WO2023125411A1 - 带宽推荐方法及装置、显示装置、控制设备 - Google Patents

带宽推荐方法及装置、显示装置、控制设备 Download PDF

Info

Publication number
WO2023125411A1
WO2023125411A1 PCT/CN2022/141924 CN2022141924W WO2023125411A1 WO 2023125411 A1 WO2023125411 A1 WO 2023125411A1 CN 2022141924 W CN2022141924 W CN 2022141924W WO 2023125411 A1 WO2023125411 A1 WO 2023125411A1
Authority
WO
WIPO (PCT)
Prior art keywords
bandwidth
traffic
link
scene
tunnel
Prior art date
Application number
PCT/CN2022/141924
Other languages
English (en)
French (fr)
Inventor
史浩
曾峰
夏斌
李粤琛
张枭山
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 WO2023125411A1 publication Critical patent/WO2023125411A1/zh

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L47/00—Traffic control in data switching networks
    • H04L47/70—Admission control; Resource allocation
    • H04L47/80—Actions related to the user profile or the type of traffic
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L12/00—Data switching networks
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L43/00—Arrangements for monitoring or testing data switching networks
    • H04L43/08—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
    • H04L43/0876—Network utilisation, e.g. volume of load or congestion level
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L47/00—Traffic control in data switching networks
    • H04L47/70—Admission control; Resource allocation
    • H04L47/80—Actions related to the user profile or the type of traffic
    • H04L47/803—Application aware

