds its available bandwidth.

[0170] For example, the third link is path 3, and the overloaded links traversed by path 3 are link <35,39> and link <39,12>. The required path bandwidth of access device 23 corresponding to path 3 is 100 Mbps. Based on this path bandwidth of 100 Mbps, the loads of link <35,39> and link <39,12> are reduced. After the reductions, the loads of link <35,39> and link <39,12> are both 100 Mbps. After the reductions, the loads of link <35,39> and link <39,12> are both less than their respective available bandwidths, and link <35,39> and link <39,12> become non-overloaded links.

[0171] 4035: Migrate the fourth path from the second path set to the first path set. If the load of each overloaded link traversed by the fourth path does not exceed the available bandwidth of each link, and if there are still paths in the second path set, return to 4033.

[0172] The fourth path is a path in the second path set where the overload degree becomes 0.

[0173] For example, the second path set includes path 2. Therefore, the loads of link <35, 39> and link <39, 12>, which path 2 passes through, do not exceed their respective available bandwidths. Therefore, path 2 is migrated from the second path set to the first path set. The first path set includes path 1, path 2, and path 4.

[0174] 4036: When no path exists in the second path set, the cloud platform through which the second path passes is selected as the cloud platform corresponding to the second access device, the second path is the path included in the first path set, and the second access device is the access device corresponding to the second path.

[0175] The access devices included in the first device set are access devices corresponding to each path in the first path set. In this way, a corresponding cloud platform is selected for each access device in the first device set based on the first path set.

[0176] For example, the first device set includes access device 21 corresponding to path 1, access device 22 corresponding to path 2, and access device 24 corresponding to path 4 in the first path set. Cloud platform 11, which is passed by path 1, is selected as the cloud platform corresponding to access device 21, cloud platform 12, which is passed by path 2, is selected as the cloud platform corresponding to access device 22, and cloud platform 13, which is passed by path 4, is selected as the cloud platform corresponding to access device 24.

[0177] In step 4036, the recommendation result includes path information for each path in the first path set. For each path in the first path set, the path information includes device information of the access device corresponding to the path, platform information of the cloud platform through which the path passes, and path demand assessment information for the path.

[0178] In step 4036, after selecting a corresponding cloud platform for the second access device, the available bandwidth of the link through which the second path passes is reduced based on the path bandwidth required by the second access device. That is, for the link through which the second path passes, the available bandwidth of the link stored in the network topology is reduced based on the path bandwidth required by the second access device.

[0179] It should be noted that the third path set also includes paths, where X represents the number of paths included in the third path set, and X is an integer greater than 0. For the X access devices corresponding to the X paths, it is also necessary to select a cloud platform for the X access devices through the following steps 501 and 502.

[0180] Step 501: Y paths are calculated based on the device identifiers of the X access devices and the path requirement information, where Y is greater than 0 and less than or equal to X.

[0181] The detailed implementation process of calculating the Y paths in step 501 can be found in the relevant content of calculating the N paths in step 402 above, which will not be described in detail here.

[0182] Step 502: Based on the Y paths, select a corresponding cloud platform for the access device in the second device set, where the second device set includes an access device corresponding to each of the Y paths.

[0183] In step 502, the following method may be used: Figure 6 The process of steps 4031-4036 shown in the figure selects a corresponding cloud platform for the access device in the second device set. During implementation, the N paths in step 4031 are replaced with the Y paths, and then the process of steps 4031-4036 is performed.

[0184] After executing steps 4031-4036, a third path set may or may not be obtained. If the third path set is not obtained, the operation is terminated. When the third path set is obtained, the third path set includes Z paths, where Z is an integer greater than 0. Assume that W represents the number of paths included in the most recently obtained third path set. When WZ exceeds a specified threshold, for the Z access devices corresponding to the Z paths, steps 501 and 502 need to be repeated to select a cloud platform for the Z access devices. If WZ does not exceed the specified threshold, the operation is terminated. The initial value of W is equal to X.

[0185] In some embodiments, the specified threshold is equal to the product of M and the specified ratio. For example, assuming the specified ratio is 0.05, the specified threshold is equal to 0.05*M, where * represents a multiplication operation.

[0186] Step 404: Display the recommendation results on the first interface.

[0187] In some embodiments, the recommendation results can be presented through text descriptions in the first interface, that is, the device information of each access device in the first device set, the device information of the cloud plane corresponding to each access device, and the path demand assessment information of the path corresponding to each access device are displayed in the first interface.

[0188] For example, see Figure 5The first interface shown displays the device information (CPE1) of the access device 21, the device information (Cloud1) of the cloud platform 11 corresponding to the access device 21, and the path demand assessment information (including a delay of 7ms) of the path 1 corresponding to the access device 21; displays the device information (CPE2) of the access device 22, the device information (Cloud2) of the cloud platform 12 corresponding to the access device 22, and the path demand assessment information (including a delay of 7ms) of the path 2 corresponding to the access device 22; displays the device information (CPE4) of the access device 24, the device information (Cloud3) of the cloud platform 13 corresponding to the access device 24, and the path demand assessment information (including a delay of 8ms) of the path 4 corresponding to the access device 24. Among them, in the first interface, the bandwidth displayed in the path demand assessment information of path 1, the path demand assessment information of path 2, and the path demand assessment information of path 4 is satisfied, indicating that the bandwidth of path 1 satisfies the path bandwidth required by the access device 21 corresponding to path 1, the bandwidth of path 2 satisfies the path bandwidth required by the access device 22 corresponding to path 2, and the bandwidth of path 4 satisfies the path bandwidth required by the access device 24 corresponding to path 4.

