WO2022166582A1 - 网络管理方法、装置、设备及计算机可读存储介质 - Google Patents

网络管理方法、装置、设备及计算机可读存储介质 Download PDF

Info

Publication number
WO2022166582A1
WO2022166582A1 PCT/CN2022/072748 CN2022072748W WO2022166582A1 WO 2022166582 A1 WO2022166582 A1 WO 2022166582A1 CN 2022072748 W CN2022072748 W CN 2022072748W WO 2022166582 A1 WO2022166582 A1 WO 2022166582A1
Authority
WO
WIPO (PCT)
Prior art keywords
link
bandwidth
target
configuration
candidate
Prior art date
Application number
PCT/CN2022/072748
Other languages
English (en)
French (fr)
Inventor
丁伋堃
张彦芳
张亮
王春宁
Original Assignee
华为技术有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 华为技术有限公司 filed Critical 华为技术有限公司
Publication of WO2022166582A1 publication Critical patent/WO2022166582A1/zh

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/08—Configuration management of networks or network elements
    • H04L41/0893—Assignment of logical groups to network elements
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/08—Configuration management of networks or network elements
    • H04L41/0803—Configuration setting
    • H04L41/0823—Configuration setting characterised by the purposes of a change of settings, e.g. optimising configuration for enhancing reliability
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/08—Configuration management of networks or network elements
    • H04L41/0894—Policy-based network configuration management
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/08—Configuration management of networks or network elements
    • H04L41/0896—Bandwidth or capacity management, i.e. automatically increasing or decreasing capacities
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/14—Network analysis or design
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/14—Network analysis or design
    • H04L41/145—Network analysis or design involving simulating, designing, planning or modelling of a network
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/14—Network analysis or design
    • H04L41/147—Network analysis or design for predicting network behaviour
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L47/00—Traffic control in data switching networks
    • H04L47/10—Flow control; Congestion control
    • H04L47/12—Avoiding congestion; Recovering from congestion
    • H04L47/125—Avoiding congestion; Recovering from congestion by balancing the load, e.g. traffic engineering
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L47/00—Traffic control in data switching networks
    • H04L47/10—Flow control; Congestion control
    • H04L47/24—Traffic characterised by specific attributes, e.g. priority or QoS