Definitions

  • the present application relates to the field of network technologies, and in particular to a bandwidth recommendation method and device, a display device, and a control device.
  • a link refers to a path established between two nodes for transmitting certain or several types of service data. For example, a link established between nodes A and B for transmitting office service data.
  • bandwidth needs to be configured for the link, and the link transmits service data according to the bandwidth.
  • this way of configuring bandwidth by default may cause subsequent bandwidth waste, or insufficient bandwidth may cause transmission quality problems.
  • the present application provides a bandwidth recommendation method and device, a display device, and a control device, which can dynamically recommend bandwidth for links based on link traffic patterns, reduce bandwidth waste and improve service transmission quality.
  • the present application provides a bandwidth recommendation method.
  • the method can be applied to control equipment.
  • the control device acquires the first traffic data of the link, determines the traffic mode of the link according to the first traffic data of the link, determines the first bandwidth according to the traffic mode of the link, and indicates the link association
  • the network device applies the first bandwidth.
  • the traffic mode indicates the change trend of the traffic value of the link within the first time period.
  • the control device collects traffic data of the link, then determines the traffic pattern of the link according to the traffic data, determines the first bandwidth based on the traffic pattern, and instructs the network device associated with the link to apply the first bandwidth.
  • this method can perform bandwidth recommendation in real time during service operation, which is more real-time than pre-configured link bandwidth, and the recommended bandwidth is more accurate, reducing bandwidth waste.
  • the traffic pattern is divided first, and then the corresponding bandwidth is determined according to the traffic pattern, so that different bandwidth recommendations can be implemented for different traffic patterns, so that the recommended bandwidth is more in line with the business traffic transmission requirements , improving the quality of service transmission.
  • control device further determines the first scene of the link according to the time corresponding to the first time period or the event corresponding to the first time period, and stores the first scene and the second scene.
  • control device further determines a second scenario of the link according to a second time period, determines that the second scenario matches the first scenario, determines a second bandwidth according to the first bandwidth, and Instructing a network device associated with the link to apply the second bandwidth.
  • control device stores the first bandwidth and the corresponding scene, and when the same or similar scene appears later, it can determine the second bandwidth according to the first bandwidth, and recommend the second bandwidth to the network device for application, so that Improve the efficiency of bandwidth recommendation while ensuring link transmission quality.
  • control device further determines a third bandwidth and a condition for applying the third bandwidth according to the traffic pattern, and when the condition for applying the third bandwidth is satisfied, indicates the link associated
  • the network device applies the third bandwidth.
  • the third bandwidth is greater than the first bandwidth.
  • the transmission quality of the link service can be further improved.
  • control device further sends the third bandwidth or the difference between the third bandwidth and the first bandwidth, and the conditions for applying the third bandwidth to the network associated with the link
  • the device is configured to instruct a network device associated with the link to apply the third bandwidth when the link satisfies the condition for applying the third bandwidth.
  • control device also receives second flow data.
  • the second traffic data includes the number of traffic violations and/or the duration of traffic violations of the link within the third time period when the first bandwidth is applied.
  • the traffic limit violation indicates that the traffic of the link exceeds the first bandwidth.
  • the control device instructs a network device associated with the link to apply the third bandwidth in response to judging that the link satisfies the condition for applying the third bandwidth according to the second traffic data.
  • control device may directly send the third bandwidth and the conditions for applying the third bandwidth to the network device, and the network device determines whether to apply the third bandwidth based on whether the conditions for applying the third bandwidth are satisfied. bandwidth.
  • control device may also receive the second data flow sent by the network device, judge whether the application condition is met according to the second data flow, and only send the third bandwidth to the network device for configuration when the application condition is met. .
  • condition for applying the third bandwidth includes: the number of traffic violations on the link exceeds a number threshold, and/or the duration of traffic violations on the link exceeds a time threshold.
  • control device further displays the second scene and the second bandwidth.
  • control device further displays the first scenario and/or the traffic pattern of the first scenario that matches the second scenario.
  • the traffic pattern includes at least one of a small-value oscillating type, a burst burr type, a steady double-peak type, and an oscillating double-peak type.
  • a display device in a second aspect, includes an acquisition unit and a display unit.
  • the acquiring unit is configured to acquire a scenario to which a link belongs, and determine a recommended bandwidth for the link based on the scenario.
  • the display unit is configured to display the scenario and the bandwidth recommended for the link.
  • a device for recommending bandwidth includes an acquisition unit, a determination unit and an indication unit.
  • the acquiring unit is configured to acquire the first traffic data of the link.
  • the determining unit is configured to determine a traffic pattern of the link according to the first traffic data of the link, and determine a first bandwidth according to the traffic pattern of the link.
  • the instructing unit is configured to instruct a network device associated with the link to apply the first bandwidth.
  • the traffic pattern indicates a change trend of a traffic value of the link within a first time period.
  • the determining unit is further configured to determine the first scene of the link according to the time corresponding to the first time period or the event corresponding to the first time period.
  • the device also includes a storage unit.
  • the storage unit is configured to store the first scene and the first bandwidth corresponding to the first scene.
  • the determining unit is further configured to determine a second scenario of the link according to a second time period.
  • the determining unit is further configured to determine that the second scene matches the first scene, and determine a second bandwidth according to the first bandwidth.
  • the instructing unit is further configured to instruct a network device associated with the link to apply the second bandwidth.
  • the determining unit is further configured to determine a third bandwidth and a condition for applying the third bandwidth according to the traffic pattern.
  • the third bandwidth is greater than the first bandwidth.
  • the instructing unit is further configured to instruct a network device associated with the link to apply the third bandwidth when the condition for applying the third bandwidth is met.
  • the indicating unit is further configured to send the third bandwidth or the difference between the third bandwidth and the first bandwidth, and the conditions for applying the third bandwidth to the link
  • the associated network device is configured to instruct the network device associated with the link to apply the third bandwidth when the link satisfies the condition for applying the third bandwidth.
  • the device further includes a receiving unit.
  • the receiving unit is configured to receive second traffic data.
  • the instructing unit is further configured to instruct a network device associated with the link to apply the third bandwidth in response to judging that the link satisfies the condition for applying the third bandwidth according to the second traffic data.
  • the second traffic data includes the number of traffic violations and/or the duration of traffic violations of the link within the third time period when the first bandwidth is applied.
  • the traffic limit violation indicates that the traffic of the link exceeds the first bandwidth.
  • condition for applying the third bandwidth includes: the number of traffic violations on the link exceeds a number threshold, and/or the duration of traffic violations on the link exceeds a time threshold.
  • the device further includes a display unit.
  • the display unit is configured to display the second scene and the second bandwidth.
  • the display unit is further configured to display the first scenario and/or the traffic pattern of the first scenario that matches the second scenario.
  • the display unit is further configured to display the first bandwidth and/or the third bandwidth corresponding to the link.
  • the traffic pattern includes at least one of a small-value oscillating type, a burst burr type, a steady double-peak type, and an oscillating double-peak type.
  • a control device in a fourth aspect, includes a processor and memory.
  • the memory is used to store software programs and modules.
  • the processor implements the above first aspect or the method in any possible implementation manner of the first aspect by running or executing a software program and/or module stored in the memory.
  • 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 set separately from the processor.
  • the memory can be a non-transitory (non-transitory) memory, such as a read-only memory (read only memory, ROM), which can be integrated with the processor on the same chip, or can be set in different On the chip, the application does not limit the type of the memory and the arrangement of the memory and the processor.
  • a non-transitory memory such as a read-only memory (read only memory, ROM)
  • ROM read only memory
  • a computer program product includes computer program code, and when the computer program code is run by a computer, the computer is made to execute the method in the above first aspect or any possible implementation manner of the first aspect.
  • the present application provides a computer-readable storage medium, the computer-readable storage medium is used to store program codes executed by a processor, and the program codes include any possibility for realizing the above-mentioned first aspect. method in the implementation of .
  • a chip including a processor, and the processor is used to call and execute instructions stored in the memory from the memory, so that the communication device installed with the chip executes any possible method of the first aspect above. method in the implementation.
  • another chip in an eighth aspect, another chip is provided.
  • the other chip includes 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.
  • the processor is configured to execute codes in the memory, and when the codes are executed, the processor is configured to execute the method in any possible implementation manner of the first aspect above.
  • FIG. 1 is a schematic diagram of an application scenario provided by an embodiment of the present application
  • FIG. 2 is a flowchart of a bandwidth recommendation method provided in an embodiment of the present application
  • Fig. 3 is a schematic diagram of a small-value oscillating flow sequence provided by the embodiment of the present application.
  • Fig. 4 is a schematic curve diagram of a burst-type traffic sequence provided by an embodiment of the present application.
  • Fig. 5 is a schematic diagram of a smooth bimodal flow sequence provided in the embodiment of the present application.
  • FIG. 6 is a schematic diagram of an oscillating double-peak flow sequence provided in an embodiment of the present application.
  • FIG. 7 is a flow chart of a bandwidth recommendation method provided by an embodiment of the present application.
  • FIG. 8 is a flow chart of a bandwidth recommendation method provided by an embodiment of the present application.
  • FIG. 9 is a flow chart of a method for determining a traffic pattern provided by an embodiment of the present application.
  • Fig. 10 is a schematic diagram of the first-order difference sequence of the flow sequence shown in Fig. 4;
  • Fig. 11 is a schematic diagram of the first-order difference sequence of the flow sequence shown in Fig. 5;
  • Fig. 12 is a schematic diagram of the first-order difference sequence of the flow sequence shown in Fig. 6;
  • Fig. 13 is a schematic diagram of a bimodal flow sequence provided by the embodiment of the present application.
  • Fig. 14 is a schematic diagram of a smoothed traffic sequence provided by the embodiment of the present application.
  • FIG. 15 is a flowchart of a method for determining a first bandwidth provided by an embodiment of the present application.
  • FIG. 16 is a flowchart of a method for determining a third bandwidth provided by an embodiment of the present application.
  • FIG. 17 is a flow chart of a bandwidth recommendation method provided by an embodiment of the present application.
  • Fig. 18 is a flow chart of a bandwidth recommendation method provided by an embodiment of the present application.
  • Fig. 19 is a block diagram of a device for recommending bandwidth according to an embodiment of the present application.
  • Fig. 20 is a block diagram of a display device provided by an embodiment of the present application.
  • Fig. 21 shows a schematic structural diagram of a control device provided by an exemplary embodiment of the present application.
  • the application scenario may be a communication network such as a distributed storage system or a data center.
  • the following uses a distributed storage system as an example to describe the application scenario of this application.
  • FIG. 1 is a schematic structural diagram of an application scenario provided by an embodiment of the present application.
  • the application scenario includes a control device 11 and a network device 12 .
  • the control device 11 may be a management node in the network, for example, a network management device.
  • the network device 12 may be a network node in the network, such as a routing device.
  • a link 13 is established between two network devices 12 for transmitting service data.
  • the link may be a physical link between devices, or a logical link between devices, for example, the link may be a tunnel (tunnel).
  • the tunnel is used for the transmission of a specific service, and can transmit at least one data flow.
  • the control device 11 is connected to at least one of the two network devices 12, and is used to implement bandwidth recommendation for the link.
  • the network devices 12 at both ends of the link are shown in the figure, other network devices may also be included between the two network devices 12, and the link passes through these network devices, and the control device 11 can communicate with the network devices in these network devices At least one connection, or none to any of these network devices.
  • Fig. 2 is a flowchart of a bandwidth recommendation method provided by an embodiment of the present application. This method can be executed by the control device 11 in the application scenario shown in FIG. 1.
  • the control device determines the traffic pattern based on the collected traffic data, and then determines the bandwidth based on the traffic pattern and recommends it to the network device. to apply.
  • the control device can collect the traffic data of the link, and recommend the bandwidth of the link to the network device, so that the network device can configure the bandwidth of the link; the control device can also collect the traffic data of the tunnel, and give The network device recommends the bandwidth of the tunnel, so that the network device can configure the bandwidth of the tunnel.
  • the process of the bandwidth recommendation method is the same regardless of whether the object is the link or the tunnel in the link.
  • the process description of the bandwidth recommendation method can also target links. As shown in Figure 2, the method includes the following steps.
  • the first traffic data includes a traffic sequence composed of a plurality of traffic samples collected by the network device according to collection time intervals for the tunnel to be collected within the collection time period.
  • the collection time period refers to a time range from the start of collection to the end of collection, and the range may be one hour, one day, one week, one month, and so on.
  • the collection time interval can be set as required, such as 1 minute, 5 minutes, 1 hour, etc.
  • Traffic samples refer to the traffic values of the tunnel collected during the collection period.
  • a flow sample includes both the collection time and the collected flow value.
  • the flow sequence includes a plurality of flow values arranged in sequence according to collection time.
  • the collection time period or the collection time interval may be a default value, for example, the collection time period is one hour, and the collection time interval is 5 minutes.
  • the collection time period or collection time interval may also be a configuration value, for example, the administrator inputs a configuration instruction on the interface of the control device to configure a specific collection time period or collection time interval.
  • S12 Determine a traffic mode of the tunnel according to the first traffic data of the tunnel.
  • the traffic pattern is used to indicate a change trend of the traffic value of the tunnel within the first time period.
  • the first time period may be the aforementioned collection time period.
  • the traffic pattern of the tunnel includes at least one of the following: small-value oscillating type, burst burr type, steady double-peak type, and oscillating double-peak type.
  • FIG. 3 shows a schematic curve diagram of a small-value oscillating flow sequence provided by an embodiment of the present application.
  • the abscissa is time in minutes
  • the ordinate is traffic in megabits per second (million bits per second, Mb/s).
  • the traffic is at a low traffic value (eg, 1 ⁇ 3 Mb/s) most of the time (eg, more than 50%) in the acquisition time period.
  • the traffic is lower than 3Mb/s for more than 90% of the time, and there are few higher traffic values.
  • the traffic exceeding 3Mb/s in the figure is only a few points (traffic samples), accounting for 5 % or less, and no peaks are formed.
  • FIG. 4 shows a schematic curve diagram of a burst-type traffic sequence provided by an embodiment of the present application.
  • the abscissa is time in minutes, and the ordinate is flow in Mb/s.
  • the span of the traffic value in the traffic sequence is very large, from a few Mb/s to hundreds of Mb/s, and the traffic change is irregular, that is, no obvious peaks and troughs are formed.
  • the traffic A certain percentile value of the sequence such as the 50% percentile value, or the average flow value of the flow sequence is used as the threshold, and abnormal flows exceeding the threshold occur more frequently.
  • 40Mb/s is used as the threshold, and the frequency of abnormal traffic exceeding this threshold is relatively high, accounting for more than 20%.
  • Fig. 5 shows a schematic curve diagram of a smooth bimodal flow sequence provided by the embodiment of the present application.
  • the abscissa is time in minutes
  • the ordinate is flow in Mb/s.
  • the flow value in the flow sequence changes according to the peak-valley-peak waveform, and there are few flow burrs in the peaks and valleys, for example, no more than a threshold.
  • the flow burr refers to the rise or fall of the flow In the changing trend, there is a sudden abnormal traffic, such as point A in Figure 5.
  • FIG. 6 shows a schematic curve diagram of an oscillating bimodal flow sequence provided by the present application.
  • the abscissa is time in minutes
  • the ordinate is flow in Mb/s.
  • the flow in the flow sequence changes according to the peak-valley-peak waveform, and there are many flow burrs in the peaks and valleys, for example, exceeding the aforementioned threshold, which can be designed according to needs, such as 20%.
  • S13 Determine the first bandwidth according to the traffic pattern of the tunnel.
  • the first bandwidth is determined according to the traffic pattern, so that the first bandwidth can meet the service data transmission requirements in the corresponding traffic pattern.
  • the first bandwidth may refer to the minimum bandwidth reserved for the tunnel, and the first bandwidth can ensure that the tunnel traffic runs smoothly without a sudden change. Moreover, when the traffic of the tunnel changes suddenly, the bandwidth of the tunnel can also be increased on the basis of the first bandwidth, so as to meet the requirement of service transmission in the tunnel.
  • the control device may send the first bandwidth to the network device, so that the network device configures the tunnel according to the first bandwidth.
  • the control device executes a configuration command on the network device, instructing the network device to transmit data for services entering the tunnel according to the first bandwidth included in the configuration command.
  • the control device usually determines the first bandwidth according to the traffic data of one network device among the plurality of network devices associated with the tunnel, for example, the network device at the entrance of the tunnel.
  • the traffic value in a traffic sample may be the rate at which the network device receives traffic within the corresponding collection time interval, for example, the traffic value is the rate at which the incoming interface associated with the tunnel on the network device receives traffic within the corresponding collection time interval rate.
  • the traffic value in a traffic sample may be the rate at which the input queue of the ingress interface associated with the tunnel on the network device receives traffic within a corresponding collection time interval.
  • the control device may send the first bandwidth to the network device used to determine the flow data of the first bandwidth, or to multiple network devices associated with the tunnel (for example, all network devices associated with the tunnel devices), instructing these network devices to apply the first bandwidth.
  • the first bandwidth may be used to configure the rate of the outgoing interface associated with the link of the network device, for example, the first bandwidth is used to configure the interface rate of the outgoing interface associated with the tunnel on the network device.
  • the first bandwidth may be used to configure the output queue of the outgoing interface associated with the tunnel on the network device, so that the rate of sending traffic of the outgoing interface is the first bandwidth.
  • control device may also determine the first bandwidth according to the traffic data of multiple network devices associated with the tunnel at the same time, and then send the first bandwidth to one or more network devices, instructing the network devices to apply the first bandwidth.
  • traffic values at the same collection time may be averaged to form an average traffic sequence, and a traffic pattern is determined according to the average traffic sequence, thereby determining the first bandwidth.
  • the maximum value of the traffic values at the same acquisition time may be determined, and then a maximum traffic sequence is formed, and a traffic pattern is determined according to the maximum traffic sequence, thereby determining the first bandwidth.
  • the traffic data of the tunnel is collected, the traffic pattern of the tunnel is determined according to the traffic data, the first bandwidth is determined based on the traffic pattern, and then the network device associated with the tunnel is instructed to apply the first bandwidth.
  • this method can recommend bandwidth in real time during service operation, which is more real-time than pre-configured tunnel bandwidth, and the recommended bandwidth is more accurate, reducing bandwidth waste.
  • the traffic pattern is divided first, and then the corresponding bandwidth is determined according to the traffic pattern, so that different bandwidth recommendations can be implemented for different traffic patterns, so that the recommended bandwidth is more in line with the business traffic transmission requirements , improving the quality of service transmission.
  • FIG. 7 is a flow chart of a bandwidth recommendation method provided by an embodiment of the present application. The method can be executed by the control device in the application scenario shown in FIG. 1 . As shown in Fig. 7, the method includes the following steps.
  • S22 Determine a traffic mode of the tunnel according to the first traffic data of the tunnel.
  • S23 Determine the first bandwidth according to the traffic pattern of the tunnel.
  • steps S21 to S23 reference may be made to steps S11 to S13, and details will not be described here.
  • S24 Determine the first scene of the tunnel according to the time corresponding to the first time period or the event corresponding to the first time period, and store the first scene and the first scene corresponding to the first scene bandwidth.
  • the first scene may include at least one of festival scene, event scene and daily scene.
  • the scene can be determined according to the current time and events that occur. For example, it is first judged whether it is a festival, if it is, it is determined as a festival scene, if not, then it is judged whether there is a set event happening, if it is, it is determined as an event scene, if not, it is determined as a daily scene.
  • judging whether a set event currently occurs can be determined based on a message or instruction received by the control device. For example, when a conference event occurs, the control device will receive a conference notification, and the scene can be judged to be an event scene.
  • festival scenes, event scenes and daily scenes can be divided into different subtypes.
  • the scene when the scene is a festival scene, it can be divided into different festival scenes according to specific festival types, for example, Mid-Autumn Festival type, National Day type, weekend type and other types.
  • specific festival types for example, Mid-Autumn Festival type, National Day type, weekend type and other types.
  • event scene When the scene is an event scene, it can be divided into different event scenes according to specific events, for example, a conference event type, a game live broadcast event type, and the like.
  • the scene when the scene is a daily scene, it can be divided into different daily scenes according to time periods, for example, daytime type, nighttime type, working time type, and non-working time type.
  • control device may repeatedly execute steps S21 to S24, so as to store various scenarios and corresponding first bandwidths.
  • S25 Determine a second scene of the tunnel according to a second time period.
  • the second time period may be a time period where the current time is located.
  • the control device determines the second scene where the tunnel is located at the current time according to the time in the second time period or events occurring in the second time period.
  • the determination is made according to the subtype when determining the scenario.
  • That is to determine the first scene that matches the second scene for example, select a scene that matches the second scene from multiple stored scenes, where the determined scene that matches the second scene is the first scene.
  • matching the second scene with the first scene may mean that the second scene is the same as the first scene, or that the second scene is similar to the first scene.
  • the second scene is the first festival, it is determined that the second scene matches the first scene, including:
  • the second scene is the first event, and it is determined that the second scene matches the first scene, including:
  • search for a second event similar to the first event If the first event is not found, then search for a second event similar to the first event.
  • S27 Determine a second bandwidth according to the first bandwidth, and instruct a network device associated with the tunnel to apply the second bandwidth.
  • the second bandwidth may be equal to the first bandwidth, or the second bandwidth may be calculated based on the first bandwidth, for example, multiply the first bandwidth by a coefficient to obtain the second bandwidth, and the like.
  • the method further includes: displaying the second scene and the second bandwidth.
  • the administrator can clearly understand the matching relationship between the bandwidth recommended for the tunnel and the scenario of the tunnel.
  • the method further includes: displaying the first scenario and/or the traffic pattern of the first scenario that matches the second scenario.
  • the administrator can clearly understand the traffic pattern basis of the recommended bandwidth for the tunnel.
  • the administrator can also adjust the bandwidth recommendation according to the traffic pattern, for example, adjust the coefficient in step S27.
  • control device may also store a traffic pattern corresponding to the first traffic data.