[0189] In some embodiments, the recommendation results can be presented in the first interface in combination with visual graphics, that is, the network topology is also displayed in the first interface, and the network topology includes at least one delay circle corresponding to the root node, and the root node is a node in the network topology. The at least one delay circle corresponds one-to-one with at least one delay threshold. The at least one delay circle includes a first delay circle, and the minimum delay from each node in the first delay circle to the root node is less than or equal to the first delay threshold. The minimum delay from each node outside the first delay circle to the root node is greater than the first delay threshold. The first delay threshold is the delay threshold corresponding to the first delay circle.

[0190] The root node is a node selected by the user in the network topology displayed in the first interface. The user may click on a node in the network topology, or the user may input a device identifier of a node in the network topology into the first interface.

[0191] In some embodiments, the operation of drawing the first delay circle in the network topology is: when a click operation on the node is detected, the node is obtained as the root node, or the device identifier of the node is received, and the node corresponding to the device identifier is used as the root node. Based on the root node, the i-th layer nodes connected to the root node are traversed, i = 1, 2, 3... For any i-th layer node, if the minimum delay from the i-th layer node to the root node is less than or equal to the first delay threshold, and the minimum delay from the i+1th layer node connected to the i-th layer node to the root node is greater than the first delay threshold, the i-th layer node is used as a boundary node of the first delay circle. In the above manner, each boundary node of the first delay circle is obtained, and the first delay circle connecting each boundary node is drawn in the network topology.

[0192] For example, see Figure 5 The first interface shown is an example of how recommendation results may be presented. Other examples exist, which are not listed here. The first interface displays a network topology, and the user selects cloud platform 11. Accordingly, cloud platform 11 is selected as the root node, and delay circles corresponding to the delay thresholds of "3ms" and "10ms" are drawn in the network topology.

[0193] from Figure 5 The first interface shown allows users to intuitively see which access devices are located within the delay circle corresponding to the cloud platform 11. For example, for the access device 21 corresponding to the device identifier "CPE1", it can be intuitively seen from the first interface that the access device 21 is located within the delay circle corresponding to the delay threshold "3ms" of the cloud platform 11. Through the first interface, users can intuitively see that the path delay from CPE1 to the cloud platform 11 is less than 10ms, which meets the user's experience requirements for the path; for the access device 22 corresponding to the device identifier "CPE2", it can be intuitively seen from the first interface that the access device 22 is located within the delay circle corresponding to the delay threshold "10ms" of the cloud platform 11. Through the first interface, users can intuitively see that the path delay from CPE2 to the cloud platform 11 is less than 10ms, which meets the user's experience requirements for the path. The path delay is equal to 10ms, which meets the user's experience requirement of a path delay less than or equal to 10ms; for the access device 23 corresponding to the device identifier "CPE3" and the device 24 corresponding to the device identifier "CPE4", it can be intuitively seen from the first interface that the access device 23 and the access device 24 are located outside the delay circle corresponding to the delay threshold "10ms" of the cloud platform 11. Through the first interface, the user can intuitively see that the path delay from CPE3 to the cloud platform 11 and the path delay from CPE4 to the cloud platform 11 are both greater than 10ms, exceeding the user's experience requirement of a path delay less than or equal to 10ms.

[0194] In some embodiments, for the access device corresponding to the root node (cloud platform) indicated by the recommendation result, the path from the access device to the root node is also displayed in the first interface. For example, see Figure 5 The root node in the cloud platform 11 is the root node, and the recommendation result indicates the access device 21 (CPE1) corresponding to the cloud platform 11. The path 1 from the access device 21 (CPE1) to the cloud platform 11 is displayed in the first interface.

[0195] In some embodiments, the first interface also displays the path demand assessment information of the path from the access device to the root node, and the displayed path demand assessment information includes information such as the delay and / or bandwidth of the path. For example, see Figure 5 Path 1 shown, in Figure 5 The first interface shown displays the path demand assessment information of path 1, which includes the delay "3ms" and / or bandwidth "120M" of path 1.

[0196] In addition to selecting the cloud platform 11 as the root node to display the latency circle corresponding to the cloud platform 11 on the first interface, the user can also select other nodes as root nodes to display the latency circles corresponding to other nodes on the first interface. Figure 7 , assuming the user selects cloud platform 12. Accordingly, cloud platform 12 is obtained as the root node. The delay thresholds corresponding to cloud platform 12 include 7ms and 10ms. Figure 7 The network topology included in the first interface shows a delay circle corresponding to a delay threshold of "7ms" and a delay circle corresponding to a delay threshold of "10ms".

[0197] from Figure 7 The first interface shown allows users to intuitively see which access devices are within the latency range corresponding to cloud platform 12. For example, for access device 22 corresponding to device identifier "CPE2," the first interface clearly shows that access device 22 is within the latency range corresponding to the latency threshold "7ms" of cloud platform 12. Through the first interface, users can intuitively see that the path latency from CPE2 to cloud platform 12 is less than 10ms, meeting the user's path experience requirements. For access device 21 corresponding to device identifier "CPE1", access device 23 corresponding to device identifier "CPE3", and access device 24 corresponding to device identifier "CPE4", it can be intuitively seen from the first interface that access device 21, access device 23, and access device 24 are outside the delay circle corresponding to the delay threshold "10ms" of cloud platform 12. Through the first interface, the user can intuitively see that the path delay from CPE1 to cloud platform 12, the path delay from CPE3 to cloud platform 12, and the path delay from CPE4 to cloud platform 12 all exceed 10ms, exceeding the user's experience requirement that the path delay is less than or equal to 10ms.

[0198] Still see Figure 7 The root node (cloud platform 12) in the recommendation result indicates the access device 22 (CPE2) corresponding to the cloud platform 12, and the path 2 from the access device 22 (CPE2) to the cloud platform 12 is displayed in the first interface. Figure 7 The first interface shown displays the path demand assessment information of path 2, which includes the delay "7ms" and / or bandwidth "140M" of path 2.