Definitions

  • the present application relates to the field of network communication, and in particular, to a network management method, apparatus, device, and computer-readable storage medium.
  • SDWAN Software-defined wide area network
  • SDN software defined network
  • the policy templates and expert experience of the SDWAN can be used to obtain policy configurations such as SPR, QoS, and FEC in SDWAN for network management. Since network management relies on preset policy templates and expert experience, the manual workload is large, resulting in low network management efficiency and poor user experience.
  • the present application provides a network management method, apparatus, device, and computer-readable storage medium, which are used to improve the efficiency of network management and improve user experience.
  • a network management method comprising: controlling a device to obtain a candidate policy configuration gain based on a candidate policy configuration of the network device, where the candidate policy configuration gain is used to indicate that the prediction effect of the candidate policy configuration is relative to that of the network device. The difference in the effect of the current configuration; the control device causes the display interface to display the candidate strategy configuration gain.
  • the efficient network management method provided by the technical solution can predict the application effect of the candidate policy configuration generated by the network device, and provide the user with the difference between the predicted effect and the effect of the current network configuration through the display interface, so that the user can clearly see the difference between the predicted effect and the effect of the current network configuration. Knowing the applicability of candidate policy configurations improves network management efficiency and user experience.
  • the method further includes: acquiring a user confirmation result for the candidate policy configuration, and determining a target based on the user confirmation result Policy configuration.
  • the candidate policy configuration includes multiple policy configurations
  • the determining a target policy configuration based on a user confirmation result includes: determining a user-confirmed policy configuration among the multiple policy configurations as the Target policy configuration. Further, the determined target policy configuration can also be delivered to the network device for configuration.
  • the candidate policy configuration includes multiple policy configurations
  • the user confirmation result includes a modified candidate policy configuration
  • determining the target policy configuration based on the user confirmation result includes:
  • the candidate policy configuration is determined to be the target policy configuration.
  • the user's confirmation result may be a policy configuration selected directly, or may be a policy configuration obtained after adjustment, which makes the user's confirmation result more flexible.
  • the network management method further includes: the control device causes the display interface to display the candidate policy configuration.
  • the control device causes the display interface to display the candidate policy configuration.
  • control device causes the display interface to display the candidate policy configuration gain, and further includes: when the user queries the candidate policy configuration on the display interface, the control device causes the candidate policy configuration to be displayed on the display interface.
  • the display interface displays the candidate strategy configuration gain.
  • the network management method further includes: acquiring first key performance indicator KPI data of the network device; comparing the first KPI data with second KPI data corresponding to historical recommendation results , based on the comparison result, a data discrepancy index is obtained, and the value of the data discrepancy index is positively correlated with the degree of difference between the first KPI data and the second KPI data; only when the data discrepancy index satisfies the policy When recommending conditions, obtain the candidate policy configuration. By determining whether the policy recommendation conditions are met based on the data difference index, whether to obtain candidate policy configurations is triggered, so that the accuracy of network management is higher, and resources are not wasted due to frequent acquisition of candidate policy configurations.
  • the candidate policy configuration includes a routing configuration
  • the control device acquiring the candidate policy configuration includes: acquiring the priority of each application category; based on the target application category and an application quality model , the candidate links are divided into compliant links and non-compliant links, the target application category is the current priority application category to be acquired, and the compliant link indicates compliance with the application quality model corresponding to the target application category
  • the non-conforming link indicates a link that does not conform to the application quality model corresponding to the target application category, and the application quality model is used to indicate the quality requirements of the corresponding application category; obtain the target application category exclusively conforming to The bandwidth of the link mode; under the condition that the bandwidth of the target application class exclusively conforms to the link mode meets the bandwidth requirement of the target application class, the target link is determined in the conforming link based on the intent model, and the target link is determined based on the target chain.
  • generating a routing configuration for the target application class Through the route selection configuration based on the intent model, the obtained candidate policy configuration is more in line with
  • the method further includes: when the bandwidth conforming to the link mode exclusively by the target application class does not meet the bandwidth requirement of the target application class Obtain the bandwidth of the balanced load mode of the target application category under the condition of A target link, generating a routing configuration of the target application category based on the target link. Under the condition that the bandwidth that exclusively conforms to the link mode does not meet the bandwidth requirement of the target application category, a routing configuration is generated based on the balanced load mode, thereby ensuring performance.
  • the method further includes: under the condition that the bandwidth of the target application class balanced load mode does not meet the bandwidth requirement of the target application class, In the non-compliant links, a target link is determined according to the optimal-in-difference model, and a routing configuration of the target application category is generated based on the target link. Under the condition that the bandwidth of the balanced load mode of the target application category does not meet the bandwidth requirements of the target application category, the target link is determined according to the optimal selection model in the difference, and the routing configuration is generated accordingly to ensure performance.
  • the non-conforming link is determined according to a model of selecting an optimal among differences
  • the target link includes: detecting whether the target application class monopolizes the bandwidth that does not conform to the link mode to meet the bandwidth requirements of the target application category; Under the condition of bandwidth requirement, among the non-conforming links, the target link is determined according to the best-in-difference model, so as to ensure the performance as much as possible.
  • the method further includes: after the target application class exclusively does not conform to the link mode Under the condition that the bandwidth of the target application category does not meet the bandwidth requirements of the target application category, an alarm is issued. Through timely alarms, network management efficiency is improved.
  • the candidate policy configuration includes a quality of service configuration
  • the control device acquires the candidate policy configuration based on the bandwidth requirements of the respective application categories, including: acquiring the priority of each application category; For the bandwidth requirements and bandwidth models of each application category, the QoS configuration of each application category is sequentially obtained according to the priority of each application category, and the bandwidth model is used to indicate the bandwidth requirements of the corresponding application category.
  • a network management apparatus comprising: a first obtaining module configured to obtain a candidate policy configuration gain based on a candidate policy configuration of a network device, where the candidate policy configuration gain is used to indicate the candidate policy configuration The difference between the predicted effect and the effect of the current policy configuration of the network device; a display module, configured to display the candidate policy configuration gain on the display interface.
  • the apparatus further includes: a second obtaining module, configured to obtain a user confirmation result for the candidate strategy configuration after the display module causes the display interface to display the candidate strategy configuration gain, based on The user confirmation result determines the target policy configuration.
  • the candidate policy configuration includes multiple policy configurations
  • the second obtaining module is configured to determine a user-confirmed policy configuration among the multiple policy configurations as the target policy configuration.
  • the candidate policy configuration includes multiple policy configurations
  • the user confirmation result includes a modified candidate policy configuration
  • the second obtaining module is configured to determine the modified candidate policy configuration as The target policy configuration.
  • the display module is further configured to display the candidate policy configuration on the display interface.
  • the display module is further configured to cause the display interface to display the gain of the candidate strategy configuration when the user queries the candidate strategy configuration on the display interface.
  • the apparatus further includes: a third acquisition module, configured to acquire the first key performance indicator KPI data of the network device; compare the first KPI data with the corresponding historical recommendation results For the second KPI data, a data discrepancy index is obtained based on the comparison result, and the value of the data discrepancy index is positively correlated with the degree of difference between the first KPI data and the second KPI data; only when the data discrepancy When the performance index satisfies the policy recommendation condition, the candidate policy configuration is acquired.
  • a third acquisition module configured to acquire the first key performance indicator KPI data of the network device; compare the first KPI data with the corresponding historical recommendation results For the second KPI data, a data discrepancy index is obtained based on the comparison result, and the value of the data discrepancy index is positively correlated with the degree of difference between the first KPI data and the second KPI data; only when the data discrepancy When the performance index satisfies the policy recommendation condition, the candidate policy configuration is acquired.
  • the candidate policy configuration includes a route selection configuration, and a third obtaining module is used to obtain the priority of each application category; based on the target application category and the application quality model, the candidate links are divided into Compliant link and non-compliant link, the target application category is the current priority application category to be obtained, a compliant link indicates a link that complies with the application quality model corresponding to the target application category, and a non-compliant link indicates that it does not meet the target application category
  • the link of the corresponding application quality model, the application quality model is used to indicate the quality requirements of the corresponding application category; obtain the bandwidth that conforms to the link mode exclusively for the target application category; Under the condition that the bandwidth satisfies the bandwidth requirement of the target application category, a target link is determined in the compliant link based on the intent model, and a routing configuration of the target application category is generated based on the target link.
  • the third obtaining module is configured to obtain, after the target application class exclusively occupies the bandwidth conforming to the link mode, is further configured to obtain the bandwidth conforming to the link mode exclusively by the target application class when the target application class exclusively occupies the bandwidth conforming to the link mode and does not satisfy the target
  • the bandwidth of the balanced load mode of the target application category is obtained; under the condition that the bandwidth of the balanced load mode of the target application category meets the bandwidth requirement of the target application category, the chain corresponding to the balanced load mode is obtained.
  • a target link is determined in the route, and a route selection configuration of the target application category is generated based on the target link.
  • the third obtaining module is configured to obtain, after obtaining the bandwidth of the target application class balanced load mode, the bandwidth of the target application class balanced load mode does not meet the bandwidth of the target application class Under the condition of the requirement, in the non-conforming links, a target link is determined according to the best-in-difference model, and a routing configuration of the target application category is generated based on the target link.
  • a third obtaining module is configured to detect whether the target application class exclusively occupies the bandwidth that does not conform to the link mode or not meets the bandwidth requirement of the target application class; Under the condition that the bandwidth of the link mode satisfies the bandwidth requirement of the target application category, the target link is determined according to the optimal-from-difference model among the non-compliant links.
  • the third obtaining module is configured to detect whether the target application class exclusively occupies the bandwidth that does not conform to the link mode meets the bandwidth requirement of the target application class, and is further configured to detect whether the target application class exclusively does not conform to the bandwidth requirement of the target application class. If the bandwidth of the link mode does not meet the bandwidth requirement of the target application category, an alarm is issued.
  • the candidate policy configuration includes a quality of service configuration
  • a third obtaining module is used to obtain the priority of each application category; based on the bandwidth requirement and bandwidth model of each application category, according to the The priority obtains the QoS configuration of each application category in turn, and the bandwidth model is used to indicate the bandwidth requirement of the corresponding application category.
  • a network management device including a processor and a computer program.
  • the network management device can implement the network management method according to any one of the first aspect above.
  • a computer-readable storage medium on which a computer program is stored.
  • the network management method according to any one of the first aspect above is implemented.
  • a computer program product including a computer program.
  • the computer program When the computer program is executed by a computer, the network management method according to any one of the first aspect above is implemented.
  • a communication apparatus comprising: a transceiver, a memory and a processor.
  • the transceiver, the memory and the processor communicate with each other through an internal connection path, the memory is used for storing instructions, and the processor is used for executing the instructions stored in the memory to control the transceiver to receive signals and control the transceiver to send signals , and when the processor executes the instructions stored in the memory, the processor is caused to execute the method in the first aspect or any possible implementation manner of the first aspect.
  • processors there are one or more processors and one or more memories.
  • the memory may be integrated with the processor, or the memory may be provided separately from the processor.
  • the memory may be a memory, for example, a read only memory (ROM), which may be integrated with the processor on the same chip, or may be separately provided on different chips.
  • ROM read only memory
  • the embodiment of the present application There is no limitation on the type of memory and how the memory and the processor are arranged.
  • a chip including a processor for invoking and executing instructions stored in the memory from a memory, so that a communication device on which the chip is installed executes the first aspect or any of the first aspects possible. method in an embodiment.
  • another chip comprising: an input interface, an output interface, a processor, and a memory, the input interface, the output interface, the processor, and the memory are connected through an internal connection path, and the processor is used to execute codes in the memory , when the code is executed, the processor is configured to execute the method in the first aspect or any possible implementation manner of the first aspect.
  • FIG. 1 is a schematic diagram of an implementation environment of a network management method provided by an embodiment of the present application
  • FIG. 2 is a flowchart of a network management method provided by an embodiment of the present application.
  • FIG. 3 is a flowchart of a method for obtaining a candidate policy configuration provided by an embodiment of the present application
  • FIG. 4 is an architecture diagram of a network management system provided by an embodiment of the present application.
  • FIG. 5 is a schematic diagram of a data aggregation module included in a network management system provided by an embodiment of the present application
  • FIG. 6 is a schematic diagram of an tuning engine module included in a network management system provided by an embodiment of the present application.
  • FIG. 7 is a schematic diagram of a recommendation engine module included in a network management system provided by an embodiment of the present application.
  • FIG. 8 is a schematic diagram of an interaction flow between a control device and a display interface included in a network management system provided by an embodiment of the present application;
  • FIG. 9 is a schematic diagram of an interaction flow between a control device and a display interface included in a network management system provided by an embodiment of the present application.
  • FIG. 10 is a schematic diagram of a process for obtaining a candidate policy configuration provided by an embodiment of the present application.
  • FIG. 11 is a schematic structural diagram of a network management apparatus provided by an embodiment of the present application.
  • FIG. 12 is a schematic structural diagram of a network management device provided by an embodiment of the present application.
  • FIG. 13 is a schematic structural diagram of a network management device provided by an embodiment of the present application.
  • SDWAN is used to connect enterprise networks, data centers, Internet applications and cloud services with a wide geographical range, aiming to help users reduce WAN expenses and improve network connection flexibility.
  • network management is an important link in SDWAN.
  • the embodiment of the present application obtains the gain of the candidate policy configuration by predicting the application effect of the candidate policy configuration, and displays the gain of the candidate policy configuration to the user through the display interface, so that the user can intuitively and conveniently determine the applicability of the candidate configuration gain, and the network is improved. Management efficiency, thereby improving user experience.
  • the network management method provided by the embodiment of the present application may be applied to the implementation environment shown in FIG. 1 .
  • the implementation environment includes a network device 101 and a control device 102 .
  • the network device 101 includes but is not limited to routers, switches, servers, and the like.
  • the network device 101 needs to communicate in the network according to the policy configuration issued by the control device 102 , and at the same time, the network device 101 collects network data and reports it to the control device 102 .
  • the control device 102 determines the network state based on the network data reported by the network device 101 .
  • the network status includes network quality and quality requirements of network services.
  • the control device 102 detects that the current policy configuration is no longer applicable to the current network state, it generates a candidate policy configuration that can be applied to the network device 101 based on the network data, which can use the key performance indicators of the network device 101. indication, KPI) data representation.
  • KPI indication
  • the KPI data of the network equipment is used to reflect the current operating status of the network equipment and its constituent networks.
  • the operating status reflected by the KPI data includes but is not limited to: the available links in the current network and the quality of the available links, the current network The category of applications to be processed by the device, the quality of user experience, and the policy configuration of the current network device.
  • the control device 102 After the control device 102 generates the candidate policy configuration, it predicts the application effect of the candidate policy configuration after it is delivered to the network device 101 based on the candidate policy configuration, and passes the difference between the predicted effect of the candidate policy configuration and the effect of the current configuration of the network device 101.
  • the candidate strategy configuration gain is used to indicate, and the candidate strategy configuration gain is sent to the display interface 103 for display.
  • the display interface 103 may be a display interface on the control device 102 or a display interface of another device other than the control device 102, and the control device 102 sends the candidate strategy configuration gain to the other device, and the display interface of the other device is displayed by the control device 102.
  • the interface 103 is displayed.
  • control device 102 may also cause the display interface to display the gain of the candidate policy configuration based on the user querying the candidate policy configuration on the display interface 103 .
  • control device 102 may also cause the display interface 103 to display candidate policy configurations.
  • the control device 102 may also obtain the user confirmation result for the candidate policy configuration, and determine the target policy configuration based on the user confirmation result. For example, the user can be allowed to adjust the candidate policy configuration displayed on the display interface 103, and the adjusted policy configuration is fed back to the control device 102, and the control device 102 then uses the adjusted policy configuration as the user confirmation result, and acquires the target accordingly. Policy configuration. Afterwards, the control device 102 may also deliver the target policy configuration to the network device for network management.
  • control device 102 may further determine the target policy configuration based on the candidate policy configuration, and deliver the target policy configuration to the network device for network management.
  • the manner in which the display interface 103 displays the candidate strategy configuration gain may be displayed through a visual image, a text description, or other presentation manners, which are not limited in this embodiment of the present application.
  • FIG. 2 shows a flowchart of a network management method provided by an embodiment of the present application.
  • Step 101 the control device obtains the candidate policy configuration gain based on the candidate policy configuration of the network device.
  • the control device acquires the candidate policy configuration gain based on the candidate policy configuration of the network device, including: acquiring the candidate policy configuration of the network device; based on the candidate policy configuration of the network device, according to the gain model, calculating different candidate policies Configure the predicted gain index after delivery to obtain the candidate policy configuration gain.
  • the control device obtains the candidate policy configuration of the network device, including but not limited to: the control device obtains the first KPI data of the network device; the control device compares the first KPI data with the first KPI data corresponding to the historical recommendation result Second KPI data, based on the comparison results to obtain the data discrepancy index, the value of the data discrepancy index is positively correlated with the degree of difference between the first KPI data and the second KPI data; only when the data discrepancy index meets the policy recommendation conditions, obtain Candidate policy configuration.
  • the process of acquiring the candidate policy configuration reference may be made to the subsequent steps 1011 to 1013 shown in FIG. 3 , and details are not described here.
  • the control device After acquiring the candidate policy configuration of the network device, calculates, based on the candidate policy configuration of the network device and the gain model, predicted gain indicators after different candidate policy configurations are issued, and obtains the candidate policy configuration gain.
  • the candidate policy configuration gain is used to indicate the difference between the application effect of the candidate policy configuration and the effect of the current network policy configuration.
  • the candidate policy configuration gain may be an index value used to indicate the application effect of the candidate policy configuration.
  • the degree of difference between the effect of the current network policy configuration and the effect of the current network policy configuration, the gain of the candidate policy configuration may also be the variation range of the index, which is not limited in this embodiment of the present application.
  • the gain model is a calculation model pre-stored in the control device for calculating the expected gain index of the system.
  • the expected gain index includes: expected quality gain and expected link occupancy rate of each application in the whole system.
  • the gain model may be a health model, and the health model evaluates the application gain and the link usage gain by calculating weighted gains.
  • Step 102 the control device causes the display interface to display the candidate strategy configuration gain.
  • control device may cause the display interface to directly display the candidate strategy configuration gains, or may cause the display interface to display the candidate strategy configuration gains when the user queries the candidate strategy configuration on the display interface.
  • control device may further cause the display interface to display candidate policy configurations.
  • the control device enables the display interface to display the candidate policy configuration and the candidate policy configuration gain, including but not limited to: the control device enables the candidate policy configuration and the candidate configuration gain to be displayed directly on the display interface, or the control device sends the candidate policy configuration and the candidate policy configuration gain
  • the display interface is configured to record the candidate strategy configuration and the candidate strategy configuration gain. When the display interface receives a user querying the candidate strategy configuration message, the control device displays the candidate strategy configuration and the candidate strategy configuration gain on the display interface.
  • methods for displaying and displaying candidate strategy configuration gains on the display interface include but are not limited to the following: 1. Displaying a before-and-after comparison table of gain index values; Time change; 3. On a time coordinate, display the change range of the gain indicator in a sequence of change range; 4. Display the radar chart based on the indicator dimension and the corresponding level of the indicator.
  • the embodiment of the present application does not limit the display method of the candidate strategy configuration gain, and the display methods used in the art to reflect the difference of the indicators are all within the protection scope of the embodiment of the present application.
  • the method further includes: acquiring a user confirmation result for the candidate policy configuration, and determining the target policy configuration based on the user confirmation result.
  • the control device determines the target policy configuration it further includes: delivering the target policy configuration to the network device.
  • the method of obtaining the user confirmation result for the candidate policy configuration is not limited in this embodiment of the present application.
  • the user confirmation result fed back by the display interface is obtained based on the display interface displaying the candidate policy configuration and the candidate policy configuration gain.
  • the candidate policy configuration includes multiple policy configurations, and determining the target policy configuration based on the user confirmation result includes but is not limited to the following two situations.
  • the policy configuration confirmed by the user among the multiple policy configurations is determined as the target policy configuration.
  • the modified candidate policy configuration is determined as the target policy configuration.
  • the user can select the desired policy configuration from the candidate policy configurations displayed on the display interface, and can also flexibly adjust the existing candidate policy configurations according to actual needs to generate the adjusted policy configuration.
  • the embodiment of the present application provides an efficient network management method, which can predict the application effect of a candidate policy configuration generated by a network device, and provide the difference between the predicted effect and the effect of the current network configuration to the user through a display interface, so that the user can
  • the applicability of candidate policy configurations can be known at a glance, which improves the efficiency of network management and improves user experience.
  • the network management method provided by the embodiment of the present application can also automatically generate a candidate policy configuration executable by the network device in the case of multi-site, multi-link and multi-state.
  • the generation process of the candidate policy configuration combines the existing network Real-time KPI data, covering the application quality model, intent model or the best-in-the-bad model, and bandwidth model, and further adjust the candidate policy configuration based on user confirmation results to obtain a more targeted policy configuration, which not only improves the impact of policy configuration on the status of the existing network It also reduces manual intervention, reduces work complexity, and saves network maintenance costs.
  • FIG. 3 shows a flowchart of a method for acquiring a candidate policy configuration provided by an embodiment of the present application.
  • the control device acquires the candidate policy configuration of the network device, including but not limited to the following steps 1011 to 1013 .
  • the process for the control device to acquire the first KPI data of the network device includes, but is not limited to, the control device receives the KPI data reported by the network device, aggregates the received KPI data, processes the aggregated KPI data, and obtains the processed KPI data. KPI data. Afterwards, the control device may store the processed KPI data, and collect the first KPI data of the network device from the stored KPI data. In a possible implementation manner, the control device can receive the KPI data that the network device continuously collects from the existing network and actively report to the control device, and the control device can also actively collect and receive the KPI data uploaded by the network device from the network device. In addition, the KPI data sent by the network device to the control device can also be encrypted.
  • control device After the control device aggregates the received KPI data, it decrypts and converts the received KPI data to obtain the aggregated KPI data.
  • the control device processes the aggregated KPI data, including but not limited to data cleaning and processing of null values and abnormal values.
  • control device may further fuse and classify the processed KPI data based on the definition information to obtain the processed KPI, and the definition information includes but is not limited to the definition of the storage granularity, type and duration of the data.
  • control device may store the processed KPI data in a storage device, where the storage device may be directly deployed in the control device, or the control device may store the processed KPI data. Devices and storage devices are deployed on different devices and communicate through the network. Furthermore, the control device may store the processed KPI data in a database corresponding to the storage device in different formats. Since the processed KPI data contains various types of data, it needs to be stored in the database corresponding to the storage device in different formats.
  • the control device periodically collects the first KPI data of the network device from the KPI data stored in the storage device.
  • the first KPI data of the network device is used to reflect the current operating state of the network device and its constituent networks, and the operating state reflected by the first KPI data includes but is not limited to: available links in the current network and available links Quality, application categories to be processed by the current network device, user experience quality, and policy configuration of the current network device, etc.
  • control device compares the first KPI data with the second KPI data corresponding to the historical recommendation results, and obtains the data difference index, including but not limited to: preprocessing the first KPI data, and obtaining the preprocessed first KPI data ; Compare the preprocessed first KPI data with the second KPI data corresponding to the historical recommendation results, and generate a data difference index.
  • the preprocessing process includes: unifying the first KPI data into a standard format. Since the first KPI data includes a variety of different types of data and are stored in the corresponding database of the storage device in different formats, in order to process the first KPI data, the first KPI data must be unified into a standard format. For example, the first KPI data is unified into a standard format of link bandwidth, packet loss rate, and delay indicators, which are used to indicate the quality of the current network.
  • the historical recommendation result may be the last time the policy recommendation condition was met, the KPI data corresponding to the last time the policy recommendation condition was met as the second KPI data, and then compare the preprocessed first KPI data with the first KPI data.
  • Two KPI data generate data difference indicators.
  • the data difference index is used to indicate the degree of difference between the first KPI data and the second KPI data, and the value of the data difference index and the degree of difference may have a positive correlation.
  • the data discrepancy indicator reflects the difference between the current state and the historical state of the network device and its constituent networks.
