Path determination method and device and storage medium

Abstract

The invention provides a path determination method and device and a storage medium, and relates to the field of network management. First traffic of a main path and first traffic of each backup path in the future time are predicted, then the first traffic of the main path in the future time is superposed on the basis of second traffic of each backup path in the future time, and third traffic of each backup path in the future time is obtained. And determining a target backup path according to the congestion condition of the third flow of each backup path in the future time. Therefore, the congestion problem caused by the backup path is avoided. Not only can the traffic of the main path be timely switched, but also the performance of the backup path after the traffic is switched can be effectively guaranteed.

Description

Technical Field

[0001] The present disclosure relates to the field of network management, and in particular to a path determination method and device and a storage medium. Background Art

[0002] Faced with increasingly complex networks and increasing network traffic, network operation and maintenance personnel need to understand the network operation status in advance and optimize or adjust the network before network failures occur to maintain normal network operation.

[0003] When all candidate paths and segment lists of SRv6 (Segment Routing IPv6 (Internet Protocol Version 6)) Policy fail, the SRv6 Policy protection switch is usually performed directly. For example, in a VPN (Virtual Private Network) dual-homing scenario, if a VPN node fails, all SRv6 Policies reaching the node will fail. At this time, it is necessary to switch to the SRv6 Policy pointing to another VPN node. Figure 1 As shown in the figure, hot standby (HSB) protection is deployed between the primary path and the backup path of SRv6 Policy1. P (Provider) represents the carrier backbone router, PE (Provider Edge) represents the carrier edge router, and CE (Customer Edge) represents the customer edge router. The path specified by Segment List1 includes routing devices such as P1, P2, and PE2, and protection mechanisms such as TI-LFA (Topology-Independent Loop-free Alternate) and FRR (Fast Reroute) are deployed on the nodes.

[0004] Currently, the shortest routing strategy is often used to select backup paths. However, this routing strategy will cause a large amount of data to converge on a key link, resulting in local congestion in the network, thereby causing a series of network problems. Summary of the invention

[0005] The disclosed embodiment predicts the first flow of the main path and each backup path at a future time, and then superimposes the first flow of the main path at the future time on the basis of the second flow of each backup path at the future time to obtain the third flow of each backup path at the future time, and determines the target backup path according to the congestion of the third flow of each backup path at the future time. This avoids the congestion problem caused by the backup path. Not only can the timely switching of the main path flow be guaranteed, but also the performance of the backup path after the flow switching can be effectively guaranteed.

[0006] Some embodiments of the present disclosure provide a path determination method, including:

[0007] Predicting the first flow of the main path at a future time;

[0008] Predicting the second flow of each backup path at the future time;

[0009] Superimposing the first flow of the primary path at the future time on the basis of the second flow of each backup path at the future time, to obtain a third flow of each backup path at the future time;

[0010] A target backup path is determined according to the congestion status of the third traffic on each backup path at the future time.

[0011] In some embodiments, it also includes: determining the congestion situation of the third traffic of each backup path at the future time by comparing the third traffic of each backup path at the future time with the dynamic traffic congestion threshold value, wherein the dynamic traffic congestion threshold value of each backup path at the future time is determined based on the historical data of each backup path.

[0012] In some embodiments, it also includes: predicting the maximum number of data packets transmitted by each backup path at the future time based on the historical data of each backup path; and determining the dynamic traffic congestion threshold value of each backup path at the future time based on the maximum number and data packet length of data packets transmitted by each backup path at the future time.

[0013] In some embodiments, the historical data of each backup path includes the maximum number of data packets transmitted by each backup path at a historical time; wherein, predicting the maximum number of data packets transmitted by each backup path at the future time includes: inputting the maximum number of data packets transmitted by each backup path at a historical time into a first prediction model, and obtaining the maximum number of data packets transmitted by each backup path at the future time predicted by the first prediction model, wherein the first prediction model is obtained based on an artificial intelligence model.

[0014] In some embodiments, determining the dynamic traffic congestion threshold value of each backup path at the future time includes:

[0015] Determine the maximum number of bytes transmitted by each backup path at the future time based on the product of the maximum number of data packets transmitted by each backup path at the future time and the length of the data packet;

[0016] Based on the maximum number of bytes transmitted by each backup path at the future time, a dynamic traffic congestion threshold value of each backup path at the future time is determined.

[0017] In some embodiments, determining the target backup path includes: determining the target backup path according to the congestion status of the third traffic of each backup path at the future time and the risk assessment status of the service level agreement indicator.