  • the control device may also receive new traffic data, determine a new traffic pattern based on the new traffic data, and determine a recommended bandwidth based on the similarity between the new traffic pattern and the stored traffic patterns. For example, when the similarity between the new traffic pattern and the stored traffic pattern one exceeds a threshold, the control device determines a recommended bandwidth for the new traffic pattern based on the bandwidth corresponding to the traffic pattern one.
  • the recommended bandwidth may be equal to the bandwidth corresponding to traffic pattern 1, or may be calculated based on the bandwidth corresponding to traffic pattern 1, for example, multiply the bandwidth corresponding to traffic pattern 1 by a coefficient to obtain the recommended bandwidth.
  • control device when the control device does not find a scene matching the second scene in step S26, the control device does not perform step S27.
  • the control device may determine the recommended bandwidth based on the traffic pattern in the second scenario.
  • the execution process please refer to the method flow shown in FIG. 2 , which will not be repeated here.
  • control device stores the first bandwidth and the corresponding scene, and when the same or similar scene appears later, it can determine the second bandwidth according to the first bandwidth, and recommend the second bandwidth to the network device for application, so that While ensuring the quality of tunnel transmission, improve the efficiency of bandwidth recommendation.
  • FIG. 8 is a flow chart of a bandwidth recommendation method provided by an embodiment of the present application. The method can be executed by the control device and the network device in the application scenario shown in FIG. 1 . As shown in Fig. 8, the method includes the following steps.
  • the control device sends a traffic collection instruction to the network device.
  • the network device receives the traffic collection instruction.
  • both the control device and the network device include acquisition modules, the acquisition module in the control device is used to send the above traffic collection instruction, and the acquisition module in the network device is used to collect traffic when receiving the traffic collection instruction.
  • the traffic collection instruction may include at least one of the following: an identifier of a tunnel to be collected, a collection time period for traffic collection, and a collection time interval.
  • the flow collection instruction may include the identification of the tunnel to be collected, the collection time period of flow collection, and some or all of the fields in the collection time interval, the fields included in the flow collection instruction shall be collected using the fields included in the flow collection instruction. Value, the field not included in the traffic collection instruction, can use the default value when collecting.
  • the traffic collection instruction includes the identifier of the tunnel to be collected, the traffic of the tunnel corresponding to the tunnel identifier to be collected is collected. If the traffic collection instruction does not include the identifier of the tunnel to be collected, a default tunnel is collected.
  • the default tunnel may be one tunnel or multiple tunnels, for example, all tunnels configured in the network device.
  • the traffic collection instruction may not include any of the above fields, that is, the traffic collection instruction only instructs the network device to collect traffic, but does not limit the parameters of traffic collection, that is, the parameters to be collected Default values are used for the tunnel ID, traffic collection time period, and collection time interval.
  • the above default values can be configured in the network device in advance, for example, all tunnels are collected by default, the collection time period is one day, and the collection time interval is 5 minutes.
  • S32 The network device collects first traffic data of the tunnel.
  • the first traffic data includes a traffic sequence composed of a plurality of traffic samples collected by the network device according to collection time intervals for the tunnel to be collected within the collection time period.
  • the network device collects tunnel traffic every 5 minutes within a day, and obtains a traffic sample composed of collection time and traffic value. Through multiple collections in a day, 288 traffic samples are obtained. 288 traffic samples are calculated according to Sequence from 0:00 to 24:00 to get the traffic sequence.
  • S33 The network device sends the first traffic data of the tunnel to the control device.
  • the control device receives the first flow data of the tunnel.
  • S34 The control device determines a traffic pattern according to the first traffic data of the tunnel.
  • the traffic pattern is used to indicate the change trend of the traffic of the tunnel within the collection time period.
  • the traffic pattern of the tunnel includes at least one of the following: small-value oscillating type, burst burr type, steady double-peak type, and oscillating double-peak type.
  • small-value oscillating type burst burr type
  • steady double-peak type steady double-peak type
  • oscillating double-peak type for the description of the above four flow modes, reference may be made to the descriptions of FIG. 3 to FIG. 6 in step S22 above.
  • the first traffic data collected by the network device corresponds to a traffic pattern, and at this time, the control device only needs to determine the traffic pattern.
  • the first traffic data collected by the network device corresponds to multiple traffic patterns, and the multiple traffic patterns are respectively located in different time periods.
  • the control device determines the various traffic patterns, and then may use one of the most important traffic patterns as the tunnel traffic pattern, or use these multiple traffic patterns together as the tunnel traffic pattern.
  • the traffic pattern with the largest time ratio can be selected.
  • various traffic patterns and their corresponding time periods can be recorded in detail.
  • S35 The control device determines the first bandwidth according to the traffic mode of the tunnel.
  • the first bandwidth determined for different traffic patterns is usually different, so that the first bandwidth can meet the transmission requirements of service data in the corresponding traffic pattern.
  • the first bandwidth refers to the minimum bandwidth reserved for the tunnel, and the first bandwidth can ensure that the tunnel traffic runs smoothly without a sudden change.
  • the bandwidth of the tunnel may also be increased on the basis of the first bandwidth, so as to meet the requirements of service transmission in the tunnel.
  • the control device determines a third bandwidth and a condition for applying the third bandwidth according to the traffic pattern.
  • the third bandwidth is greater than the first bandwidth.
  • the third bandwidth is the bandwidth used when the first bandwidth cannot meet the service transmission requirements in the tunnel, and the condition for applying the third bandwidth is the condition that the first bandwidth cannot meet the service transmission requirements in the tunnel.
  • condition for applying the third bandwidth includes: within a time period, the number of traffic violations exceeds a number threshold, and/or the duration of traffic violations exceeds a time threshold.
  • the traffic exceeding the limit refers to that the traffic of the tunnel exceeds the first bandwidth.
  • the foregoing time period, frequency threshold, and time threshold can be set as required, for example, the time period is one day or one week, the frequency threshold is 10 or 30 times, and the time threshold is 1 hour or 5 hours.
  • control device further includes a traffic profile generation module, and the traffic profile generation module is configured to execute step S37.
  • S37 The control device generates a traffic image of the tunnel.
  • the traffic profile includes a traffic pattern, a first bandwidth, and a third bandwidth.
  • the control device can find the traffic profile based on the traffic pattern and recommend bandwidth for the tunnel.
  • the traffic profile further includes at least one of the following: tunnel identifier, scene, traffic peak, abnormal mode, and peak-to-average ratio.
  • the scenes include at least one of festival scenes, event scenes and everyday scenes. In this way, the traffic profile can more comprehensively describe and describe the traffic of the tunnel.
  • the tunnel identifier is used to uniquely identify a tunnel.
  • the tunnel identifier in the traffic profile is the tunnel identifier obtained from the traffic collection instruction. If the traffic collection instruction does not include the identifier of the tunnel to be collected, the tunnel in the traffic profile is the default tunnel identifier set.
  • the identifier of the tunnel can be a combination of source node name, destination node name, and bearer service type, such as SHBJ01, where SH represents the source node name, BJ represents the destination node name, and 01 is the identifier of the tunnel bearer service type.
  • the holiday scene means that the time corresponding to the traffic data for generating the traffic profile is a festival;
  • the event scene means that the traffic data for generating the traffic profile mainly includes the traffic of a certain event, and the event here usually refers to bandwidth requirements and needs to be guaranteed.
  • Traffic events such as game live events. Due to the high bandwidth requirements of live game events, traffic profiling needs to be performed separately. In daily scenarios, the time does not belong to festivals and the collected traffic does not include events.
  • the scene can be determined according to the current time and events that occur. For example, it is first judged whether it is a festival, if it is, it is determined as a festival scene, if not, then it is judged whether there is a set event happening, if it is, it is determined as an event scene, if not, it is determined as a daily scene.
  • judging whether a set event currently occurs can be determined based on a message or instruction received by the control device. For example, when a conference event occurs, the control device will receive a conference notification, and the scene can be judged to be an event scene.
  • festival scenes, event scenes and daily scenes can be divided into different subtypes.
  • the scene when the scene is a festival scene, according to the specific festival type, it can be divided into types such as Mid-Autumn Festival type and National Day type.
  • the scene when the scene is an event scene, it can be divided into conference event types, game live event types, and the like.
  • the scene When the scene is a daily scene, it can be divided into a daytime type, a nighttime type, and the like.
  • the same tunnel when generating traffic profiles, the same tunnel can generate different traffic profiles in different scenarios, so that a tunnel can have multiple traffic profiles, and these traffic profiles can be used in different scenarios according to their own scenarios. Make bandwidth recommendations.
  • the flow peak value can be obtained by analyzing the flow data, for example, determining the maximum flow value from the flow sequence, and the maximum flow value is the flow peak value.
  • the abnormal mode is used to indicate the occurrence probability, degree of deviation and duration of abnormal traffic.
  • the abnormal traffic refers to traffic exceeding a threshold, and the threshold may be an average traffic value of a traffic sequence.
  • the probability of occurrence of abnormal traffic refers to the ratio of the number of traffic samples corresponding to the abnormal traffic to the total traffic samples in the traffic sequence.
  • the deviation refers to the deviation between the abnormal traffic and the threshold value.
  • the duration can include the duration of each abnormal traffic and all The total duration of abnormal traffic.
  • the average peak ratio refers to the ratio of the flow average value to the flow peak value
  • the flow average value is the average value of the flow values of all flow samples in the flow sequence
  • the flow peak value is the maximum value of the flow value in the flow sequence.
  • S38 The control device persistently stores the traffic portrait.
  • control device further includes a profile storage module, configured to persistently store the traffic profile, and the granularity of the persistent storage can be set by the control device according to historical traffic changes of the tunnel, or by an administrator.
  • profile storage module configured to persistently store the traffic profile, and the granularity of the persistent storage can be set by the control device according to historical traffic changes of the tunnel, or by an administrator.
  • control device determines the time granularity of the persistent storage of the traffic profile according to the magnitude of the historical traffic change of the tunnel.
  • the smaller the magnitude of the historical traffic change the larger the time granularity of the persistent storage can be set;
  • the larger the range the smaller the time granularity of persistent storage can be set.
  • the magnitude of the historical traffic change of the tunnel is generally related to the service type carried by the tunnel. For example, if some business traffic is relatively stable, the historical traffic of the tunnel changes less, and the time granularity of the persistent storage of the traffic portrait can be set larger, such as one month. However, some business traffic increases or decreases rapidly, and the historical tunnel traffic changes greatly. The time granularity of persistent storage of traffic portraits can be set to a small value, such as one week.
  • the corresponding relationship between the identifier of the tunnel and the time for persistent storage of the traffic profile can be set in advance, and after the control device generates the traffic profile, it can be determined according to the corresponding relationship
  • the time for persistent storage is set so that the traffic profile can be stored persistently, without analyzing the historical traffic changes of the tunnel.
  • the administrator can set the settings according to the granularity of hour, day, week, and month to realize the persistent storage of traffic portraits by the control device.
  • control device may store the traffic profile in a form of a table, for example, each field of a traffic profile is stored in each cell of the same row of the table.
  • the first bandwidth and the third bandwidth are represented by numerical values, and other fields may be represented by corresponding identifiers.
  • the finally stored traffic profile includes parameters such as the traffic pattern, the first bandwidth and the third bandwidth, and there is no need to store the traffic sequence, which avoids the problem of increasing storage pressure caused by the traffic sequence increasing with time, and can Greatly reduce the storage pressure of the equipment.
  • control device stores the first scenario and the first bandwidth corresponding to the first scenario in the form of a traffic profile.
  • the control device recommends bandwidth for the network device based on the traffic profile.
  • control device can perform scene matching and bandwidth recommendation through traffic profiling.
  • control device may select a traffic profile corresponding to the tunnel according to the tunnel identifier, scene, etc., and then recommend the bandwidth applied to the tunnel to the network device according to the first bandwidth and/or the third bandwidth in the traffic profile.
  • the method further includes: displaying the identifier of the tunnel and the traffic pattern of the tunnel, so as to provide guidance for network management personnel to perform network configuration.
  • the name of the flow mode and the corresponding flow curve may be displayed.
  • the method further includes: displaying the first bandwidth and/or the third bandwidth corresponding to the tunnel.
  • displaying the above-mentioned first bandwidth and/or third bandwidth it may be displayed in the form of a graph or the like.
  • the administrator can clearly understand the matching relationship between the bandwidth recommended for the tunnel and the traffic actually transmitted by the tunnel.
  • the administrator can also actively adjust the bandwidth recommendation method according to the matching relationship, for example, adjust the parameter value used in the bandwidth recommendation method.
  • FIG. 9 is a flowchart of a method for determining a traffic pattern provided by an embodiment of the present application. The method can be executed by the control device in the application scenario shown in FIG. 1 . As shown in Fig. 9, the method includes the following steps.
  • S41 According to the first flow data, determine whether the flow of the tunnel meets the small-value oscillation condition.
  • step S42 is executed.
  • a traffic sample whose traffic exceeds a first threshold in the traffic sequence is positioned as an abnormal traffic sample.
  • Small-value oscillation conditions include: the ratio of the total number of abnormal flow samples in the flow series to the total number of flow samples in the flow series is less than the second threshold, and the maximum time length of continuous abnormal flow samples in the flow series accounts for the ratio of the collection time period to less than the second threshold.
  • the traffic value corresponding to the first threshold is relatively low, for example, it is set to 3Mb/s.
  • the second threshold is set to a small value to ensure that the traffic is low most of the time, for example, the value of the second threshold is less than 20%, for example, the value is 5% to 10%.
  • the third threshold is relatively small, such as less than 5%.
  • the third threshold is The ratio x of the total number of abnormal traffic samples in the statistical traffic series to the total number of traffic samples in the traffic series, if Then it is considered that the flow pattern is not a small-value oscillation type; the ratio y of the maximum time length of abnormal flow samples that appear continuously in the statistical flow sequence to the collection time period, if If the above two conditions are not satisfied, the flow pattern is considered to be a small-value oscillation type.
  • the flow sequence of the small-value oscillation type at least most of the flows are less than the first threshold, at most small Part of the traffic is greater than the first threshold. Referring to FIG. 3 , all traffic in the traffic sequence is less than the first threshold 3Mb/s.
  • S42 According to the first flow data, determine whether the flow of the tunnel meets the burst condition.
  • step S43 is executed.
  • the burst glitch condition includes: the probability of exceeding the burst difference threshold in the probability density distribution of the first-order difference sequence of the traffic sequence exceeds the fourth threshold.
  • the first-order difference sequence of the flow sequence is a sequence formed by the difference between two adjacent flow samples in the flow sequence.
  • the probability density distribution refers to the distribution of the probability (that is, the proportion) of each value in the first-order difference sequence.
  • the burst difference threshold is used to limit the difference between the difference between two adjacent traffic samples, which is considered as burst traffic.
  • the probability of exceeding the burst difference threshold in the probability density distribution is the proportion of burst traffic in the entire traffic sequence. If the proportion of burst traffic (that is, the aforementioned probability) exceeds the fourth threshold, it is considered as burst traffic.
  • S43 According to the first flow data, determine whether the flow of the tunnel meets the oscillation condition.
  • the oscillation condition includes: the probability of exceeding the oscillation difference threshold in the probability density distribution of the first-order difference sequence of the traffic sequence exceeds the fifth threshold.
  • the oscillating difference threshold is used to limit the difference between two adjacent traffic samples, which is considered as oscillating traffic.
  • the probability of exceeding the shock difference threshold in the probability density distribution is the proportion of shock traffic in the entire traffic sequence. If the proportion of oscillating traffic exceeds the fifth threshold, it is considered as oscillating traffic.
  • the burst difference threshold is greater than the oscillation difference threshold.
  • the burst difference threshold is 0.8
  • the oscillation difference threshold is 0.16
  • the fourth threshold is 0.1
  • the fifth threshold is 0.25.
  • the first-order difference sequence of the flow sequence is calculated, and its probability density distribution is obtained, and the flow pattern is distinguished through the probability density distribution.
  • FIG. 10 is a schematic diagram of a first-order difference sequence of the burst-type traffic sequence shown in FIG. 4 .
  • the abscissa is the serial number, for example, the serial number 1 represents the difference between the first flow sample and the second flow sample, and the serial number 2 represents the difference between the second flow sample and the third flow sample, and so on.
  • the coordinates are flow differential values, and the unit is Mb/s. It can be seen that the first-order difference sequence of the burst-type traffic sequence has a wide distribution range, ranging from -5 to 2, and there are more bursts in the corresponding traffic sequence.
  • FIG. 11 is a schematic diagram of the first-order difference sequence of the stationary bimodal flow sequence shown in FIG. 5 .
  • the abscissa is the serial number
  • the ordinate is the flow differential value
  • the unit is Mb/s. It can be seen that the distribution range of the first-order difference sequence of the stationary bimodal flow sequence is relatively narrow, mainly concentrated between 0 and -1, and the flow change in the corresponding flow sequence is relatively stable.
  • FIG. 12 is a schematic curve diagram of the first-order difference sequence of the oscillating bimodal flow sequence shown in FIG. 6 .
  • the abscissa is the serial number
  • the ordinate is the flow differential value
  • the unit is Mb/s. It can be seen that the first-order differential sequence distribution of the oscillating bimodal flow sequence is narrower than that of the burst burr type, wider than that of the steady bimodal type, and the main distribution is between -1 and 2, and the corresponding flow sequence changes more than the burst
  • the glitch type is smooth, but not as smooth as the bimodal type.
  • the traffic types are distinguished by setting the burst difference threshold, the oscillation difference threshold, the fourth threshold, and the fifth threshold, and performing condition judgment.
  • the above judgment conditions are expressed by the formula as follows:
  • the burst differential threshold be The oscillation difference threshold is The fourth threshold is The fifth threshold is Use f(t) to represent the flow sequence, and use f'(t) to represent the first-order difference sequence of f(t).
  • f(t) is considered to be a burst glitch type; where, Indicates the probability of exceeding the burst difference threshold in the probability density distribution of the first-order difference sequence of the traffic sequence;
  • f(t) is considered to be an oscillating type; Indicates the probability of exceeding the shock difference threshold in the probability density distribution of the first-order difference sequence;
  • f(t) is considered to be stationary.
  • S44 According to the first flow data, determine whether the flow of the tunnel belongs to the bimodal type.
  • tunnel traffic When the tunnel traffic is stable and bimodal, it is determined that the tunnel traffic is stable bimodal; when the tunnel traffic is oscillating and bimodal, it is determined that the tunnel traffic is oscillating bimodal.
  • step S44 includes the following steps:
  • the first step is to perform kernel smoothing on the traffic sequence.
  • Kernel smoothing is to perform a weighted average of the traffic sample and several adjacent samples. The weight is determined by the kernel. For example, the closer the traffic sample, the greater the weight.
  • the kernel function used for kernel smoothing may be a uniform kernel function.
  • FIG. 13 is a schematic diagram of a bimodal flow sequence provided by the present application. Referring to Fig. 13, the abscissa is time in minutes, and the ordinate is flow in Mb/s. L1 represents the original flow sequence, L2 represents the smoothed flow sequence, and L2 is shown separately as shown in Figure 14.
  • the second step is to find the valley value in the smoothed flow sequence, that is, point t1 in Figure 13 and Figure 14.
  • Valley values are located where the descending series (to the left of the valley) and the ascending series (to the right of the valley) meet.
  • the value of the valley value can be determined by limiting the duration of the descending sequence and ascending sequence on the left and right sides of the valley value to a certain value, such as exceeding 1 hour.
  • the ascending sequence and descending sequence are not required to be strictly ascending and descending sequences.
  • the ascending and descending sequences may be some mutations in the ascending and descending sequences, but as long as the part of the sequence exceeding the set ratio (such as 90%) is rising or descending That's it.
  • the valley value is used as the dividing point to divide the smoothed flow sequence into two sequences, that is, the left and right sides of t1 in Figure 13 and Figure 14 two paragraphs.
  • the fourth step is to determine the mountain peaks in the two sequences, that is, points t2 and t3 in Figure 13 and Figure 14.
  • the mountain peak is located at the intersection of the ascending sequence (the left side of the mountain peak) and the descending sequence (the right side of the mountain peak).
  • the value of the mountain peak can be determined by limiting the duration of the ascending sequence and descending sequence on the left and right sides of the mountain peak to a certain value, for example, more than 1 hour.
  • the 2 mountain peaks and the previous valley value divide the smoothed flow sequence into 4 segments, and the four segments from left to right are ascending sequence, descending sequence, ascending sequence, and descending sequence.
  • the traffic pattern of the tunnel belongs to the bimodal type.
  • the above conditions are as follows: the difference between the larger peak value and the smaller peak value will not be too large, such as smaller than the first difference value, and the difference between the smaller peak value and the valley value will not be too small, such as greater than the second difference value , the second difference is smaller than the first difference.
  • the embodiment of the present application can also use the ratio relationship between the larger mountain peak, the smaller mountain peak and the valley value as the condition:
  • ⁇ p is a threshold
  • the threshold can be set based on needs, for example, the value is between 1 and 3.
  • f(t1) is the valley value.
  • the numerator is required as small as possible, as large as possible, due to more than the then when and The difference is small, and It is established when the difference between f(t1) and f(t1) is large.
  • the flow type of the flow is other types, that is, when the flow does not belong to any of the above flow types, it is other types.
  • the way to determine the first bandwidth and the third bandwidth can refer to one of the small-value oscillating type, the glitch burst type, the smooth bimodal type, and the oscillating bimodal type, or other methods can be used to determine .
  • the traffic pattern can also be divided into other ways, such as dividing into small value type, oscillating type and stable type.
  • Traffic patterns can be determined by calculating the variance of the mean. For example, first calculate the mean value of the flow series, compare the mean value with the threshold value 1, if the mean value is less than the threshold value 1, it is a small-value type, otherwise it is not a small-value type; when it is not a small-value type, then calculate the variance of the flow series, and compare the variance and The size of the threshold 2, if the variance is greater than the threshold 2, it is an oscillating type, otherwise it is a stable type.
  • FIG. 15 is a flow chart of a first bandwidth determination method provided by an embodiment of the present application. The method can be executed by the control device in the application scenario shown in FIG. 1 , and as shown in FIG. 15 , the method includes the following steps.
  • the first threshold used when judging the small-value oscillating type is 3 Mb/s, then 3 Mb/s is used as the first bandwidth of the small-value oscillating type.
  • the first priority service refers to the highest priority (core) service, for example, the priorities are 1, 2, 3, 4, etc. in descending order.
  • the peak value of the traffic sequence is directly used as the first bandwidth in consideration of its importance and the characteristics of the traffic pattern.
  • the median of the overall traffic level may be the 50% to 95th percentile of the overall traffic level.
  • the 80th percentile of the overall traffic level may be the 50% to 95th percentile of the overall traffic level.
  • the second priority is lower than the first priority, for example, the second priority means that the priority is at least one of 2, 3 and 4.
  • the point density threshold is used to limit the maximum value of the density of points in the traffic sequence whose traffic is higher than the first bandwidth when the first bandwidth is used.