  • the first KPI data is the same as the second KPI data, and the control device judges that the current state of the network device and its constituent networks has not occurred compared to the historical state. Variety.
  • the method further includes: the control device determines whether the data difference index satisfies the policy recommendation condition.
  • the control device determines whether the data discrepancy index meets the policy recommendation conditions based on the data discrepancy index, including but not limited to: generating recommendation suppression values based on historical recommendation trigger information; determining data discrepancy indices based on data discrepancy indices, recommendation suppression values, and business rules Whether the policy recommendation conditions are met; if the policy recommendation conditions are met, a recommendation trigger signal is generated.
  • the business rules are a series of rules that are stored in the control device and formulated in the process of determining whether the policy recommendation conditions are met.
  • the business rules may include but are not limited to: initial recommendation trigger timing and tuning period.
  • the initial recommendation trigger timing indicates the timing for determining whether the policy recommendation conditions are met for the first time. For example, if the current network device and its constituent networks have just finished upgrading and updating at the current moment, the current moment can be used as an initial recommendation trigger timing.
  • the tuning period specifies the time period for determining whether the policy recommendation conditions are met. The tuning period can be set based on experience or adjusted according to application scenarios.
  • the historical recommendation trigger information is the information stored by the control device that satisfies the policy recommendation condition every time in the past.
  • the historical recommendation trigger information may include: the time when the policy recommendation condition was satisfied each time in the past and the corresponding KPI data at that time.
  • the recommendation suppression value is generated based on the historical recommendation trigger information to reflect the frequency of satisfying the policy recommendation conditions. For example, in a historical period of reference length, the number of times the policy recommendation conditions are met exceeds the set number limit. At this time, the recommendation suppression value generated based on the historical recommendation trigger information will limit the policy recommendation conditions.
  • the recommendation trigger signal is used to indicate that the policy recommendation condition is currently satisfied, and trigger the next process of the control device.
  • the control device may record the current time and the corresponding first KPI data, and generate new historical recommendation trigger information and new historical recommendation results.
  • the candidate policy configuration includes but is not limited to routing configuration and quality of service (quality of service, QoS) configuration.
  • the routing configuration may be a smart policy routing (smart policy routing, SPR) configuration.
  • the candidate policy configuration includes routing configuration, and the control device acquires the candidate policy configuration, including the following 10131 to 10134.
  • the priority of each application category provides a sequence for acquiring candidate policy configurations of each application category, and subsequent steps will sequentially acquire candidate policy configurations of each application category according to the priority of each application category.
  • the target application category is the current priority application category to be acquired, that is, in the process of routing each application category in order of priority, the current application category is the target application category.
  • a compliant link indicates a link that complies with the application quality model corresponding to the target application category, and a non-compliant link indicates a link that does not comply with the application quality model corresponding to the target application category.
  • the application quality model is a recommendation model that provides optional policy configuration based on application quality, and is used to indicate the quality requirements of the corresponding application category.
  • the application quality model classifies applications according to preset priorities, and determines the quality attribute thresholds according to the attributes of each application category, according to industry standards and business requirements.
  • the application categories may include: audio, video, enterprise services, and data
  • the quality attribute thresholds may include: delay, jitter, and packet loss rate.
  • the application quality model may be preset based on experience, or may be adjusted according to actual needs, which is not limited in this embodiment of the present application.
  • the application quality model used is as follows:
  • the priority from high to low is: audio applications, video applications, enterprise business applications, and data applications; for audio applications, the quality thresholds include: delay 150 milliseconds (millisecond, ms), jitter threshold 30ms, loss Packet rate 1%; for video applications, the quality thresholds include: delay 150ms, jitter threshold 20ms, packet loss rate 1%; for enterprise business applications, quality thresholds include: delay 100ms, jitter threshold 30ms, packet loss rate 5%; For data applications, the quality thresholds include: delay 300ms, jitter threshold 40ms, and packet loss rate 5%.
  • the bandwidth requirements of each application category are determined based on the first KPI data. For example, when the data difference index satisfies the policy recommendation condition, that is, when a recommendation trigger signal is detected, the control device performs the step of determining the application category corresponding to the first KPI data and the bandwidth requirements of each application category.
  • the intent model is a recommendation model that provides optional policy configuration based on user intent, and is used to adjust the routing configuration of each application category on multiple links according to the user intent, so as to achieve the user intent of cost, quality or balance.
  • the intent model includes a cost intent model, which represents the highest occupancy rate of the Internet link; a quality intent model, which represents the best application quality; and a balance intent model, which represents the balance between cost and quality.
  • the intent model may be preset based on experience, or may be adjusted according to actual needs, which is not limited in this embodiment of the present application.
  • the intent models used are as follows: Cost Intent Model, all applications prefer Internet links; Quality Intent Model, all applications prefer the lowest latency link; Balanced Intent Model, audio, video, enterprise services are preferred The link with the lowest latency is selected, and the Internet link is preferred for data.
  • the method further includes: obtaining the balanced load mode of the target application class under the condition that the bandwidth conforming to the link mode exclusively by the target application class does not meet the bandwidth requirement of the target application class.
  • the load balance mode refers to the balanced allocation of target applications to multiple links for coordinated transmission; under the condition that the bandwidth of the target application category balanced load mode meets the bandwidth requirements of the target application category, in the balanced load mode A target link is determined from the corresponding link, and a routing configuration of the target application category is generated based on the target link.
  • the method further includes: under the condition that the bandwidth of the target application class balancing load mode does not meet the bandwidth requirement of the target application class, selecting the optimal model according to the difference in the links that do not meet the requirements.
  • a target link is determined, and a routing configuration of the target application category is generated based on the target link.
  • the optimal selection model is a recommendation model that provides optional policy configuration based on user requirements when the application quality cannot be guaranteed, and is used to adjust the selection of each application category on multiple links when the application quality cannot be guaranteed. Road configuration, as far as possible to meet user needs.
  • the optimal model among differences includes: a cost optimal model, a quality optimal model, and a balanced optimal model.
  • the model for selecting the best among the differences may be preset based on experience, or may be adjusted according to actual needs, which is not limited in this embodiment of the present application.
  • the best-of-difference models used are as follows: a cost-optimized model, where all applications prefer the lowest-latency link; a quality-optimized model, where all applications prefer the lowest-latency link; and a balanced best model, where all applications prefer the lowest-latency link The link with the lowest latency is preferred.
  • the target link is determined according to the optimal selection model among the non-conforming links, including: detecting that the target application class does not meet the exclusive requirements. Whether the bandwidth of the link mode meets the bandwidth requirements of the target application category; under the condition that the bandwidth of the target application category that does not conform to the link mode meets the bandwidth requirements of the target application category, the optimal model is selected according to the difference among the non-compliant links Determine the target link.
  • the method further includes: when the target application class exclusively occupies the bandwidth that does not conform to the link mode does not satisfy the bandwidth requirement of the target application class If the bandwidth requirements of the target application category are met, an alarm will be generated.
  • the candidate policy configuration includes a quality of service configuration
  • the control device acquires the candidate policy configuration, including the following sub-steps 10135 to 10136.
  • the priority of each application category provides a sequence for acquiring candidate policy configurations of each application category, and subsequent steps will sequentially acquire candidate policy configurations of each application category according to the priority of each application category.
  • the bandwidth requirements of each application category are determined based on the first KPI data. For example, when the data difference index meets the policy recommendation condition, that is, when a recommendation trigger signal is detected, the control device performs the step of determining the application category corresponding to the first KPI data and the bandwidth requirements of each application category.
  • the bandwidth model is a recommended model that provides optional policy configuration based on bandwidth occupancy to ensure the quality of key applications.
  • the bandwidth model estimates the bandwidth occupancy according to the characteristics of different application categories, optimizes the link bandwidth occupancy, and obtains the policy configuration.
  • the bandwidth model may be preset based on experience, or may be adjusted according to actual needs, which is not limited in this embodiment of the present application.
  • the bandwidth model used is as follows: For audio applications, the traffic is estimated to increase by 20%, and when the total traffic on the link occupies more than 50% of the bandwidth, QoS is enabled to ensure bandwidth occupation; for video applications, When the estimated traffic increases by 30%, and the total traffic on the link occupies more than 50% of the bandwidth, enable QoS to ensure bandwidth occupation; for enterprise business applications, the estimated traffic increases by 5%, and the total traffic on the link occupies more than 50% of the bandwidth. At 50%, enable QoS to ensure bandwidth occupancy; for data applications, no protection.
  • control device further includes: delivering the candidate policy configuration to the network device as the target policy configuration of the network device.
  • FIG. 4 shows an architecture diagram of a network management system provided by an embodiment of the present application.
  • the network management system provided in this embodiment includes: a controller, a display interface, a route reflector (RR), an access router (AR) 1 to 4, a multi-protocol label switching ( multi-protocol label switching, MPLS) links 1 to 2, Internet (Internet) links, and storage devices.
  • the AR1 device to the AR4 device are respectively deployed at site #1 to site #4.
  • the AR device is used to continuously collect KPIs from the live network and report them to the controller side through the device data upload channel. After the controller obtains the target policy configuration, the AR device is further configured to receive the target policy configuration through the controller data delivery channel, and process tasks according to the target policy configuration.
  • the AR device is further configured to receive the target policy configuration through the RR device control channel, where the target policy configuration is obtained by the controller and delivered to the RR device, which is further delivered to the AR device by the RR device.
  • the AR device is connected to an alternative link through a site routing domain connectivity channel, and the alternative link refers to a link that the AR device can use when sending service data to the next hop.
  • the AR1 device is connected to the MPLS1 link and the Internet link through the site routing domain connectivity channel, that is, when AR1 sends service data to the next hop, it can be transmitted through one or both of the MPLS1 link and the Internet link. .
  • AR2 devices are connected to MPLS1 links, MPLS2 links, and Internet links through the site routing domain connectivity channel, that is, when AR2 sends service data to the next hop, it can pass through the MPLS1 link, MPLS2 link, and Internet link.
  • One or more links for transmission are possible.
  • the MPLS link is a technology that uses labels to guide the high-speed and efficient transmission of data on an open communication network.
  • the MPLS link has the characteristics of high efficiency, safety and reliability, but high cost.
  • the Internet link is a public broadband Internet link. Compared with the MPLS link, it has the characteristics of lower cost but lower network quality.
  • the controller is used to acquire the candidate policy configuration of the network device; acquire the candidate policy configuration gain based on the candidate policy configuration; make the display interface display the candidate policy configuration gain.
  • the controller is used to obtain the first KPI data of the AR device; compare the first KPI data with the second KPI data corresponding to the historical recommendation result, and obtain the data difference index based on the comparison result; when the data difference index meets the policy recommendation condition Get candidate policy configurations.
  • the controller is further configured to deliver the candidate policy configuration to the AR device as the target policy configuration of the AR device, or the controller is further configured to obtain a user confirmation result for the candidate policy configuration; obtain the target policy configuration of the AR device based on the user confirmation result ;Deliver the target policy configuration to the AR device.
  • the controller is further configured to display the candidate strategy configuration and the candidate strategy configuration gain on the display interface, and obtain the user confirmation result fed back by the display interface.
  • the controller includes four modules: a data aggregation module, a tuning engine module, a recommendation model module, and a recommendation engine module.
  • the data aggregation module is used to obtain the first KPI data of the AR device;
  • the tuning engine module is used to compare the first KPI data and the second KPI data corresponding to the historical recommendation result, and obtain the data difference index based on the comparison result, Determine whether the data difference index satisfies the policy recommendation condition;
  • the recommendation engine module is used to respond to meeting the policy recommendation condition, determine the bandwidth requirements of each application category based on the first KPI data, and obtain candidate policy configurations based on the bandwidth requirements of each application category.
  • the strategy configuration obtains the candidate strategy configuration gain, so that the display interface displays the candidate strategy configuration gain.
  • the recommendation engine module is further configured to acquire the target policy configuration of the AR device based on the candidate policy configuration.
  • the recommendation engine module is configured to directly use the candidate policy configuration as the target policy configuration of the AR device, or the recommendation engine module is configured to determine the target policy configuration of the network device based on the user confirmation result of the candidate policy configuration based on the user confirmation result.
  • the recommendation model module is used to provide a recommendation model when the recommendation engine module obtains the policy configuration.
  • the storage device is used to store the KPI processed by the controller, and provide the controller with the stored KPI as the first KPI data.
  • the controller obtains the first KPI data of the AR device, it needs to process the KPI reported by the AR device, store the processed KPI in the storage device, and periodically retrieve the KPI from the storage device.
  • the KPI is collected as the first KPI data of the AR device.
  • the controller collects KPIs from the storage device, the controller can collect the KPIs uniformly and then send them to different functional modules inside the controller, or the different functional modules inside the controller can collect data from the storage device by themselves. This embodiment of the present application does not limit this.
  • the storage device is directly deployed in the controller, and for the sake of simplicity and readability of the illustration, the cloud storage device is omitted in FIG. 4 .
  • the display interface in FIG. 4 is used to display the candidate strategy configuration gains obtained by the controller.
  • the display interface is further configured to display the candidate strategy configuration corresponding to the candidate strategy configuration gain.
  • the display interface can directly display the candidate strategy configuration and the candidate strategy configuration gain received from the controller to the user, or can save the candidate strategy configuration and the candidate strategy configuration gain received from the controller, after receiving the user's query instruction Then, the candidate policy configuration and the candidate policy configuration gain are displayed to the user.
  • the display interface is further configured to obtain a user confirmation result based on the displayed candidate strategy configuration and the candidate strategy configuration gain, and then feed it back to the controller.
  • the user confirmation result includes the policy configuration selected by the user among the multiple candidate policy configurations, or the policy configuration obtained after the candidate policy configuration is modified.
  • the user can select the desired policy configuration from the candidate policy configurations displayed on the display interface, and can also flexibly adjust the existing candidate policy configurations according to actual needs to generate the adjusted policy configuration.
  • FIG. 5 shows a schematic diagram of a data aggregation module included in a network management system provided by an embodiment of the present application.
  • the data aggregation module is deployed in the control device, and is used to acquire the first KPI data of the network device.
  • the data aggregation module includes: a data receiving unit, a data preprocessing unit, a data modeling unit, and a data processing unit.
  • the data receiving unit is used to receive the KPI reported by the network device; aggregate the received KPI, decrypt and convert the received KPI to obtain the aggregated KPI; and send the aggregated KPI to the data preprocessing unit.
  • the data preprocessing unit is used for receiving the aggregated KPIs; preprocessing the aggregated KPIs; and sending the preprocessed KPIs to the data processing unit.
  • the preprocessing process includes data cleaning and null and outlier handling.
  • the data model unit is used to store and provide definition information to the data processing unit.
  • the definition information includes the definition of data storage granularity, type and duration.
  • the data processing unit is used to receive the preprocessed KPIs and the definition information; fuse and classify the preprocessed KPIs according to the definition information to obtain the processed KPIs; and store the processed KPIs in the storage device.
  • the KPI data processed by the data processing unit and saved to the storage device is the first KPI data collected by the control device in the subsequent process.
  • FIG. 6 shows a schematic diagram of an tuning engine module included in a network management system provided by an embodiment of the present application.
  • the tuning engine module is deployed in the control device and is used to compare the first KPI data and the second KPI data corresponding to the historical recommendation results, obtain a data discrepancy index based on the comparison result, and determine whether the data discrepancy index satisfies the policy. recommended conditions.
  • the tuning engine module includes a data acquisition unit, a data preprocessing unit, a memorandum unit, a data comparison unit, a business rule unit, a recommendation suppression unit, and a data processing unit.
  • the data collection unit is used for collecting the first KPI data from the storage device; and sending the first KPI data to the data preprocessing unit.
  • the data preprocessing unit is configured to receive the first KPI data; preprocess the first KPI data to obtain the preprocessed first KPI data; and send the preprocessed first KPI data to the data comparison unit.
  • the preprocessing process includes: unifying the first KPI data into a standard format.
  • the memorandum unit is used to store the historical recommendation result; and send the KPI data corresponding to the historical recommendation result as the second KPI data to the data comparison unit.
  • the historical recommendation result may be the last time the policy recommendation condition was satisfied.
  • the memorandum unit is further configured to receive the current first KPI data returned by the data processing unit when the data processing unit determines that the policy recommendation conditions are met, and generate new historical recommendation results and second KPI data for the next tuning engine detection Whether the policy recommendation conditions are met.
  • the data comparison unit is configured to receive the preprocessed first KPI data and the second KPI data corresponding to the historical recommendation result; compare the difference between the two to generate a data difference index; and send the data difference index to the data processing unit.
  • the business rules unit is used for storing business rules and sending the business rules to the data processing unit.
  • the business rules are a series of rules formulated for the process of determining whether the policy recommendation conditions are met.
  • the business rules may include but are not limited to: initial recommendation trigger timing and tuning period.
  • the initial recommendation trigger timing specifies the timing for determining whether the policy recommendation condition is met for the first time
  • the tuning period specifies the time period for determining whether the policy recommendation condition is met.
  • the recommendation suppression unit is used to generate a recommendation suppression value based on the historical recommendation trigger information; and send the recommendation suppression value to the data processing unit.
  • the recommendation suppression unit is further configured to receive information such as the current time and the current first KPI data returned by the data processing unit when the data processing unit determines that the policy recommendation condition is satisfied.
  • the data processing unit is used to receive data difference indicators, business rules, and recommendation suppression values; based on the data difference indicators, business rules, and recommendation suppression values, determine whether the policy recommendation conditions are met; if the policy recommendation conditions are met, generate a recommendation trigger Signal; send recommendation trigger signal to recommendation engine.
  • the data processing unit is further configured to send the current time and the current first KPI data to the memorandum unit and the recommendation suppression unit when it is determined that the policy recommendation condition is satisfied, for the next time the tuning engine detects whether the policy is satisfied or not. Policy recommendation conditions.
  • FIG. 7 shows a schematic diagram of a recommendation engine module included in a network management system provided by an embodiment of the present application.
  • the recommendation engine module is configured to determine the bandwidth requirements of each application category based on the first KPI data when the policy recommendation conditions are met; obtain candidate policy configurations based on the bandwidth requirements of each application category; obtain candidate policies based on the candidate policy configurations Configuration gain, so that the display interface displays the candidate policy configuration gain; based on the user confirmation result, the target policy configuration of the AR device is obtained.
  • the recommendation engine module includes: a data acquisition unit, a data preprocessing unit, a data analysis unit, a recommendation result cache unit, a gain model unit, and a recommendation result management unit.
  • the data collection unit is configured to receive a recommendation trigger signal sent by the tuning engine when the policy recommendation conditions are met; in response to the recommendation trigger signal, start the recommendation engine to subsequently determine the bandwidth requirements of each application category.
  • the data collection unit is further configured to collect the first KPI data from the storage device, and send the first KPI data to the data preprocessing unit.
  • the data preprocessing unit is used for preprocessing the first KPI data; and sending the preprocessed first KPI data to the data analysis unit.
  • the preprocessing process includes: unifying the first KPI data into a standard format.
  • the data analysis unit is used to receive the first KPI data after preprocessing; obtain the application category corresponding to the first KPI data and the bandwidth requirements of each application category based on the preprocessed first KPI data; obtain the priority of each application category; According to the bandwidth requirements of the categories, the candidate policy configurations of each application category are sequentially obtained according to the priority of each application category; the candidate policy configurations are cached in the recommendation result cache unit.
  • the data analysis unit is further configured to receive a recommendation model sent by the recommendation model module, wherein the recommendation model is used to generate a candidate policy configuration, and the recommendation model includes but is not limited to any one or more of the following models: application quality model, The intent model, the best-in-the-difference model, and the bandwidth model.
  • the recommendation result cache unit is used to cache the candidate policy configuration; send the candidate policy configuration to the recommendation result management unit.
  • the gain model unit is used to store the gain model; send the gain model to the recommendation result management unit.
  • the gain model is a calculation model used to calculate the expected gain index of the system.
  • the expected gain index includes: expected quality gain and expected link occupancy rate of each application in the whole system.
  • the recommendation result management unit is used to receive the candidate strategy configuration and the gain model; based on the candidate strategy configuration, according to the gain model, calculate the expected gain index of the system after the different strategy recommendation results are issued, and obtain the candidate strategy configuration gain;
  • the policy configuration gain is sent to the display interface for display; the user confirmation result for the candidate policy configuration fed back by the display interface is obtained.
  • the user confirmation result fed back by the display interface includes a policy configuration selected by the user among the multiple candidate policy configurations, or a policy configuration obtained after the user modifies the candidate policy configuration.
  • the user can select the desired policy configuration from the candidate policy configurations displayed on the display interface, and can also flexibly adjust the existing candidate policy configurations according to actual needs to generate the adjusted policy configuration.
  • the recommendation result management unit may directly use the candidate policy configuration as the target policy configuration of the network device, or may obtain the target policy configuration of the network device based on the user confirmation result.
  • the recommendation result management unit is further configured to, after acquiring the target policy configuration of the network device, deliver the target policy configuration to the network device to control the operation of the network device.
  • FIG. 8 shows a schematic diagram of an interaction flow between a control device and a display interface included in a network management system provided by an embodiment of the present application.
  • the interaction process is performed through the control device and the display interface.
  • the interaction process between the control device and the display interface includes: the control device pushes the candidate strategy configuration and the candidate strategy configuration gain to the display interface; the display interface receives the candidate strategy configuration and the candidate strategy configuration gain and displays it to the user;
  • the query details instruction sends a query details request to the control device.
  • the user can issue a query details command by clicking on the page; the control device receives the query details request, and pushes the candidate policy configuration details to the display interface; the display interface receives the candidate policy configuration details, and The candidate policy configuration is modified based on the modification configuration instruction issued by the user, and the adjusted policy configuration is sent to the control device; the control device receives the adjusted policy configuration and sends the modification status prompt to the display interface; the display interface receives the modification status prompt , based on the user's one-click confirmation, feedback the user confirmation result to the control device; based on the user confirmation result, the control device takes the adjusted policy configuration as the target policy configuration, and delivers it to the network device side, and then pushes the policy delivery status prompt to the display interface.
  • FIG. 9 shows a schematic diagram of an interaction flow between a control device and a display interface included in a network management system provided by an embodiment of the present application.
  • the interaction process is performed through the control device and the display interface.
  • the interaction process between the control device and the display interface includes: the control device pushes the candidate policy configuration, the candidate policy configuration gain, and the policy delivery status prompt to the display interface; the display interface receives the candidate policy configuration and the candidate policy configuration gain and displays it to the user.
  • the control device directly delivers the obtained candidate policy configuration to the network device for network management, and only displays the candidate policy configuration and the candidate policy configuration gain to the user on the display interface.
  • FIG. 10 shows a schematic diagram of a process for acquiring a candidate policy configuration provided by an embodiment of the present application.
  • the control device obtains the bandwidth requirements of each application category based on the first KPI data.
  • the application categories corresponding to the first KPI data in this embodiment include: Audio, video, enterprise business and data.
  • the control device acquires the application classification priorities.
  • the application classification priorities in this embodiment are (from high to low): audio, video, enterprise service, and data.
  • the control device Based on the bandwidth requirements of each application category, the control device sequentially obtains the candidate policy configurations of each application category according to the priority of each application category.
  • the process of obtaining the audio routing configuration is as follows: : The control device first divides the existing 6 candidate links into the links that meet the above thresholds and those that do not meet the above thresholds according to the delay, jitter and packet loss rate thresholds determined by the application quality model corresponding to the audio, as shown in the figure , 1, 2, and 3 are in line with the link, 4, 5, and 6 are in the non-conformity link; then determine the routing configuration for the audio according to the following four possible situations.
  • Scenario 1 Calculation of the 1, 2, and 3 links exclusively conforming to the link mode, that is, if the "audio" transmission exclusively occupies a conforming link, find a link that meets the audio bandwidth requirement. If a satisfying link can be found, continue to execute case 1, as shown by arrow 1 in the figure, in this embodiment, it is calculated that in the exclusive conforming link mode, links 1 and 3 satisfy the audio bandwidth requirement (link 2 does not satisfy the audio bandwidth requirement). and excluded), take 1 and 3 as optional links, and then further filter according to the intent model, get link 1 as the target link, that is, the link that transmits audio, and finally generate the audio routing configuration based on link 1, The process of acquiring the audio routing configuration ends. If a satisfying link cannot be found, then execute Case 2.
  • Scenario 2 After performing the exclusive calculation on links 1, 2, and 3 in accordance with the link mode, it is found that no link can meet the audio bandwidth requirement (that is, the first case cannot be executed), then load balancing for links 1, 2, and 3. Mode calculation, that is, split the "audio” and assign it to different links for common transmission, and find the link that meets the audio bandwidth requirements at this time. If a link can be found, continue to execute the second case, as shown by arrow 2 in the figure As shown, in this embodiment, it is calculated that in the balanced load mode, only when link 1 allocates 40% audio and link 3 allocates 60% audio, the audio bandwidth requirement can be met.
  • this routing scheme is used as the audio frequency
  • the target link (link 2 is excluded because it is not satisfied), and then generates an audio routing configuration based on link 1 and link 3, and the process of acquiring the audio routing configuration ends. If no satisfying link can be found, then execute the third case.