[0199] In some embodiments, in a network topology, a path from a first access device to a first cloud platform is displayed in a specified display mode, the first access device is an access device in a first device set, and the first cloud platform is a cloud platform corresponding to the first access device.

[0200] The designated display mode includes a highlight display mode, a bold display mode, and / or a mode of displaying the path using a color corresponding to the path, etc. The color corresponding to each path in the first path set may be the same or different.

[0201] It should be noted that, because the recommendation results displayed in the first interface include the path requirement assessment information for the path corresponding to the access device in the first device set, the user can use the path requirement assessment information for the path corresponding to the access device to determine whether a path exists between the access device and the cloud platform whose path requirement assessment information satisfies the access device's requirement information. If such a path exists, the network management device sends the path information and the platform information of the cloud platform to the access device, enabling the access device to access the cloud platform through the path based on the path information and the platform information of the cloud platform.

[0202] In an embodiment of the present application, business information is obtained, and the business information includes the device identification and path requirement information of M access devices. Based on the device identification of the M access devices and the path requirement information, N paths are calculated, each path corresponds to a different access device, each path in the N paths meets the path requirement information, and each path passes through a cloud platform. Based on the N paths, a corresponding cloud platform is selected for the terminal device in the first device set, and a recommendation result is obtained. The recommendation result is used to indicate the cloud platform corresponding to each access device in the first device set, and the first device set includes the M access devices and some of the M access devices. The recommendation result is displayed in the first interface. Since the corresponding cloud platform is selected for the terminal device in the first device set based on the N paths, the recommendation result is obtained, so that the corresponding cloud platform can be automatically selected for the access device, thereby improving the efficiency of selecting the cloud platform and reducing labor costs. Since the recommendation result is displayed, the user can know whether the cloud platform corresponding to the access device meets the requirement information of the access device.

[0203] See also Figure 8 , the embodiment of the present application provides a device 800 for selecting a cloud platform, the device 800 is deployed on Figure 1 The network management device or Figure 4 On the network management device in the method 400, the apparatus 800 includes:

[0204] Processing unit 801 is configured to obtain service information, where the service information includes access device information and path requirement information, where the access device information includes device identifiers of M access devices, and the path requirement information includes bandwidth information, where M is an integer greater than 0;

[0205] Processing unit 801 is further configured to obtain a cloud platform recommendation result based on the service information, the recommendation result being used to indicate a cloud platform corresponding to each access device in the first device set, the first device set including a first access device, the first access device corresponding to the first cloud platform, path requirement assessment information of a path from the first access device to the first cloud platform meeting the path requirement information, the first device set including the M access devices or some of the M access devices, the cloud platforms corresponding to each access device belonging to a candidate cloud platform set, the candidate cloud platform set including P cloud platforms, where P is an integer greater than 0;

[0206] The display unit 802 is used to display the recommendation results on the first interface.

[0207] Optionally, the detailed implementation process of the processing unit 801 obtaining the business information is as follows: Figure 4 The relevant contents in step 401 of the method 400 are not described in detail here.

[0208] Optionally, the detailed implementation process of the processing unit 801 obtaining the recommendation results of the cloud platform can be found in Figure 4 The relevant contents in steps 402 - 403 of the method 400 are not described in detail here.

[0209] Optionally, the display unit 802 displays the recommended results in the first interface for a detailed implementation process, see Figure 4 The relevant contents in step 404 of the method 400 are not described in detail here.

[0210] Optionally, the display unit 802 is further configured to:

[0211] The network topology is displayed in the first interface. The nodes in the network topology include M access devices and P cloud platforms. The network topology includes at least one delay circle corresponding to the root node. The root node is a node in the network topology. At least one delay circle corresponds one-to-one to at least one delay threshold. At least one delay circle includes a first delay circle. The minimum delay from each node in the first delay circle to the root node is less than or equal to the first delay threshold. The minimum delay from each node outside the first delay circle to the root node is greater than the first delay threshold. The first delay threshold is the delay threshold corresponding to the first delay circle.

[0212] Optionally, the display unit 802 displays the detailed implementation process of the network topology, see Figure 4 The relevant contents in step 404 of the method 400 are not described in detail here.

[0213] Optionally, the display unit 802 is further configured to:

[0214] In the network topology, a path from the first access device to the first cloud platform is displayed in a specified display mode.

[0215] Optionally, the specified display mode includes a highlight display mode, a bold display mode, and / or a mode of displaying the path using a color corresponding to the path.

[0216] Optionally, the processing unit 801 is configured to:

[0217] Calculate N paths based on the service information, where N is greater than 0 and less than or equal to M, each path corresponds to a different access device, the N paths including a first path, path requirement assessment information of the first path meeting the path requirement information, the first path being a path from an access device in the first device set to a virtual node, where the virtual node is a parent node of the P cloud platforms;

[0218] Based on the N paths, a cloud platform corresponding to each access device in the first device set is selected to obtain a recommendation result.

[0219] Optionally, the detailed implementation process of the processing unit 801 calculating N paths is as follows: Figure 4 The relevant contents in step 402 of the method 400 are not described in detail here.

[0220] Optionally, the processing unit 801 selects the cloud platform corresponding to each access device in the first device set for detailed implementation process, see Figure 4 The relevant contents in step 403 of the method 400 are not described in detail here.

[0221] Optionally, the first path corresponds to a first access device, and the processing unit 801 is configured to:

[0222] A first path is calculated based on a device identifier of the first access device, the path requirement information, and a network topology of the network, where nodes in the network topology include virtual nodes, M access devices, and P cloud platforms.

[0223] Optionally, the detailed implementation process of the processing unit 801 calculating the first path is as follows: Figure 4 The relevant contents in step 402 of the method 400 are not described in detail here.

[0224] Optionally, the network topology further includes link information of a link between two adjacent nodes in the network, where the link information includes available bandwidth of the link.