  • the point density D(BW) is defined as follows:
  • f(t) represents a traffic sequence
  • BW is the first bandwidth
  • N is the number of traffic samples in the traffic sequence
  • t represents time
  • T is the collection time of the last traffic sample
  • I represents the point where the traffic is greater than BW count value.
  • each flow sequence Represents 1 unit width
  • the total width of the flow sequence is N
  • the height from 0 to the maximum flow is 1
  • the height from 0 to the first bandwidth is BW/max t ⁇ [0,T] f(t)
  • the height from the first bandwidth to the maximum flow is 1-BW/max t ⁇ [0,T] f(t).
  • the number of points exceeding the first bandwidth BW is divided by the area between the first bandwidth and the maximum flow of the entire flow sequence to obtain the point density.
  • a threshold ⁇ on the point density is set.
  • the specific expression for the reserved bandwidth is as follows:
  • each point in the flow sequence f(t) is used as the first bandwidth BW, and the point density D(BW) is calculated respectively to obtain a plurality of point density values.
  • the first bandwidth should be kept as small as possible. The advantage of doing so is that the first bandwidth to be reserved can be effectively reduced on the premise that the abnormal probability does not increase much.
  • the traffic sequence is divided into a sparsely distributed upper part and a densely distributed lower part, which can not only ensure the transmission of dense traffic in the lower layer, but also filter out the burst traffic in the upper layer.
  • the method may further include: when it is determined according to the point density threshold that the first bandwidth is lower than the 80% quantile bandwidth of the traffic sequence, using the 80% quantile bandwidth of the traffic sequence instead of the burst.
  • the glitch-type first bandwidth ensures that the abnormal probability of traffic is within a reasonable range.
  • the following table 1 shows the scheme for determining the first bandwidth of the smooth double peak, oscillating double peak and burst glitch type provided by the embodiment of the present application:
  • this solution can classify and target traffic of different services, characteristics and modes by performing different bandwidth reservations for different traffic patterns.
  • Bandwidth recommendation can be performed accurately, so as to avoid traffic waste, reduce costs, and ensure service transmission quality at the same time.
  • the first bandwidth of different traffic patterns can also be set in the following manner: for example, the first bandwidth of the smooth bimodal type adopts the peak value of the traffic sequence, and the small value oscillating type, the oscillating bimodal type and the burst burr type The first bandwidth of all uses the 85% quantile value of the traffic sequence.
  • Fig. 16 is a flow chart of a third bandwidth determination method provided by an embodiment of the present application. The method may be executed by the control device in the application scenario shown in FIG. 1 , and as shown in FIG. 16 , the method includes the following steps.
  • the peak over threshold (POT) method is a commonly used analysis method, which provides modeling for the analysis of the part of the data that exceeds a certain high threshold. Assume ⁇ X 1 ,X 2 ,X 3 ,....X n ⁇ is a set of independently distributed random variables. By selecting an appropriate threshold u, the data above the threshold can be filtered out as extreme values. The extreme value theory believes that the flow of the extreme value part obeys the generalized Pareto distribution (Generalized Pareto Distribution, GPD).
  • GPD Generalized Pareto Distribution
  • CDF cumulative distribution function
  • the distribution is determined by three parameters: the position coefficient ⁇ , the extent coefficient ⁇ , and the shape coefficient ⁇ .
  • the position coefficient ⁇ may be a threshold used when determining the extremum of the sequence.
  • the cumulative probability distribution function of the GPD distribution can be fitted by the maximum likelihood method.
  • S62 Determine the third bandwidth according to the cumulative probability distribution function of the Pareto distribution and the expected abnormal burst probability.
  • the method further includes: determining a condition for a network device associated with a tunnel to apply the third bandwidth according to the first bandwidth.
  • the condition for applying the third bandwidth includes: the number of traffic violations exceeds a number threshold, and/or the duration of traffic violations exceeds a time threshold.
  • the foregoing time period, frequency threshold, and time threshold can be set as required, for example, the time period is one day or one week, the frequency threshold is 10 or 30 times, and the time threshold is 1 hour or 5 hours.
  • an appropriate burst reservation is determined through the confidence degree of the customer's expectation on the third bandwidth. For example, if the customer's expected confidence level for the third bandwidth is 90%, then the quantile value corresponding to the CDF of 0.9 in the cumulative probability distribution function is found, and the quantile value is the obtained third bandwidth.
  • the third bandwidth can also be set in the following manner: for example, divide the first bandwidth corresponding to the traffic pattern by a coefficient to obtain the third bandwidth, and the coefficient takes a value between 0 and 1, for example, the coefficient The value is 0.7 or 0.8.
  • the third bandwidth can also be directly determined according to the traffic pattern, for example, the third bandwidth of the steady double-peak type is 120% of the peak value of the traffic sequence, and the small-value oscillating type, the oscillating double-peak type, and the burst burr type The third bandwidth is used for the peak value of the traffic sequence.
  • Fig. 17 is a flowchart of a bandwidth recommendation method provided by an embodiment of the present application. The method can be executed by the control device and the network device in the application scenario shown in FIG. 1 . As shown in FIG. 17 , the method includes the following steps.
  • S71 Control the device to acquire traffic portraits.
  • control device includes a determination module, and the determination module obtains the traffic portrait corresponding to the identifier of the tunnel from the portrait storage module.
  • step S71 includes the following steps:
  • the determination is made according to the subtype when determining the scenario.
  • the current time is the first festival
  • the acquired scene is the traffic portrait of the festival scene, including:
  • the first event occurs at the current time, and the acquired scene is the traffic portrait of the event scene, including:
  • traffic portraits of multiple tunnels may be stored in the portrait storage module of the control device, so when acquiring traffic portraits, tunnel identifiers can be used for retrieval.
  • tunnel identifiers can be used for retrieval.
  • only the traffic image of one tunnel is stored in the image storage module of the control device, there is no need to use the identifier of the tunnel for retrieval.
  • the process of acquiring the traffic profile in step S71 is also the process of determining the matching scene and the first bandwidth corresponding to the matching scene.
  • the control device recommends the network bandwidth for the network device associated with the tunnel according to the first bandwidth.
  • control device may also consider the entire network situation when recommending bandwidth to network devices. For example, when the network is not congested, it may directly use the first bandwidth for bandwidth recommendation, and when the network is congested, it may use the first bandwidth Appropriate reduction is recommended on the basis.
  • the network congestion is judged according to at least one of network parameters such as time delay and packet loss, which will not be described in detail in this application.
  • S73 The network device performs bandwidth configuration according to the network bandwidth recommended by the control device.
  • the network device further includes a bandwidth configuration module, which configures the tunnel bandwidth of the tunnel according to the bandwidth recommended by the control device.
  • the traffic profile also includes a third bandwidth.
  • the bandwidth recommendation process is as follows: the control device first sends the first bandwidth (or the bandwidth determined according to the first bandwidth) to the network device, so that the network device uses the first bandwidth.
  • the bandwidth (or the bandwidth determined according to the first bandwidth) configures the bandwidth of the tunnel.
  • the control device receives the number of traffic violation times and the duration after the configuration of the first bandwidth (or the bandwidth determined according to the first bandwidth) sent by the network device. If the number of traffic violations and the duration meet the conditions, the control device sends the third bandwidth to the network device, so that the network device uses the third bandwidth to adjust the bandwidth configured for the tunnel. This further improves the service transmission quality.
  • exceeding the limit means that the traffic exceeds the first bandwidth. Every time the flow exceeds the basic flow, the number of limit violations will be increased by 1.
  • the duration of limit violations is calculated based on the number of limit violations. For example, one time of limit violation is 5 minutes, and when the number of limit violations is 10, the duration of limit violations is 50 minutes.
  • FIG. 18 is a flowchart of a bandwidth recommendation method provided by an embodiment of the present application.
  • FIG. 18 shows the detailed process of the above steps S72 and S73. As shown in FIG. 18, the method includes the following steps.
  • the network device sends the bandwidth currently configured for the tunnel to the control device.
  • the bandwidth currently configured for the tunnel is provided by the bandwidth configuration module of the network device, and the control device outputs the bandwidth currently configured for the tunnel to the determination module of the control device after receiving it.
  • the determination module of the control device acquires the first bandwidth in the traffic profile from the storage module.
  • step 7233 is executed.
  • the control device sends the first bandwidth to the network device.
  • the network device After receiving, the network device outputs the first bandwidth to the bandwidth configuration module.
  • the bandwidth configuration module of the network device uses the first bandwidth to configure the bandwidth.
  • the network device sends the second flow data to the control device.
  • the second traffic data includes when the first bandwidth is applied, the number of traffic violations and/or the duration of traffic violations of the tunnel within the third time period, and the traffic violations indicate that the link traffic exceeds the first bandwidth.
  • control device outputs the second flow data to the determination module of the control device after receiving it.
  • the network device may periodically report the second traffic data to the control device.
  • the control device judges whether to query and deliver the third bandwidth according to the received second traffic data.
  • the determination module of the control device acquires the third bandwidth in the traffic profile from the storage module.
  • the condition for applying the third bandwidth includes: the number of traffic violations exceeds a number threshold, and/or the duration of traffic violations exceeds a time threshold.
  • the foregoing time period, frequency threshold, and time threshold can be set as required, for example, the time period is one day or one week, the frequency threshold is 10 or 30 times, and the time threshold is 1 hour or 5 hours.
  • the control device sends a bandwidth adjustment instruction to the network device according to the third bandwidth.
  • control device may directly include the third bandwidth in the bandwidth adjustment instruction, or include a difference between the third bandwidth and the first bandwidth.
  • the control device may also increase or decrease the third bandwidth according to the number of limit violations, and then include it in the bandwidth adjustment instruction. For example, if the number of limit violations exceeds a certain number of times, the third bandwidth may be increased and then included in the bandwidth adjustment instruction.
  • the bandwidth configuration module of the network device adjusts the bandwidth configured for the tunnel according to the bandwidth adjustment instruction.
  • the difference between the third bandwidth and the first bandwidth is added to the original first bandwidth, or the originally configured bandwidth is directly adjusted to the third bandwidth for bandwidth adjustment.
  • the first bandwidth and the third bandwidth are indicated step by step.
  • the network control device may also send the first bandwidth, the third bandwidth, and the conditions for applying the third bandwidth to the network device, so that the network device may, after applying the first bandwidth, The condition determines whether the third bandwidth is to be further applied.
  • the third bandwidth is used to adjust the configured bandwidth when the number of traffic violations and the duration are too high, which improves the accuracy of bandwidth recommendation and improves Improve bandwidth utilization, reduce bandwidth waste, and save costs.
  • Fig. 19 is a block diagram of an apparatus for recommending bandwidth according to an embodiment of the present application.
  • the apparatus for recommending bandwidth can be implemented as all or a part of the control device through software, hardware or a combination of the two.
  • the apparatus for recommending bandwidth may include: an acquiring unit 801 , a determining unit 802 and an indicating unit 803 .
  • the acquiring unit 801 is configured to acquire the first flow data of the link.
  • the determining unit 802 is configured to determine a traffic pattern of the link according to the first traffic data of the link, and determine a first bandwidth according to the traffic pattern.
  • the instructing unit 803 is configured to instruct a network device associated with the link to apply the first bandwidth.
  • the traffic pattern indicates a change trend of a traffic value of the link within a first time period.
  • the determining unit 802 is further configured to determine the first scene of the link according to the time corresponding to the first time period or the event corresponding to the first time period.
  • the device further includes a storage unit 804 .
  • the storage unit 804 is configured to store the first scene and the first bandwidth corresponding to the first scene.
  • the determining unit 802 is further configured to determine a second scene of the link according to a second time period.
  • the determining unit 802 is further configured to determine that the second scene matches the first scene, and determine a second bandwidth according to the first bandwidth.
  • the instructing unit 803 is further configured to instruct a network device associated with the link to apply the second bandwidth.
  • the determining unit 802 is further configured to determine a third bandwidth and a condition for applying the third bandwidth according to the traffic pattern, where the third bandwidth is greater than the first bandwidth.
  • the instructing unit 803 is further configured to instruct a network device associated with the link to apply the third bandwidth when the condition for applying the third bandwidth is met.
  • the instructing unit 803 is further configured to send the third bandwidth or the difference between the third bandwidth and the first bandwidth, and the conditions for applying the third bandwidth to the link
  • the associated network device is configured to instruct the network device associated with the link to apply the third bandwidth when the link satisfies the condition for applying the third bandwidth.
  • the device further includes a receiving unit 805 .
  • the receiving unit 805 is configured to receive second flow data.
  • the instructing unit 803 is further configured to instruct a network device associated with the link to apply the third bandwidth in response to judging that the link satisfies the condition for applying the third bandwidth according to the second traffic data.
  • the second traffic data includes the number of traffic violations and/or the duration of traffic violations of the link within the third time period when the first bandwidth is applied.
  • the traffic limit violation indicates that the traffic of the link exceeds the first bandwidth.
  • condition for applying the third bandwidth includes: the number of traffic violations on the link exceeds a number threshold, and/or the duration of traffic violations on the link exceeds a time threshold.
  • the device further includes a display unit 806 .
  • the display unit 806 is configured to display the second scene and the second bandwidth.
  • the display unit 806 is further configured to display the first scenario and/or the traffic pattern of the first scenario that matches the second scenario.
  • the traffic pattern includes at least one of a small-value oscillating type, a burst burr type, a steady double-peak type, and an oscillating double-peak type.
  • the foregoing units may be implemented by one device or by different devices, for example, the acquiring unit and the determining unit are implemented by one device, and the storage unit, indicating unit and display unit are implemented by one device.
  • the bandwidth recommendation device when the bandwidth recommendation device provided in the above-mentioned embodiments performs bandwidth recommendation, it only uses the division of the above-mentioned functional units for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units according to needs That is, the internal structure of the device is divided into different functional units to complete all or part of the functions described above.
  • the device for recommending bandwidth provided by the above-mentioned embodiments belongs to the same idea as the embodiment of the bandwidth recommending method, and its specific implementation process is detailed in the method embodiment, and will not be repeated here.
  • FIG. 20 is a block diagram of a display device provided by an embodiment of the present application.
  • the display device can be implemented as a part of the control device or a display device independent of the control device through software, hardware or a combination of the two.
  • the display device may include: an acquisition unit 901 and a display unit 902 .
  • the acquiring unit 901 is configured to acquire a scene to which a link belongs, and determine a recommended bandwidth for the link based on the scene.
  • the display unit 902 is configured to display the scenario and the bandwidth recommended for the link.
  • the display unit 902 is further configured to display at least one of a scenario matching the scenario, a bandwidth corresponding to the matching scenario, and a traffic pattern corresponding to the matching scenario.
  • the display device provided by the above-mentioned embodiments performs display
  • the division of the above-mentioned functional units is used as an example for illustration.
  • the above-mentioned function allocation can be completed by different functional units according to needs.
  • the internal structure of the device is divided into different functional units to complete all or part of the functions described above.
  • the display device provided by the above embodiment and the embodiment of the bandwidth recommendation method belong to the same idea, and the specific implementation process thereof is detailed in the method embodiment, and will not be repeated here.
  • FIG. 21 shows a schematic structural diagram of a control device 150 provided by an embodiment of the present application.
  • the control device 150 shown in FIG. 21 is configured to perform the operations involved in the bandwidth recommendation method shown in any one of FIGS. 2 to 18 above.
  • the control device 150 can be realized by a general bus architecture.
  • control device 150 includes at least one processor 151 , a memory 153 and at least one communication interface 154 .
  • the processor 151 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 data processing unit (Data Processing Unit, DPU), A microprocessor or one or more integrated circuits used to implement the solutions of this application.
  • the processor 151 includes an application-specific integrated circuit (application-specific integrated circuit, ASIC), a programmable logic device (programmable logic device, PLD) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof.
  • the PLD is, for example, a complex programmable logic device (complex programmable logic device, CPLD), a field-programmable gate array (field-programmable gate array, FPGA), a general array logic (generic array logic, GAL) or any combination thereof. It can realize or execute various logical blocks, modules and circuits described in conjunction with the disclosure of the embodiments of the present application.
  • the processor may also be a combination that implements computing functions, for example, a combination of one or more microprocessors, a combination of a DSP and a microprocessor, and the like.
  • control device 150 also includes a bus.
  • the bus is used to transfer information between the various components of the control device 150 .
  • the bus may be a peripheral component interconnect standard (PCI for short) bus or an extended industry standard architecture (EISA for short) bus or the like.
  • PCI peripheral component interconnect standard
  • 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 used in FIG. 21 , but it does not mean that there is only one bus or one type of bus.
  • the memory 153 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 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 disc storage, optical disc Storage (including Compact Disc, Laser Disc, Optical Disc, Digital Versatile Disc, Blu-ray Disc, etc.), magnetic disk storage medium, or other magnetic storage device, or is 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, but not limited to.
  • the memory 153 exists independently, for example, and is connected to the processor 151 via a bus.
  • the memory 153 can also be integrated with the processor 151 .
  • the communication interface 154 uses any device such as a transceiver for communicating with other devices or a communication network.
  • the communication network can be Ethernet, radio access network (RAN) or wireless local area network (wireless local area networks, WLAN).
  • the communication interface 154 may include a wired communication interface, and may also include a wireless communication interface.
  • the communication interface 154 can be an Ethernet (Ethernet) interface, a Fast Ethernet (Fast Ethernet, FE) interface, a Gigabit Ethernet (Gigabit Ethernet, GE) interface, an Asynchronous Transfer Mode (Asynchronous Transfer Mode, ATM) interface, a wireless local area network ( wireless local area networks, WLAN) interface, cellular network communication interface or a combination thereof.
  • the Ethernet interface can be an optical interface, an electrical interface or a combination thereof.
  • the communication interface 154 may be used for the control device 150 to communicate with other devices.
  • the processor 151 may include one or more CPUs, such as CPU0 and CPU1 shown in FIG. 21 . Each of these processors may 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).
  • control device 150 may include multiple processors, such as the processor 151 and the processor 155 shown in FIG. 21 .
  • 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 such as computer program instructions.
  • control device 150 may further include an output device and an input device.
  • Output devices are in communication with processor 151 and can display information in a variety of ways.
  • the output device may be a liquid crystal display (liquid crystal display, LCD), a light emitting diode (light emitting diode, LED) display device, a cathode ray tube (cathode ray tube, CRT) display device, or a projector (projector).
  • the input device is in communication with the processor 151 and can receive user input in a variety of ways.
  • the input device may be a mouse, a keyboard, a touch screen device, or a sensing device, among others.
  • the memory 153 is used to store the program code 1510 for implementing the solution of the present application, and the processor 151 can execute the program code 1510 stored in the memory 153 . That is, the control device 150 can implement the data processing method provided by the method embodiment by executing the program code 1510 in the memory 153 through the processor 151 .
  • One or more software modules may be included in the program code 1510 .
  • the processor 151 itself may also store program codes or instructions for executing the solutions of the present application.
  • control device 150 in the embodiment of the present application may correspond to the controller in each method embodiment above, and the processor 151 in the control device 150 reads the instructions in the memory 153, so that the control shown in FIG. 21
  • the device 150 is capable of performing all or part of the operations performed by the controller.
  • the processor 151 is configured to obtain the first traffic data of the link, determine the traffic pattern of the link according to the first traffic data of the link, determine the first bandwidth according to the traffic pattern, and instruct the A network device associated with the link applies the first bandwidth.
  • the traffic pattern indicates a change trend of a traffic value of the link within a first time period.
  • each step of the bandwidth recommendation method shown in any one of FIG. 2 to FIG. 18 is implemented by an integrated logic circuit of hardware in the processor of the control device 150 or an instruction in the form of software.
  • the steps of the methods disclosed in connection with the embodiments of the present application may be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules in the processor.
  • the software module can be located in a mature storage medium in the field such as random access memory, flash memory, read-only memory, programmable read-only memory or electrically erasable programmable memory, register.
  • 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. To avoid repetition, no detailed description is given here.
  • the embodiment of the present application also provides a chip, including: 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 internal connection paths.
  • the processor is configured to execute codes in the memory, and when the codes are executed, the processor is configured to execute any one of the traffic profile generation method or bandwidth recommendation method described above.
  • processor may be a CPU, or other general-purpose processors, DSP, ASIC, FPGA or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, and the like.
  • 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 the ARM architecture.
  • 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 separated from the processor.
  • the above-mentioned memory may include read-only memory and random-access memory, and provides instructions and data to the processor.
  • Memory may also include non-volatile random access memory.
  • the memory may also store reference blocks and target blocks.
  • the memory can be either volatile memory or nonvolatile memory, or can include both volatile and nonvolatile memory.
  • the non-volatile memory may be ROM, PROM, EPROM, EEPROM or flash memory.
  • Volatile memory can be RAM, which acts as external cache memory.
  • many forms of RAM are available. For example, SRAM, DRAM, SDRAM, DDR SDRAM, ESDRAM, SLDRAM, and DR RAM.
  • a computer-readable storage medium stores computer instructions.
  • the control device executes the above-mentioned Provided traffic profile generation method or bandwidth recommendation method.
  • a computer program product including instructions is also provided, which, when running on the control device, causes the control device to execute the traffic profile generation method or the bandwidth recommendation method provided above.
  • all or part of them may be implemented by software, hardware, firmware or any combination thereof.
  • software When implemented using software, it may 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. When the computer program instructions are loaded and executed on the computer, the processes or functions according to the present application will be generated in whole or in part.
  • the computer can be a general purpose computer, a special purpose computer, a computer network, or other programmable devices.
  • 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 transmitted from a website, computer, server or data center Transmission to another website site, computer, server, or data center by wired (eg, coaxial cable, optical fiber, DSL) or wireless (eg, infrared, wireless, microwave, etc.) means.
  • 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 or a data center integrated with one or more available media.
  • the available medium may be a magnetic medium (for example, a floppy disk, a hard disk, or a magnetic tape), an optical medium (for example, a DVD), or a semiconductor medium (for example, a Solid State Disk).
  • the program can be stored in a computer-readable storage medium.
  • the above-mentioned The storage medium mentioned may be a read-only memory, a magnetic disk or an optical disk, and the like.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Environmental & Geological Engineering (AREA)
  • Data Exchanges In Wide-Area Networks (AREA)