  • Scenario 3 After performing the exclusive calculation on links 1, 2, and 3 in accordance with the link mode, it is found that no link can meet the audio bandwidth requirement (that is, the first case cannot be executed), and then balance the load on links 1, 2, and 3. After the mode calculation, it is found that no link can meet the audio bandwidth requirements (that is, the second case cannot be executed), and the activation does not meet the links 4, 5, and 6. Perform the calculation of the exclusive non-conforming link mode for the 4, 5, and 6 links, that is, if the "audio" transmission exclusively occupies a non-conforming link, find a link that meets the audio bandwidth requirement.
  • Scenario 4 After performing the exclusive calculation on links 1, 2, and 3 that conforms to the link mode, it is found that no link can meet the audio bandwidth requirement (that is, the situation 1 cannot be executed), and the 1, 2, and 3 links are in a balanced load mode. After the calculation, it is found that no link can meet the audio bandwidth requirement (that is, the second case cannot be executed), and the exclusive calculation of the 4, 5, and 6 links does not conform to the link mode, and it is found that no link can meet the audio bandwidth requirement ( That is, the third case cannot be executed), then as shown in the figure, an alarm is given, and the process of acquiring the audio routing configuration ends.
  • Table 1 shows an example of a candidate policy configuration provided by the embodiment of the present application. As shown in Table 1, it shows the obtained candidate policy configuration for a network device of a site when the candidate link is dual link (MPLS and Internet).
  • the first column of Table 1 is the scenario description; the second column is the application type identified by the control device and the traffic size of the application type; the third and fourth columns are the quality of the MPLS link and the Internet link, respectively.
  • the values shown are the delay, jitter, packet loss rate of the link, currently occupied bandwidth and total bandwidth of the link; the fifth column is the obtained candidate policy configuration.
  • FIG. 11 shows a schematic structural diagram of a network management apparatus provided by an embodiment of the present application.
  • the network management apparatus includes: a first obtaining module 901, configured to obtain a candidate policy configuration gain based on a candidate policy configuration of the network device, where the candidate policy configuration gain is used to indicate the predicted effect of the candidate policy configuration relative to the effect of the current policy configuration of the network device. difference; the display module 902 is configured to display the candidate strategy configuration gain on the display interface.
  • the candidate policy configuration includes multiple policy configurations
  • the second obtaining module 903 is configured to determine the policy configuration confirmed by the user among the multiple policy configurations as the target policy configuration.
  • the candidate policy configuration includes multiple policy configurations
  • the user confirmation result includes the modified candidate policy configuration
  • the second obtaining module 903 is configured to determine the modified candidate policy configuration as the target policy configuration.
  • the second obtaining module 903 is further configured to use the candidate policy configuration as the target policy configuration.
  • the display module 902 is further configured to display the candidate policy configuration on the display interface.
  • the display module 902 is further configured to cause the display interface to display the gain of the candidate strategy configuration when the user queries the candidate strategy configuration on the display interface.
  • the network management apparatus further includes: a third obtaining module 904, configured to obtain the first key performance indicator KPI data of the network device; compare the first KPI data and the second KPI data corresponding to the historical recommendation results, based on the comparison As a result, the data discrepancy index is obtained, and the value of the data discrepancy index is positively correlated with the degree of difference between the first KPI data and the second KPI data; only when the data discrepancy index meets the policy recommendation condition, the candidate policy configuration is obtained.
  • a third obtaining module 904 configured to obtain the first key performance indicator KPI data of the network device; compare the first KPI data and the second KPI data corresponding to the historical recommendation results, based on the comparison As a result, the data discrepancy index is obtained, and the value of the data discrepancy index is positively correlated with the degree of difference between the first KPI data and the second KPI data; only when the data discrepancy index meets the policy recommendation condition, the candidate policy configuration is obtained.
  • the third obtaining module 904 is configured to obtain the bandwidth of the balanced load mode of the target application class, it is further configured to obtain the bandwidth of the target application class balanced load mode under the condition that the bandwidth of the target application class balanced load mode does not meet the bandwidth requirement of the target application class.
  • the road middle determines the target link according to the optimal selection model among the differences, and generates the route selection configuration of the target application category based on the target link.
  • the third obtaining module 904 is configured to detect whether the target application class exclusively occupies the bandwidth that does not conform to the link mode meets the bandwidth requirement of the target application class; the target application class exclusively occupies the bandwidth that does not conform to the link mode meets the bandwidth of the target application class Under the condition of the demand, the target link is determined according to the optimal selection model among the non-conforming links.
  • the third obtaining module 904 is configured to detect whether the target application class monopolizes the bandwidth that does not conform to the link mode meets the bandwidth requirement of the target application class, it is further configured to detect whether the target application class monopolizes the bandwidth that does not conform to the link mode does not satisfy the bandwidth requirement of the target application class. If the bandwidth requirements of the target application category are met, an alarm will be generated.
  • the candidate policy configuration includes a quality of service configuration
  • the third obtaining module 904 is configured to obtain the priority of each application category; based on the bandwidth requirement and bandwidth model of each application category, according to the priority of each application category
  • the QoS configuration of each application category is sequentially acquired, and the bandwidth model is used to indicate the bandwidth requirement of the corresponding application category.
  • the third obtaining module 904 is further configured to send the obtained candidate policy configuration to the second obtaining module 903 as the target policy configuration.
  • FIG. 12 shows a schematic structural diagram of a network management device 2000 provided by an exemplary embodiment of the present application.
  • the network management device 2000 shown in FIG. 12 is configured to perform the operations involved in the network management methods shown in the above-mentioned FIGS. 2-10 .
  • the network management device 2000 is, for example, a switch, a router, etc., and the network management device 2000 can be implemented by a general bus architecture.
  • the network management device 2000 includes at least one processor 2001 , memory 2003 and at least one communication interface 2004 .
  • the processor 2001 is, for example, a general-purpose central processing unit (central processing unit, CPU), a digital signal processor (digital signal processor, DSP), a network processor (network processor, NP), a graphics processing unit (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.
  • the processor 2001 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.
  • ASIC application-specific integrated circuit
  • PLD programmable logic device
  • the network management device 2000 further includes a bus.
  • the bus is used to transfer information between the components of the network management device 2000 .
  • the bus may be a peripheral component interconnect (PCI for short) bus or an extended industry standard architecture (EISA for short) bus or the like.
  • PCI peripheral component interconnect
  • EISA extended industry standard architecture
  • the bus can be divided into address bus, data bus, control bus and so on. For ease of representation, only one thick line is shown in FIG. 12, but it does not mean that there is only one bus or one type of bus.
  • the memory 2003 is, for example, a read-only memory (read-only memory, ROM) or other types of static storage devices that can store static information and instructions, or a random access memory (random access memory, RAM) or a memory device that can store information and instructions.
  • Other types of dynamic storage devices such as electrically erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disk storage, optical disks storage (including compact discs, laser discs, compact discs, digital versatile discs, Blu-ray discs, etc.), magnetic disk storage media, or other magnetic storage devices, or capable of carrying or storing desired program code in the form of instructions or data structures and capable of Any other medium accessed by a computer without limitation.
  • the memory 2003 exists independently, for example, and is connected to the processor 2001 through a bus.
  • the memory 2003 may also be integrated with the processor 2001 .
  • the communication interface 2004 uses any device such as a transceiver for communicating with other devices or a communication network, which may be Ethernet, a radio access network (RAN), or a wireless local area network (WLAN), or the like.
  • Communication interface 2004 may include a wired communication interface and may also include a wireless communication interface.
  • the communication interface 2004 may be an ethernet (ethernet) interface, a fast ethernet (FE) interface, a gigabit ethernet (GE) interface, an asynchronous transfer mode (ATM) interface, a wireless local area network ( wireless local area networks, WLAN) interfaces, cellular network communication interfaces, or a combination thereof.
  • the Ethernet interface can be an optical interface, an electrical interface, or a combination thereof.
  • the communication interface 2004 may be used for the network management device 2000 to communicate with other devices.
  • the processor 2001 may include one or more CPUs, such as CPU0 and CPU1 as shown in FIG. 12 .
  • Each of these processors can be a single-core (single-CPU) processor or a multi-core (multi-CPU) processor.
  • a processor herein may refer to one or more devices, circuits, and/or processing cores for processing data (eg, computer program instructions).
  • the network management device 2000 may include multiple processors, such as the processor 2001 and the processor 2005 shown in FIG. 12 .
  • processors can be a single-core processor (single-CPU) or a multi-core processor (multi-CPU).
  • a processor herein may refer to one or more devices, circuits, and/or processing cores for processing data (eg, computer program instructions).
  • the network management device 2000 may further include an output device and an input device.
  • the output device communicates with the processor 2001 and can display information in a variety of ways.
  • the output device may be a liquid crystal display (LCD), a light emitting diode (LED) display device, a cathode ray tube (CRT) display device, a projector, or the like.
  • the input device communicates with the processor 2001 and can receive user input in various ways.
  • the input device may be a mouse, a keyboard, a touch screen device, or a sensor device, or the like.
  • the memory 2003 is used to store the program code 2010 for executing the solutions of the present application
  • the processor 2001 can execute the program code 2010 stored in the memory 2003 . That is, the network management device 2000 can implement the network management method provided by the method embodiment through the processor 2001 and the program code 2010 in the memory 2003 .
  • One or more software modules may be included in the program code 2010 .
  • the processor 2001 itself may also store program codes or instructions for executing the solutions of the present application.
  • the network management device 2000 in this embodiment of the present application may correspond to the control device in each of the above network management method embodiments.
  • the processor 2001 in the network management device 2000 reads the instructions in the memory 2003, so that FIG. 12
  • the illustrated network management device 2000 is capable of performing all or part of the operations performed by the control device.
  • the processor 2001 is configured to send the candidate strategy configuration gain to the display interface through the communication interface, and the candidate strategy configuration gain is obtained through the candidate strategy configuration.
  • Other optional implementation manners are not repeated here for brevity.
  • the network management device 2000 in this embodiment of the present application may correspond to the display interface in each of the above method embodiments, and the processor 2001 in the network management device 2000 reads the instructions in the memory 2003 to make the network management shown in FIG. 12 .
  • the device 2000 can perform all or part of the operations performed by the display interface.
  • the processor 2001 is configured to receive, through the communication interface, the candidate strategy configuration gain sent by the control device to the display interface, where the candidate strategy configuration gain is obtained through the candidate strategy configuration.
  • Other optional implementation manners are not repeated here for brevity.
  • the network management device 2000 may also correspond to the network management device shown in FIG. 11 above, and each functional module in the network management device is implemented by software of the network management device 2000 .
  • the functional modules included in the network management apparatus are generated after the processor 2001 of the network management device 2000 reads the program code 2010 stored in the memory 2003 .
  • each step of the network management method shown in FIGS. 2-10 is completed by an integrated logic circuit of hardware in the processor of the network management device 2000 or an instruction in the form of software.
  • the steps of the methods disclosed in conjunction with the embodiments of the present application may be directly embodied as executed by a hardware processor, or executed by a combination of hardware and software modules in the processor.
  • the software modules may be located in random access memory, flash memory, read-only memory, programmable read-only memory or electrically erasable programmable memory, registers and other storage media mature in the art.
  • the storage medium is located in the memory, and the processor reads the information in the memory, and completes the steps of the above method in combination with its hardware, which will not be described in detail here to avoid repetition.
  • FIG. 13 shows a schematic structural diagram of a network management device 2100 provided by another exemplary embodiment of the present application.
  • the network management device 2100 shown in FIG. 13 is configured to perform all or part of the operations involved in the network management methods shown in FIGS. 2-10 above.
  • the network management device 2100 is, for example, a switch, a router, etc., and the network management device 2100 can be implemented by a general bus architecture.
  • the network management device 2100 includes: a main control board 2110 and an interface board 2130 .
  • the main control board is also called the main processing unit (MPU) or the route processor card (route processor card).
  • the main control board 2110 is used to control and manage various components in the network management device 2100 Management, equipment maintenance, protocol processing functions.
  • the main control board 2110 includes: a central processing unit 2111 and a memory 2112 .
  • the interface board 2130 is also referred to as a line processing unit (LPU), a line card (line card) or a service board.
  • the interface board 2130 is used to provide various service interfaces and realize data packet forwarding.
  • the service interface includes, but is not limited to, an Ethernet interface, a POS (packet over SONET/SDH) interface, etc.
  • the Ethernet interface is, for example, a flexible Ethernet service interface (flexible ethernet clients, FlexE Clients).
  • the interface board 2130 includes: a central processing unit 2131, a network processor 2132, a forwarding table entry memory 2134, and a physical interface card (PIC) 2133.
  • PIC physical interface card
  • the central processing unit 2131 on the interface board 2130 is used to control and manage the interface board 2130 and communicate with the central processing unit 2111 on the main control board 2110 .
  • the network processor 2132 is used to implement packet forwarding processing.
  • the form of the network processor 2132 may be a forwarding chip.
  • the forwarding chip may be a network processor (NP).
  • the forwarding chip may be implemented by an application-specific integrated circuit (ASIC) or a field programmable gate array (FPGA).
  • ASIC application-specific integrated circuit
  • FPGA field programmable gate array
  • the network processor 2132 is configured to forward the received message based on the forwarding table stored in the forwarding table entry memory 2134.
  • the message is sent to the CPU (such as the central processing unit 2131) processing; if the destination address of the message is not the address of the network management device 2100, the next hop and outgoing interface corresponding to the destination address are found from the forwarding table according to the destination address, and the message Forwarding to the outbound interface corresponding to the destination address.
  • the processing of the uplink message may include: processing of the incoming interface of the message, and forwarding table lookup; the processing of the downlink message may include: forwarding table lookup, and so on.
  • the central processing unit can also perform the function of a forwarding chip, for example, software forwarding is implemented based on a general-purpose CPU, so that a forwarding chip is not required in the interface board.
  • the physical interface card 2133 is used to realize the interconnection function of the physical layer, the original traffic enters the interface board 2130 through this, and the processed packets are sent from the physical interface card 2133 .
  • the physical interface card 2133 is also called a daughter card, which can be installed on the interface board 2130, and is responsible for converting the photoelectric signal into a message, and after checking the validity of the message, it is forwarded to the network processor 2132 for processing.
  • the central processing unit 2131 can also perform the functions of the network processor 2132 , such as implementing software forwarding based on a general-purpose CPU, so that the network processor 2132 is not required in the physical interface card 2133 .
  • the network management device 2100 includes multiple interface boards.
  • the network management device 2100 further includes an interface board 2140.
  • the interface board 2140 includes: a central processing unit 2141, a network processor 2142, a forwarding table entry storage 2144, and a physical interface card 2143 .
  • the functions and implementation manners of the components in the interface board 2140 are the same as or similar to those of the interface board 2130, and will not be repeated here.
  • the network management device 2100 further includes a switch fabric board 2120 .
  • the switch fabric unit 2120 may also be referred to as a switch fabric unit (switch fabric unit, SFU).
  • SFU switch fabric unit
  • the switching network board 2120 is used to complete data exchange between the interface boards.
  • the interface board 2130 and the interface board 2140 can communicate through the switch fabric board 2120 .
  • the main control board 2110 is coupled with the interface board.
  • the main control board 2110, the interface board 2130, the interface board 2140, and the switch fabric board 2120 are connected to the system backplane through the system bus to realize intercommunication.
  • an inter-process communication (IPC) channel is established between the main control board 2110 and the interface board 2130 and the interface board 2140, and the main control board 2110 and the interface board 2130 and the interface board 2140 The communication is carried out through the IPC channel.
  • IPC inter-process communication
  • the network management device 2100 includes a control plane and a forwarding plane
  • the control plane includes the main control board 2110 and the central processing unit 2111
  • the forwarding plane includes various components that perform forwarding, such as the forwarding entry storage 2134, the physical interface card 2133 and the network processor 2132.
  • the control plane performs functions such as routers, generating forwarding tables, processing signaling and protocol packets, and configuring and maintaining the status of network devices.
  • the control plane issues the generated forwarding tables to the forwarding plane.
  • the network processor 2132 controls the The following forwarding table forwards the packets received by the physical interface card 2133 by looking up the table.
  • the forwarding table issued by the control plane may be stored in the forwarding table entry storage 2134 . In some embodiments, the control plane and forwarding plane may be completely separate and not on the same network device.
  • main control boards there may be one or more main control boards, and when there are multiple main control boards, they may include the main main control board and the backup main control board.
  • the network management device can have at least one switching network board, and the switching network board realizes data exchange between multiple interface boards, providing large-capacity data exchange and processing capabilities. Therefore, the data access and processing capabilities of the network management device of the distributed architecture are greater than those of the network management device of the centralized architecture.
  • the network management device can also be in the form of only one board, that is, there is no switching network board, and the functions of the interface board and the main control board are integrated on this board.
  • the central processing unit on the control board can be combined into a central processing unit on this board to perform the superimposed functions of the two.
  • This form of network management equipment has low data exchange and processing capabilities (for example, low-end switches or routers and other network devices).
  • the specific architecture used depends on the specific networking deployment scenario, and there is no restriction here.
  • the network management device 2100 corresponds to the network management apparatus shown in FIG. 11 and applied to the control device. In some embodiments, the network management device 2100 also corresponds to the network management device shown in FIG. 11 and applied to the control device. In some embodiments, the first acquisition module 901 and the display module 902 in the network management device shown in FIG. 11 are equivalent to the physical interface card 2133 in the network management device 2100 ; the second acquisition module 903 and the third acquisition module 904 are equivalent The CPU 2111 or the network processor 2132 in the network management device 2100.
  • an embodiment of the present application further provides a network management system, where the system includes a control device and a display interface.
  • the control device is the network management device 2000 shown in FIG. 12 or the network management device 2100 shown in FIG. 13
  • the display interface is the network management device 2000 shown in FIG. 12 or the network management device 2100 shown in FIG. 13 .
  • An embodiment of the present application also provides a communication apparatus, the apparatus includes: a transceiver, a memory, and a processor.
  • the transceiver, the memory and the processor communicate with each other through an internal connection path, the memory is used for storing instructions, and the processor is used for executing the instructions stored in the memory to control the transceiver to receive signals and control the transceiver to send signals , and when the processor executes the instructions stored in the memory, the processor is made to execute the network management method required to be executed by the control device.
  • An embodiment of the present application also provides a communication apparatus, the apparatus includes: a transceiver, a memory, and a processor.
  • the transceiver, the memory and the processor communicate with each other through an internal connection path, the memory is used for storing instructions, and the processor is used for executing the instructions stored in the memory to control the transceiver to receive signals and control the transceiver to send signals , and when the processor executes the instructions stored in the memory, the processor executes the network management method required to be executed by the display interface.
  • processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (digital signal processing, DSP), application specific integrated circuits (application specific integrated circuits, ASIC), field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.
  • a general purpose processor may be a microprocessor or any conventional processor or the like. It should be noted that the processor may be a processor supporting an advanced RISC machine (ARM) architecture.
  • ARM advanced RISC machine
  • the above-mentioned memory may include read-only memory and random access memory, and provide instructions and data to the processor.
  • the memory may also include non-volatile random access memory.
  • the memory may also store device type information.
  • the memory may be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory.
  • the non-volatile memory may be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically programmable Erase programmable read-only memory (electrically EPROM, EEPROM) or flash memory.
  • Volatile memory may be random access memory (RAM), which acts as an external cache. By way of example and not limitation, many forms of RAM are available.
  • SRAM static RAM
  • DRAM dynamic random access memory
  • SDRAM synchronous dynamic random access memory
  • double data rate synchronous dynamic random access Memory double data date SDRAM, DDR SDRAM
  • enhanced synchronous dynamic random access memory enhanced SDRAM, ESDRAM
  • synchronous link dynamic random access memory direct memory bus random access memory
  • direct rambus RAM direct rambus RAM
  • An embodiment of the present application further provides a computer-readable storage medium, where at least one instruction is stored in the storage medium, and the instruction is loaded and executed by a processor to implement any one of the network management methods described above.
  • Embodiments of the present application also provide a computer program (product), which, when the computer program is executed by a computer, can cause a processor or computer to execute each step and/or process of the corresponding network management method in the above method embodiments.
  • An embodiment of the present application further provides a chip, including a processor, configured to call and execute an instruction stored in the memory from a memory, so that a communication device installed with the chip executes the network management method in the above aspects.
  • An embodiment of the present application further provides another chip, including: an input interface, an output interface, a processor, and a memory, wherein the input interface, the output interface, the processor, and the memory are connected through an internal connection path, and the The processor is configured to execute the code in the memory, and when the code is executed, the processor is configured to execute the network management method in the above aspects.
  • the above-mentioned embodiments it may be implemented in whole or in part by software, hardware, firmware or any combination thereof.
  • software it can be implemented in whole or in part in the form of a computer program product.
  • the computer program product includes one or more computer instructions.
  • the computer program instructions when loaded and executed on a computer, result in whole or in part of the processes or functions described herein.
  • the computer may be a general purpose computer, special purpose computer, computer network, or other programmable device.
  • the computer instructions may be stored in or transmitted from one computer readable storage medium to another computer readable storage medium, for example, the computer instructions may be downloaded from a website site, computer, server or data center Transmission to another website site, computer, server, or data center by wire (eg, coaxial cable, optical fiber, digital subscriber line) or wireless (eg, infrared, wireless, microwave, etc.).
  • the computer-readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that includes an integration of one or more available media.
  • the usable media may be magnetic media (eg, floppy disks, hard disks, magnetic tapes), optical media (eg, DVDs), or semiconductor media (eg, solid state disks), and the like.
  • the computer program product includes one or more computer program instructions.
  • the methods of the embodiments of the present application may be described in the context of machine-executable instructions, such as included in program modules executed in a device on a target's real or virtual processor.
  • program modules include routines, programs, libraries, objects, classes, components, data structures, etc. that perform particular tasks or implement particular abstract data structures.
  • the functionality of the program modules may be combined or divided among the described program modules.
  • Machine-executable instructions for program modules may be executed within local or distributed devices. In a distributed facility, program modules may be located in both local and remote storage media.
  • Computer program code for implementing the methods of the embodiments of the present application may be written in one or more programming languages. Such computer program code may be provided to a processor of a general purpose computer, special purpose computer or other programmable data processing apparatus such that the program code, when executed by the computer or other programmable data processing apparatus, causes the flowchart and/or block diagrams The functions/operations specified in are implemented.
  • the program code may execute entirely on the computer, partly on the computer, as a stand-alone software package, partly on the computer and partly on a remote computer or entirely on the remote computer or server.
  • computer program code or related data may be carried by any suitable carrier to enable a device, apparatus or processor to perform the various processes and operations described above.
  • suitable carriers include signals, computer-readable media, and the like.
  • Examples of signals may include electrical, optical, radio, acoustic, or other forms of propagated signals, such as carrier waves, infrared signals, and the like.
  • a machine-readable medium may be any tangible medium that contains or stores a program for or in connection with an instruction execution system, apparatus, or device.
  • the machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium.
  • Machine-readable media may include, but are not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or devices, or any suitable combination thereof. More detailed examples of machine-readable storage media include electrical connections with one or more wires, portable computer disks, hard disks, random access memory (RAM), read only memory (ROM), erasable programmable read only Memory (EPROM or flash memory), optical storage devices, magnetic storage devices, or any suitable combination thereof.
  • the disclosed systems, devices and methods may be implemented in other manners.
  • the device embodiments described above are only illustrative.
  • the division of the modules is only a logical function division. In actual implementation, there may be other division methods.
  • multiple modules or components may be combined or Integration into another system, or some features can be ignored, or not implemented.
  • the shown or discussed mutual coupling or direct coupling or communication connection may be indirect coupling or communication connection through some interfaces, devices or modules, and may also be electrical, mechanical or other forms of connection.
  • modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, that is, may be located in one place, or may be distributed to multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solutions of the embodiments of the present application.
  • each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist physically alone, or two or more modules may be integrated into one module.
  • the above-mentioned integrated modules can be implemented in the form of hardware, and can also be implemented in the form of software function modules.
  • the integrated modules are implemented in the form of software functional modules and sold or used as independent products, they may be stored in a computer-readable storage medium.
  • the technical solutions of the present application are essentially or part of contributions to the prior art, or all or part of the technical solutions can be embodied in the form of software products, and the computer software products are stored in a storage medium , including several instructions to cause a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods in the various embodiments of the present application.
  • the aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), magnetic disk or optical disk and other media that can store program codes .
  • first, second and other words are used to distinguish the same or similar items with basically the same function and function, and it should be understood that between “first”, “second” and “nth” There are no logical or timing dependencies, and no restrictions on the number and execution order. It will also be understood that, although the following description uses the terms first, second, etc. to describe various elements, these elements should not be limited by the terms. These terms are only used to distinguish one element from another. For example, a first image may be referred to as a second image, and, similarly, a second image may be referred to as a first image, without departing from the scope of various described examples. Both the first image and the second image may be images, and in some cases, may be separate and distinct images.
  • the size of the sequence number of each process does not mean the sequence of execution, and the execution sequence of each process should be determined by its function and internal logic, and should not be used in the embodiment of the present application.
  • the implementation process constitutes any limitation.
  • the meaning of the term “at least one” refers to one or more, and the meaning of the term “plurality” in this application refers to two or more.
  • a plurality of second messages refers to two or more more than one second message.
  • system and “network” are often used interchangeably herein.
  • determining B according to A does not mean that B is only determined according to A, and B may also be determined according to A and/or other information.
  • references throughout the specification to "one embodiment,” “an embodiment,” and “one possible implementation” mean that a particular feature, structure, or characteristic associated with the embodiment or implementation is included herein. in at least one embodiment of the application. Thus, appearances of "in one embodiment” or “in an embodiment” or “one possible implementation” in various places throughout this specification are not necessarily necessarily referring to the same embodiment. Furthermore, the particular features, structures or characteristics may be combined in any suitable manner in one or more embodiments.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Computer And Data Communications (AREA)
  • User Interface Of Digital Computer (AREA)
  • Data Exchanges In Wide-Area Networks (AREA)