[0225] Optionally, the link information further includes the link delay and / or routing weight, where the routing weight is used to indicate the routing cost of the link.

[0226] Optionally, the first path is the shortest path from the first access device to the virtual node.

[0227] Optionally, the processing unit 801 is configured to:

[0228] An overloaded link set is obtained based on the path demand information and the N paths, where the overloaded link set includes at least one overloaded link and includes all or part of the links passed by the N paths, and a load of the overloaded link exceeds the available bandwidth of the overloaded link.

[0229] Acquire a first path set based on the overloaded link set, where the first path set includes some or all of the N paths, and the loads of the links passed by the paths in the first path set do not exceed the available bandwidth of the links;

[0230] The cloud platform that the second path passes through is selected as the cloud platform corresponding to the second access device, the second path is the path included in the first path set, and the second access device is the access device corresponding to the second path.

[0231] Optionally, the processing unit 801 obtains the detailed implementation process of the overload link set, see Figure 4 The relevant contents in step 4031 of the method 400 are not described in detail here.

[0232] Optionally, the detailed implementation process of the processing unit 801 obtaining the first path set is as follows: Figure 4 The relevant contents in steps 4032-4035 of the method 400 are not described in detail here.

[0233] Optionally, the processing unit 801 is configured to:

[0234] Obtaining loads of multiple links based on the path demand information and the N paths, where the multiple links include links traversed by the N paths, the multiple links include a first link, and the load of the first link is equal to the sum of path bandwidths required by access devices corresponding to at least one path, where the at least one path traverses the first link.

[0235] An overloaded link set is obtained based on the loads of the multiple links.

[0236] Optionally, the detailed implementation process of the processing unit 801 obtaining the load of multiple links is described in Figure 4 The content of operation (1) in step 4031 of the method 400 is not described in detail here.

[0237] Optionally, the detailed implementation process of the processing unit 801 obtaining the overload link set based on the loads of the multiple links is as follows: Figure 4 The content of operation (2) in step 4031 of the method 400 is not described in detail here.

[0238] Optionally, the processing unit 801 is configured to:

[0239] Acquire a second path set based on the overloaded link set, where each path in the second path set passes through one or more overloaded links in the overloaded link set;

[0240] Selecting a third path that meets a specified condition from the second path set;

[0241] Reducing the load of a target link based on the path bandwidth required by the access device corresponding to the third path, where the target link is an overloaded link through which the third path passes;

[0242] The fourth path is migrated from the second path set to the first path set, and the load of each overloaded link passed by the fourth path does not exceed the respective available bandwidth.

[0243] Optionally, the detailed implementation process of the processing unit 801 obtaining the second path set is as follows: Figure 4 The relevant contents in step 4032 of the method 400 are not described in detail here.

[0244] Optionally, the detailed implementation process of the processing unit 801 selecting the third path is as follows: Figure 4 The relevant contents in step 4033 of the method 400 are not described in detail here.

[0245] Optionally, for the detailed implementation process of the processing unit 801 reducing the load of the target link, see Figure 4 The relevant contents in step 4034 of the method 400 are not described in detail here.

[0246] Optionally, the specified conditions satisfied by the third path include one or more of the following:

[0247] The third path has the largest overload degree, includes the largest number of links, and the access device corresponding to the third path requires the smallest path bandwidth, wherein the overload degree of the third path is used to indicate the number of overloaded links passed by the third path.

[0248] Optionally, the processing unit 801 is further configured to:

[0249] The third path is migrated from the second path set to the third path set.

[0250] Optionally, the first path set further includes paths in the N paths except the second path set.

[0251] Optionally, the processing unit 801 is further configured to:

[0252] Based on the path bandwidth required by the second access device, the available bandwidth of the link through which the second path passes is reduced.

[0253] Optionally, for a detailed implementation process of the processing unit 801 reducing the available bandwidth of the link through which the second path passes, see Figure 4 The relevant contents in step 4036 of the method 400 are not described in detail here.

[0254] Optionally, the processing unit 801 is further configured to:

[0255] Calculate Y paths based on device identifiers of X access devices and the path requirement information, where the X access devices include an access device corresponding to each path in the third path set, X is an integer greater than 0, and Y is greater than 0 and less than or equal to X;

[0256] Based on the Y paths, a corresponding cloud platform is selected for the access device in the second device set, and the second device set includes an access device corresponding to each path in the Y paths.

[0257] Optionally, the detailed implementation process of the processing unit 801 calculating Y paths is as follows: Figure 4 The relevant contents in step 501 of the method 400 are not described in detail here.

[0258] Optionally, the processing unit 801 selects a corresponding cloud platform for the access device in the second device set. Figure 4 The relevant contents in step 502 of the method 400 are not described in detail here.

[0259] In an embodiment of the present application, since the processing unit obtains a recommendation result for a cloud platform based on the business information, the recommendation result is used to indicate the cloud platform corresponding to each access device in the first device set, so that the processing unit can automatically recommend a cloud platform for each access device in the first device set, and the display unit displays the recommendation result on the first interface. For any access device in the first device set, that is, for the first access device, since the path requirement assessment information of the path from the first access device to the first cloud platform meets the path requirement information, when the display unit displays the recommendation result on the first interface, the cloud platform corresponding to the first access device indicated by the recommendation result can be directly selected for the first access device, so that the first access device can access the cloud platform corresponding to the first access device indicated by the recommendation result. This improves the efficiency of platform selection and reduces labor costs.

[0260] See also Figure 9 In an embodiment of the present application, a system 900 for selecting a cloud platform is provided. The system 900 includes:

[0261] An information acquisition module 901 is configured to acquire service information, including access device information and path requirement information. The access device information includes device identifiers of M access devices, and the path requirement information includes bandwidth information, where M is an integer greater than 0.