Abstract

公开了一种带宽推荐方法及装置、显示装置和控制设备。方法可以应用于控制设备。控制设备获取链路的第一流量数据，根据链路的第一流量数据确定链路的流量模式，根据链路的流量模式确定第一带宽，并指示链路关联的网络设备应用第一带宽。

Description

带宽推荐方法及装置、显示装置、控制设备
本申请要求于2021年12月31日提交的申请号202111671672.1、申请名称为“带宽推荐方法及装置、显示装置、控制设备”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
本申请涉及网络技术领域，特别涉及一种带宽推荐方法及装置、显示装置、控制设备。
背景技术
链路是指在两个节点之间建立的用于传输某种或某几种业务数据的通路。例如，在节点A之间和节点B之间建立的用于传输办公类业务数据的链路。
通常，在建立链路时需要给链路配置带宽，链路按照该带宽进行业务数据的传输。但是，这种默认配置带宽的方式可能造成后续带宽的浪费，或者带宽不足并带来传输质量问题。
发明内容
本申请提供了一种带宽推荐方法及装置、显示装置、控制设备，能够基于链路的流量模式为链路动态推荐带宽，减少了带宽浪费并可以提高业务传输质量。
第一方面，本申请提供了一种带宽推荐方法。该方法可以应用于控制设备。控制设备获取链路的第一流量数据，根据所述链路的第一流量数据确定所述链路的流量模式，根据所述链路的流量模式确定第一带宽，并指示所述链路关联的网络设备应用所述第一带宽。其中，流量模式指示所述链路在第一时间段内的流量值的变化趋势。
在本申请中，控制设备通过采集链路的流量数据，然后根据该流量数据确定链路的流量模式，基于流量模式确定第一带宽，再指示链路关联的网络设备应用第一带宽。一方面，该方法可以在业务运行过程中实时进行带宽的推荐，相比于预先配置链路带宽而言，更具有实时性，推荐的带宽更准确，减少了带宽浪费。另一方面，上述第一带宽的确定过程中，先划分流量模式，然后按照流量模式确定对应的带宽，从而可以实现针对不同流量模式进行不同的带宽推荐，使得推荐的带宽更加符合业务流量传输需求，提高了业务传输质量。
可选地，所述控制设备还根据所述第一时间段对应的时间或所述第一时间段对应的事件确定所述链路的第一场景，并存储所述第一场景和所述第一场景对应的所述第一带宽。
可选地，所述控制设备还根据第二时间段确定所述链路的第二场景，确定所述第二场景和所述第一场景匹配，根据所述第一带宽确定第二带宽，并指示所述链路关联的网络设备应用所述第二带宽。
在该实现方式中，控制设备存储第一带宽及对应的场景，在后续出现相同或相似场景时，可以根据第一带宽确定第二带宽，并将第二带宽推荐给网络设备进行应用，从而在保证链路传输质量的同时，提高带宽推荐效率。
可选地，所述控制设备还根据所述流量模式确定第三带宽和应用所述第三带宽的条件，以及当所述应用所述第三带宽的条件满足时，指示所述链路关联的网络设备应用所述第三带宽。其中，所述第三带宽大于第一带宽。
在该实现方式中，通过在第一带宽基础上设置更大的第三带宽和应用所述第三带宽的条件，当应用所述第三带宽的条件满足时，指示网络设备应用第三带宽，可以进一步提升链路业务的传输质量。
可选地，所述控制设备还发送所述第三带宽或所述第三带宽和所述第一带宽的差值，以及所述应用所述第三带宽的条件给所述链路关联的网络设备，以指示所述链路关联的网络设备在所述链路满足所述应用所述第三带宽的条件时应用所述第三带宽。
可选地，所述控制设备还接收第二流量数据。所述第二流量数据包括在所述第一带宽被应用时，所述链路在第三时间段内的流量越限的次数和/或流量越限的持续时间。所述流量越限指示所述链路的流量超过所述第一带宽。所述控制设备响应于根据所述第二流量数据判断所述链路满足所述应用所述第三带宽的条件，指示所述链路关联的网络设备应用所述第三带宽。
在一种实现方式中，控制设备可以直接将第三带宽和应用所述第三带宽的条件发送给网络设备，由网络设备自行根据是否满足应用所述第三带宽的条件来确定是否应用第三带宽。在另一种实现方式中，控制设备也可以通过接收网络设备发送的第二数据流量，根据第二数据流量判断是否满足应用条件，在满足应用条件时，才发送第三带宽给网络设备进行配置。通过上述两种实现方式，均能够实现第三带宽的推荐和应用，提升链路业务的传输质量，增强了第三带宽应用的灵活性。
可选地，所述应用所述第三带宽的条件包括：所述链路的流量越限的次数超过次数阈值，和/或，所述链路的流量越限的持续时间超过时间阈值。
可选地，所述控制设备还显示所述第二场景和所述第二带宽。
可选地，所述控制设备还显示与所述第二场景匹配的所述第一场景和/或所述第一场景的流量模式。
可选地，所述流量模式包括小值震荡型、突发毛刺型、平稳双峰型和震荡双峰型中的至少一种。
第二方面，提供了一种显示装置。所述显示装置包括获取单元和显示单元。
所述获取单元，用于获取链路所属的场景，并基于所述场景确定为所述链路推荐的带宽。所述显示单元，用于显示所述场景和所述为所述链路推荐的带宽。
第三方面，提供了一种带宽推荐装置。所述装置包括获取单元、确定单元和指示单元。
所述获取单元，用于获取链路的第一流量数据。所述确定单元，用于根据所述链路的第一流量数据确定所述链路的流量模式，并根据所述链路的流量模式确定第一带宽。所述指示单元，用于指示所述链路关联的网络设备应用所述第一带宽。所述流量模式指示所述链路在第一时间段内的流量值的变化趋势。
可选地，所述确定单元，还用于根据所述第一时间段对应的时间或所述第一时间段对应的事件确定所述链路的第一场景。所述装置还包括存储单元。所述存储单元，用于存储所述 第一场景和所述第一场景对应的所述第一带宽。
可选地，所述确定单元，还用于根据第二时间段确定所述链路的第二场景。所述确定单元，还用于确定所述第二场景和所述第一场景匹配，并根据所述第一带宽确定第二带宽。所述指示单元，还用于指示所述链路关联的网络设备应用所述第二带宽。
可选地，所述确定单元，还用于根据所述流量模式确定第三带宽和应用所述第三带宽的条件。所述第三带宽大于第一带宽。所述指示单元，还用于当所述应用所述第三带宽的条件满足时，指示所述链路关联的网络设备应用所述第三带宽。
可选地，所述指示单元，还用于发送所述第三带宽或所述第三带宽和所述第一带宽的差值，以及所述应用所述第三带宽的条件给所述链路关联的网络设备，以指示所述链路关联的网络设备在所述链路满足所述应用所述第三带宽的条件时应用所述第三带宽。
可选地，所述装置还包括接收单元。所述接收单元，用于接收第二流量数据。所述指示单元，还用于响应于根据所述第二流量数据判断所述链路满足所述应用所述第三带宽的条件，指示所述链路关联的网络设备应用所述第三带宽。所述第二流量数据包括在所述第一带宽被应用时，所述链路在第三时间段内的流量越限的次数和/或流量越限的持续时间。所述流量越限指示所述链路的流量超过所述第一带宽。
可选地，所述应用所述第三带宽的条件包括：所述链路的流量越限的次数超过次数阈值，和/或，所述链路的流量越限的持续时间超过时间阈值。
可选地，所述装置还包括显示单元。所述显示单元，用于显示所述第二场景和所述第二带宽。
可选地，所述显示单元，还用于显示与所述第二场景匹配的所述第一场景和/或所述第一场景的流量模式。
可选地，所述显示单元还用于显示所述链路对应的所述第一带宽和/或所述第三带宽。
可选地，所述流量模式包括小值震荡型、突发毛刺型、平稳双峰型和震荡双峰型中的至少一种。
第四方面，提供了一种控制设备。所述控制设备包括处理器和存储器。所述存储器用于存储软件程序以及模块。所述处理器通过运行或执行存储在所述存储器内的软件程序和/或模块实现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。
可选地，所述处理器为一个或多个，所述存储器为一个或多个。
可选地，所述存储器可以与所述处理器集成在一起，或者所述存储器与处理器分离设置。
在具体实现过程中，存储器可以为非瞬时性(non-transitory)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。
第五方面，提供了一种计算机程序产品。所述计算机程序产品包括计算机程序代码，当所述计算机程序代码被计算机运行时，使得所述计算机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。
第六方面，本申请提供了一种计算机可读存储介质，所述计算机可读存储介质用于存储 处理器所执行的程序代码，所述程序代码包括用于实现上述第一方面任一种可能的实施方式中的方法。
第七方面，提供了一种芯片，包括处理器，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第一方面任一种可能的实施方式中的方法。
第八方面，提供另一种芯片。所述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第一方面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应用场景的示意图；
图2是本申请实施例提供的一种带宽推荐方法的流程图；
图3是本申请实施例提供的一种小值震荡型的流量序列的曲线示意图；
图4是本申请实施例提供的一种突发毛刺型的流量序列的曲线示意图；
图5是本申请实施例提供的一种平稳双峰型的流量序列的曲线示意图；
图6是本申请实施例提供的一种震荡双峰型的流量序列的曲线示意图；
图7是本申请实施例提供的一种带宽推荐方法的流程图；
图8是本申请实施例提供的一种带宽推荐方法的流程图；
图9是本申请实施例提供的一种流量模式确定方法的流程图；
图10是图4所示的流量序列的一阶差分序列的示意图；
图11是图5所示的流量序列的一阶差分序列的示意图；
图12是图6所示的流量序列的一阶差分序列的示意图；
图13是本申请实施例提供的一种双峰型的流量序列的曲线示意图；
图14是本申请实施例提供的一种平滑后的流量序列的曲线示意图；
图15是本申请实施例提供的一种确定第一带宽的方法流程图；
图16是本申请实施例提供的一种确定第三带宽的方法流程图；
图17是本申请实施例提供的一种带宽推荐方法的流程图；
图18是本申请实施例提供的一种带宽推荐方法的流程图；
图19是本申请实施例提供的一种带宽推荐装置的框图；
图20是本申请实施例提供的一种显示装置的框图；
图21示出了本申请一个示例性实施例提供的控制设备的结构示意图。
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。
为便于对本申请实施例提供的技术方案的理解，首先介绍一下本申请的应用场景。该应用场景可以是分布式存储系统或者数据中心等通信网络。下面以分布式存储系统为例，对本申请应用场景进行说明。
图1是本申请实施例提供的一种应用场景的结构示意图。参见图1，该应用场景包括控制设备11和网络设备12。控制设备11可以是网络中的管理节点，例如，网管设备。网络设备12可以是网络中的网络节点，例如路由设备。如图1所示，两个网络设备12之间建立链路13，用于传输业务数据。该链路可以是设备间的物理链路，也可以是设备间的逻辑链路，例如，该链路可以是隧道(tunnel)。该隧道用于特定业务的传输，可以传输至少一条数据流。控制设备11和两个网络设备12中的至少一个连接，用于实现对该链路的带宽推荐。当然，图中仅示出了链路两端的网络设备12，在两个网络设备12之间还可以包括其他网络设备，且链路经过这些网络设备，控制设备11既可以与这些网络设备中的至少一个连接，也可以不与这些网络设备中的任一个连接。
图2是本申请实施例提供的一种带宽推荐方法的流程图。该方法可以由图1所示的应用场景中的控制设备11执行，在本申请提供的带宽推荐方法中，控制设备基于采集的流量数据确定流量模式，然后基于流量模式确定带宽并推荐给网络设备进行应用。在该带宽推荐方法中，控制设备可以采集链路的流量数据，并给网络设备推荐链路的带宽，以使网络设备进行链路的带宽配置；控制设备也可以采集隧道的流量数据，并给网络设备推荐隧道的带宽，以使网络设备进行隧道的带宽配置。但无论是以链路为对象，还是以链路中的隧道为对象，该带宽推荐方法的过程都是相同的，后续关于带宽推荐方法的过程描述以隧道为例进行说明，可以理解的是后续关于带宽推荐方法的过程描述，也可以以链路为对象。如图2所示，该方法包括如下步骤。
S11：获取隧道的第一流量数据。
在本申请实施例中，第一流量数据包括在采集时间段内，网络设备针对待采集的隧道按照采集时间间隔采集到的多个流量样本组成的流量序列。
其中，采集时间段是指从采集开始到采集结束的时间范围，该范围可以是一个小时、一天、一周、一个月等。采集时间间隔可以根据需要设置，例如1分钟、5分钟、1小时等。流量样本是指在采集时间段采集到的隧道的流量值。一个流量样本既包括采集时间，也包括采集到的流量值。流量序列包括按照采集时间先后排列的多个流量值。采集时间段或采集时间间隔可以为默认值，例如，采集时间段为一个小时，采集时间间隔为5分钟。采集时间段或采集时间间隔还可以是配置值，例如，管理员在控制设备的界面上输入配置指令以配置具体的采集时间段或采集时间间隔。
S12：根据所述隧道的第一流量数据确定所述隧道的流量模式。
在本申请实施例中，流量模式用于指示隧道在第一时间段内的流量值的变化趋势。其中，第一时间段可以是前述采集时间段。
示例性地，隧道的流量模式包括如下至少一种：小值震荡型、突发毛刺型、平稳双峰型和震荡双峰型。
图3示出了本申请实施例提供的一种小值震荡型的流量序列的曲线示意图。如图3所示，横坐标为时间，单位为分钟，纵坐标为流量，单位为兆比特每秒(million bits per second，Mb/s)。 在小值震荡型流量模式中，在采集时间段内的大部分时间(例如50％以上)中流量均为一较低流量值(例如1～3Mb/s)。如图3中90％以上时间中流量均低于3Mb/s，且其中出现的较高流量值较少，例如图中超过3Mb/s的流量仅为数个点(流量样本)，占比在5％以下，并且没有形成山峰状。
图4示出了本申请实施例提供的一种突发毛刺型的流量序列的曲线示意图。如图4所示，横坐标为时间，单位为分钟，纵坐标为流量，单位为Mb/s。在突发毛刺型流量模式中，流量序列中流量值的跨度很大，从几Mb/s到上百Mb/s，流量变化也没有规律，也即没有形成明显的波峰和波谷，如果将流量序列的某一百分位值，例如50％分位值，或者流量序列的平均流量值作为阈值，超过该阈值的异常流量出现的频率较高。例如图4中以40Mb/s作为阈值，超过该阈值的异常流量出现的频率较高，占比超过20％。
图5示出了本申请实施例提供的一种平稳双峰型的流量序列的曲线示意图。如图5所示，横坐标为时间，单位为分钟，纵坐标为流量，单位为Mb/s。在平稳双峰型流量模式中，流量序列中流量值按峰-谷-峰波形变化，且在山峰和山谷中流量毛刺少，例如不超过一个阈值，流量毛刺是指在流量呈现上升或下降的变化趋势中，突发的异常流量，如图5中的A点。
图6示出了本申请提供的一种震荡双峰型的流量序列的曲线示意图。如图6所示，横坐标为时间，单位为分钟，纵坐标为流量，单位为Mb/s。在震荡双峰型流量模式中，流量序列中流量按峰-谷-峰波形变化，且在山峰和山谷中流量毛刺多，例如超过前述阈值，该阈值可以根据需要设计，例如20％等。
S13：根据所述隧道的流量模式确定第一带宽。
在本申请实施例中，根据流量模式确定第一带宽，使得第一带宽可以满足对应流量模式下的业务数据传输需求。
其中，第一带宽可以是指为隧道预留的最低限度的带宽，该第一带宽能够保证隧道流量在不发生突变的情况下平稳运行。并且，当隧道流量发生突变时，还可以在该第一带宽的基础上，为隧道增加带宽，以满足隧道中业务传输的需求。
S14：指示所述隧道关联的网络设备应用所述第一带宽。
控制设备可以将该第一带宽发送给网络设备，使得网络设备按照该第一带宽配置隧道。或者，控制设备在该网络设备上执行配置命令，指示该网络设备按照该配置命令包括的第一带宽为进入该隧道的业务传输数据。
在图2提供的方法中，控制设备通常是根据隧道关联的多个网络设备中一个网络设备的流量数据确定第一带宽，例如隧道入口的网络设备。一个流量样本中的流量值可以是该网络设备在对应的采集时间间隔内接收流量的速率，例如，流量值是该网络设备上与该隧道关联的入接口在对应的采集时间间隔内接收流量的速率。例如，一个流量样本中的流量值可以是该网络设备上与该隧道关联的入接口的输入队列在对应的采集时间间隔内接收流量的速率。而在确定出第一带宽之后，控制设备既可以将第一带宽发送给用来确定第一带宽的流量数据的网络设备，也可以发送给隧道关联的多个网络设备(例如隧道关联的全部网络设备)，指示这些网络设备应用该第一带宽。第一带宽可以用于配置该网络设备与链路关联的出接口速率，例如，第一带宽用于配置该网络设备上与该隧道关联的出接口的接口速率。具体地，该第一带宽可以用于配置该网络设备上与该隧道关联的出接口的输出队列，以使得该出接口的发送流量的速率为第一带宽。
当然，控制设备也可以同时根据隧道关联的多个网络设备的流量数据确定第一带宽，然后发送第一带宽给一个或多个网络设备，指示网络设备应用该第一带宽。示例性地，在使用多个网络设备的流量数据时，可以将相同采集时间的流量值进行平均，然后形成均值流量序列，根据均值流量序列确定流量模式，进而确定第一带宽。或者，在使用多个网络设备的流量数据时，可以确定相同采集时间的流量值中的最大值，然后形成最大值流量序列，根据最大值流量序列确定流量模式，进而确定第一带宽。
在本申请实施例中，通过采集隧道的流量数据，然后根据该流量数据确定隧道的流量模式，基于流量模式确定第一带宽，再指示隧道关联的网络设备应用第一带宽。一方面，该方法可以在业务运行过程中实时进行带宽的推荐，相比于预先配置隧道的带宽，更具有实时性，推荐的带宽更准确，减少了带宽的浪费。另一方面，上述第一带宽的确定过程中，先划分流量模式，然后按照流量模式确定对应的带宽，从而可以实现针对不同流量模式进行不同的带宽推荐，使得推荐的带宽更加符合业务流量传输需求，提高了业务传输质量。
图7是本申请实施例提供的一种带宽推荐方法的流程图。该方法可以由图1所示的应用场景中的控制设备执行。如图7所示，该方法包括如下步骤。
S21：获取隧道的第一流量数据。
S22：根据所述隧道的第一流量数据确定所述隧道的流量模式。
S23：根据所述隧道的流量模式确定第一带宽。
步骤S21～步骤S23可以参考步骤S11～S13，这里不做赘述。
S24：根据所述第一时间段对应的时间或所述第一时间段对应的事件确定所述隧道的第一场景，并存储所述第一场景和所述第一场景对应的所述第一带宽。
其中，第一场景可以包括为节日场景、事件场景和日常场景中的至少一个。
场景可以根据当前的时间、发生的事件确定。例如，先判断当前是否为节日，如果是则确定为节日场景，如果不是再判断当前是否有设定事件发生，如果是则确定为事件场景，如果不是则确定为日常场景。
示例性地，判断当前是否有设定事件发生可以基于控制设备收到的消息或指令确定，例如，当有会议事件发生时，控制设备会收到会议通知，此时可以判断场景为事件场景。
示例性地，节日场景、事件场景和日常场景又可以划分为不同子类型。
例如，当场景为节日场景时，根据具体的节日类型，可以划分为不同的节日场景，例如，中秋节型、国庆节型、周末型等类型。当场景为事件场景时，根据具体的事件可以划分为不同的事件场景，例如，会议事件类型、比赛直播事件类型等。当场景为日常场景时，根据时段可以划分为不同的日常场景，例如，白天型、夜间型、工作时段型和非工作时段型等。
在本申请实施例中，控制设备可以重复执行步骤S21～S24，从而存储多种场景及对应的第一带宽。
S25：根据第二时间段确定所述隧道的第二场景。
第二时间段可以是当前时间所在的时间段。控制设备根据第二时间段的时间或者第二时间段所发生的事件，确定当前时间下隧道所处的第二场景。
例如，确定第二时间段是否为节日或有事件发生；当第二时间段为节日时，确定场景为节日场景；当第二时间段有事件发生时，确定场景为事件场景；当第二时间段不是节日，且 没有事件发生时，确定场景为日常场景。
可以理解的，当上述场景还包括子类型时，则确定场景时按照子类型进行确定。
S26：确定第二场景和第一场景匹配。
也即确定和第二场景匹配的第一场景，例如，从存储的多个场景中，选择与第二场景匹配的场景，这里确定出的与第二场景匹配的场景是第一场景。
这里，第二场景和第一场景匹配可以是指第二场景和第一场景相同，或者第二场景和第一场景的相似。
例如，第二场景为第一节日，确定第二场景和第一场景匹配，包括：
查找第一节日；
若未查找到第一节日，则查找与第一节日相似的第二节日。
第二场景为第一事件，确定第二场景和第一场景匹配，包括：
查找第一事件；
若未查找到第一事件，则查找与第一事件相似的第二事件。
其中，哪些节日具有相似性，哪些事件具有相似性，可以在控制设备中事先定义，例如，事先将中秋节和端午节定义为相似节日。
S27：根据所述第一带宽确定第二带宽，并指示所述隧道关联的网络设备应用所述第二带宽。
其中，第二带宽可以和第一带宽相等，或者第二带宽可以是基于第一带宽计算得到的，例如将第一带宽乘以系数，得到第二带宽等。
可选地，该方法还包括：显示第二场景和第二带宽。
通过显示场景及对应的推荐带宽，可以使得管理员清楚地了解为该隧道推荐的带宽与该隧道的场景的匹配关系。
可选地，该方法还包括：显示与所述第二场景匹配的所述第一场景和/或所述第一场景的流量模式。
通过显示匹配的场景及对应的流量模式，可以使得管理员清楚地了解为该隧道推荐的带宽的流量模式依据。管理员还可以根据该流量模式调整带宽推荐，例如，调整步骤S27中的系数。
可选地，控制设备还可以存储第一流量数据对应的流量模式。控制设备还可以接收新的流量数据，基于新的流量数据确定新的流量模式，并基于新的流量模式与已经存储的流量模式之间的相似度确定推荐的带宽。例如，当新的流量模式与已经存储的流量模式一之间的相似度超过阈值时，控制设备基于该流量模式一对应的带宽为新的流量模式确定推荐的带宽。该推荐的带宽可以和流量模式一对应的带宽相等，也可以是基于流量模式一对应的带宽计算得到的，例如将流量模式一对应的带宽乘以系数，得到该推荐的带宽。
可选地，当控制设备在步骤S26中未找到与第二场景匹配的场景时，控制设备不执行步骤S27。此时，控制设备可以基于第二场景下的流量模式确定推荐的带宽。该执行过程请参见图2所示的方法流程，此处不再赘述。
在上述实施例中，控制设备存储第一带宽及对应的场景，在后续出现相同或相似场景时，可以根据第一带宽确定第二带宽，并将第二带宽推荐给网络设备进行应用，从而在保证隧道传输质量的同时，提高带宽推荐效率。
图8是本申请实施例提供的一种带宽推荐方法的流程图。该方法可以由图1所示的应用场景中的控制设备和网络设备执行。如图8所示，该方法包括如下步骤。
S31：控制设备向网络设备发送流量采集指令。网络设备接收该流量采集指令。
示例性地，控制设备和网络设备中均包括获取模块，控制设备中的获取模块用于发送上述流量采集指令，网络设备中的获取模块用于在收到该流量采集指令时，进行流量采集。
在一种可能的实现方式中，该流量采集指令中可以包括如下至少一项：待采集的隧道的标识、流量采集的采集时间段、采集时间间隔。
由于流量采集指令可以包括待采集的隧道的标识、流量采集的采集时间段、采集时间间隔中的部分或全部字段，因此，在流量采集指令中包括的字段，采集时采用流量采集指令中的取值，在流量采集指令中不包括的字段，采集时可以采用默认值。
例如，若流量采集指令中包括待采集的隧道的标识，则采集待采集的隧道的标识对应的隧道的流量。若流量采集指令中不包括待采集的隧道的标识，则采集默认的隧道，默认的隧道既可以是一条隧道，也可以是多条隧道，例如网络设备中配置的全部隧道。
在另一种可能的实现方式中，该流量采集指令也可以不包括上述任一字段，也即该流量采集指令仅指示网络设备进行流量采集，但不对流量采集的参数进行限定，也即待采集的隧道的标识、流量采集的采集时间段和采集时间间隔均采用默认值。
上述默认值可以事先配置在网络设备中，例如，默认采集全部隧道、采集时间段为一天、采集时间间隔为5分钟等。
S32：网络设备采集隧道的第一流量数据。
其中，第一流量数据包括在采集时间段内，网络设备针对待采集的隧道按照采集时间间隔采集到的多个流量样本组成的流量序列。
例如，网络设备在1天内，每间隔5分钟采集一次隧道的流量，获得一个由采集时间和流量值组成的流量样本，通过在1天内的多次采集得到288个流量样本，288个流量样本按照从0时到24时的先后排序，得到流量序列。
S33：网络设备向控制设备发送隧道的第一流量数据。控制设备接收该隧道的第一流量数据。
S34：控制设备根据该隧道的第一流量数据确定流量模式。
在本申请实施例中，流量模式用于指示隧道的流量在采集时间段内的变化趋势。
示例性地，隧道的流量模式包括如下至少一种：小值震荡型、突发毛刺型、平稳双峰型和震荡双峰型。关于上述四种流量模式的说明，可以参考前文步骤S22中关于图3至图6的描述。
在一种可能的实现方式中，网络设备采集到的第一流量数据对应于一种流量模式，此时控制设备只需要确定出该流量模式即可。
在另一种可能的实现方式中，网络设备采集到的第一流量数据对应于多种流量模式，这多种流量模式分别位于不同时间段。此时，控制设备确定出这多种流量模式，然后既可以将其中最重要的一种流量模式作为隧道的流量模式，也可以将这种多种流量模式共同作为隧道的流量模式。
其中，在采用最重要的一种流量模式作为隧道的流量模式时，可以选择时间占比最大的 流量模式。在采用多种流量模式共同作为隧道的流量模式时，可以详细记录各种流量模式及其对应的时间段。
S35：控制设备根据隧道的流量模式确定第一带宽。
在本申请实施例中，对于不同的流量模式确定出的第一带宽通常是不同的，使得第一带宽可以满足对应流量模式下的业务数据的传输需求。
其中，第一带宽是指为隧道预留的最低限度的带宽，该第一带宽能够保证隧道流量在不发生突变的情况下平稳运行。
当隧道流量发生突变时，还可以在该第一带宽的基础上，为隧道增加带宽，以满足隧道中业务传输的需求。
S36：控制设备根据流量模式确定第三带宽和应用第三带宽的条件。第三带宽大于第一带宽。
其中，第三带宽是在第一带宽不能满足隧道中业务传输需求时使用的带宽，而应用第三带宽的条件即是第一带宽不能满足隧道中业务传输需求的条件。
示例性地，应用第三带宽的条件包括：在一个时间周期内，流量越限的次数超过次数阈值，和/或，流量越限的持续时间超过时间阈值。
其中，流量越限是指隧道的流量超过第一带宽。
前述时间周期、次数阈值、时间阈值等可以根据需要设置，例如时间周期为一天或一周，次数阈值为10次或30次，时间阈值为1小时或5小时等。
示例性地，控制设备还包括流量画像生成模块，流量画像生成模块用于执行步骤S37。
S37：控制设备生成隧道的流量画像。
示例性地，流量画像包括流量模式、第一带宽和第三带宽。控制设备可以基于流量模式查找流量画像为隧道推荐带宽。
可选地，流量画像还包括如下至少一项：隧道的标识、场景、流量峰值、异常模式和均峰比。场景包括节日场景、事件场景和日常场景中的至少一个。这样，流量画像能够更加全面地对隧道的流量进行描述和刻画。
其中，隧道的标识用于唯一标识一条隧道。当流量采集指令中包括待采集的隧道的标识时，流量画像中的隧道标识即为从流量采集指令中获得的隧道的标识。如果流量采集指令中不包括待采集的隧道的标识时，流量画像中的隧道即为设置的默认的隧道的标识。
隧道的标识可以采用源节点名称、目的节点名称、承载业务类型组合，例如SHBJ01，其中SH表示源节点名称，BJ表示目的节点名称，01为该隧道承载业务类型的标识。
其中，节日场景是指生成流量画像的流量数据对应的时间为节日；事件场景是指生成流量画像的流量数据主要包括某一事件的流量，这里的事件通常是指对带宽有要求、且需要保障流量的事件，例如比赛直播事件。由于比赛直播事件对带宽要求高，因此需要单独进行流量画像。日常场景则是时间不属于节日且采集的流量不包括事件。
场景可以根据当前的时间、发生的事件确定。例如，先判断当前是否为节日，如果是则确定为节日场景，如果不是再判断当前是否有设定事件发生，如果是则确定为事件场景，如果不是则确定为日常场景。
示例性地，判断当前是否有设定事件发生可以基于控制设备收到的消息或指令确定，例如，当有会议事件发生时，控制设备会收到会议通知，此时可以判断场景为事件场景。
示例性地，节日场景、事件场景和日常场景又可以划分为不同子类型。
例如，当场景为节日场景时，根据具体的节日类型，可以划分为中秋节型、国庆节型等类型。当场景为事件场景时，可以划分为会议事件类型、比赛直播事件类型等。当场景为日常场景时，可以划分为白天型、夜间型等。
由于存在上述多种场景，因此在流量画像生成时，同一条隧道可以在不同场景下生成不同的流量画像，进而使得一条隧道具有多个流量画像，这些流量画像可以根据自身的场景在不同场景下进行带宽推荐。
其中，流量峰值可以通过分析流量数据得到，例如从流量序列中确定最大流量值，该最大流量值即为流量峰值。
其中，该异常模式用于指示异常流量的发生概率、偏离度和持续时间。其中，异常流量是指超过阈值的流量，该阈值可以为流量序列的平均流量值。异常流量的发生概率是指异常流量对应的流量样本数量占流量序列中总流量样本数量的比例，偏离度是指异常流量和阈值的偏差值，持续时间可以包括每次异常流量的持续时间和所有异常流量的持续总时间。
其中，均峰比是指流量均值和流量峰值的比值，流量均值是流量序列中所有流量样本的流量值的平均值，流量峰值是流量序列中流量值的最大值。
S38：控制设备对流量画像进行持久化存储。
示例性地，控制设备还包括画像存储模块，用于对流量画像进行持久化存储，持久化存储的粒度可以由控制设备根据隧道的历史流量变化进行设置，或者，由管理员进行设置。
例如，控制设备根据隧道的历史流量变化的幅度，确定流量画像持久化存储的时间粒度，历史流量变化的幅度越小，则持久化存储的时间粒度可以设置得越大，反之，历史流量变化的幅度越大，则持久化存储的时间粒度可以设置得越小。
其中，隧道的历史流量变化的幅度通常和隧道承载的业务类型相关。例如，部分业务流量相对平稳，则隧道的历史流量变化的幅度较小，流量画像的持久化存储的时间粒度可以设置得更大，例如1个月。而部分业务流量增长或下降速度较大，隧道的历史流量变化的幅度较大，流量画像的持久化存储的时间粒度可以设置得小，例如一周等。
示例性地，由于隧道承载的业务通常是不变的，因此可以提前设置隧道的标识和流量画像的持久化存储的时间的对应关系，在控制设备生成流量画像后，根据该对应关系即可确定出持久化存储的时间，以进行该流量画像的持久化存储，而无需再去分析隧道的历史流量变化。
再例如，管理员可以按照小时、天、周、月的粒度进行设置，实现控制设备对流量画像持久化存储。
在本申请实施例中，控制设备可以采用表格形式对流量画像进行存储，例如将一个流量画像的各个字段分别存储在表格的同一行的各个单元格中。示例性地，在该表格中，第一带宽和第三带宽采用数值表示，其他字段可以采用对应的标识表示。
在本申请实施例中，最终存储的流量画像包括流量模式、第一带宽和第三带宽等参数，无需再存储流量序列，避免了流量序列随着时间增长而导致存储压力增大的问题，可以大大降低设备的存储压力。
在该实现方式中，控制设备以流量画像的形式存储第一场景和第一场景对应的第一带宽。
S39：控制设备基于流量画像为网络设备推荐带宽。
在该实现方式中，控制设备可以通过流量画像来进行场景的匹配以及带宽的推荐。
在本申请实施例中，控制设备可以根据隧道的标识、场景等选择隧道对应的流量画像，然后根据流量画像中第一带宽和/或第三带宽给网络设备推荐应用到该隧道上的带宽。
可选地，该方法还包括：显示所述隧道的标识及隧道的流量模式，从而给网络管理人员进行网络配置提供指导。
示例性地，显示流量模式时，可以显示流量模式的名称以及对应的流量曲线等。
可选地，该方法还包括：显示所述隧道对应的所述第一带宽和/或所述第三带宽。显示上述第一带宽和/或的第三带宽时，可以采用图表等形式显示。
通过显示隧道的标识、流量模式、推荐的带宽信息，可以使得管理员清楚地了解为该隧道推荐的带宽与该隧道实际传输的业务流量的匹配关系。管理员还可以根据该匹配关系主动的调整带宽推荐方法，例如，调整带宽推荐方法中使用的参数值。
图9是本申请实施例提供的一种流量模式确定方法的流程图。该方法可以由图1所示的应用场景中的控制设备执行。如图9所示，该方法包括如下步骤。
S41：根据第一流量数据，确定隧道的流量是否符合小值震荡条件。
当隧道的流量符合小值震荡条件时，确定流量模式为小值震荡型；当隧道的流量不符合小值震荡条件时，执行步骤S42。
示例性地，将流量序列中流量超过第一阈值的流量样本定位异常流量样本。小值震荡条件包括：流量序列中异常流量样本总数占流量序列中流量样本总数之比少于第二阈值，流量序列中连续出现的异常流量样本的最大时间长度占采集时间段之比少于第三阈值。
其中，第一阈值对应的流量值较低，例如设置为3Mb/s。第二阈值设置小值，以保证大部分时间中流量较低，例如第二阈值的取值小于20％，例如取值为5％至10％。
连续出现的异常流量样本是指连续采集的若干个流量样本均为异常流量样本，连续出现的异常流量样本的最大时间长度是指在流量序列中最长的连续出现的异常流量样本对应的时间，例如，在流量序列中，存在连续的3个异常流量样本、连续的5个异常流量样本、连续的7个异常流量样本，采集时间间隔为5分钟，则连续出现的异常流量样本的最大时间长度为7×5＝35分钟。第三阈值较小，比如小于5％。