Abstract

一种网络管理方法、装置、设备及计算机可读存储介质。在获取网络设备的候选策略配置后，预测候选策略配置的应用效果，并基于预测效果与当前网络配置的效果的差异获取候选策略配置增益，通过显示界面显示给用户。本申请能够使用户直观地获知候选策略配置对现网的适用性，提高了网络管理的效率，也提升了用户体验。

Description

网络管理方法、装置、设备及计算机可读存储介质
本申请要求于2021年2月5日提交的申请号为202110164951.2、发明名称为“网络管理方法、装置、设备及计算机可读存储介质”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请涉及网络通信领域，特别涉及网络管理方法、装置、设备及计算机可读存储介质。
背景技术
软件定义广域网络(software-defined wide area network，SDWAN)是将(software defined network，SDN)技术应用到广域网场景中所形成的一种服务。在SDWAN中，通过一些策略配置进行网络管理，能够有效地降低广域网的开支并提高网络连接灵活性。
以获取智能策略路由(smart policy routing，SPR)、服务质量(quality of service，QoS)以及前馈纠错(forward error correction，FEC)等三方面的策略配置为例，相关技术中，依据预设的策略模板和专家经验获取SDWAN中的SPR、QoS以及FEC等策略配置进行网络管理。由于进行网络管理时依赖于预设的策略模板以及专家经验，人工工作量大，导致网络管理的效率不高，用户体验不佳。
发明内容
本申请提出一种网络管理方法、装置、设备及计算机可读存储介质，用于提高网络管理的效率，提升用户体验。
第一方面，提供了一种网络管理方法，该方法包括：控制设备基于网络设备的候选策略配置获取候选策略配置增益，所述候选策略配置增益用于指示候选策略配置的预测效果相对网络设备的当前配置的效果的差异；所述控制设备使显示界面显示所述候选策略配置增益。
该技术方案提供的高效的网络管理方法，能够预测对网络设备生成的候选策略配置的应用效果，并将该预测效果与当前网络配置的效果的差异通过显示界面提供给用户，使用户能够一目了然地获悉候选策略配置的适用性，提高了网络管理的效率，提升了用户体验。
在一种可能的实现方式中，所述控制设备使所述显示界面显示所述候选策略配置增益之后，还包括：获取针对所述候选策略配置的用户确认结果，基于所述用户确认结果确定目标策略配置。通过在显示界面显示候选策略配置增益，并据此获取用户确认结果，基于用户确认结果获取目标策略配置，使得获取的目标策略配置更加符合用户的实际需求，使得网络管理的精确度更高。
在一种可能的实现方式中，所述候选策略配置包括多个策略配置，所述基于用户确认结果确定目标策略配置，包括：将所述多个策略配置中用户确认的策略配置确定为所述目标策略配置。进一步的，还可将确定的目标策略配置下发至网络设备进行配置。
在一种可能的实现方式中，所述候选策略配置包括多个策略配置，所述用户确认结果包 括修改后的候选策略配置，所述基于用户确认结果确定目标策略配置，包括：将修改后的候选策略配置确定为所述目标策略配置。用户确认结果可以是直接选择的策略配置，也可以是调整之后得到的策略配置，使得用户确认结果的灵活性更高。
在一种可能的实现方式中，所述网络管理方法，还包括：所述控制设备使所述显示界面显示所述候选策略配置。通过将候选策略配置以及所述候选策略配置增益在显示界面进行显示，使得显示的信息更为全面。
在一种可能的实现方式中，所述控制设备使所述显示界面显示所述候选策略配置增益，还包括：当用户在所述显示界面查询所述候选策略配置时，所述控制设备使所述显示界面显示所述候选策略配置增益。
在一种可能的实现方式中，所述网络管理方法，还包括：获取所述网络设备的第一关键性能指标KPI数据；比较所述第一KPI数据以及历史推荐结果所对应的第二KPI数据，基于比较结果获取数据差异性指标，所述数据差异性指标的值与所述第一KPI数据及所述第二KPI数据之间的差异程度正相关；仅当所述数据差异性指标满足策略推荐条件时，获取所述候选策略配置。通过基于数据差异性指标来确定是否满足策略推荐条件，以此来触发是否获取候选策略配置，使得网络管理的准确性更高，不会因为频繁获取候选策略配置而浪费资源。
在一种可能的实现方式中，所述候选策略配置包括选路配置，所述控制设备获取所述候选策略配置，包括：获取所述各个应用类别的优先级；基于目标应用类别以及应用质量模型，将备选链路分为符合链路与不符合链路，所述目标应用类别为所要获取的当前优先级应用类别，所述符合链路表示符合所述目标应用类别所对应的应用质量模型的链路，所述不符合链路表示不符合所述目标应用类别所对应的应用质量模型的链路，所述应用质量模型用于指示对应的应用类别的质量要求；获取目标应用类别独占符合链路模式的带宽；在所述目标应用类别独占符合链路模式的带宽满足目标应用类别的带宽需求的条件下，基于意图模型在所述符合链路中确定目标链路，基于所述目标链路生成所述目标应用类别的选路配置。通过基于意图模型进行选路配置，使得获取的候选策略配置更加符合用户需求，网络管理的准确性更高。
在一种可能的实现方式中，所述获取目标应用类别独占符合链路模式的带宽之后，还包括：在所述目标应用类别独占符合链路模式的带宽不满足所述目标应用类别的带宽需求的条件下，获取目标应用类别均衡负载模式的带宽；在所述目标应用类别均衡负载模式的带宽满足所述目标应用类别的带宽需求的条件下，在所述均衡负载模式对应的链路中确定目标链路，基于所述目标链路生成所述目标应用类别的选路配置。在独占符合链路模式的带宽不满足所述目标应用类别的带宽需求的条件下，基于均衡负载模式生成选路配置，进而保证性能。
在一种可能的实现方式中，所述获取目标应用类别均衡负载模式的带宽之后，还包括：在所述目标应用类别均衡负载模式的带宽不满足所述目标应用类别的带宽需求的条件下，在所述不符合链路中根据差中选优模型确定目标链路，基于所述目标链路生成所述目标应用类别的选路配置。在目标应用类别均衡负载模式的带宽不满足目标应用类别的带宽需求的条件下，根据差中选优模型确定目标链路，据此生成选路配置，进而保证性能。
在一种可能的实现方式中，所述在所述目标应用类别均衡负载模式的带宽不满足所述目标应用类别的带宽需求的条件下，在所述不符合链路中根据差中选优模型确定目标链路，包括：检测目标应用类别独占不符合链路模式的带宽是否满足所述目标应用类别的带宽需求； 在所述目标应用类别独占不符合链路模式的带宽满足所述目标应用类别的带宽需求的条件下，在所述不符合链路中根据差中选优模型确定目标链路，从而尽量保证性能。
在一种可能的实现方式中，所述检测目标应用类别独占不符合链路模式的带宽是否满足所述目标应用类别的带宽需求之后，还包括：在所述目标应用类别独占不符合链路模式的带宽不满足所述目标应用类别的带宽需求的条件下，进行告警。通过及时告警，提高网络管理效率。
在一种可能的实现方式中，所述候选策略配置包括服务质量配置，所述控制设备基于所述各个应用类别的带宽需求获取所述候选策略配置，包括：获取各个应用类别的优先级；基于各个应用类别的带宽需求以及带宽模型，按照所述各个应用类别的优先级依次获取所述各个应用类别的服务质量配置，所述带宽模型用于指示对应的应用类别的带宽要求。
第二方面，提供了一种网络管理装置，该装置包括：第一获取模块，用于基于网络设备的候选策略配置获取候选策略配置增益，所述候选策略配置增益用于指示所述候选策略配置的预测效果相对网络设备的当前策略配置的效果的差异；显示模块，用于使显示界面显示所述候选策略配置增益。
在一种可能的实现方式中，所述装置还包括：第二获取模块，用于在显示模块使显示界面显示所述候选策略配置增益之后，获取针对所述候选策略配置的用户确认结果，基于所述用户确认结果确定目标策略配置。
在一种可能的实现方式中，所述候选策略配置包括多个策略配置，所述第二获取模块用于将所述多个策略配置中用户确认的策略配置确定为所述目标策略配置。
在一种可能的实现方式中，所述候选策略配置包括多个策略配置，所述用户确认结果包括修改后的候选策略配置，所述第二获取模块用于将修改后的候选策略配置确定为所述目标策略配置。
在一种可能的实现方式中，所述显示模块，还用于使所述显示界面显示所述候选策略配置。
在一种可能的实现方式中，所述显示模块，还用于当用户在所述显示界面查询所述候选策略配置时，使所述显示界面显示所述候选策略配置增益。
在一种可能的实现方式中，所述装置还包括：第三获取模块，用于获取所述网络设备的第一关键性能指标KPI数据；比较所述第一KPI数据以及历史推荐结果所对应的第二KPI数据，基于比较结果获取数据差异性指标，所述数据差异性指标的值与所述第一KPI数据及所述第二KPI数据之间的差异程度正相关；仅当所述数据差异性指标满足所述策略推荐条件时，获取所述候选策略配置。
在一种可能的实现方式中，候选策略配置包括选路配置，第三获取模块，用于获取所述各个应用类别的优先级；基于目标应用类别以及应用质量模型，将备选链路分为符合链路与不符合链路，目标应用类别为所要获取的当前优先级应用类别，符合链路表示符合目标应用类别所对应的应用质量模型的链路，不符合链路表示不符合目标应用类别所对应的应用质量模型的链路，应用质量模型用于指示对应的应用类别的质量要求；获取所述目标应用类别独占符合链路模式的带宽；在所述目标应用类别独占符合链路模式的带宽满足目标应用类别的带宽需求的条件下，基于意图模型在所述符合链路中确定目标链路，基于所述目标链路生成 目标应用类别的选路配置。
在一种可能的实现方式中，第三获取模块，用于获取目标应用类别独占符合链路模式的带宽之后，还用于在所述目标应用类别独占符合链路模式的带宽不满足所述目标应用类别的带宽需求的条件下，获取目标应用类别均衡负载模式的带宽；在所述目标应用类别均衡负载模式的带宽满足所述目标应用类别的带宽需求的条件下，在均衡负载模式对应的链路中确定目标链路，基于所述目标链路生成目标应用类别的选路配置。
在一种可能的实现方式中，第三获取模块，用于获取目标应用类别均衡负载模式的带宽之后，还用于在所述目标应用类别均衡负载模式的带宽不满足所述目标应用类别的带宽需求的条件下，在所述不符合链路中根据差中选优模型确定目标链路，基于所述目标链路生成目标应用类别的选路配置。
在一种可能的实现方式中，第三获取模块，用于检测所述目标应用类别独占不符合链路模式的带宽是否满足所述目标应用类别的带宽需求；在所述目标应用类别独占不符合链路模式的带宽满足所述目标应用类别的带宽需求的条件下，在所述不符合链路中根据差中选优模型确定目标链路。
在一种可能的实现方式中，第三获取模块，用于检测目标应用类别独占不符合链路模式的带宽是否满足目标应用类别的带宽需求之后，还用于在所述目标应用类别独占不符合链路模式的带宽不满足所述目标应用类别的带宽需求的条件下，进行告警。
在一种可能的实现方式中，候选策略配置包括服务质量配置，第三获取模块，用于获取各个应用类别的优先级；基于各个应用类别的带宽需求以及带宽模型，按照所述各个应用类别的优先级依次获取各个应用类别的服务质量配置，所述带宽模型用于指示对应的应用类别的带宽要求。
第三方面，提供了一种网络管理设备，包括处理器及计算机程序，处理器执行计算机程序时，以使网络管理设备实现如上第一方面任一的网络管理方法。
第四方面，提供了一种计算机可读存储介质，其上存储有计算机程序，计算机程序被计算机执行时，实现如上第一方面任一的网络管理方法。
第五方面，提供了一种计算机程序产品，包括计算机程序，计算机程序被计算机执行时，实现如上第一方面任一的网络管理方法。
第六方面，提供了一种通信装置，该装置包括：收发器、存储器和处理器。其中，该收发器、该存储器和该处理器通过内部连接通路互相通信，该存储器用于存储指令，该处理器用于执行该存储器存储的指令，以控制收发器接收信号，并控制收发器发送信号，并且当该处理器执行该存储器存储的指令时，使得该处理器执行第一方面或第一方面的任一种可能的实施方式中的方法。
作为一种示例性实施例，处理器为一个或多个，存储器为一个或多个。
作为一种示例性实施例，存储器可以与处理器集成在一起，或者存储器与处理器分离设置。
在具体实现过程中，存储器可以为存储器，例如，只读存储器(read only memory，ROM)，其可以与处理器集成在同一块芯片上，也可以分别设置在不同的芯片上，本申请实施例对存储器的类型以及存储器与处理器的设置方式不做限定。
第七方面，提供了一种芯片，包括处理器，用于从存储器中调用并运行存储器中存储的指令，使得安装有芯片的通信设备执行上述第一方面或第一方面的任一种可能的实施方式中的方法。
第八方面，提供了另一种芯片，包括：输入接口、输出接口、处理器和存储器，输入接口、输出接口、处理器以及存储器之间通过内部连接通路相连，处理器用于执行存储器中的代码，当代码被执行时，处理器用于执行上述第一方面或第一方面的任一种可能的实施方式中的方法。
附图说明
图1是本申请实施例提供的一种网络管理方法的实施环境示意图；
图2是本申请实施例提供的一种网络管理方法的流程图；
图3是本申请实施例提供的一种获取候选策略配置的方法流程图；
图4是本申请实施例提供的一种网络管理系统的架构图；
图5是本申请实施例提供的一种网络管理系统所包括的数据汇聚模块的示意图；
图6是本申请实施例提供的一种网络管理系统所包括的调优引擎模块的示意图；
图7是本申请实施例提供的一种网络管理系统所包括的推荐引擎模块的示意图；
图8是本申请实施例提供的一种网络管理系统所包括的控制设备与显示界面交互流程示意图；
图9是本申请实施例提供的一种网络管理系统所包括的控制设备与显示界面交互流程示意图；
图10是本申请实施例提供的一种候选策略配置获取流程的示意图；
图11是本申请实施例提供的一种网络管理装置的结构示意图；
图12是本申请实施例提供的一种网络管理设备的结构示意图；
图13是本申请实施例提供的一种网络管理设备的结构示意图。
具体实施方式
为使本申请的目的、技术方案和优点更加清楚，下面将结合附图对本申请实施方式作进一步地详细描述。
SDWAN用于连接广阔地理范围的企业网络、数据中心、互联网应用及云服务，旨在帮助用户降低广域网的开支和提高网络连接灵活性。其中，网络管理是SDWAN中的重要环节。本申请实施例通过预测候选策略配置的应用效果，获取候选策略配置增益，并通过显示界面将候选策略配置增益展示给用户，使用户能够直观、便捷地确定候选配置增益的适用性，提升了网络管理的效率，进而提升用户体验。
本申请实施例提供的网络管理方法可以应用于图1所示的实施环境中。如图1所示，该实施环境包括网络设备101和控制设备102。可选地，网络设备101包括但不限于路由器、交换机、服务器等。在SDWAN中，网络设备101需要按照控制设备102下发的策略配置在网络中进行通信，同时网络设备101采集网络数据上报到控制设备102。控制设备102基于网络设备101上报的网络数据判断网络状态。其中，网络状态包括网络质量和网络业务的质量需求。如果控制设备102检测到当前的策略配置不再适用于当前的网络状态，则基于网络 数据生成可应用于网络设备101的候选策略配置，该网络数据可以用网络设备101的关键性能指标(key performance indication，KPI)数据表示。其中，网络设备的KPI数据用于反映当前网络设备及其组成网络的运行状态，该KPI数据所反映的运行状态包括但不限于：当前网络中的可用链路及可用链路的质量、当前网络设备待处理的应用类别、用户体验质量以及当前网络设备的策略配置等。
控制设备102生成候选策略配置后，再基于候选策略配置预测该候选策略配置下发到网络设备101后的应用效果，将候选策略配置的预测效果与网络设备101当前配置的效果之间的差异通过候选策略配置增益来进行指示，将候选策略配置增益发送至显示界面103进行显示。其中，显示界面103可以是控制设备102上的显示界面，也可以是控制设备102之外的其他设备的显示界面，而控制设备102将候选策略配置增益发送至该其他设备，由其他设备的显示界面103进行显示。可选地，控制设备102还可以基于用户在显示界面103查询候选策略配置，使显示界面显示候选策略配置增益。可选地，控制设备102还可使显示界面103显示候选策略配置。
控制设备102使显示界面103显示候选策略配置增益之后，还可以获取针对候选策略配置的用户确认结果，基于用户确认结果确定目标策略配置。例如，可以允许用户对显示界面103上显示的候选策略配置进行调整，并将调整后的策略配置反馈给控制设备102，控制设备102再将调整后的策略配置作为用户确认结果，据此获取目标策略配置。之后，控制设备102还可将目标策略配置下发到网络设备进行网络管理。
可选地，在使显示界面103显示候选策略配置增益之前或者之后，控制设备102还可以基于候选策略配置确定目标策略配置，并将该目标策略配置下发至网络设备进行网络管理。
可选地，显示界面103显示候选策略配置增益的方式，可以是通过可视化图像显示，也可以是文字描述，还可以是其他呈现方式，本申请实施例对此不做限制。
基于图1所示的实施环境，本申请实施例提供了一种网络管理方法。请参考图2，其示出了本申请实施例提供的一种网络管理方法的流程图。
步骤101，控制设备基于网络设备的候选策略配置获取候选策略配置增益。
在一种可能的实现方式中，控制设备基于网络设备的候选策略配置获取候选策略配置增益，包括：获取网络设备的候选策略配置；基于网络设备的候选策略配置，根据增益模型，计算不同候选策略配置下发之后的预测增益指标，得到候选策略配置增益。
在一种可能的实现方式中，控制设备获取网络设备的候选策略配置，包括但不限于：控制设备获取网络设备的第一KPI数据；控制设备比较第一KPI数据以及历史推荐结果所对应的第二KPI数据，基于比较结果获取数据差异性指标，数据差异性指标的值与第一KPI数据及第二KPI数据之间的差异程度正相关；仅当数据差异性指标满足策略推荐条件时，获取候选策略配置。关于获取候选策略配置的过程可参见后续图3所示的步骤1011至步骤1013，此处暂不赘述。
在获取网络设备的候选策略配置之后，控制设备基于网络设备的候选策略配置，根据增益模型，计算不同候选策略配置下发之后的预测增益指标，得到候选策略配置增益。其中，候选策略配置增益用于指示候选策略配置的应用效果和当前网络策略配置的效果之间的差异，可选地，候选策略配置增益可以为一个指标数值，用于指示候选策略配置的应用效果和当前 网络策略配置的效果的差异程度，候选策略配置增益也可以为指标的变化幅度，本申请实施例对此不做限定。
其中，增益模型是控制设备中预先存放的用于计算系统的预期增益指标的计算模型。可选地，预期增益指标包括：全系统各应用预期质量增益及预期链路占用率。示例性地，增益模型可以是健康度模型，健康度模型通过计算加权增益来评估应用增益和链路使用度增益。
步骤102，控制设备使显示界面显示候选策略配置增益。
可选地，控制设备可以使显示界面直接显示候选策略配置增益，也可以在用户在显示界面查询候选策略配置的情况下，控制设备使显示界面显示候选策略配置增益。可选地，控制设备还可以使显示界面显示候选策略配置。
控制设备使显示界面显示候选策略配置以及候选策略配置增益，包括但不限于：控制设备使候选策略配置以及候选配置增益直接在显示界面进行显示，或者，控制设备发送候选策略配置以及候选策略配置增益给显示界面，使显示界面记录候选策略配置以及候选策略配置增益，当显示界面接收用户查询候选策略配置消息，控制设备使候选策略配置以及候选策略配置增益在显示界面进行显示。
可选地，显示界面显示显示候选策略配置增益的方法包括但不限于如下几种：1、显示增益指标数值的前后对比表格；2、在一个时间坐标上，以增益指标时间序列显示增益指标随时间的变化；3、在一个时间坐标上，以变化幅度序列显示增益指标的变化幅度；4、显示基于指标维度和指标对应的等级的雷达图。本申请实施例对候选策略配置增益的显示方法不做限制，本领域内用于反映指标差异的显示方法都在本申请实施例的保护范围内。
可选地，控制设备使显示界面显示候选策略配置增益之后，还包括：获取针对候选策略配置的用户确认结果，基于用户确认结果确定目标策略配置。在一种可能的实现方式中，控制设备确定目标策略配置之后，还包括：将目标策略配置下发至网络设备。
关于获取针对候选策略配置的用户确认结果的方式，本申请实施例不进行限定，例如，基于使显示界面显示候选策略配置以及候选策略配置增益，获取显示界面反馈的用户确认结果。
其中，候选策略配置包括多个策略配置，基于用户确认结果确定目标策略配置包括但不限于如下两种情况。
情况一，将多个策略配置中用户确认的策略配置确定为目标策略配置。
情况二，将修改后的候选策略配置确定为目标策略配置。
用户可以在显示界面显示的候选策略配置中选择所需要的策略配置，也可以依据实际需求对已有候选策略配置进行灵活调整，生成调整之后得到的策略配置。
本申请实施例提供了一种高效的网络管理方法，能够预测对网络设备生成的候选策略配置的应用效果，并将该预测效果与当前网络配置的效果的差异通过显示界面提供给用户，使用户能够一目了然地获悉候选策略配置的适用性，提高了网络管理的效率，提升了用户体验。
此外，本申请实施例提供的网络管理方法还能够在多站点多链路多状态的情况下全自动地生成网络设备可实行的候选策略配置，该候选策略配置的生成过程，结合了现网的实时KPI数据，涵盖了应用质量模型、意图模型或差中选优模型、带宽模型，并进一步结合用户确认结果调整候选策略配置，得到更有针对性的策略配置，既提高了策略配置对现网状态的适应性，也减少了人工干预，降低了工作复杂程度，节约了网络维护的成本。
请参考图3，其示出了本申请实施例提供的一种获取候选策略配置的方法流程图。如图3所示，控制设备获取网络设备的候选策略配置，包括但不限于如下步骤1011至步骤1013。
1011、获取网络设备的第一KPI数据。
可选地，控制设备获取网络设备的第一KPI数据的过程包括但不限于控制设备接收网络设备上报的KPI数据，汇聚所接收的KPI数据，对汇聚之后的KPI数据进行处理，得到处理后的KPI数据。之后，该控制设备可对处理后的KPI数据进行存储，从存储后的KPI数据中采集网络设备的第一KPI数据。在一种可能的实现方式中，控制设备可以接收网络设备从现网中持续采集并主动上报至控制设备的KPI数据，控制设备也可以主动向网络设备采集并接收网络设备上传的KPI数据。此外，网络设备向控制设备发送的KPI数据还可以进行加密，则控制设备汇聚所接收的KPI数据后，对所接收的KPI数据进行解密和转换，得到汇聚后的KPI数据。可选地，控制设备对汇聚之后的KPI数据进行处理，包括但不限于数据清洗以及空值和异常值的处理。可选地，控制设备还可以基于定义信息对处理后的KPI数据进行融合和分类，得到处理后的KPI，定义信息包括但不限于对数据的存储粒度、种类和时长的定义。
本申请实施例不对控制设备存储处理后的KPI数据的方式进行限定，例如，控制设备可将处理后的KPI数据存储至存储设备，其中，存储设备可以直接部署于控制设备中，也可以将控制设备和存储设备分别部署于不同设备上，再通过网络进行通信。再有，控制设备可将处理后的KPI数据以不同的格式存储至存储设备对应的数据库中。由于处理后的KPI数据包含多种类型的数据，所以需要以不同的格式存储至存储设备对应的数据库中。可选地，控制设备定期从存放于存储设备的KPI数据中采集网络设备的第一KPI数据。
其中，网络设备的第一KPI数据用于反映当前网络设备及其组成网络的运行状态，该第一KPI数据所反映的运行状态包括但不限于：当前网络中的可用链路及可用链路的质量、当前网络设备待处理的应用类别、用户体验质量以及当前网络设备的策略配置等。
1012、比较第一KPI数据以及历史推荐结果所对应的第二KPI数据，基于比较结果获取数据差异性指标，数据差异性指标的值与第一KPI数据及第二KPI数据之间的差异程度正相关。
其中，控制设备比较第一KPI数据以及历史推荐结果所对应的第二KPI数据，获取数据差异性指标，包括但不限于：对第一KPI数据进行预处理，获得预处理后的第一KPI数据；比较预处理后的第一KPI数据与历史推荐结果所对应的第二KPI数据，生成数据差异性指标。
其中，预处理过程包括：将第一KPI数据统一成标准格式。由于第一KPI数据包含多种不同类型的数据，且以不同的格式保存在存储设备的对应数据库中，为了对第一KPI数据进行处理，要先将第一KPI数据统一成标准格式。例如，将第一KPI数据统一成链路带宽、丢包率和时延指标的标准格式，用于指示当前网络的质量。
可选地，历史推荐结果可以是上一次满足策略推荐条件的情况，将上一次满足策略推荐条件的情况所对应的KPI数据作为第二KPI数据，再比较预处理后的第一KPI数据与第二KPI数据，生成数据差异性指标。其中，数据差异性指标用于指示第一KPI数据与第二KPI数据的差异程度，数据差异性指标的值与差异程度可以是正相关的关系。数据差异性指标反映了网络设备及其组成网络当前状态与历史状态的差异，例如：第一KPI数据与第二KPI数据相同，控制设备判断网络设备及其组成网络当前状态比起历史状态没有发生变化。
1013、仅当数据差异性指标满足策略推荐条件时，获取候选策略配置。
在控制设备获取候选策略配置之前，还包括：控制设备确定数据差异性指标是否满足策略推荐条件。控制设备基于数据差异性指标确定数据差异性指标是否满足策略推荐条件，包括但不限于：基于历史推荐触发信息生成推荐压抑值；基于数据差异性指标、推荐压抑值以及业务规则确定数据差异性指标是否满足策略推荐条件；在满足策略推荐条件的情况下，生成推荐触发信号。
其中，业务规则是控制设备保存的对是否满足策略推荐条件的确定过程制定的一系列规则，业务规则可以包括但不限于：初始推荐触发时机和调优周期等。初始推荐触发时机指示了第一次确定是否满足策略推荐条件的时机，例如：当前网络设备及其组成网络在当前时刻刚完成升级更新，可以将当前时刻作为一种初始推荐触发时机。调优周期规定了确定是否满足策略推荐条件的时间周期，该调优周期可基于经验设置，也可以根据应用场景进行调整。
历史推荐触发信息是控制设备保存的过去每一次满足策略推荐条件的信息。可选地，历史推荐触发信息可以包括：过去每一次满足策略推荐条件的时间和当时所对应的KPI数据。推荐压抑值基于历史推荐触发信息生成，用以反映满足策略推荐条件的频率。例如：在一段参考长度的历史时间内，满足策略推荐条件的次数超出了设置的数量限度，此时基于历史推荐触发信息生成的推荐压抑值将会限制满足策略推荐条件。
推荐触发信号用于指示当前满足策略推荐条件，并触发控制设备的下一流程。可选地，在满足策略推荐条件的情况下，控制设备可以将此时的时间以及对应的第一KPI数据进行记录，并生成新的历史推荐触发信息和新的历史推荐结果。
其中，候选策略配置包括但不限于选路配置以及服务质量(quality of service，QoS)配置。可选地，选路配置可以是智能策略路由(smart policy routing，SPR)配置。
示例性地，候选策略配置包括选路配置，控制设备获取候选策略配置，包括如下10131至10134。
10131、获取各个应用类别的优先级。