[0262] A result acquisition module 902 is configured to acquire a cloud platform recommendation result based on the service information, the recommendation result being used to indicate a cloud platform corresponding to each access device in a first device set, the first device set including a first access device, the first access device corresponding to a first cloud platform, path requirement assessment information of a path from the first access device to the first cloud platform meeting the path requirement information, the first device set including M access devices or some of the M access devices, the cloud platform corresponding to each access device belonging to a candidate cloud platform set, the candidate cloud platform set including P cloud platforms, where P is an integer greater than 0;

[0263] The display module 903 is used to display the recommendation results in the first interface.

[0264] Optionally, the information acquisition module 901 , the result acquisition module 902 and the display module 903 are deployed on different devices, or on the same device.

[0265] Optionally, for the detailed implementation process of the information acquisition module 901 acquiring business information, see Figure 4 The relevant contents in step 401 of the method 400 are not described in detail here.

[0266] Optionally, the detailed implementation process of the result acquisition module 902 acquiring the recommendation results of the cloud platform can be found in Figure 4The relevant contents in steps 402 - 403 of the method 400 are not described in detail here.

[0267] Optionally, the display module 903 displays the recommended results in the first interface for detailed implementation process, see Figure 4 The relevant contents in step 404 of the method 400 are not described in detail here.

[0268] Optionally, the display module 903 is further configured to:

[0269] The network topology is displayed in the first interface. The nodes in the network topology include M access devices and P cloud platforms. The network topology includes at least one delay circle corresponding to the root node. The root node is a node in the network topology. At least one delay circle corresponds one-to-one to at least one delay threshold. At least one delay circle includes a first delay circle. The minimum delay from each node in the first delay circle to the root node is less than or equal to the first delay threshold. The minimum delay from each node outside the first delay circle to the root node is greater than the first delay threshold. The first delay threshold is the delay threshold corresponding to the first delay circle.

[0270] Optionally, the display module 903 displays the detailed implementation process of the network topology, see Figure 4 The relevant contents in step 404 of the method 400 are not described in detail here.

[0271] Optionally, the display module 903 is further configured to:

[0272] In the network topology, a path from the first access device to the first cloud platform is displayed in a specified display mode.

[0273] Optionally, the specified display mode includes a highlight display mode, a bold display mode, and / or a mode of displaying the path using a color corresponding to the path.

[0274] Optionally, the result acquisition module 902 is used to:

[0275] Calculate N paths based on the service information, where N is greater than 0 and less than or equal to M, each path corresponds to a different access device, and the N paths include a first path. Path requirement assessment information of the first path satisfies the path requirement information. The first path is a path from an access device in the first device set to a virtual node, and the virtual node is a parent node of the P cloud platforms.

[0276] Based on the N paths, a cloud platform corresponding to each access device in the first device set is selected to obtain a recommendation result.

[0277] Optionally, for the detailed implementation process of the result acquisition module 902 calculating N paths, see Figure 4The relevant contents in step 402 of the method 400 are not described in detail here.

[0278] Optionally, the detailed implementation process of the result acquisition module 902 selecting the cloud platform corresponding to each access device in the first device set is described in detail in Figure 4 The relevant contents in step 403 of the method 400 are not described in detail here.

[0279] Optionally, the first path corresponds to the first access device, and the result acquisition module 902 is configured to:

[0280] A first path is calculated based on a device identifier of the first access device, the path requirement information, and a network topology of the network, where nodes in the network topology include virtual nodes, M access devices, and P cloud platforms.

[0281] Optionally, for the detailed implementation process of the result acquisition module 902 calculating the first path, see Figure 4 The relevant contents in step 402 of the method 400 are not described in detail here.

[0282] Optionally, the network topology further includes link information of a link between two adjacent nodes in the network, where the link information includes available bandwidth of the link.

[0283] Optionally, the link information further includes the link delay and / or routing weight, where the routing weight is used to indicate the routing cost of the link.

[0284] Optionally, the first path is the shortest path from the first access device to the virtual node.

[0285] Optionally, the result acquisition module 902 is used to:

[0286] An overloaded link set is obtained based on the path demand information and the N paths, where the overloaded link set includes at least one overloaded link and includes all or part of the links passed by the N paths, and a load of the overloaded link exceeds the available bandwidth of the overloaded link.

[0287] Acquire a first path set based on the overloaded link set, where the first path set includes some or all of the N paths, and the loads of the links passed by the paths in the first path set do not exceed the available bandwidth of the links;

[0288] The cloud platform that the second path passes through is selected as the cloud platform corresponding to the second access device, the second path is the path included in the first path set, and the second access device is the access device corresponding to the second path.

[0289] Optionally, the detailed implementation process of the result acquisition module 902 acquiring the overload link set is as follows: Figure 4The relevant contents in step 4031 of the method 400 are not described in detail here.

[0290] Optionally, the detailed implementation process of the result acquisition module 902 acquiring the first path set is as follows: Figure 4 The relevant contents in steps 4032-4035 of the method 400 are not described in detail here.

[0291] Optionally, the result acquisition module 902 is used to:

[0292] Obtaining loads of multiple links based on the path demand information and the N paths, where the multiple links include links traversed by the N paths, and the multiple links include a first link, where the load of the first link is equal to the sum of path bandwidths required by access devices corresponding to at least one path, and the at least one path traverses the first link.

[0293] An overloaded link set is obtained based on the loads of the multiple links.

[0294] Optionally, the detailed implementation process of the result acquisition module 902 acquiring the load of multiple links is as follows: Figure 4 The content of operation (1) in step 4031 of the method 400 is not described in detail here.

[0295] Optionally, the detailed implementation process of the result acquisition module 902 acquiring the overload link set based on the loads of the multiple links is as follows: Figure 4 The content of operation (2) in step 4031 of the method 400 is not described in detail here.