例如，设第二阈值为
Figure PCTCN2022141924-appb-000001
第三阈值为
Figure PCTCN2022141924-appb-000002
统计流量序列中异常流量样本总数占流量序列中流量样本总数之比x，若
Figure PCTCN2022141924-appb-000003
则认为该流量模式不是小值震荡型；统计流量序列中连续出现的异常流量样本的最大时间长度占采集时间段之比y，若
Figure PCTCN2022141924-appb-000004
则认为该流量模式不是小值震荡型；若以上两个条件全部不满足，则认为流量模式为小值震荡型，在小值震荡型的流量序列中至少大部分流量小于第一阈值、至多小部分流量大于第一阈值。参见图3，流量序列中所有的流量均小于第一阈值3Mb/s。
S42：根据第一流量数据，确定隧道的流量是否符合突发毛刺条件。
当隧道的流量符合突发毛刺条件时，确定流量模式为突发毛刺型；当隧道的流量不符合突发毛刺条件时，执行步骤S43。
示例性地，突发毛刺条件包括：流量序列的一阶差分序列的概率密度分布中超过突发差分阈值的概率超过第四阈值。
其中，流量序列的一阶差分序列是将流量序列中相邻的两个流量样本之差形成的序列。 概率密度分布是指一阶差分序列中各个取值的概率(也即占比)的分布情况。突发差分阈值用来限定相邻的两个流量样本的差值相差多少，被认为是突发流量。概率密度分布中超过突发差分阈值的概率，也即是整个流量序列中突发流量的占比。若突发流量的占比(也即前述概率)超过第四阈值，则认为是突发毛刺型流量。
S43：根据第一流量数据，确定隧道的流量是否符合震荡条件。
当隧道的流量符合震荡条件时，确定流量模式属于震荡型；当隧道的流量不符合震荡条件时，确定流量模式属于平稳型。
示例性地，震荡条件包括：流量序列的一阶差分序列的概率密度分布中超过震荡差分阈值的概率超过第五阈值。
其中，震荡差分阈值用来限定相邻的两个流量样本的差值相差多少，被认为是震荡流量。概率密度分布中超过震荡差分阈值的概率，也即是整个流量序列中震荡流量的占比。若震荡流量的占比超过第五阈值，则认为是震荡型流量。
示例性地，突发差分阈值大于震荡差分阈值。
例如，突发差分阈值为0.8，震荡差分阈值为0.16，第四阈值为0.1，第五阈值为0.25。
在本申请实施例中，计算流量序列的一阶差分序列，并求出其概率密度分布，通过概率密度分布来进行流量模式的区分，下面结合附图来进行说明：
图10是图4所示的突发毛刺型的流量序列的一阶差分序列的示意图。如图10所示，横坐标为序号，例如序号1表示第1个流量样本和第2个流量样本的差分，序号2表示第2个流量样本和第3个流量样本的差分，依次类推，纵坐标为流量差分值，单位为Mb/s。可以看出，突发毛刺型的流量序列的一阶差分序列分布范围较宽，从-5至2都有分布，对应流量序列中突发毛刺较多。
图11是图5所示的平稳双峰型的流量序列的一阶差分序列的示意图。如图11所示，横坐标为序号，纵坐标为流量差分值，单位为Mb/s。可以看出，平稳双峰型的流量序列的一阶差分序列分布范围较窄，主要集中在0至-1之间，对应流量序列中流量变化较为平稳。
图12是图6所示的震荡双峰型的流量序列的一阶差分序列的曲线示意图。如图12所示，横坐标为序号，纵坐标为流量差分值，单位为Mb/s。可以看出，震荡双峰型的流量序列的一阶差分序列分布比突发毛刺型更窄，比平稳双峰型更宽，主要分布-1至2之间，对应的流量序列变化比突发毛刺型平稳，但没有平稳双峰型平稳。
由于突发毛刺型、平稳双峰型和震荡双峰型的流量序列的一阶差分序列存在上述明显的差异型。因此，本申请实施例通过设置突发差分阈值、震荡差分阈值、第四阈值及第五阈值，并进行条件判断，对流量类型进行区分。上述判断条件用公式表示如下：
设突发差分阈值为
Figure PCTCN2022141924-appb-000005
震荡差分阈值为
Figure PCTCN2022141924-appb-000006
第四阈值为
Figure PCTCN2022141924-appb-000007
第五阈值为
Figure PCTCN2022141924-appb-000008
用f(t)来表示流量序列，用f’(t)来表示f(t)的一阶差分序列。
若
Figure PCTCN2022141924-appb-000009
则认为f(t)为突发毛刺型；其中，
Figure PCTCN2022141924-appb-000010
表示流量序列的一阶差分序列的概率密度分布中超过突发差分阈值的概率；
若
Figure PCTCN2022141924-appb-000011
则认为f(t)为震荡型；
Figure PCTCN2022141924-appb-000012
表示一阶差分序列的概率密度分布中超过震荡差分阈值的概率；
上述两个式子都不满足，则认为f(t)为平稳型。
S44：根据第一流量数据，确定隧道的流量是否属于双峰型。
当隧道的流量属于平稳型且属于双峰型时，确定隧道的流量为平稳双峰型；当隧道的流量属于震荡型且属于双峰型时，确定隧道的流量为震荡双峰型。
示例性地，步骤S44包括如下步骤：
第一步，对流量序列进行核平滑(kernel smoothing)，核平滑是将流量样本和前后相邻的若干样本进行加权平均值，权重由核确定，比如越近的流量样本权重越大。核平滑使用的核函数可以为均匀核函数。
图13为本申请提供的一种双峰型的流量序列的曲线示意图。参见图13，横坐标为时间，单位为分钟，纵坐标为流量，单位为Mb/s。L1表示原流量序列，L2表示平滑后的流量序列，将L2单独示出则如图14所示。
第二步，在平滑后的流量序列中寻找山谷值，也即图13和图14中的t1点。山谷值位于下降序列(山谷值左侧)和上升序列(山谷值右侧)交汇处。为了准确找到山谷值，避免震荡产生的干扰，可以通过限定山谷值左右两侧下降序列和上升序列的持续时间均达到一定值，才确定该值为山谷值，例如超过1小时。
其中，上升序列和下降序列并不要求是严格的上升和下降序列，例如上升和下降序列可以存在一些突变，但只要序列中超过设定比例(例如90％)的部分都是呈上升或下降变化即可。
如果该步骤中未能找到山谷值，则确定不是双峰型，结束流程。
第三步，当平滑后的流量序列中存在山谷值时，以山谷值为分界点，将平滑后的流量序列分为两段序列，也即图13和图14中t1左侧和右侧的两段。
第四步，分别在两段序列中确定山峰值，也即图13和图14中的t2和t3点。
其中，山峰值位于上升序列(山峰值左侧)和下降序列(山峰值右侧)交汇处。为了准确找到山峰值，避免震荡产生的干扰，可以通过限定山峰值左右两侧上升序列和下降序列的持续时间均达到一定值，才确定该值为山峰值，例如超过1小时。
2个山峰值和前面的山谷值一起将平滑后的流量序列分为4段，且从左到右这四段依次为上升序列、下降序列、上升序列、下降序列。
第五步，当两个山峰值中较大山峰值和较小山峰值满足条件时，确定隧道的流量模式属于双峰型。
示例性地，上述条件如下：较大山峰值和较小山峰值的差不会过大，例如小于第一差值，较小山峰值和山谷值的差不会过小，例如大于第二差值，第二差值小于第一差值。
除了采用差值来限定外，本申请实施例还可以采用较大山峰值、较小山峰值及山谷值之间的比值关系来作为条件：
例如，用
Figure PCTCN2022141924-appb-000013
表示较大山峰值，
Figure PCTCN2022141924-appb-000014
表示较小山峰值。则该条件可以表示为：
Figure PCTCN2022141924-appb-000015
其中，θ p是阈值，阈值可以基于需要设定，例如取值在1～3之间。f(t1)是山谷值。
Figure PCTCN2022141924-appb-000016
要小于阈值，则需要分子
Figure PCTCN2022141924-appb-000017
尽量小，
Figure PCTCN2022141924-appb-000018
尽量大，由于
Figure PCTCN2022141924-appb-000019
大于
Figure PCTCN2022141924-appb-000020
则当
Figure PCTCN2022141924-appb-000021
和
Figure PCTCN2022141924-appb-000022
相差小，且
Figure PCTCN2022141924-appb-000023
和f(t1)相差大时成立。
若满足该条件，则认为双峰尺寸的差距合理，流量序列f(t)是双峰型；反之，流量序列f(t)不是双峰型。
当然流量不满足上述小值震荡型、毛刺突发型、平稳双峰型和震荡双峰型时，流量的流量类型为其他类型，也即当流量不属于以上任一种流量类型时，即为其他类型。当流量类型为其他类型时，确定第一带宽和第三带宽的方式可以参考小值震荡型、毛刺突发型、平稳双峰型和震荡双峰型中的一种，也可以采用其他方式确定。
在其他实施例中，流量模式还可以有其他划分方式，例如划分为小值型、震荡型和平稳型。流量模式可以采用计算均值方差的方式确定。例如，先计算流量序列均值，比较均值和阈值1的大小，如果均值小于阈值1则为小值型，否则不是小值型；当不是小值型时，再计算流量序列的方差，比较方差和阈值2的大小，如果方差大于阈值2则为震荡型，否则为平稳型。
图15是本申请实施例提供的一种第一带宽确定方法的流程图。该方法可以由图1所示的应用场景中的控制设备执行，如图15所示，该方法包括如下步骤。
S51：当流量模式为小值震荡型时，采用第一阈值作为第一带宽。
示例性地，在判断小值震荡型时使用的第一阈值为3Mb/s，则采用3Mb/s作为小值震荡型的第一带宽。
S52：当隧道用于承载第一优先级业务且流量模式为平稳双峰型时，采用流量数据中流量序列的峰值作为第一带宽。
在本申请实施例中，第一优先级业务是指最高优先级(核心)业务，例如优先级从高依次为1、2、3、4等。针对优先级为1且流量模式为平稳双峰的流量，考虑到其重要程度和流量模式的特点，直接用流量序列的峰值作为第一带宽。
S53：当流量模式为震荡双峰型，或者隧道为第二优先级业务且流量模式为平稳双峰型时，采用流量数据中流量序列的整体流量水平的中间值作为第一带宽。
例如，整体流量水平的中间值可以是整体流量水平的50％至95％分位值。例如，整体流量水平的80％分位值。
其中，第二优先级低于第一优先级，例如第二优先级是指优先级为2、3和4中的至少一个。
S54：当流量模式为突发毛刺型时，根据点密度阈值确定第一带宽。
其中，点密度阈值用于限定采用第一带宽时，流量序列中流量高于第一带宽的点的密度的最大值。
其中，点密度D(BW)的定义如下：
Figure PCTCN2022141924-appb-000024
其中，f(t)表示一个流量序列，BW为第一带宽，N为流量序列中流量样本的个数，t表示时间，T为最后一个流量样本的采集时间，I表示流量大于BW的点的计数值。
在点密度的表达式中，分子表示超过第一带宽BW的点的个数，分母表示第一带宽与整个流量序列的最大流量之间区域的面积，该面积采用如下方式表示：每个流量序列代表1个单位宽度，流量序列的总宽度为N，从0到最大流量之间的高度为1，则0到第一带宽间的高度为BW/max t∈[0,T]f(t)，从第一带宽到最大流量之间的高度为1-BW/max t∈[0,T]f(t)。将上述宽度乘以高度，得到前述面积。
超过第一带宽BW的点的个数除以第一带宽与整个流量序列的最大流量之间区域的面积， 得到点的密度。
设置一个关于点密度的阈值β，为了选取一个合适的第一带宽，要求在第一带宽之上的区域中，点密度不能超过β。根据这一规则，给出预留带宽的具体表达式如下：
Figure PCTCN2022141924-appb-000025
该公式的含义如下：以流量序列f(t)中各个点作为第一带宽BW，分别算出点密度D(BW)，得到多个点密度的值。从这些点密度中找出最小的点密度min(D(BW))，如果β≥min(D(BW))，则说明f(t)中存在点，使得点密度符合阈值要求。在所有小于β的点密度对应的点中，选出最小的点，作为第一带宽BW。如果β＜min(D(BW))，则说明f(t)中不存在点，使得点密度符合阈值要求，此时选择f(t)中的最大点作为第一带宽BW。
其中，阈值β表示的实际上是希望第一带宽之上的区域中点密度可以低于一定比例的整体水平。例如，设置β＝0.1，就表示希望BW以上区域的点密度可以低于整体水平的10％。但是，要在满足上述条件的情况下，使第一带宽尽量小，这样做的好处是可以在异常概率增加不多的前提下，有效降低需要预留的第一带宽。基于点密度确定出来的第一带宽，将流量序列划分为分布稀疏的上层部分以及分布密集的下层部分，既能保障下层密集流量的传输，又可以过滤掉上层的突发型流量。
可选地，在步骤S54之后，该方法还可以包括：当根据点密度阈值确定第一带宽低于流量序列的80％分位值带宽时，采用流量序列的80％分位值带宽代替突发毛刺型的第一带宽，以保证流量的异常概率在合理的范围内。
下表1给出了本申请实施例提供的关于平稳双峰、震荡双峰和突发毛刺型的第一带宽的确定方案：
表1
Figure PCTCN2022141924-appb-000026
该方案通过对不同流量模式进行不同方式的带宽预留，相比于为所有情况均按照峰值预留或者P95预留的方式，能够实现对不同业务、不同特性、不同模式的流量分类并针对性的进行带宽推荐，从而避免流量浪费，降低成本，同时保证业务传输质量。
在其他实施例中，不同流量模式的第一带宽还可以按照如下方式设置：例如，平稳双峰 型的第一带宽采用流量序列的峰值，小值震荡型、震荡双峰型和突发毛刺型的第一带宽均采用流量序列的85％分位值。
图16是本申请实施例提供的一种第三带宽确定方法的流程图。该方法可以由图1所示的应用场景中的控制设备执行，如图16所示，该方法包括如下步骤。
S61：采用流量模式对应的第一带宽作为帕累托分布阈值，拟合流量数据中流量序列中大于帕累托分布阈值的流量样本的帕累托分布的累计概率分布函数。
在极值理论中，超越阈值方法(peak over threshold，POT)是常用的分析方法，该方法为数据中超出某一高阈值部分的分析提供建模。假设{X 1,X 2,X 3,….X n}是一组独立分布的随机变量。通过选择一个合适的阈值u，可以将高出阈值部分的数据筛选出来作为极值。极值理论认为，极值部分的流量服从广义帕累托分布(Generalized Pareto Distribution，GPD)。
对于一个标准的GPD分布，其累计概率分布函数(cumulative distribution function，CDF)为：
Figure PCTCN2022141924-appb-000027
该分布由三个参数决定：位置系数μ，范围系数σ，以及形状系数ξ。其中，位置系数μ可以是在确定序列的极值时所用到的阈值。在位置系数μ给定的情况下，可以通过极大似然方法拟合出GPD分布的累计概率分布函数。
S62：根据帕累托分布的累计概率分布函数和期望异常突发概率，确定出第三带宽。
可选地，该方法还包括：根据所述第一带宽确定隧道关联的网络设备应用所述第三带宽的条件。
示例性地，应用所述第三带宽的条件包括：流量越限的次数超过次数阈值，和/或，流量越限的持续时间超过时间阈值。
前述时间周期、次数阈值、时间阈值等可以根据需要设置，例如时间周期为一天或一周，次数阈值为10次或30次，时间阈值为1小时或5小时等。
在为流量序列拟合出累计概率分布函数的基础上，通过客户对第三带宽的期望置信度确定合适的突发预留。例如，如果客户对第三带宽的期望置信度为90％，则找出累计概率分布函数中CDF为0.9所对应的分位值，该分位值即为求得的第三带宽。
在其他实施例中，第三带宽还可以采用如下方式设置：例如，将流量模式对应的第一带宽除以系数，得到第三带宽，该系数取值在0和1之间，例如该系数的取值为0.7或0.8。
在其他实施例中，第三带宽还可以根据流量模式直接确定，例如，平稳双峰型的第三带宽为流量序列的峰值的120％，小值震荡型、震荡双峰型和突发毛刺型的第三带宽均采用流量序列的峰值。
图17是本申请实施例提供的一种带宽推荐方法的流程图。该方法可以由图1所示的应用场景中的控制设备和网络设备执行，如图17所示，该方法包括如下步骤。
S71：控制设备获取流量画像。
示例性地，控制设备包括确定模块，确定模块从画像存储模块中获取隧道的标识对应的 流量画像。
示例性地，当流量画像包括场景时，步骤S71包括如下步骤：
确定当前时间是否为节日或有事件发生；
当当前时间为节日时，获取场景为节日场景的流量画像；当当前时间有事件发生时，获取场景为事件场景的流量画像；当当前时间不是节日，且没有事件发生时，获取场景为日常场景的流量画像。
可以理解的，当上述场景还包括子类型时，则确定场景时按照子类型进行确定。
例如，当前时间为第一节日，获取场景为节日场景的流量画像，包括：
查找节日类型为第一节日的流量画像；
若未查找到节日类型为第一节日的流量画像，则获取节日类型为与第一节日相似的第二节日的流量画像。
当前时间发生第一事件，获取场景为事件场景的流量画像，包括：
查找事件类型为第一事件的流量画像；
若未查找到事件类型为第一事件的流量画像，则获取事件类型为与第一事件相似的第二事件的流量画像。
其中，哪些节日具有相似性，哪些事件具有相似性，可以在控制设备中事先定义，例如，事先将中秋节和端午节定义为相似节日。
通过将重大节日和重大事件的流量画像单独设置以及基于相似节日和事件进行流量画像的选取，从而能够更加准确地为这些节日和事件进行带宽推荐，降低重大节日和事件时流量异常风险发生的概率。
另外，在控制设备的画像存储模块中可能存储多条隧道的流量画像，因此在获取流量画像时可以使用隧道的标识进行检索。而在控制设备的画像存储模块中仅存储一条隧道的流量画像时，则无需采用隧道的标识进行检索。
步骤S71中获取流量画像的过程，也即是确定匹配的场景及匹配的场景对应的第一带宽的过程。
S72：控制设备根据第一带宽为隧道关联的网络设备推荐网络带宽。
示例性地，控制设备在给网络设备推荐带宽时还可以考虑全网情况，例如当网络未发生拥塞时，可以直接采用第一带宽进行带宽推荐，而当网络发生拥塞时，可以在第一带宽基础上适当减小进行推荐。
其中，网络拥塞根据时延、丢包等网络参数中的至少一项进行判断，本申请对此不做赘述。
S73：网络设备根据控制设备推荐的网络带宽进行带宽配置。
示例性地，网络设备还包括带宽配置模块，带宽配置模块根据控制设备推荐的带宽进行隧道的隧道带宽配置。
示例性地，该流量画像还包括第三带宽，此时带宽推荐的流程如下：控制设备先将第一带宽(或根据第一带宽确定的带宽)发送给网络设备，以使网络设备采用第一带宽(或根据第一带宽确定的带宽)对隧道的带宽进行配置。然后，控制设备接收网络设备发送的在配置第一带宽(或根据第一带宽确定的带宽)之后流量越限次数和持续时间。如果流量越限次数和持续时间满足条件，则控制设备将第三带宽发送给网络设备，以使网络设备采用第三带宽 对配置给隧道的带宽进行调整。这进一步提升了业务传输质量。
其中，越限是指流量超过第一带宽。流量每超过一次基础流量，则越限次数加1。越限持续时间基于越限次数计算，例如越限1次5分钟，则越限次数为10次时，越限持续时间为50分钟。
图18是本申请实施例提供的一种带宽推荐方法的流程图。图18所示为上述步骤S72和S73的详细过程，如图18所示，该方法包括如下步骤。
7231：网络设备向控制设备发送当前配置给隧道的带宽。
其中，当前配置给隧道的带宽由网络设备的带宽配置模块提供，控制设备接收后将当前配置给隧道的带宽输出给向控制设备的确定模块。
7232：控制设备的确定模块从存储模块中获取流量画像中的第一带宽。
若根据该第一带宽确定的推荐带宽和网络设备当前配置给隧道的带宽不同，则执行步骤7233。
7233：控制设备将第一带宽发送给网络设备。
网络设备接收后将第一带宽输出给带宽配置模块。
7234：网络设备的带宽配置模块采用第一带宽进行带宽配置。
7235：网络设备向控制设备发送第二流量数据。
第二流量数据包括在所述第一带宽被应用时，所述隧道在第三时间段内的流量越限的次数和/或流量越限的持续时间，所述流量越限指示所述链路的流量超过所述第一带宽。
其中，控制设备接收后将第二流量数据输出给向控制设备的确定模块。
在本申请实施例中，网络设备可以周期性地向控制设备上报第二流量数据。而控制设备则根据接收到的第二流量数据，判断是否进行第三带宽的查询和下发。
7236：如果隧道满足应用第三带宽的条件，则控制设备的确定模块从存储模块中获取流量画像中的第三带宽。
示例性地，应用所述第三带宽的条件包括：流量越限的次数超过次数阈值，和/或，流量越限的持续时间超过时间阈值。
前述时间周期、次数阈值、时间阈值等可以根据需要设置，例如时间周期为一天或一周，次数阈值为10次或30次，时间阈值为1小时或5小时等。
7237：控制设备根据第三带宽向网络设备发送带宽调整指示。
其中，控制设备可以在带宽调整指示中直接包括第三带宽，或者包括第三带宽和第一带宽的差值。控制设备也可以根据越限次数对第三带宽进行增减，然后包括在带宽调整指示中，例如越限次数超过一定次数，则可以增第三带宽，然后包括在带宽调整指示中。
7238：网络设备的带宽配置模块根据带宽调整指示对配置给隧道的带宽进行调整。
例如，在原来第一带宽基础上加上第三带宽和第一带宽的差值，或者直接将原来配置的带宽调整为带宽调整第三带宽。
在上述实现方式中，第一带宽和第三带宽是分步指示的。在其他实现方式中，网络控制设备还可以将第一带宽、第三带宽以及应用第三带宽的条件一起下发给网络设备，这样网络设备可以在应用第一带宽后，根据应用第三带宽的条件确定是否要进一步应用第三带宽。
在本申请实施例中，通过先给网络设备配置第一带宽，在流量越限次数和持续时间过高 时，才使用第三带宽对配置的带宽进行调整，提高了带宽推荐的准确性，提高了带宽利用率，降低了带宽浪费，节省成本。
图19是本申请实施例提供的一种带宽推荐装置的框图。该带宽推荐装置可以通过软件、硬件或者两者的结合实现成为控制设备的全部或者一部分。该带宽推荐装置可以包括：获取单元801、确定单元802和指示单元803。
其中，所述获取单元801用于获取链路的第一流量数据。所述确定单元802用于根据所述链路的第一流量数据确定所述链路的流量模式，并根据所述流量模式确定第一带宽。所述指示单元803用于指示所述链路关联的网络设备应用所述第一带宽。所述流量模式指示所述链路在第一时间段内的流量值的变化趋势。
可选地，所述确定单元802还用于根据所述第一时间段对应的时间或所述第一时间段对应的事件确定所述链路的第一场景。
可选地，所述装置还包括存储单元804。所述存储单元804用于存储所述第一场景和所述第一场景对应的所述第一带宽。
可选地，所述确定单元802还用于根据第二时间段确定所述链路的第二场景。确定单元802还用于确定所述第二场景和所述第一场景匹配，并根据所述第一带宽确定第二带宽。所述指示单元803还用于指示所述链路关联的网络设备应用所述第二带宽。
可选地，所述确定单元802还用于根据所述流量模式确定第三带宽和应用所述第三带宽的条件，所述第三带宽大于第一带宽。所述指示单元803还用于当所述应用所述第三带宽的条件满足时，指示所述链路关联的网络设备应用所述第三带宽。
可选地，所述指示单元803还用于发送所述第三带宽或所述第三带宽和所述第一带宽的差值，以及所述应用所述第三带宽的条件给所述链路关联的网络设备，以指示所述链路关联的网络设备在所述链路满足所述应用所述第三带宽的条件时应用所述第三带宽。
可选地，所述装置还包括接收单元805。所述接收单元805用于接收第二流量数据。所述指示单元803还用于响应于根据所述第二流量数据判断所述链路满足所述应用所述第三带宽的条件，指示所述链路关联的网络设备应用所述第三带宽。所述第二流量数据包括在所述第一带宽被应用时，所述链路在第三时间段内的流量越限的次数和/或流量越限的持续时间。所述流量越限指示所述链路的流量超过所述第一带宽。
可选地，所述应用所述第三带宽的条件包括：所述链路的流量越限的次数超过次数阈值，和/或，所述链路的流量越限的持续时间超过时间阈值。
可选地，所述装置还包括显示单元806。所述显示单元806用于显示所述第二场景和所述第二带宽。
可选地，所述显示单元806还用于显示与所述第二场景匹配的所述第一场景和/或所述第一场景的流量模式。
可选地，所述流量模式包括小值震荡型、突发毛刺型、平稳双峰型和震荡双峰型中的至少一种。
可以理解的是，前述各个单元可以由一个设备实现，也可以由不同设备实现，例如，获取单元和确定单元由1个设备实现，存储单元、指示单元和显示单元由1个设备实现。
需要说明的是，上述实施例提供的带宽推荐装置在进行带宽推荐时，仅以上述各功能单元的划分进行举例说明，实际应用中，可以根据需要而将上述功能分配由不同的功能单元完 成，即将设备的内部结构划分成不同的功能单元，以完成以上描述的全部或者部分功能。另外，上述实施例提供的带宽推荐装置与带宽推荐方法实施例属于同一构思，其具体实现过程详见方法实施例，这里不再赘述。
图20是本申请实施例提供的一种显示装置的框图。该显示装置可以通过软件、硬件或者两者的结合实现成为控制设备的一部分或者独立于控制设备的显示设备。该显示装置可以包括：获取单元901和显示单元902。
其中，获取单元901用于获取链路所属的场景，并基于所述场景确定为所述链路推荐的带宽。显示单元902用于显示所述场景和所述为所述链路推荐的带宽。
可选地，所述显示单元902还用于显示与所述场景匹配的场景、该匹配的场景对应的带宽和该匹配的场景对应的流量模式中的至少一种。
需要说明的是，上述实施例提供的显示装置在进行显示时，仅以上述各功能单元的划分进行举例说明，实际应用中，可以根据需要而将上述功能分配由不同的功能单元完成，即将设备的内部结构划分成不同的功能单元，以完成以上描述的全部或者部分功能。另外，上述实施例提供的显示装置与带宽推荐方法实施例属于同一构思，其具体实现过程详见方法实施例，这里不再赘述。
上述各个附图对应的流程的描述各有侧重，某个流程中没有详述的部分，可以参见其他流程的相关描述。
图21示出了本申请实施例提供的控制设备150的结构示意图。图21所示的控制设备150用于执行上述图2至图18任一幅所示的带宽推荐方法所涉及的操作。该控制设备150可以由一般性的总线体系结构来实现。
如图21所示，控制设备150包括至少一个处理器151、存储器153以及至少一个通信接口154。
处理器151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)、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151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申请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，控制设备150还包括总线。总线用于在控制设备150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21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153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153例如是独立存在，并通过总线与处理器151相连接。存储器153也可以和处理器151集成在一起。
通信接口154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 networks，WLAN)等。通信接口154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154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154可以用于控制设备150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151可以包括一个或多个CPU，如图21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，控制设备150可以包括多个处理器，如图21中所示的处理器151和处理器155。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，控制设备150还可以包括输出设备和输入设备。输出设备和处理器151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151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153用于存储执行本申请方案的程序代码1510，处理器151可以执行存储器153中存储的程序代码1510。也即是，控制设备150可以通过处理器151执行存储器153中的程序代码1510，来实现方法实施例提供的数据处理方法。程序代码1510中可以包括一个或多个软件模块。可选地，处理器151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，本申请实施例的控制设备150可对应于上述各个方法实施例中的控制器，控制设备150中的处理器151读取存储器153中的指令，使图21所示的控制设备150能够执行控制器所执行的全部或部分操作。
具体的，处理器151用于获取链路的第一流量数据，根据所述链路的第一流量数据确定所述链路的流量模式，根据所述流量模式确定第一带宽，并指示所述链路关联的网络设备应用所述第一带宽。所述流量模式指示所述链路在第一时间段内的流量值的变化趋势。
其他可选的实施方式，为了简洁，在此不再赘述。
其中，图2至图18任一幅所示的带宽推荐方法的各步骤通过控制设备150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。
本申请实施例还提供了一种芯片，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任一种的流量画像生成方法或带宽推荐方法。
应理解的是，上述处理器可以是CPU，还可以是其他通用处理器、DSP、ASIC、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ARM架构的处理器。
进一步地，在一种可选的实施例中，上述处理器为一个或多个，存储器为一个或多个。可选地，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。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，存储器还可以存储参考块和目标块。
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ROM、PROM、EPROM、EEPROM或闪存。易失性存储器可以是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，SRAM、DRAM、SDRAM、DDR SDRAM、ESDRAM、SLDRAM和DR RAM。
本申请实施例中，还提供了一种计算机可读存储介质，计算机可读存储介质存储有计算机指令，当计算机可读存储介质中存储的计算机指令被控制设备执行时，使得控制设备执行上述所提供的流量画像生成方法或带宽推荐方法。
本申请实施例中，还提供了一种包含指令的计算机程序产品，当其在控制设备上运行时，使得控制设备执行上述所提供的流量画像生成方法或带宽推荐方法。
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，所述的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。
以上所述仅为本申请的可选实施例，但本申请的保护范围并不局限于此，任何熟悉本技术领域的技术人员在本申请揭露的技术范围内，可轻易想到的变化或替换，都应涵盖在本申请的保护范围之内。因此，本申请的保护范围应该以权利要求的保护范围为准。
除非另作定义，此处使用的技术术语或者科学术语应当为本申请所属领域内具有一般技能的人士所理解的通常意义。本申请专利申请说明书以及权利要求书中使用的“第一”、“第二”、“第三”以及类似的词语并不表示任何顺序、数量或者重要性，而只是用来区分不同的组成部分。同样，“一个”或者“一”等类似词语也不表示数量限制，而是表示存在至少一个。“包括”或者“包含”等类似的词语意指出现在“包括”或者“包含”前面的元件或者物件涵盖出现在“包括”或者“包含”后面列举的元件或者物件及其等同，并不排除其他元件或者物件。
以上仅为本申请一个实施例，并不用以限制本申请，凡在本申请的精神和原则之内，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 (24)