各个应用类别的优先级为获取各个应用类别的候选策略配置提供了先后顺序，后续步骤将按照各个应用类别的优先级依次获取各个应用类别的候选策略配置。
10132、基于目标应用类别以及应用质量模型，将备选链路分为符合链路与不符合链路。其中，目标应用类别为所要获取的当前优先级应用类别，即在按照优先级的顺序依次为各个应用类别选路过程中，当前轮到的应用类别即为目标应用类别。符合链路表示符合目标应用类别所对应的应用质量模型的链路，不符合链路表示不符合目标应用类别所对应的应用质量模型的链路。
应用质量模型是一种基于应用质量提供可选策略配置的推荐模型，用于指示对应的应用类别的质量要求。可选地，应用质量模型将应用按照预设的优先级分类，并按照各个应用类别属性，依据业界标准及业务需求，确定的质量属性阈值。可选地，应用类别可以包括：音频、视频、企业业务以及数据，质量属性阈值可以包括：时延、抖动以及丢包率。可选地，应用质量模型可以基于经验预设，也可以根据实际需求调整，本申请实施例对此不做限定。
在一个示例中，所使用的应用质量模型如下所示：
优先级从高到低的依次为：音频类应用、视频类应用、企业业务类应用、数据类应用；对于音频类应用，质量阈值包括：延迟150毫秒(millisecond，ms)，抖动阈值30ms，丢包率1％；对于视频类应用，质量阈值包括：延迟150ms，抖动阈值20ms，丢包率1％；对于企 业业务类应用，质量阈值包括：延迟100ms，抖动阈值30ms，丢包率5％；对于数据类应用，质量阈值包括：延迟300ms，抖动阈值40ms，丢包率5％。
10133、获取目标应用类别独占符合链路模式的带宽。
10134、在目标应用类别独占符合链路模式的带宽满足目标应用类别的带宽需求的条件下，基于意图模型在符合链路中确定目标链路，基于目标链路生成目标应用类别的选路配置。
在一种可能的实现方式中，各个应用类别的带宽需求基于第一KPI数据确定。例如，控制设备在数据差异性指标满足策略推荐条件的情况下，即检测到推荐触发信号的情况下，执行确定第一KPI数据对应的应用类别以及各个应用类别的带宽需求的步骤。
其中，意图模型是一种基于用户意图提供可选策略配置的推荐模型，用于根据用户意图调整各个应用类别在多链路上的选路配置，以达到成本、质量或平衡的用户意图。可选地，意图模型包括成本意图模型，用以代表互联网链路的占用率最高；质量意图模型，用以代表应用的质量最优；平衡意图模型，用以代表成本与质量的平衡。可选地，意图模型可以基于经验预设，也可以根据实际需求调整，本申请实施例对此不做限定。
在一个示例中，所使用的意图模型如下所示：成本意图模型，所有应用优先选择互联网链路；质量意图模型，所有应用优先选择延迟最低链路；平衡意图模型，音频、视频、企业业务优先选择延迟最低链路，数据优先选择互联网链路。
可选地，获取目标应用类别独占符合链路模式的带宽之后，还包括：在目标应用类别独占符合链路模式的带宽不满足目标应用类别的带宽需求的条件下，获取目标应用类别均衡负载模式的带宽，其中，均衡负载模式指的是将目标应用平衡分摊到多个链路上进行协同传输；在目标应用类别均衡负载模式的带宽满足目标应用类别的带宽需求的条件下，在均衡负载模式对应的链路中确定目标链路，基于目标链路生成目标应用类别的选路配置。
可选地，获取目标应用类别均衡负载模式的带宽之后，还包括：在目标应用类别均衡负载模式的带宽不满足目标应用类别的带宽需求的条件下，在不符合链路中根据差中选优模型确定目标链路，基于目标链路生成目标应用类别的选路配置。
其中，差中选优模型是一种在应用质量无法保障的情况下，基于用户需求提供可选策略配置的推荐模型，用于在应用质量无法保证情况下调整各个应用类别在多链路上的选路配置，尽可能满足用户需求。可选地，差中选优模型包括：成本选优模型、质量选优模型以及平衡选优模型。可选地，差中选优模型可以基于经验预设，也可以根据实际需求调整，本申请实施例对此不做限定。在一个示例中，使用的差中选优模型如下所示：成本选优模型，所有应用优先选择延迟最低链路；质量选优模型，所有应用优先选择延迟最低链路；平衡选优模型，所有应用优先选择延迟最低链路。
可选地，在目标应用类别均衡负载模式的带宽不满足目标应用类别的带宽需求的条件下，在不符合链路中根据差中选优模型确定目标链路，包括：检测目标应用类别独占不符合链路模式的带宽是否满足所述目标应用类别的带宽需求；在目标应用类别独占不符合链路模式的带宽满足目标应用类别的带宽需求的条件下，在不符合链路中根据差中选优模型确定目标链路。
在一种可能的实现方式中，检测目标应用类别独占不符合链路模式的带宽是否满足目标应用类别的带宽需求之后，还包括：在目标应用类别独占不符合链路模式的带宽不满足所述目标应用类别的带宽需求的条件下，进行告警。
示例性地，候选策略配置包括服务质量配置，控制设备获取候选策略配置，包括如下10135至10136子步骤。
10135、获取各个应用类别的优先级。
各个应用类别的优先级为获取各个应用类别的候选策略配置提供了先后顺序，后续步骤将按照各个应用类别的优先级依次获取各个应用类别的候选策略配置。
10136、基于各个应用类别的带宽需求以及带宽模型，按照各个应用类别的优先级依次获取各个应用类别的服务质量配置。
在一种可能的实现方式中，各个应用类别的带宽需求基于第一KPI数据确定。例如，控制设备在数据差异性指标满足策略推荐条件的情况下，即检测到推荐触发信号的情况下，执行确定第一KPI数据对应的应用类别以及各个应用类别的带宽需求的步骤。
带宽模型是一种基于带宽占用提供可选策略配置的推荐模型，用于保证关键应用质量。带宽模型根据不同应用类别特点，估算带宽占用，同时优化链路带宽占用，得到策略配置。可选地，带宽模型可以基于经验预设，也可以根据实际需求调整，本申请实施例对此不做限定。
在一个示例中，使用的带宽模型如下所示：对于音频类应用，流量预估上浮20％，且所在链路总流量占据带宽比例超过50％时，启动QoS保证带宽占用；对于视频类应用，流量预估上浮30％，且所在链路总流量占据带宽比例超过50％时，启动QoS保证带宽占用；对于企业业务类应用，流量预估上浮5％，且所在链路总流量占据带宽比例超过50％时，启动QoS保证带宽占用；对于数据类应用，无保护。
可选地，控制设备获取网络设备的候选策略配置之后，还包括：将候选策略配置作为网络设备的目标策略配置下发至网络设备。
接下来，请参考图4，其示出了本申请实施例提供的一种网络管理系统的架构图。如图4所示，本实施例提供的网络管理系统包括：控制器、显示界面、路由反射器(route reflector，RR)、接入路由器(access router，AR)1至4、多协议标签交换(multi-protocol label switching，MPLS)链路1至2、互联网(Internet)链路以及存储设备。
图4中，AR1设备至AR4设备分别部署于站点(site)#1至站点#4。AR设备用于从现网中持续采集KPI，并通过设备数据上传通道上报给控制器侧。在控制器获得目标策略配置后，AR设备还用于通过控制器数据下发通道接收目标策略配置，并根据目标策略配置处理任务。
可选地，AR设备还用于通过RR设备控制通道接收目标策略配置，其中目标策略配置通过控制器获得，并下发给RR设备，再由RR设备进一步下发给AR设备。可选地，AR设备通过站点路由域连通通道与备选链路连接，备选链路指的是AR设备向下一跳发送业务数据时可以使用的链路。例如：AR1设备通过站点路由域连通通道与MPLS1链路和互联网链路连接，即为AR1向下一跳发送业务数据时可以通过MPLS1链路和互联网链路中的一条或两条链路进行传输。再例如：AR2设备通过站点路由域连通通道与MPLS1链路、MPLS2链路以及互联网链路连接，即AR2向下一跳发送业务数据时可以通过MPLS1链路、MPLS2链路以及互联网链路中的一条或多条链路进行传输。
其中，MPLS链路是一种在开放的通信网上利用标签引导数据高速且高效传输的技术， MPLS链路具有效率高、安全可靠但是成本高昂的特点。互联网链路是公共的宽带互联网链路，比起MPLS链路，具有成本低但是网络质量不高的特点。
控制器用于获取网络设备的候选策略配置；基于候选策略配置获取候选策略配置增益；使显示界面显示候选策略配置增益。控制器用于获取AR设备的第一KPI数据；比较第一KPI数据以及历史推荐结果所对应的第二KPI数据，基于比较结果获取数据差异性指标；在数据差异性指标满足策略推荐条件的情况下获取候选策略配置。
控制器还用于将候选策略配置作为AR设备的目标策略配置下发至AR设备，或者，控制器还用于获取针对候选策略配置的用户确认结果；基于用户确认结果获取AR设备的目标策略配置；将目标策略配置下发至AR设备。可选地，控制器还用于使显示界面显示候选策略配置以及候选策略配置增益，获取显示界面反馈的用户确认结果。
示例性地，控制器包括四个模块：数据汇聚模块、调优引擎模块、推荐模型模块以及推荐引擎模块。可选地，数据汇聚模块用于获取AR设备的第一KPI数据；调优引擎模块用于比较第一KPI数据以及历史推荐结果所对应的第二KPI数据，基于比较结果获取数据差异性指标，确定数据差异性指标是否满足策略推荐条件；推荐引擎模块用于响应于满足策略推荐条件，基于第一KPI数据确定各个应用类别的带宽需求，基于各个应用类别的带宽需求获取候选策略配置，基于候选策略配置获取候选策略配置增益，使显示界面显示候选策略配置增益。可选地，推荐引擎模块还用于基于候选策略配置获取AR设备的目标策略配置。可选地，推荐引擎模块用于直接将候选策略配置作为AR设备的目标策略配置，或者，推荐引擎模块用于针对候选策略配置的用户确认结果，基于用户确认结果确定网络设备的目标策略配置。推荐模型模块用于在推荐引擎模块获取策略配置时，提供推荐模型。
可选地，存储设备用于存储经控制器处理后KPI，并为控制器提供已存储的KPI作为第一KPI数据。在本实施例所提供的网络管理流程中，控制器获取AR设备的第一KPI数据时，需要将AR设备上报的KPI进行处理，并将处理后KPI存储至存储设备，再定期从存储设备中采集KPI作为AR设备的第一KPI数据。可选地，控制器从存储设备中采集KPI时，可以由控制器统一采集后再分别发送给其内部的不同功能模块，也可以由控制器内部的不同功能模块分别自行向存储设备采集数据，本申请实施例对此不做限定。
需要注意的是，在本实施例中，存储设备直接部署于控制器中，且为了图示的简洁易读，图4中省略了云端存储设备。
图4中的显示界面用于显示控制器获得的候选策略配置增益。可选地，显示界面还用于显示候选策略配置增益对应的候选策略配置。显示界面可以将从控制器接收到的候选策略配置以及候选策略配置增益直接显示给用户，也可以将从控制器接收到的候选策略配置以及候选策略配置增益保存下来，在接收到用户的查询指令后，再将候选策略配置以及候选策略配置增益显示给用户。
在一种可能的实现方式中，显示界面还用于基于显示的候选策略配置以及候选策略配置增益，获取用户确认结果再反馈给控制器。用户确认结果包括在多个候选策略配置中用户选择的策略配置，或者对候选策略配置进行修改之后得到的策略配置。用户可以在显示界面显示的候选策略配置中选择所需要的策略配置，也可以依据实际需求对已有候选策略配置进行灵活调整，生成调整之后得到的策略配置。
请参考图5，其示出了本申请实施例提供的一种网络管理系统所包括的数据汇聚模块的示意图。可选地，数据汇聚模块部署于控制设备中，用于获取网络设备的第一KPI数据。可选地，数据汇聚模块包括：数据接收单元、数据预处理单元、数据模型单元以及数据处理单元。
其中，数据接收单元用于接收网络设备上报的KPI；汇聚所接收的KPI，并对所接收的KPI进行解密和转换，得到汇聚后KPI；将汇聚后KPI发送给数据预处理单元。
数据预处理单元用于接收汇聚后KPI；对汇聚后KPI进行预处理；将预处理后KPI发送给数据处理单元。可选地，预处理过程包括数据清洗以及空值和异常值处理。
数据模型单元用于存放并向数据处理单元提供定义信息。可选地，定义信息包括对数据存储粒度、种类和时长的定义。
数据处理单元用于接收预处理后KPI和定义信息；根据定义信息对预处理后KPI进行融合和分类，得到处理后KPI；将处理后KPI存储至存储设备。经数据处理单元处理并保存至存储设备的KPI数据，即为后续流程中控制设备所采集的第一KPI数据。
请参考图6，其示出了本申请实施例提供的一种网络管理系统所包括的调优引擎模块的示意图。可选地，调优引擎模块部署于控制设备中，用于比较第一KPI数据以及历史推荐结果所对应的第二KPI数据，基于比较结果获取数据差异性指标，确定数据差异性指标是否满足策略推荐条件。可选地，调优引擎模块包括数据采集单元、数据预处理单元、备忘录单元、数据比较单元、业务规则单元、推荐压抑单元以及数据处理单元。
数据采集单元用于从存储设备采集得到第一KPI数据；并将第一KPI数据发送给数据预处理单元。
数据预处理单元用于接收第一KPI数据；对第一KPI数据进行预处理，获得预处理后第一KPI数据；将预处理后第一KPI数据发送给数据比较单元。可选地，预处理过程包括：将第一KPI数据统一成标准格式。
备忘录单元用于存放历史推荐结果；并将历史推荐结果对应的KPI数据作为第二KPI数据发送给数据比较单元。可选地，历史推荐结果可以是上一次满足策略推荐条件的情况。
备忘录单元还用于在数据处理单元确定满足策略推荐条件的情况下，接收数据处理单元返回的当前第一KPI数据，生成新的历史推荐结果及第二KPI数据，用于下一次调优引擎检测是否满足策略推荐条件。
数据比较单元用于接收预处理后第一KPI数据和历史推荐结果所对应的第二KPI数据；比较二者的差异，生成数据差异性指标；将数据差异性指标发送给数据处理单元。
业务规则单元用于存放业务规则并将业务规则发送给数据处理单元。其中业务规则是对确定是否满足策略推荐条件过程制定的一系列规则，可选地，业务规则可以包括但不限于：初始推荐触发时机和调优周期等。其中，初始推荐触发时机规定了第一次确定是否满足策略推荐条件的时机，调优周期规定了确定是否满足策略推荐条件的时间周期。
推荐压抑单元用于基于历史推荐触发信息生成推荐压抑值；将推荐压抑值发送给数据处理单元。可选地，推荐压抑单元还用于在数据处理单元确定满足策略推荐条件的情况下，接收数据处理单元返回的当前时间和当前第一KPI数据等信息。
数据处理单元用于接收数据差异性指标、业务规则以及推荐压抑值；基于数据差异性指 标、业务规则以及推荐压抑值，确定是否满足策略推荐条件；在满足策略推荐条件的情况下，生成推荐触发信号；将推荐触发信号发送给推荐引擎。可选地，数据处理单元还用于在确定满足策略推荐条件的情况下，将当前的时间以及当前的第一KPI数据发送给备忘录单元和推荐压抑单元，用于下一次调优引擎检测是否满足策略推荐条件。
请参考图7，其示出了本申请实施例提供的一种网络管理系统所包括的推荐引擎模块的示意图。可选地，推荐引擎模块用于在满足策略推荐条件的情况下，基于第一KPI数据确定各个应用类别的带宽需求；基于各个应用类别的带宽需求获取候选策略配置；基于候选策略配置获取候选策略配置增益，使显示界面显示候选策略配置增益；基于用户确认结果获取AR设备的目标策略配置。
可选地，推荐引擎模块包括：数据采集单元、数据预处理单元、数据分析单元、推荐结果缓存单元、增益模型单元以及推荐结果管理单元。
数据采集单元用于在满足策略推荐条件的情况下，接收调优引擎发送的推荐触发信号；响应于推荐触发信号，启动推荐引擎后续确定各个应用类别的带宽需求的步骤。数据采集单元还用于从存储设备采集第一KPI数据，并将第一KPI数据发送给数据预处理单元。
数据预处理单元用于对第一KPI数据进行预处理；将预处理后第一KPI数据发送给数据分析单元。可选地，预处理过程包括：将第一KPI数据统一成标准格式。
数据分析单元用于接收预处理后第一KPI数据；基于预处理后第一KPI数据获取第一KPI数据对应的应用类别以及各个应用类别的带宽需求；获取各个应用类别的优先级；基于各个应用类别的带宽需求，按照各个应用类别的优先级依次获取各个应用类别的候选策略配置；将候选策略配置缓存至推荐结果缓存单元。可选地，数据分析单元还用于接收推荐模型模块发送的推荐模型，其中，推荐模型用于生成候选策略配置，推荐模型包括但不限于下述任一种或多种模型：应用质量模型、意图模型、差中选优模型以及带宽模型。
推荐结果缓存单元用于缓存候选策略配置；将候选策略配置发送给推荐结果管理单元。
增益模型单元用于存放增益模型；将增益模型发送给推荐结果管理单元。其中，增益模型是用于计算系统的预期增益指标的计算模型。可选地，预期增益指标包括：全系统各应用预期质量增益及预期链路占用率。
推荐结果管理单元用于接收候选策略配置以及增益模型；基于候选策略配置，根据增益模型，计算不同策略推荐结果下发之后，系统的预期增益指标，得到候选策略配置增益；将候选策略配置以及候选策略配置增益发送至显示界面进行显示；获取显示界面反馈的针对候选策略配置的用户确认结果。可选地，显示界面反馈的用户确认结果包括在多个候选策略配置中的用户选择的策略配置，或者用户对候选策略配置进行修改之后得到的策略配置。用户可以在显示界面显示的候选策略配置中选择所需要的策略配置，也可以依据实际需求对已有候选策略配置进行灵活调整，生成调整之后得到的策略配置。
可选地，推荐结果管理单元可以将候选策略配置直接作为网络设备的目标策略配置，也可以基于用户确认结果获取网络设备的目标策略配置。
推荐结果管理单元还用于获取网络设备的目标策略配置之后，将目标策略配置下发给网络设备，控制网络设备的运行。
请参考图8，其示出了本申请实施例提供的一种网络管理系统所包括的控制设备与显示界面交互流程示意图。可选地，该交互流程通过控制设备与显示界面进行。
可选地，控制设备与显示界面交互流程包括：控制设备将候选策略配置以及候选策略配置增益推送给显示界面；显示界面接收候选策略配置以及候选策略配置增益并展示给用户；显示界面基于用户下达查询详情指令向控制设备发送查询详情请求，可选地，用户可以通过点击页面下达查询详情指令；控制设备接收查询详情请求，向显示界面推送候选策略配置详情；显示界面接收候选策略配置详情，并基于用户下达的修改配置指令对候选策略配置进行修改，并将调整后的策略配置发送给控制设备；控制设备接收调整后的策略配置，并向显示界面发送修改状态提示；显示界面接收修改状态提示，基于用户一键确认，向控制设备反馈用户确认结果；控制设备基于用户确认结果，将调整后的策略配置作为目标策略配置，下发至网络设备侧，再将策略下发状态提示推送给显示界面。
请参考图9，其示出了本申请实施例提供的一种网络管理系统所包括的控制设备与显示界面交互流程示意图。可选地，该交互流程通过控制设备与显示界面进行。
可选地，控制设备与显示界面交互流程包括：控制设备将候选策略配置、候选策略配置增益以及策略下发状态提示推送给显示界面；显示界面接收候选策略配置以及候选策略配置增益并展示给用户。需要说明的是，图10中，控制设备直接将获取的候选策略配置下发给网络设备进行网络管理，在显示界面仅是将候选策略配置及候选策略配置增益展示给用户。
请参考图10，其示出了本申请实施例提供的一种候选策略配置获取流程的示意图。如图10所示，控制设备在检测到推荐触发信号的情况下，基于第一KPI数据获取各个应用类别的带宽需求，如图10所示，本实施例第一KPI数据对应的应用分类包括：音频、视频、企业业务以及数据。
控制设备获取应用分类优先级，例如本实施例应用分类优先级为(从高到低)：音频、视频、企业业务以及数据。
控制设备基于各个应用类别的带宽需求，按照各个应用类别的优先级依次获取各个应用类别的候选策略配置，在本实施例中，以优先级最高的音频为例，获取音频选路配置的流程为：控制设备先按照音频对应的应用质量模型所确定的延迟、抖动以及丢包率阈值，将现有的6条备选链路分为符合和不符合上述阈值的链路，如图中所示，1、2、3为符合链路，4、5、6为不符合链路；再按照下述可能的四种情况为音频确定选路配置。
情况一：对1、2、3链路进行独占符合链路模式的计算，即，若“音频”传输独占一条符合链路，寻找满足音频带宽需求的链路。若能找到满足链路，则继续执行情况一，如图中箭头1所示，在本实施例中，计算得到独占符合链路模式下链路1和3满足音频带宽需求(链路2不满足而被排除)，将1和3作为可选链路，再根据意图模型进一步筛选，得到链路1为目标链路，即传输音频的链路，最后基于链路1生成音频的选路配置，获取音频选路配置的流程结束。若不能找到满足链路，则执行情况二。
情况二：对1、2、3链路进行独占符合链路模式的计算后发现没有链路能够满足音频的带宽需求(即情况一无法执行)，那么对1、2、3链路进行均衡负载模式的计算，即，将“音频”拆分，分配给不同链路共同传输，寻找此时满足音频带宽需求的链路，若能找到满足链路，则继续执行情况二，如图中箭头2所示，在本实施例中，计算得到均衡负载模式下只有 当链路1分配40％音频和链路3分配60％音频时，可以满足音频带宽需求，此时将这个选路方案作为音频的目标链路(链路2不满足而被排除)，再基于链路1和链路3生成音频的选路配置，获取音频选路配置的流程结束。若不能找到满足链路，则执行情况三。
情况三：对1、2、3链路进行独占符合链路模式的计算后发现没有链路能够满足音频的带宽需求(即情况一无法执行)，再对1、2、3链路进行均衡负载模式的计算后发现也没有链路能够满足音频的带宽需求(即情况二也无法执行)，此时启用不符合链路4、5、6。对4、5、6链路进行独占不符合链路模式的计算，即，若“音频”传输独占一条不符合链路，寻找满足音频带宽需求的链路。若能找到满足链路，则继续执行情况三，如图中箭头3所示，在本实施例中，计算得到独占不符合链路模式下链路5和6满足音频带宽需求(链路4不满足而被排除)，将5和6作为可选链路，根据差中选优模型进一步筛选，得到链路5为目标链路，基于链路5生成音频的选路配置，获取音频选路配置的流程结束。若不能找到满足链路，则执行情况四。
情况四：对1、2、3链路进行独占符合链路模式的计算后发现没有链路能够满足音频的带宽需求(即情况一无法执行)，对1、2、3链路进行均衡负载模式的计算后发现没有链路能够满足音频的带宽需求(即情况二也无法执行)，对4、5、6链路进行独占不符合链路模式的计算发现没有链路能够满足音频的带宽需求(即情况三也无法执行)，则如图中所示，给出告警，获取音频选路配置的流程结束。
请参考下述表1，其示出了本申请实施例提供的一种候选策略配置的示例。如表1所示，其示出了备选链路为双链路(MPLS和互联网)情况下，对于一个站点的网络设备，所获取的候选策略配置。
其中，表1第一列为场景描述；第二列为控制设备所识别的应用类型和该应用类型的流量大小；第三列和第四列分别为MPLS链路和互联网链路的质量，所示出的数值依次为链路的延迟、抖动、丢包率、当前已占用的带宽以及该链路的总带宽；第五列为获得的候选策略配置。
表1
Figure PCTCN2022072748-appb-000001
Figure PCTCN2022072748-appb-000002
请参考图11，其示出了本申请实施例提供的一种网络管理装置的结构示意图。该网络管理装置包括：第一获取模块901，用于基于网络设备的候选策略配置获取候选策略配置增益，候选策略配置增益用于指示候选策略配置的预测效果相对网络设备的当前策略配置的效果的差异；显示模块902，用于使显示界面显示候选策略配置增益。
可选地，该网络管理装置还包括：第二获取模块903，用于在显示模块902使显示界面显示所述候选策略配置增益之后，获取针对候选策略配置的用户确认结果，基于用户确认结果确定目标策略配置。
可选地，候选策略配置包括多个策略配置，第二获取模块903用于将多个策略配置中用户确认的策略配置确定为目标策略配置。
可选地，候选策略配置包括多个策略配置，用户确认结果包括修改后的候选策略配置，第二获取模块903用于将修改后的所述候选策略配置确定为所述目标策略配置。
可选地，第二获取模块903还用于将候选策略配置作为目标策略配置。
可选地，显示模块902，还用于使所述显示界面显示所述候选策略配置。
可选地，显示模块902，还用于当用户在显示界面查询候选策略配置时，使显示界面显示候选策略配置增益。
可选地，该网络管理装置还包括：第三获取模块904，用于获取网络设备的第一关键性能指标KPI数据；比较第一KPI数据以及历史推荐结果所对应的第二KPI数据，基于比较结果获取数据差异性指标，数据差异性指标的值与第一KPI数据及第二KPI数据之间的差异程度正相关；仅当数据差异性指标满足策略推荐条件时，获取候选策略配置。
可选地，第三获取模块904用于获取各个应用类别的优先级；基于目标应用类别以及应用质量模型，将备选链路分为符合链路与不符合链路，目标应用类别为所要获取的当前优先级应用类别，符合链路表示符合目标应用类别所对应的应用质量模型的链路，不符合链路表示不符合目标应用类别所对应的应用质量模型的链路，应用质量模型用于指示对应的应用类别的质量要求；获取目标应用类别独占符合链路模式的带宽；在目标应用类别独占符合链路模式的带宽满足所述目标应用类别的带宽需求的条件下，基于意图模型在所述符合链路中确定目标链路，基于目标链路生成目标应用类别的选路配置。
可选地，第三获取模块904用于获取目标应用类别独占符合链路模式的带宽之后，还用于在目标应用类别独占符合链路模式的带宽不满足目标应用类别的带宽需求的条件下，获取目标应用类别均衡负载模式的带宽；在目标应用类别均衡负载模式的带宽满足目标应用类别的带宽需求的条件下，在均衡负载模式对应的链路中确定目标链路，基于目标链路生成目标应用类别的选路配置。
可选地，第三获取模块904用于获取目标应用类别均衡负载模式的带宽之后，还用于在目标应用类别均衡负载模式的带宽不满足目标应用类别的带宽需求的条件下，在不符合链路中根据差中选优模型确定目标链路，基于目标链路生成目标应用类别的选路配置。
示例性地，第三获取模块904用于检测目标应用类别独占不符合链路模式的带宽是否满足目标应用类别的带宽需求；在目标应用类别独占不符合链路模式的带宽满足目标应用类别的带宽需求的条件下，在不符合链路中根据差中选优模型确定目标链路。
可选地，第三获取模块904用于检测目标应用类别独占不符合链路模式的带宽是否满足目标应用类别的带宽需求之后，还用于在目标应用类别独占不符合链路模式的带宽不满足目标应用类别的带宽需求的条件下，进行告警。
在一种可能的实现方式中，候选策略配置包括服务质量配置，第三获取模块904用于获取各个应用类别的优先级；基于各个应用类别的带宽需求以及带宽模型，按照各个应用类别的优先级依次获取各个应用类别的服务质量配置，所述带宽模型用于指示对应的应用类别的带宽要求。
可选地，第三获取模块904还用于将获得的候选策略配置作为目标策略配置发送给第二获取模块903。
参见图12，图12示出了本申请一个示例性实施例提供的网络管理设备2000的结构示意图。图12所示的网络管理设备2000用于执行上述图2-10所示的网络管理方法所涉及的操作。该网络管理设备2000例如是交换机、路由器等，该网络管理设备2000可以由一般性的总线体系结构来实现。
如图12所示，网络管理设备2000包括至少一个处理器2001、存储器2003以及至少一个通信接口2004。