[0296] Optionally, the result acquisition module 902 is used to:

[0297] Acquire a second path set based on the overloaded link set, where each path in the second path set passes through one or more overloaded links in the overloaded link set;

[0298] Selecting a third path that meets a specified condition from the second path set;

[0299] Reducing the load of a target link based on the path bandwidth required by the access device corresponding to the third path, where the target link is an overloaded link through which the third path passes;

[0300] The fourth path is migrated from the second path set to the first path set, and the load of each overloaded link passed by the fourth path does not exceed the respective available bandwidth.

[0301] Optionally, the detailed implementation process of the result acquisition module 902 acquiring the second path set is as follows: Figure 4 The relevant contents in step 4032 of the method 400 are not described in detail here.

[0302] Optionally, for the detailed implementation process of the result acquisition module 902 selecting the third path, see Figure 4 The relevant contents in step 4033 of the method 400 are not described in detail here.

[0303] Optionally, for the detailed implementation process of the result acquisition module 902 reducing the load of the target link, see Figure 4 The relevant contents in step 4034 of the method 400 are not described in detail here.

[0304] Optionally, the specified conditions satisfied by the third path include one or more of the following:

[0305] The third path has the largest overload degree, includes the largest number of links, and the access device corresponding to the third path requires the smallest path bandwidth, wherein the overload degree of the third path is used to indicate the number of overloaded links passed by the third path.

[0306] Optionally, the system 900 further includes:

[0307] The path migration module 904 is configured to migrate the third path from the second path set to the third path set.

[0308] Optionally, the first path set further includes paths in the N paths except the second path set.

[0309] Optionally, the system 900 further includes:

[0310] The bandwidth reducing module 905 is configured to reduce the available bandwidth of the link through which the second path passes based on the path bandwidth required by the second access device.

[0311] Optionally, the detailed implementation process of the bandwidth reduction module 905 reducing the available bandwidth of the link through which the second path passes is described in detail. Figure 4 The relevant contents in step 4036 of the method 400 are not described in detail here.

[0312] Optionally, the result acquisition module 902 is further configured to:

[0313] Calculate Y paths based on device identifiers of X access devices and the path requirement information, where the X access devices include an access device corresponding to each path in the third path set, X is an integer greater than 0, and Y is greater than 0 and less than or equal to X;

[0314] Based on the Y paths, a corresponding cloud platform is selected for the access device in the second device set, where the second device set includes an access device corresponding to each of the Y paths.

[0315] Optionally, the detailed implementation process of the result acquisition module 902 calculating Y paths can be found in Figure 4 The relevant contents in step 501 of the method 400 are not described in detail here.

[0316] Optionally, the detailed implementation process of the result acquisition module 902 selecting the corresponding cloud platform for the access device in the second device set is as follows: Figure 4 The relevant contents in step 502 of the method 400 are not described in detail here.

[0317] In an embodiment of the present application, since the result acquisition module obtains a recommendation result for a cloud platform based on the business information, the recommendation result is used to indicate the cloud platform corresponding to each access device in the first device set, so that the result acquisition module can automatically recommend a cloud platform for each access device in the first device set, and the display module displays the recommendation result in the first interface. For any access device in the first device set, that is, for the first access device, since the path requirement assessment information of the path from the first access device to the first cloud platform meets the path requirement information, when the display module displays the recommendation result in the first interface, the cloud platform corresponding to the first access device indicated by the recommendation result can be directly selected for the first access device, so that the first access device can access the cloud platform corresponding to the first access device indicated by the recommendation result, thereby improving the efficiency of platform selection and reducing labor costs.

[0318] See also Figure 10 , the embodiment of the present application provides a schematic diagram of a device 1000 for selecting a cloud platform. The device 1000 may be a network management device provided by any of the above embodiments, for example, Figure 1 The network management device 4 in the network architecture 100 shown, or Figure 4 The network management device in the method 400 is shown. The device 1000 includes at least one processor 1001 , an internal connection 1002 , a memory 1003 and at least one network interface 1004 .

[0319] The device 1000 is a hardware structured apparatus.

[0320] In some embodiments, it can be used to implement Figure 8 The functional modules in the device 800 are as follows. For example, those skilled in the art may think of Figure 8 The processing unit 801 and the display unit 802 in the device 800 shown can be implemented by the at least one processor 1001 calling the code in the memory 1003. Or,

[0321] In some embodiments, the memory 1003 is used to store program modules and data. The program modules include a processing module 10031, a sending module 10032, and a receiving module 10033. In some embodiments, Figure 10Each module in the memory 1003 is respectively Figure 8 The processor 1001 can execute the computer-readable instructions in each module in the memory 1003. Figure 8 The operations that can be performed by each module shown.

[0322] The device 1000 can also be used to implement the functions of the network management device in any of the above embodiments.

[0323] The processor 1001 is, for example, a general-purpose central processing unit (CPU), a digital signal processor (DSP), a network processor (NP), a graphics processing unit (GPU), a neural network processing unit (NPU), a data processing unit (DPU), a microprocessor, or one or more integrated circuits for implementing the solution of the present application. For example, the processor 1001 includes an application-specific integrated circuit (ASIC), a programmable logic device (PLD) or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. The PLD is, for example, a complex programmable logic device (CPLD), a field programmable gate array (FPGA), a generic array logic (GAL), or any combination thereof. It can implement or execute the various logic blocks, modules, and circuits described in conjunction with the disclosure of the embodiments of the present application. The processor may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, and the like.

[0324] The internal connection 1002 may include a path for transmitting information between the components. The internal connection 1002 may be a single board or a bus. The bus may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. Buses may be classified as address buses, data buses, control buses, etc. For ease of presentation, Figure 10 Only one thick line is used in the diagram, but this does not mean that there is only one bus or one type of bus.