  1. 一种带宽推荐方法，其特征在于，所述方法包括：
    获取链路的第一流量数据；
    根据所述链路的第一流量数据确定所述链路的流量模式，所述流量模式指示所述链路在第一时间段内的流量值的变化趋势；
    根据所述流量模式确定第一带宽；
    指示所述链路关联的网络设备应用所述第一带宽。
  2. 根据权利要求1所述的方法，其特征在于，所述方法还包括：
    根据所述第一时间段对应的时间或所述第一时间段对应的事件确定所述链路的第一场景，并存储所述第一场景和所述第一场景对应的所述第一带宽。
  3. 根据权利要求2所述的方法，其特征在于，所述方法还包括：
    根据第二时间段确定所述链路的第二场景；
    确定所述第二场景和所述第一场景匹配；
    根据所述第一带宽确定第二带宽，并指示所述链路关联的网络设备应用所述第二带宽。
  4. 根据权利要求1至3任一所述的方法，其特征在于，所述方法还包括：
    根据所述流量模式确定第三带宽和应用所述第三带宽的条件，所述第三带宽大于所述第一带宽；
    当所述应用所述第三带宽的条件满足时，指示所述链路关联的网络设备应用所述第三带宽。
  5. 根据权利要求4所述的方法，其特征在于，所述方法还包括：
    发送所述第三带宽或所述第三带宽和所述第一带宽的差值，以及所述应用所述第三带宽的条件给所述链路关联的网络设备，以指示所述链路关联的网络设备在所述链路满足所述应用所述第三带宽的条件时应用所述第三带宽。
  6. 根据权利要求4所述的方法，其特征在于，所述方法还包括：
    接收第二流量数据，所述第二流量数据包括在所述第一带宽被应用时，所述链路在第三时间段内的流量越限的次数和/或流量越限的持续时间，所述流量越限指示所述链路的流量超过所述第一带宽；
    响应于根据所述第二流量数据判断所述链路满足所述应用所述第三带宽的条件，指示所述链路关联的网络设备应用所述第三带宽。
  7. 根据权利要求4至6任一所述的方法，其特征在于，所述应用所述第三带宽的条件包括：所述链路的流量越限的次数超过次数阈值，和/或，所述链路的流量越限的持续时间超过时间阈值。
  8. 根据权利要求3所述的方法，其特征在于，所述方法还包括：
    显示所述第二场景和所述第二带宽。
  9. 根据权利要求8所述的方法，其特征在于，所述方法还包括：
    显示与所述第二场景匹配的所述第一场景和/或所述第一场景的流量模式。
  10. 根据权利要求1至9任一项所述的方法，其特征在于，所述流量模式包括小值震荡型、突发毛刺型、平稳双峰型和震荡双峰型中的至少一种。
  11. 一种显示装置，其特征在于，所述显示装置包括：
    获取单元，用于获取链路所属的场景；
    所述获取单元，还用于基于所述场景确定为所述链路推荐的带宽；
    显示单元，用于显示所述场景和所述为所述链路推荐的带宽。
  12. 一种带宽推荐装置，其特征在于，所述装置包括：
    获取单元，用于获取链路的第一流量数据；
    确定单元，用于根据所述链路的第一流量数据确定所述链路的流量模式，所述流量模式指示所述链路在第一时间段内的流量值的变化趋势；
    所述确定单元，还用于根据所述流量模式确定第一带宽；
    指示单元，用于指示所述链路关联的网络设备应用所述第一带宽。
  13. 根据权利要求12所述的装置，其特征在于，所述装置还包括存储单元，
    所述确定单元，还用于根据所述第一时间段对应的时间或所述第一时间段对应的事件确定所述链路的第一场景；
    所述存储单元，用于存储所述第一场景和所述第一场景对应的所述第一带宽。
  14. 根据权利要求13所述的装置，其特征在于，
    所述确定单元，还用于根据第二时间段确定所述链路的第二场景；
    所述确定单元，还用于确定所述第二场景和所述第一场景匹配，并根据所述第一带宽确定第二带宽；
    所述指示单元，还用于指示所述链路关联的网络设备应用所述第二带宽。
  15. 根据权利要求12至14任一项所述的装置，其特征在于，
    所述确定单元，还用于根据所述流量模式确定第三带宽和应用所述第三带宽的条件，所述第三带宽大于所述第一带宽；
    所述指示单元，还用于当所述应用所述第三带宽的条件满足时，指示所述链路关联的网络设备应用所述第三带宽。
  16. 根据权利要求15所述的装置，其特征在于，
    所述指示单元，还用于发送所述第三带宽或所述第三带宽和所述第一带宽的差值，以及所述应用所述第三带宽的条件给所述链路关联的网络设备，以指示所述链路关联的网络设备在所述链路满足所述应用所述第三带宽的条件时应用所述第三带宽。
  17. 根据权利要求15所述的装置，其特征在于，所述装置还包括接收单元，
    所述接收单元，用于接收第二流量数据，所述第二流量数据包括在所述第一带宽被应用时，所述链路在第三时间段内的流量越限的次数和/或流量越限的持续时间，所述流量越限指示所述链路的流量超过所述第一带宽；
    所述指示单元，还用于响应于根据所述第二流量数据判断所述链路满足所述应用所述第三带宽的条件，指示所述链路关联的网络设备应用所述第三带宽。
  18. 根据权利要求15至17任一项所述的装置，其特征在于，所述应用所述第三带宽的条件包括：所述链路的流量越限的次数超过次数阈值，和/或，所述链路的流量越限的持续时间超过时间阈值。
  19. 根据权利要求14所述的装置，其特征在于，所述装置还包括显示单元，
    所述显示单元，用于显示所述第二场景和所述第二带宽。
  20. 根据权利要求19所述的装置，其特征在于，
    所述显示单元，还用于显示与所述第二场景匹配的所述第一场景和/或所述第一场景的流量模式。
  21. 根据权利要求12至20任一项所述的装置，其特征在于，所述流量模式包括小值震荡型、突发毛刺型、平稳双峰型和震荡双峰型中的至少一种。
  22. 一种控制设备，其特征在于，所述控制设备包括处理器和存储器，所述存储器用于存储软件程序，所述处理器通过运行或执行存储在所述存储器内的软件程序，以使所述控制设备实现如权利要求1至10任一项所述的方法。
  23. 一种计算机可读存储介质，其特征在于，所述计算机可读存储介质用于存储处理器所执行的程序代码，所述程序代码包括用于实现如权利要求1至10任一项所述的方法的指令。
  24. 一种计算机程序产品，其特征在于，包括程序代码，当计算机运行所述计算机程序产品时，使得所述计算机执行如权利要求1至10任一项所述的方法。
PCT/CN2022/141924 2021-12-31 2022-12-26 带宽推荐方法及装置、显示装置、控制设备 WO2023125411A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202111671672.1A CN116418761A (zh) 2021-12-31 2021-12-31 带宽推荐方法及装置、显示装置、控制设备
CN202111671672.1 2021-12-31