处理器2001例如是通用中央处理器(central processing unit，CPU)、数字信号处理器(digital signal processor，DSP)、网络处理器(network processer，NP)、图形处理器(graphics processing unit，GPU)、神经网络处理器(neural-network processing units，NPU)、数据处理单元(data processing unit，DPU)、微处理器或者一个或多个用于实现本申请方案的集成电路。例如，处理器2001包括专用集成电路(application-specific integrated circuit，ASIC)，可编程逻辑器件(programmable logic device，PLD)或者其他可编程逻辑器件、晶体管逻辑器件、硬件部件或者其任意组合。PLD例如是复杂可编程逻辑器件(complex programmable logic device，CPLD)、现场可编程逻辑门阵列(field-programmable gate array，FPGA)、通用阵列逻辑(generic array logic，GAL)或其任意组合。其可以实现或执行结合本发明实施例公开内容所描述的各种逻辑方框、模块和电路。所述处理器也可以是实现计算功能的组合，例如包括一个或多个微处理器组合，DSP和微处理器的组合等等。
可选的，网络管理设备2000还包括总线。总线用于在网络管理设备2000的各组件之间传送信息。总线可以是外设部件互连标准(peripheral component interconnect，简称PCI)总线或扩展工业标准结构(extended industry standard architecture，简称EISA)总线等。总线可以分为地址总线、数据总线、控制总线等。为便于表示，图12中仅用一条粗线表示，但并不表示仅有一根总线或一种类型的总线。
存储器2003例如是只读存储器(read-only memory，ROM)或可存储静态信息和指令的其它类型的静态存储设备，又如是随机存取存储器(random access memory，RAM)或者可存储信息和指令的其它类型的动态存储设备，又如是电可擦可编程只读存储器(electrically erasable programmable read-only memory，EEPROM)、只读光盘(compact disc read-only memory，CD-ROM)或其它光盘存储、光碟存储(包括压缩光碟、激光碟、光碟、数字通用光碟、蓝光光碟等)、磁盘存储介质或者其它磁存储设备，或者是能够用于携带或存储具有指令或数据结构形式的期望的程序代码并能够由计算机存取的任何其它介质，但不限于此。存储器2003例如是独立存在，并通过总线与处理器2001相连接。存储器2003也可以和处理器2001集成在一起。
通信接口2004使用任何收发器一类的装置，用于与其它设备或通信网络通信，通信网络可以为以太网、无线接入网(RAN)或无线局域网(wireless local area network，WLAN)等。通信接口2004可以包括有线通信接口，还可以包括无线通信接口。具体的，通信接口2004可以为以太(ethernet)接口、快速以太(fast ethernet，FE)接口、千兆以太(gigabit ethernet，GE)接口，异步传输模式(asynchronous transfer mode，ATM)接口，无线局域网(wireless local area networks，WLAN)接口，蜂窝网络通信接口或其组合。以太网接口可以是光接口，电接口或其组合。在本申请实施例中，通信接口2004可以用于网络管理设备2000与其他设备进 行通信。
在具体实现中，作为一种实施例，处理器2001可以包括一个或多个CPU，如图12中所示的CPU0和CPU1。这些处理器中的每一个可以是一个单核(single-CPU)处理器，也可以是一个多核(multi-CPU)处理器。这里的处理器可以指一个或多个设备、电路、和/或用于处理数据(例如计算机程序指令)的处理核。
在具体实现中，作为一种实施例，网络管理设备2000可以包括多个处理器，如图12中所示的处理器2001和处理器2005。这些处理器中的每一个可以是一个单核处理器(single-CPU)，也可以是一个多核处理器(multi-CPU)。这里的处理器可以指一个或多个设备、电路、和/或用于处理数据(如计算机程序指令)的处理核。
在具体实现中，作为一种实施例，网络管理设备2000还可以包括输出设备和输入设备。输出设备和处理器2001通信，可以以多种方式来显示信息。例如，输出设备可以是液晶显示器(liquid crystal display，LCD)、发光二级管(light emitting diode，LED)显示设备、阴极射线管(cathode ray tube，CRT)显示设备或投影仪(projector)等。输入设备和处理器2001通信，可以以多种方式接收用户的输入。例如，输入设备可以是鼠标、键盘、触摸屏设备或传感设备等。
在一些实施例中，存储器2003用于存储执行本申请方案的程序代码2010，处理器2001可以执行存储器2003中存储的程序代码2010。也即是，网络管理设备2000可以通过处理器2001以及存储器2003中的程序代码2010，来实现方法实施例提供的网络管理方法。程序代码2010中可以包括一个或多个软件模块。可选地，处理器2001自身也可以存储执行本申请方案的程序代码或指令。
在具体实施例中，本申请实施例的网络管理设备2000可对应于上述各个网络管理方法实施例中的控制设备，网络管理设备2000中的处理器2001读取存储器2003中的指令，使图12所示的网络管理设备2000能够执行控制设备所执行的全部或部分操作。
具体的，处理器2001用于通过通信接口向显示界面发送候选策略配置增益，候选策略配置增益通过候选策略配置获得。其他可选的实施方式，为了简洁，在此不再赘述。
又例如，本申请实施例的网络管理设备2000可对应于上述各个方法实施例中的显示界面，网络管理设备2000中的处理器2001读取存储器2003中的指令，使图12所示的网络管理设备2000能够执行显示界面所执行的全部或部分操作。
具体的，处理器2001用于通过通信接口接收控制设备向显示界面发送的候选策略配置增益，候选策略配置增益通过候选策略配置获得。其他可选的实施方式，为了简洁，在此不再赘述。
网络管理设备2000还可以对应于上述图11所示的网络管理装置，网络管理装置中的每个功能模块采用网络管理设备2000的软件实现。换句话说，网络管理装置中包括的功能模块为网络管理设备2000的处理器2001读取存储器2003中存储的程序代码2010后生成的。
其中，图2-10所示的网络管理方法的各步骤通过网络管理设备2000的处理器中的硬件的集成逻辑电路或者软件形式的指令完成。结合本申请实施例所公开的方法的步骤可以直接体现为硬件处理器执行完成，或者用处理器中的硬件及软件模块组合执行完成。软件模块可以位于随机存储器，闪存、只读存储器，可编程只读存储器或者电可擦写可编程存储器、寄存器等本领域成熟的存储介质中。该存储介质位于存储器，处理器读取存储器中的信息，结 合其硬件完成上述方法的步骤，为避免重复，这里不再详细描述。
参见图13，图13示出了本申请另一个示例性实施例提供的网络管理设备2100的结构示意图。图13所示的网络管理设备2100用于执行上述图2-10所示的网络管理方法所涉及的全部或部分操作。该网络管理设备2100例如是交换机、路由器等，该网络管理设备2100可以由一般性的总线体系结构来实现。
如图13所示，网络管理设备2100包括：主控板2110和接口板2130。
主控板也称为主处理单元(main processing unit，MPU)或路由处理卡(route processor card)，主控板2110用于对网络管理设备2100中各个组件的控制和管理，包括路由计算、设备管理、设备维护、协议处理功能。主控板2110包括：中央处理器2111和存储器2112。
接口板2130也称为线路接口单元卡(line processing unit，LPU)、线卡(line card)或业务板。接口板2130用于提供各种业务接口并实现数据包的转发。业务接口包括而不限于以太网接口、POS(packet over SONET/SDH)接口等，以太网接口例如是灵活以太网业务接口(flexible ethernet clients，FlexE Clients)。接口板2130包括：中央处理器2131网络处理器2132、转发表项存储器2134和物理接口卡(physical interface card，PIC)2133。
接口板2130上的中央处理器2131用于对接口板2130进行控制管理并与主控板2110上的中央处理器2111进行通信。
网络处理器2132用于实现报文的转发处理。网络处理器2132的形态可以是转发芯片。转发芯片可以是网络处理器(network processor，NP)。在一些实施例中，转发芯片可以通过专用集成电路(application-specific integrated circuit，ASIC)或现场可编程门阵列(field programmable gate array，FPGA)实现。具体而言，网络处理器2132用于基于转发表项存储器2134保存的转发表转发接收到的报文，如果报文的目的地址为网络管理设备2100的地址，则将该报文上送至CPU(如中央处理器2131)处理；如果报文的目的地址不是网络管理设备2100的地址，则根据该目的地址从转发表中查找到该目的地址对应的下一跳和出接口，将该报文转发到该目的地址对应的出接口。其中，上行报文的处理可以包括：报文入接口的处理，转发表查找；下行报文的处理可以包括：转发表查找等等。在一些实施例中，中央处理器也可执行转发芯片的功能，比如基于通用CPU实现软件转发，从而接口板中不需要转发芯片。
物理接口卡2133用于实现物理层的对接功能，原始的流量由此进入接口板2130，以及处理后的报文从该物理接口卡2133发出。物理接口卡2133也称为子卡，可安装在接口板2130上，负责将光电信号转换为报文并对报文进行合法性检查后转发给网络处理器2132处理。在一些实施例中，中央处理器2131也可执行网络处理器2132的功能，比如基于通用CPU实现软件转发，从而物理接口卡2133中不需要网络处理器2132。
可选地，网络管理设备2100包括多个接口板，例如网络管理设备2100还包括接口板2140，接口板2140包括：中央处理器2141、网络处理器2142、转发表项存储器2144和物理接口卡2143。接口板2140中各部件的功能和实现方式与接口板2130相同或相似，在此不再赘述。
可选地，网络管理设备2100还包括交换网板2120。交换网板2120也可以称为交换网板单元(switch fabric unit，SFU)。在网络管理设备有多个接口板的情况下，交换网板2120用于完成各接口板之间的数据交换。例如，接口板2130和接口板2140之间可以通过交换网板2120通信。
主控板2110和接口板耦合。例如。主控板2110、接口板2130和接口板2140，以及交换 网板2120之间通过系统总线与系统背板相连实现互通。在一种可能的实现方式中，主控板2110和接口板2130及接口板2140之间建立进程间通信协议(inter-process communication，IPC)通道，主控板2110和接口板2130及接口板2140之间通过IPC通道进行通信。
在逻辑上，网络管理设备2100包括控制面和转发面，控制面包括主控板2110和中央处理器2111，转发面包括执行转发的各个组件，比如转发表项存储器2134、物理接口卡2133和网络处理器2132。控制面执行路由器、生成转发表、处理信令和协议报文、配置与维护网络设备的状态等功能，控制面将生成的转发表下发给转发面，在转发面，网络处理器2132基于控制面下发的转发表对物理接口卡2133收到的报文查表转发。控制面下发的转发表可以保存在转发表项存储器2134中。在有些实施例中，控制面和转发面可以完全分离，不在同一网络设备上。
值得说明的是，主控板可能有一块或多块，有多块的时候可以包括主用主控板和备用主控板。接口板可能有一块或多块，网络管理设备的数据处理能力越强，提供的接口板越多。接口板上的物理接口卡也可以有一块或多块。交换网板可能没有，也可能有一块或多块，有多块的时候可以共同实现负荷分担冗余备份。在集中式转发架构下，网络管理设备可以不需要交换网板，接口板承担整个系统的业务数据的处理功能。在分布式转发架构下，网络管理设备可以有至少一块交换网板，通过交换网板实现多块接口板之间的数据交换，提供大容量的数据交换和处理能力。所以，分布式架构的网络管理设备的数据接入和处理能力要大于集中式架构的网络管理设备。可选地，网络管理设备的形态也可以是只有一块板卡，即没有交换网板，接口板和主控板的功能集成在该一块板卡上，此时接口板上的中央处理器和主控板上的中央处理器在该一块板卡上可以合并为一个中央处理器，执行两者叠加后的功能，这种形态网络管理设备的数据交换和处理能力较低(例如，低端交换机或路由器等网络设备)。具体采用哪种架构，取决于具体的组网部署场景，此处不做任何限定。
在具体实施例中，网络管理设备2100对应于上述图11所示的应用于控制设备的网络管理装置。在一些实施例中，网络管理设备2100还对应于上述图11所示的应用于控制设备的网络管理设备。在一些实施例中，图11所示的网络管理装置中的第一获取模块901及显示模块902相当于网络管理设备2100中的物理接口卡2133；第二获取模块903及第三获取模块904相当于网络管理设备2100中的中央处理器2111或网络处理器2132。
基于上述图12及图13所示的网络管理设备，本申请实施例还提供了一种网络管理系统，该系统包括：控制设备以及显示界面。可选的，控制设备为图12所示的网络管理设备2000或图13所示的网络管理设备2100，显示界面为图12所示的网络管理设备2000或图13所示的网络管理设备2100。
网络管理设备所执行的网络管理方法可参见上述图2-10所示实施例的相关描述，此处不再加以赘述。
本申请实施例还提供了一种通信装置，该装置包括：收发器、存储器和处理器。其中，该收发器、该存储器和该处理器通过内部连接通路互相通信，该存储器用于存储指令，该处理器用于执行该存储器存储的指令，以控制收发器接收信号，并控制收发器发送信号，并且当该处理器执行该存储器存储的指令时，使得该处理器执行控制设备所需执行的网络管理方法。
本申请实施例还提供了一种通信装置，该装置包括：收发器、存储器和处理器。其中， 该收发器、该存储器和该处理器通过内部连接通路互相通信，该存储器用于存储指令，该处理器用于执行该存储器存储的指令，以控制收发器接收信号，并控制收发器发送信号，并且当该处理器执行该存储器存储的指令时，使得该处理器执行显示界面所需执行的网络管理方法。
应理解的是，上述处理器可以是中央处理器(central processing unit，CPU)，还可以是其他通用处理器、数字信号处理器(digital signal processing，DSP)、专用集成电路(application specific integrated circuit，ASIC)、现场可编程门阵列(field programmable gate array，FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件等。通用处理器可以是微处理器或者是任何常规的处理器等。值得说明的是，处理器可以是支持进阶精简指令集机器(advanced RISC machines，ARM)架构的处理器。
进一步地，在一种可选的实施例中，上述存储器可以包括只读存储器和随机存取存储器，并向处理器提供指令和数据。存储器还可以包括非易失性随机存取存储器。例如，存储器还可以存储设备类型的信息。
该存储器可以是易失性存储器或非易失性存储器，或可包括易失性和非易失性存储器两者。其中，非易失性存储器可以是只读存储器(read-only memory，ROM)、可编程只读存储器(programmable ROM，PROM)、可擦除可编程只读存储器(erasable PROM，EPROM)、电可擦除可编程只读存储器(electrically EPROM，EEPROM)或闪存。易失性存储器可以是随机存取存储器(random access memory，RAM)，其用作外部高速缓存。通过示例性但不是限制性说明，许多形式的RAM可用。例如，静态随机存取存储器(static RAM，SRAM)、动态随机存取存储器(dynamic random access memory，DRAM)、同步动态随机存取存储器(synchronous DRAM，SDRAM)、双倍数据速率同步动态随机存取存储器(double data date SDRAM，DDR SDRAM)、增强型同步动态随机存取存储器(enhanced SDRAM，ESDRAM)、同步连接动态随机存取存储器(synchlink DRAM，SLDRAM)和直接内存总线随机存取存储器(direct rambus RAM，DR RAM)。
本申请实施例还提供了一种计算机可读存储介质，存储介质中存储有至少一条指令，指令由处理器加载并执行以实现如上任一所述的网络管理方法。
本申请实施例还提供了一种计算机程序(产品)，当计算机程序被计算机执行时，可以使得处理器或计算机执行上述方法实施例中对应的网络管理方法的各个步骤和/或流程。
本申请实施例还提供了一种芯片，包括处理器，用于从存储器中调用并运行所述存储器中存储的指令，使得安装有所述芯片的通信设备执行上述各方面中的网络管理方法。
本申请实施例还提供另一种芯片，包括：输入接口、输出接口、处理器和存储器，所述输入接口、输出接口、所述处理器以及所述存储器之间通过内部连接通路相连，所述处理器用于执行所述存储器中的代码，当所述代码被执行时，所述处理器用于执行上述各方面中的网络管理方法。
在上述实施例中，可以全部或部分地通过软件、硬件、固件或者其任意组合来实现。当使用软件实现时，可以全部或部分地以计算机程序产品的形式实现。所述计算机程序产品包括一个或多个计算机指令。在计算机上加载和执行所述计算机程序指令时，全部或部分地产生按照本申请所述的流程或功能。所述计算机可以是通用计算机、专用计算机、计算机网络、或者其他可编程装置。所述计算机指令可以存储在计算机可读存储介质中，或者从一个计算 机可读存储介质向另一个计算机可读存储介质传输，例如，所述计算机指令可以从一个网站站点、计算机、服务器或数据中心通过有线(例如同轴电缆、光纤、数字用户线)或无线(例如红外、无线、微波等)方式向另一个网站站点、计算机、服务器或数据中心进行传输。所述计算机可读存储介质可以是计算机能够存取的任何可用介质或者是包含一个或多个可用介质集成的服务器、数据中心等数据存储设备。所述可用介质可以是磁性介质，(例如，软盘、硬盘、磁带)、光介质(例如，DVD)、或者半导体介质(例如固态硬盘solid state disk)等。
本领域普通技术人员可以意识到，结合本文中所公开的实施例中描述的各方法步骤和模块，能够以软件、硬件、固件或者其任意组合来实现，为了清楚地说明硬件和软件的可互换性，在上述说明中已经按照功能一般性地描述了各实施例的步骤及组成。这些功能究竟以硬件还是软件方式来执行，取决于技术方案的特定应用和设计约束条件。本领域普通技术人员可以对每个特定的应用来使用不同方法来实现所描述的功能，但是这种实现不应认为超出本申请的范围。
本领域普通技术人员可以理解实现上述实施例的全部或部分步骤可以通过硬件来完成，也可以通过程序来指令相关的硬件完成，该程序可以存储于一种计算机可读存储介质中，上述提到的存储介质可以是只读存储器，磁盘或光盘等。
当使用软件实现时，可以全部或部分地以计算机程序产品的形式实现。该计算机程序产品包括一个或多个计算机程序指令。作为示例，本申请实施例的方法可以在机器可执行指令的上下文中被描述，机器可执行指令诸如包括在目标的真实或者虚拟处理器上的器件中执行的程序模块中。一般而言，程序模块包括例程、程序、库、对象、类、组件、数据结构等，其执行特定的任务或者实现特定的抽象数据结构。在各实施例中，程序模块的功能可以在所描述的程序模块之间合并或者分割。用于程序模块的机器可执行指令可以在本地或者分布式设备内执行。在分布式设备中，程序模块可以位于本地和远程存储介质二者中。
用于实现本申请实施例的方法的计算机程序代码可以用一种或多种编程语言编写。这些计算机程序代码可以提供给通用计算机、专用计算机或其他可编程的数据处理装置的处理器，使得程序代码在被计算机或其他可编程的数据处理装置执行的时候，引起在流程图和/或框图中规定的功能/操作被实施。程序代码可以完全在计算机上、部分在计算机上、作为独立的软件包、部分在计算机上且部分在远程计算机上或完全在远程计算机或服务器上执行。
在本申请实施例的上下文中，计算机程序代码或者相关数据可以由任意适当载体承载，以使得设备、装置或者处理器能够执行上文描述的各种处理和操作。载体的示例包括信号、计算机可读介质等等。
信号的示例可以包括电、光、无线电、声音或其它形式的传播信号，诸如载波、红外信号等。
机器可读介质可以是包含或存储用于或有关于指令执行系统、装置或设备的程序的任何有形介质。机器可读介质可以是机器可读信号介质或机器可读存储介质。机器可读介质可以包括但不限于电子的、磁的、光学的、电磁的、红外的或半导体系统、装置或设备，或其任意合适的组合。机器可读存储介质的更详细示例包括带有一根或多根导线的电气连接、便携式计算机磁盘、硬盘、随机存储存取器(RAM)、只读存储器(ROM)、可擦除可编程只读存储器(EPROM或闪存)、光存储设备、磁存储设备，或其任意合适的组合。
所属领域的技术人员可以清楚地了解到，为了描述的方便和简洁，上述描述的系统、设 备和模块的具体工作过程，可以参见前述方法实施例中的对应过程，在此不再赘述。
在本申请所提供的几个实施例中，应该理解到，所揭露的系统、设备和方法，可以通过其它的方式实现。例如，以上所描述的设备实施例仅仅是示意性的，例如，该模块的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，例如多个模块或组件可以结合或者可以集成到另一个系统，或一些特征可以忽略，或不执行。另外，所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口、设备或模块的间接耦合或通信连接，也可以是电的，机械的或其它的形式连接。
该作为分离部件说明的模块可以是或者也可以不是物理上分开的，作为模块显示的部件可以是或者也可以不是物理模块，即可以位于一个地方，或者也可以分布到多个网络模块上。可以根据实际的需要选择其中的部分或者全部模块来实现本申请实施例方案的目的。
另外，在本申请各个实施例中的各功能模块可以集成在一个处理模块中，也可以是各个模块单独物理存在，也可以是两个或两个以上模块集成在一个模块中。上述集成的模块既可以采用硬件的形式实现，也可以采用软件功能模块的形式实现。
该集成的模块如果以软件功能模块的形式实现并作为独立的产品销售或使用时，可以存储在一个计算机可读存储介质中。基于这样的理解，本申请的技术方案本质上或者说对现有技术做出贡献的部分，或者该技术方案的全部或部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质中，包括若干指令用以使得一台计算机设备(可以是个人计算机，服务器，或者网络设备等)执行本申请各个实施例中方法的全部或部分步骤。而前述的存储介质包括：U盘、移动硬盘、只读存储器(read-only memory，ROM)、随机存取存储器(random access memory，RAM)、磁碟或者光盘等各种可以存储程序代码的介质。
本申请中术语“第一”“第二”等字样用于对作用和功能基本相同的相同项或相似项进行区分，应理解，“第一”、“第二”、“第n”之间不具有逻辑或时序上的依赖关系，也不对数量和执行顺序进行限定。还应理解，尽管以下描述使用术语第一、第二等来描述各种元素，但这些元素不应受术语的限制。这些术语只是用于将一元素与另一元素区别分开。例如，在不脱离各种所述示例的范围的情况下，第一图像可以被称为第二图像，并且类似地，第二图像可以被称为第一图像。第一图像和第二图像都可以是图像，并且在某些情况下，可以是单独且不同的图像。
还应理解，在本申请的各个实施例中，各个过程的序号的大小并不意味着执行顺序的先后，各过程的执行顺序应以其功能和内在逻辑确定，而不应对本申请实施例的实施过程构成任何限定。
本申请中术语“至少一个”的含义是指一个或多个，本申请中术语“多个”的含义是指两个或两个以上，例如，多个第二报文是指两个或两个以上的第二报文。本文中术语“系统”和“网络”经常可互换使用。
应理解，在本文中对各种所述示例的描述中所使用的术语只是为了描述特定示例，而并非旨在进行限制。如在对各种所述示例的描述和所附权利要求书中所使用的那样，单数形式“一个(“a”,“an”)”和“该”旨在也包括复数形式，除非上下文另外明确地指示。
还应理解，本文中所使用的术语“和/或”是指并且涵盖相关联的所列出的项目中的一个或多个项目的任何和全部可能的组合。术语“和/或”，是一种描述关联对象的关联关系，表示可以存在三种关系，例如，A和/或B，可以表示：单独存在A，同时存在A和B，单独存 在B这三种情况。另外，本申请中的字符“/”，一般表示前后关联对象是一种“或”的关系。
还应理解，术语“包括”(也称“includes”、“including”、“comprises”和/或“comprising”)当在本说明书中使用时指定存在所陈述的特征、整数、步骤、操作、元素、和/或部件，但是并不排除存在或添加一个或多个其他特征、整数、步骤、操作、元素、部件、和/或其分组。
还应理解，术语“若”和“如果”可被解释为意指“当...时”(“when”或“upon”)或“响应于确定”或“响应于检测到”。类似地，根据上下文，短语“若确定...”或“若检测到[所陈述的条件或事件]”可被解释为意指“在确定...时”或“响应于确定...”或“在检测到[所陈述的条件或事件]时”或“响应于检测到[所陈述的条件或事件]”。
应理解，根据A确定B并不意味着仅仅根据A确定B，还可以根据A和/或其它信息确定B。
还应理解，说明书通篇中提到的“一个实施例”、“一实施例”、“一种可能的实现方式”意味着与实施例或实现方式有关的特定特征、结构或特性包括在本申请的至少一个实施例中。因此，在整个说明书各处出现的“在一个实施例中”或“在一实施例中”、“一种可能的实现方式”未必一定指相同的实施例。此外，这些特定的特征、结构或特性可以任意适合的方式结合在一个或多个实施例中。
以上描述仅为本申请的可选实施例，并不用以限制本申请，凡在本申请的原则之内，所作的任何修改、等同替换、改进等，均应包含在本申请的保护范围之内。