[0325] The at least one network interface 1004 uses any transceiver-like device for communicating with other devices or communication networks, and the communication network can be Ethernet, wireless access network, or wireless local area network (WLAN). The network interface 1004 can include a wired communication interface and a wireless communication interface. Specifically, the network interface 1004 can be an Ethernet interface, a Fast Ethernet (FE) interface, a Gigabit Ethernet (GE) interface, an Asynchronous Transfer Mode (ATM) interface, a wireless local area network (WLAN) interface, a cellular network communication interface, or a combination thereof. The Ethernet interface can be an optical interface, an electrical interface, or a combination thereof. In the embodiment of the present application, the network interface 1004 can be used for the device 1000 to communicate with other devices.

[0326] The above-mentioned memory 1003 can be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical disc, laser disc, optical disc, digital versatile disc, Blu-ray disc, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store desired program codes in the form of instructions or data structures and can be accessed by a computer, but is not limited to this. The memory can exist independently and be connected to the processor via a bus. The memory 1003 can also be integrated with the processor 1001.

[0327] In a specific implementation, as an embodiment, the processor 1001 may include one or more CPUs, such as Figure 10 Each of these CPUs can be a single-core processor or a multi-core processor. A processor here can refer to one or more devices, circuits, and / or processing cores for processing data (such as computer program instructions).

[0328] In a specific implementation, as an embodiment, the device 1000 may include multiple processors, such as Figure 10 1 and 1007. Each of these processors may be a single-CPU processor or a multi-CPU processor. A processor herein may refer to one or more devices, circuits, and / or processing cores for processing data (e.g., computer program instructions).

[0329] In a specific implementation, as an embodiment, the device 1000 may further include an output device and an input device. The output device communicates with the processor 1001 and can display information in a variety of ways. For example, the output device can be a liquid crystal display (LCD), a light emitting diode (LED) display device, a cathode ray tube (CRT) display device, or a projector. The input device communicates with the processor 1001 and can receive user input in a variety of ways. For example, the input device can be a mouse, a keyboard, a touch screen device, or a sensor device.

[0330] In a specific embodiment, the device 1000 of the embodiment of the present application may correspond to the above-mentioned multiple embodiments, for example, Figure 1 and Figure 4 In the corresponding network management device of multiple embodiments, the processor 1001 in the device 1000 reads the instructions in the memory 1003, so that Figure 10 The device 1000 shown can perform all or part of the operations of the network management device in the above-mentioned multiple embodiments.

[0331] Those skilled in the art will understand that all or part of the steps to implement the above embodiments may be accomplished by hardware, or by a program to instruct the relevant hardware, and the program may be stored in a computer-readable storage medium, which may be a read-only memory, a disk, or an optical disk, etc.

[0332] The above description is merely an optional embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the principles of the present application shall be included in the scope of protection of the present application.

Claims

1. A method for selecting a cloud platform, characterized in that: The method comprises: Obtaining service information, where the service information includes access device information and path requirement information, where the access device information includes device identifiers of M access devices, and the path requirement information includes bandwidth information, where M is an integer greater than 0; Obtaining a cloud platform recommendation result based on the business information, the recommendation result being used to indicate a cloud platform corresponding to each access device in a first device set, the first device set including a first access device, the first access device corresponding to a first cloud platform, path requirement assessment information of a path from the first access device to the first cloud platform meeting the path requirement information, the first device set including the M access devices or some of the M access devices, the cloud platforms corresponding to each access device belonging to a candidate cloud platform set, the candidate cloud platform set including P cloud platforms, where P is an integer greater than 0; The network topology is displayed in the first interface, where the nodes in the network topology include the M access devices and the P cloud platforms. The network topology includes at least one delay circle corresponding to a root node. The root node is a node selected in the network topology. The at least one delay circle corresponds one-to-one to at least one delay threshold. The at least one delay circle includes a first delay circle. The first delay circle is obtained by drawing a plurality of boundary nodes. The boundary node is the i-th layer node connected to the root node, i=1, 2, 3..., the minimum delay from the i-th layer node to the root node is less than or equal to the first delay threshold, and the minimum delay from the i+1-th layer node connected to the i-th layer node to the root node is greater than the first delay threshold. The first delay threshold is the delay threshold corresponding to the first delay circle.

2. The method according to claim 1, wherein The obtaining of a recommendation result from the cloud platform based on the business information includes: Calculating N paths based on the service information, where N is greater than 0 and less than or equal to M, each path corresponding to a different access device, the N paths including a first path, path requirement assessment information of the first path meeting the path requirement information, the first path being a path from an access device in the first device set to a virtual node, the virtual node being a parent node of the P cloud platforms; Based on the N paths, a cloud platform corresponding to each access device in the first device set is selected to obtain the recommendation result.

3. The method according to claim 2, wherein The first path corresponds to the first access device, and the calculating N paths based on the service information includes: The first path is calculated based on the device identification of the first access device, the path requirement information and the network topology of the network, where the nodes in the network topology include the virtual node, the M access devices and the P cloud platforms.

4. The method according to claim 3, wherein The network topology further includes link information of a link between two adjacent nodes in the network, where the link information includes available bandwidth of the link.

5. The method according to claim 4, wherein The link information also includes the delay and / or routing weight of the link, where the routing weight is used to indicate the routing cost of the link.

6. The method according to any one of claims 3 to 5, characterized in that The first path is the shortest path from the first access device to the virtual node.

7. The method according to any one of claims 2 to 5, characterized in that The selecting, based on the N paths, a cloud platform corresponding to each access device in the first device set includes: acquiring an overloaded link set based on the path demand information and the N paths, where the overloaded link set includes at least one overloaded link, the overloaded link set includes all or part of the links passed by the N paths, and a load of the overloaded link exceeds the available bandwidth of the overloaded link; Acquire a first path set based on the overloaded link set, where the first path set includes some or all of the N paths, and the loads of links passed by the paths in the first path set do not exceed their own available bandwidths; The cloud platform through which the second path passes is selected as the cloud platform corresponding to the second access device, the second path is the path included in the first path set, and the second access device is the access device corresponding to the second path.