Publications (1)

Publication Number Publication Date
WO2023125411A1 true WO2023125411A1 (zh) 2023-07-06

Family

ID=86997802

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/141924 WO2023125411A1 (zh) 2021-12-31 2022-12-26 带宽推荐方法及装置、显示装置、控制设备

Country Status (2)

Country Link
CN (1) CN116418761A (zh)
WO (1) WO2023125411A1 (zh)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20080273591A1 (en) * 2007-05-04 2008-11-06 Brooks Paul D Methods and apparatus for predictive capacity allocation
US20090245107A1 (en) * 2008-03-25 2009-10-01 Verizon Data Services Inc. System and method of forecasting usage of network links
CN102088403A (zh) * 2010-11-10 2011-06-08 中国人民解放军信息工程大学 一种网络链路动态带宽的计算方法及系统
US20200296023A1 (en) * 2019-03-15 2020-09-17 Juniper Networks, Inc. Real-time application-driven synthetic probing
CN113301392A (zh) * 2021-05-26 2021-08-24 百果园技术(新加坡)有限公司 码率确定方法、装置、设备及存储介质

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20080273591A1 (en) * 2007-05-04 2008-11-06 Brooks Paul D Methods and apparatus for predictive capacity allocation
US20090245107A1 (en) * 2008-03-25 2009-10-01 Verizon Data Services Inc. System and method of forecasting usage of network links
CN102088403A (zh) * 2010-11-10 2011-06-08 中国人民解放军信息工程大学 一种网络链路动态带宽的计算方法及系统
US20200296023A1 (en) * 2019-03-15 2020-09-17 Juniper Networks, Inc. Real-time application-driven synthetic probing
CN113301392A (zh) * 2021-05-26 2021-08-24 百果园技术(新加坡)有限公司 码率确定方法、装置、设备及存储介质

Also Published As

Publication number Publication date
CN116418761A (zh) 2023-07-11

Similar Documents

Publication Publication Date Title
US9705783B2 (en) Techniques for end-to-end network bandwidth optimization using software defined networking
CN109032801B (zh) 一种请求调度方法、系统及电子设备和存储介质
CN111416729B (zh) 一种网络切片的资源调度的方法及设备
WO2018177012A1 (zh) 一种控制带宽的方法、装置和设备
US11075843B2 (en) Model management in a dynamic QOS environment
US9391749B2 (en) System and method for distributed data management in wireless networks
KR101228854B1 (ko) 서비스 차별화된 무선 네트워크에서 ＱｏＳ를 측정하고감시하는 방법
GB2541047A (en) Model management in a dynamic QOS environment
CN103595651B (zh) 基于分布式的数据流处理方法和系统
EP3318009B1 (en) Model management in a dynamic qos environment
CN111147395B (zh) 一种网络资源调整方法及装置
WO2021027783A1 (zh) 分配射频资源的方法、装置、设备、系统和存储介质
US10200871B2 (en) Radio resource allocation method and radio network controller
WO2023125411A1 (zh) 带宽推荐方法及装置、显示装置、控制设备
CN111800291B (zh) 一种服务功能链部署方法及装置
CN112039689B (zh) 网络设备性能评估方法、装置、设备及存储介质
CN107409315A (zh) 基于性能的QoS因子优化
CN106997310A (zh) 负载均衡的装置和方法
CN114896296A (zh) 云服务资源配置方法、装置、电子设备及计算机可读介质
WO2024066623A1 (zh) 调度策略的确定方法及相关装置
TWI735520B (zh) 調整元件邏輯執行緒數量的方法及裝置
CN112399596B (zh) 分配射频资源的方法、装置、设备、系统和存储介质
EP3804381A1 (en) Cellular telecommunications network
WO2020162208A1 (ja) 通信制御装置、および、通信制御方法
CN118201025A (zh) 基于Wi-Fi的网格网络的组网方法、装置、设备及存储介质

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: 22914665

Country of ref document: EP

Kind code of ref document: A1