Claims (29)

  1. 一种网络管理方法，其特征在于，所述方法包括：
    控制设备基于网络设备的候选策略配置获取候选策略配置增益，所述候选策略配置增益用于指示所述候选策略配置的预测效果相对所述网络设备的当前策略配置的效果的差异；
    所述控制设备使显示界面显示所述候选策略配置增益。
  2. 根据权利要求1所述的方法，其特征在于，所述控制设备使显示界面显示所述候选策略配置增益之后，还包括：
    获取针对所述候选策略配置的用户确认结果，基于所述用户确认结果确定目标策略配置。
  3. 根据权利要求2所述的方法，其特征在于，所述候选策略配置包括多个策略配置，所述基于所述用户确认结果确定目标策略配置，包括：将所述多个策略配置中用户确认的策略配置确定为所述目标策略配置。
  4. 根据权利要求2所述的方法，其特征在于，所述候选策略配置包括多个策略配置，所述用户确认结果包括修改后的候选策略配置，所述基于所述用户确认结果确定目标策略配置，包括：将所述修改后的候选策略配置确定为所述目标策略配置。
  5. 根据权利要求1-4任一所述的方法，其特征在于，还包括：
    所述控制设备使所述显示界面显示所述候选策略配置。
  6. 根据权利要求1-5任一所述的方法，其特征在于，所述控制设备使显示界面显示所述候选策略配置增益，还包括：
    当用户在所述显示界面查询所述候选策略配置时，所述控制设备使所述显示界面显示所述候选策略配置增益。
  7. 根据权利要求1-6任一所述的方法，其特征在于，还包括：
    获取所述网络设备的第一关键性能指标(KPI)数据；
    比较所述第一KPI数据以及历史推荐结果所对应的第二KPI数据，基于比较结果获取数据差异性指标，所述数据差异性指标的值与所述第一KPI数据及所述第二KPI数据之间的差异程度正相关；
    仅当所述数据差异性指标满足策略推荐条件时，获取所述候选策略配置。
  8. 根据权利要求7所述的方法，其特征在于，所述候选策略配置包括选路配置，所述获取所述候选策略配置，包括：
    获取各个应用类别的优先级；
    基于目标应用类别以及应用质量模型，将备选链路分为符合链路与不符合链路，所述目 标应用类别为所要获取的当前优先级应用类别，所述符合链路表示符合所述目标应用类别所对应的应用质量模型的链路，所述不符合链路表示不符合所述目标应用类别所对应的应用质量模型的链路，所述应用质量模型用于指示对应的应用类别的质量要求；
    获取目标应用类别独占符合链路模式的带宽；
    在所述目标应用类别独占符合链路模式的带宽满足目标应用类别的带宽需求的条件下，基于意图模型在所述符合链路中确定目标链路，基于所述目标链路生成所述目标应用类别的选路配置。
  9. 根据权利要求8所述的方法，其特征在于，所述获取目标应用类别独占符合链路模式的带宽之后，还包括：
    在所述目标应用类别独占符合链路模式的带宽不满足所述目标应用类别的带宽需求的条件下，获取目标应用类别均衡负载模式的带宽；
    在所述目标应用类别均衡负载模式的带宽满足所述目标应用类别的带宽需求的条件下，在所述均衡负载模式对应的链路中确定目标链路，基于所述目标链路生成所述目标应用类别的选路配置。
  10. 根据权利要求9所述的方法，其特征在于，所述获取目标应用类别均衡负载模式的带宽之后，还包括：
    在所述目标应用类别均衡负载模式的带宽不满足所述目标应用类别的带宽需求的条件下，在所述不符合链路中根据差中选优模型确定目标链路，基于所述目标链路生成所述目标应用类别的选路配置。
  11. 根据权利要求10所述的方法，其特征在于，所述在所述目标应用类别均衡负载模式的带宽不满足所述目标应用类别的带宽需求的条件下，在所述不符合链路中根据差中选优模型确定目标链路，包括：
    检测目标应用类别独占不符合链路模式的带宽是否满足所述目标应用类别的带宽需求；
    在所述目标应用类别独占不符合链路模式的带宽满足所述目标应用类别的带宽需求的条件下，在所述不符合链路中根据差中选优模型确定目标链路。
  12. 根据权利要求11所述的方法，其特征在于，所述检测目标应用类别独占不符合链路模式的带宽是否满足所述目标应用类别的带宽需求之后，还包括：
    在所述目标应用类别独占不符合链路模式的带宽不满足所述目标应用类别的带宽需求的条件下，进行告警。
  13. 根据权利要求7所述的方法，其特征在于，所述候选策略配置包括服务质量配置，所述获取所述候选策略配置，包括：
    获取各个应用类别的优先级；
    基于各个应用类别的带宽需求以及带宽模型，按照所述各个应用类别的优先级依次获取所述各个应用类别的服务质量配置，所述带宽模型用于指示对应的应用类别的带宽要求。
  14. 一种网络管理装置，其特征在于，所述装置包括：
    第一获取模块，用于基于网络设备的候选策略配置获取候选策略配置增益，所述候选策略配置增益用于指示所述候选策略配置的预测效果相对所述网络设备的当前策略配置的效果的差异；
    显示模块，用于使显示界面显示所述候选策略配置增益。
  15. 根据权利要求14所述的装置，其特征在于，所述装置还包括：第二获取模块，用于获取针对所述候选策略配置的用户确认结果，基于所述用户确认结果确定目标策略配置。
  16. 根据权利要求15所述的装置，其特征在于，所述候选策略配置包括多个策略配置，所述第二获取模块，用于将所述多个策略配置中用户确认的策略配置确定为所述目标策略配置。
  17. 根据权利要求15所述的装置，其特征在于，所述候选策略配置包括多个策略配置，所述用户确认结果包括修改后的候选策略配置，所述第二获取模块，用于将所述修改后的候选策略配置确定为所述目标策略配置。
  18. 根据权利要求14-17任一所述的装置，其特征在于，所述显示模块，还用于使所述显示界面显示所述候选策略配置。
  19. 根据权利要求14-18任一所述的装置，其特征在于，所述显示模块，还用于当用户在所述显示界面查询所述候选策略配置时，使所述显示界面显示所述候选策略配置增益。
  20. 根据权利要求14-19任一所述的装置，其特征在于，所述装置还包括：第三获取模块，用于获取所述网络设备的第一关键性能指标(KPI)数据；比较所述第一KPI数据以及历史推荐结果所对应的第二KPI数据，基于比较结果获取数据差异性指标，所述数据差异性指标的值与所述第一KPI数据及所述第二KPI数据之间的差异程度正相关；仅当所述数据差异性指标满足策略推荐条件时，获取所述候选策略配置。
  21. 根据权利要求20所述的装置，其特征在于，所述候选策略配置包括选路配置，所述第三获取模块，用于获取各个应用类别的优先级；基于目标应用类别以及应用质量模型，将备选链路分为符合链路与不符合链路，所述目标应用类别为所要获取的当前优先级应用类别，所述符合链路表示符合所述目标应用类别所对应的应用质量模型的链路，所述不符合链路表示不符合所述目标应用类别所对应的应用质量模型的链路，所述应用质量模型用于指示对应的应用类别的质量要求；获取目标应用类别独占符合链路模式的带宽；在所述目标应用类别独占符合链路模式的带宽满足目标应用类别的带宽需求的条件下，基于意图模型在所述符合链路中确定目标链路，基于所述目标链路生成所述目标应用类别的选路配置。
  22. 根据权利要求21所述的装置，其特征在于，所述第三获取模块，用于获取目标应用类别独占符合链路模式的带宽之后，还用于在所述目标应用类别独占符合链路模式的带宽不满足所述目标应用类别的带宽需求的条件下，获取目标应用类别均衡负载模式的带宽；在所述目标应用类别均衡负载模式的带宽满足所述目标应用类别的带宽需求的条件下，在所述均衡负载模式对应的链路中确定目标链路，基于所述目标链路生成所述目标应用类别的选路配置。
  23. 根据权利要求22所述的装置，其特征在于，所述第三获取模块，用于获取目标应用类别均衡负载模式的带宽之后，还用于在所述目标应用类别均衡负载模式的带宽不满足所述目标应用类别的带宽需求的条件下，在所述不符合链路中根据差中选优模型确定目标链路，基于所述目标链路生成所述目标应用类别的选路配置。
  24. 根据权利要求23所述的装置，其特征在于，所述第三获取模块，用于检测目标应用类别独占不符合链路模式的带宽是否满足所述目标应用类别的带宽需求；在所述目标应用类别独占不符合链路模式的带宽满足所述目标应用类别的带宽需求的条件下，在所述不符合链路中根据差中选优模型确定目标链路。
  25. 根据权利要求24所述的装置，其特征在于，所述第三获取模块，用于检测目标应用类别独占不符合链路模式的带宽是否满足所述目标应用类别的带宽需求之后，还用于在所述目标应用类别独占不符合链路模式的带宽不满足所述目标应用类别的带宽需求的条件下，进行告警。
  26. 根据权利要求20所述的装置，其特征在于，所述候选策略配置包括服务质量配置，所述第三获取模块，用于获取所述各个应用类别的优先级；基于各个应用类别的带宽需求以及带宽模型，按照所述各个应用类别的优先级依次获取所述各个应用类别的服务质量配置，所述带宽模型用于指示对应的应用类别的带宽要求。
  27. 一种网络管理设备，其特征在于，包括处理器及计算机程序，所述处理器执行所述计算机程序时，以使所述网络管理设备实现权利要求1-13中任一所述的网络管理方法。
  28. 一种计算机可读存储介质，其上存储有计算机程序，其特征在于，所述计算机程序被计算机执行时，实现如权利要求1-13中任一所述的网络管理方法。
  29. 一种计算机程序产品，其特征在于，包括计算机程序，所述计算机程序被计算机执行时，实现如权利要求1-13任一项所述的网络管理方法。
PCT/CN2022/072748 2021-02-05 2022-01-19 网络管理方法、装置、设备及计算机可读存储介质 WO2022166582A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202110164951.2A CN114938334A (zh) 2021-02-05 2021-02-05 网络管理方法、装置、设备及计算机可读存储介质
CN202110164951.2 2021-02-05

Publications (1)

Publication Number Publication Date
WO2022166582A1 true WO2022166582A1 (zh) 2022-08-11

Family

ID=82741882

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/072748 WO2022166582A1 (zh) 2021-02-05 2022-01-19 网络管理方法、装置、设备及计算机可读存储介质

Country Status (2)

Country Link
CN (1) CN114938334A (zh)
WO (1) WO2022166582A1 (zh)

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106384194A (zh) * 2016-09-09 2017-02-08 国家电网公司 一种电力调控方法
US20170269651A1 (en) * 2016-03-16 2017-09-21 Advanced Micro Devices, Inc. Method and apparatus for managing power in a thermal couple aware system
CN109710401A (zh) * 2018-12-17 2019-05-03 国云科技股份有限公司 一种云计算资源成本优化方法
CN111142968A (zh) * 2019-12-26 2020-05-12 联想(北京)有限公司 电子设备配置推荐处理方法、装置及存储介质
CN111277442A (zh) * 2020-01-21 2020-06-12 赣江新区智慧物联研究院有限公司 无线意图驱动网络的管理方法、装置及系统
CN112306574A (zh) * 2020-10-30 2021-02-02 联想(北京)有限公司 一种配置方法及装置

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111553749A (zh) * 2020-05-09 2020-08-18 支付宝(杭州)信息技术有限公司 一种活动推送策略配置方法及装置

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20170269651A1 (en) * 2016-03-16 2017-09-21 Advanced Micro Devices, Inc. Method and apparatus for managing power in a thermal couple aware system
CN106384194A (zh) * 2016-09-09 2017-02-08 国家电网公司 一种电力调控方法
CN109710401A (zh) * 2018-12-17 2019-05-03 国云科技股份有限公司 一种云计算资源成本优化方法
CN111142968A (zh) * 2019-12-26 2020-05-12 联想(北京)有限公司 电子设备配置推荐处理方法、装置及存储介质
CN111277442A (zh) * 2020-01-21 2020-06-12 赣江新区智慧物联研究院有限公司 无线意图驱动网络的管理方法、装置及系统
CN112306574A (zh) * 2020-10-30 2021-02-02 联想(北京)有限公司 一种配置方法及装置

Also Published As

Publication number Publication date
CN114938334A (zh) 2022-08-23

Similar Documents

Publication Publication Date Title
US11863458B1 (en) Reflected packets
US11552841B2 (en) Method and apparatus for configuring service
US10063630B2 (en) System and method for service orchestration in distributed cloud environment
EP3072260B1 (en) Methods, systems, and computer readable media for a network function virtualization information concentrator
CN110505101B (zh) 一种网络切片编排方法及装置
WO2021052374A1 (zh) 网络拥塞控制方法、节点、系统及存储介质
US10411972B2 (en) Determining impact of network failures
US20220191140A1 (en) Data transmission control method, apparatus, and storage medium
US11165716B2 (en) Data flow processing method and device
WO2021244247A1 (zh) 转发数据报文的方法、网络节点、系统及存储介质
CN114444708A (zh) 获取模型的方法、装置、设备、系统及可读存储介质
CN116389238A (zh) 一种软件定义广域网sd-wan保障应用体验的方法和系统
US9356876B1 (en) System and method for classifying and managing applications over compressed or encrypted traffic
WO2022166582A1 (zh) 网络管理方法、装置、设备及计算机可读存储介质
EP4340320A1 (en) Communication method, device and system
CN115277504A (zh) 一种网络流量监控方法、装置和系统
WO2022042403A1 (zh) 生成路由信息、发送位置信息及转发报文的方法及设备
KR101802037B1 (ko) Ｓｄｎ 환경에서 서비스 기능 체이닝을 위한 ｏａｍ 메시지 전송 방법 및 시스템
WO2022253194A1 (zh) 报文转发方法、装置及通信网络
WO2022253190A1 (zh) 业务流的性能检测方法、装置及通信网络
WO2022253192A1 (zh) 报文转发方法、装置及通信网络
WO2023193498A1 (zh) 网络的可靠性评估方法、装置、计算设备以及存储介质
WO2023005817A1 (zh) 路径确定方法、装置、设备、系统及计算机可读存储介质
US20230171180A1 (en) Data processing method, packet sending method, and apparatus
US10834005B2 (en) Buffer shortage management system

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22748861

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 22748861

Country of ref document: EP

Kind code of ref document: A1