8. The method according to claim 7, wherein The acquiring of an overloaded link set based on the path demand information and the N paths includes: Obtaining loads of multiple links based on the path demand information and the N paths, where the multiple links include links through which the N paths pass, and the multiple links include a first link, where the load of the first link is equal to the sum of path bandwidths required by access devices corresponding to at least one path, and the at least one path passes through the first link; An overloaded link set is obtained based on the loads of the multiple links.

9. The method according to claim 7, wherein The acquiring a first path set based on the overloaded link set includes: acquiring a second path set based on the overloaded link set, wherein each path in the second path set passes through one or more overloaded links in the overloaded link set; Selecting a third path that meets a specified condition from the second path set; reducing a load on a target link based on a path bandwidth required by an access device corresponding to the third path, the target link being an overloaded link through which the third path passes; A fourth path is migrated from the second path set to the first path set, and a load of each overloaded link passed by the fourth path does not exceed the respective available bandwidth.

10. The method according to claim 9, wherein The specified conditions satisfied by the third path include one or more of the following: The overload degree of the third path is the largest, the third path includes the largest number of links, and the access device corresponding to the third path requires the smallest path bandwidth, wherein the overload degree of the third path is used to indicate the number of overloaded links passed by the third path.

11. The method according to claim 9 or 10, wherein: The method further comprises: The third path is migrated from the second path set to a third path set.

12. The method according to claim 9 or 10, wherein: The first path set also includes paths in the N paths except the second path set.

13. The method according to claim 7, wherein After selecting the cloud platform through which the second path passes as the cloud platform corresponding to the second access device, the method further includes: Based on the path bandwidth required by the second access device, the available bandwidth of the link through which the second path passes is reduced.

14. The method according to claim 11, wherein The method further comprises: Calculating Y paths based on device identifiers of X access devices and the path requirement information, where the X access devices include an access device corresponding to each path in the third path set, X is an integer greater than 0, and Y is greater than 0 and less than or equal to X; Based on the Y paths, a corresponding cloud platform is selected for the access device in the second device set, where the second device set includes an access device corresponding to each of the Y paths.

15. A device for selecting a cloud platform, characterized in that: The device comprises: a processing unit, configured to obtain service information, wherein the service information includes access device information and path requirement information, wherein the access device information includes device identifiers of M access devices, and the path requirement information includes bandwidth information, where M is an integer greater than 0; The processing unit is further configured to obtain a recommendation result for a cloud platform based on the business information, the recommendation result being used to indicate a cloud platform corresponding to each access device in a first device set, the first device set including a first access device, the first access device corresponding to a first cloud platform, path requirement assessment information of a path from the first access device to the first cloud platform meeting the path requirement information, the first device set including the M access devices or some of the M access devices, the cloud platforms corresponding to each access device belonging to a candidate cloud platform set, the candidate cloud platform set including P cloud platforms, where P is an integer greater than 0; A display unit is used to display a network topology in a first interface, where the nodes in the network topology include the M access devices and the P cloud platforms, and the network topology includes at least one delay circle corresponding to a root node, where the root node is a node selected in the network topology, and the at least one delay circle corresponds one-to-one to at least one delay threshold. The at least one delay circle includes a first delay circle, where the first delay circle is obtained by drawing a plurality of boundary nodes, where the boundary node is an i-th layer node connected to the root node, i=1, 2, 3..., and the minimum delay from the i-th layer node to the root node is less than or equal to the first delay threshold, and the minimum delay from the i+1th layer node connected to the i-th layer node to the root node is greater than the first delay threshold, and the first delay threshold is the delay threshold corresponding to the first delay circle.

16. The device according to claim 15, characterized in that The processing unit is configured to: Calculating N paths based on the service information, where N is greater than 0 and less than or equal to M, each path corresponding to a different access device, the N paths including a first path, path requirement assessment information of the first path meeting the path requirement information, the first path being a path from an access device in the first device set to a virtual node, the virtual node being a parent node of the P cloud platforms; Based on the N paths, a cloud platform corresponding to each access device in the first device set is selected to obtain the recommendation result.

17. The device according to claim 16, characterized in that The first path corresponds to the first access device, and the processing unit is configured to: The first path is calculated based on the device identification of the first access device, the path requirement information and the network topology of the network, where the nodes in the network topology include the virtual node, the M access devices and the P cloud platforms.

18. The device according to claim 16 or 17, characterized in that The processing unit is configured to: acquiring an overloaded link set based on the path demand information and the N paths, where the overloaded link set includes at least one overloaded link, the overloaded link set includes all or part of the links passed by the N paths, and a load of the overloaded link exceeds the available bandwidth of the overloaded link; Acquire a first path set based on the overloaded link set, where the first path set includes some or all of the N paths, and the loads of links passed by the paths in the first path set do not exceed their own available bandwidths; The cloud platform through which the second path passes is selected as the cloud platform corresponding to the second access device, the second path is the path included in the first path set, and the second access device is the access device corresponding to the second path.

19. The device according to claim 18, wherein The processing unit is configured to: Obtaining loads of multiple links based on the path demand information and the N paths, where the multiple links include links through which the N paths pass, and the multiple links include a first link, where the load of the first link is equal to the sum of path bandwidths required by access devices corresponding to at least one path, and the at least one path passes through the first link; An overloaded link set is obtained based on the loads of the multiple links.

20. A device for selecting a cloud platform, characterized in that: The device comprises a processor and a computer program, and when the processor executes the computer program, the device implements the method according to any one of claims 1 to 14.

21. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a computer, the method according to any one of claims 1 to 14 is implemented.

22. A computer program product, characterized in that The method comprises a computer program, which, when executed by a computer, implements the method according to any one of claims 1 to 14.

Images