[0018] In some embodiments, determining the target backup path includes: determining a backup path without congestion and risk for the third traffic at the future time as a candidate backup path, and determining the target backup path based on the candidate backup path.

[0019] In some embodiments, determining the target backup path based on the candidate backup paths includes: if there are multiple candidate backup paths, determining the shortest candidate backup path as the target backup path.

[0020] In some embodiments, it also includes: determining the service level agreement indicator risk assessment status of each backup path at the future time by comparing the bandwidth utilization of each backup path at the future time with the preset service level agreement bandwidth utilization.

[0021] In some embodiments, predicting the first flow of the main path at a future time includes: inputting the flow data of the main path at a historical time into a second prediction model, and obtaining the first flow of the main path at a future time predicted and output by the second prediction model, wherein the second prediction model is obtained based on an artificial intelligence model.

[0022] In some embodiments, predicting the second flow of each backup path at the future time includes: inputting the flow data of each backup path at a historical time into a second prediction model, and obtaining the second flow of each backup path at the future time predicted and output by the second prediction model, wherein the second prediction model is obtained based on an artificial intelligence model.

[0023] In some embodiments, the method further includes: if the primary path fails at the future time, switching the service of the primary path to the target backup path.

[0024] In some embodiments, the primary path and the backup path are segment routing (SRv6) paths based on Internet Protocol version 6.

[0025] Some embodiments of the present disclosure provide a path determination device, comprising: a memory; and a processor coupled to the memory, wherein the processor is configured to execute a path determination method based on instructions stored in the memory.

[0026] Some embodiments of the present disclosure provide a path determination device, including: a module for executing a path determination method.

[0027] Some embodiments of the present disclosure provide a non-transitory computer-readable storage medium having a computer program stored thereon, which implements the steps of the path determination method when the program is executed by a processor. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] The following is a brief introduction to the drawings required for use in the embodiments or related technical descriptions. The present disclosure can be more clearly understood according to the following detailed description with reference to the drawings.

[0029] Obviously, the drawings described below are only some embodiments of the present disclosure, and a person skilled in the art can obtain other drawings based on these drawings without creative work.

[0030] Figure 1 A schematic diagram of hot standby protection between an SRv6 primary path and a backup path is shown.

[0031] Figure 2 A schematic flow chart showing a path determination method according to some embodiments of the present disclosure.

[0032] Figure 3 A flowchart of a method for determining a dynamic traffic congestion threshold value according to some embodiments of the present disclosure is shown.

[0033] Figure 4 A schematic diagram showing the structure of a path determination device according to some embodiments of the present disclosure.

[0034] Figure 5 A schematic diagram showing the structure of a path determination device according to some embodiments of the present disclosure. DETAILED DESCRIPTION

[0035] The technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure.

[0036] Unless otherwise specified, descriptions such as “first” and “second” in the present disclosure are used to distinguish different objects and are not used to indicate meanings such as size or time sequence.

[0037] Figure 2 A schematic flow chart showing a path determination method according to some embodiments of the present disclosure.

[0038] like Figure 2 As shown, the path determination method of this embodiment includes steps 210-250 and 270, and may further include one or more of steps 260 or 280 as needed.

[0039] In step 210, traffic prediction related data is obtained, and the obtained data may also be pre-processed and stored.

[0040] In some embodiments, step 210 includes steps (1)-(3).

[0041] In step (1), in response to a path switching solution verification request, traffic prediction related data such as configuration data, traffic data, and performance data of a primary path and a backup path are obtained.

[0042] The configuration data of the path includes, for example, but is not limited to, information of the head-end device and the terminal device of the path, and other information that can represent the path or its directionality.

[0043] The flow data of the path includes, for example, but is not limited to, the flow data of each collection period of the path in the historical time. The collection period is set according to business needs, for example, the collection period can be 5 minutes, 1 hour, 1 day, etc., but is not limited to the examples given.

[0044] The performance data of the path includes, but is not limited to, data such as delay and jitter that can characterize the performance of the path.

[0045] The primary path and the backup path may include, for example, but are not limited to, an SRv6 path.

[0046] In step (2), the acquired data is preprocessed by data cleaning.

[0047] Data cleaning is the process of removing or correcting erroneous, incomplete, malformed, or redundant data from the acquired data. Data cleaning can not only correct errors, but also enhance the consistency of different data from individual devices or path segments.

[0048] In step (3), the pre-processed massive data is stored efficiently and quickly in a certain format.

[0049] For example, for the storage of massive data, reference can be made to relevant big data storage technologies.

[0050] In step 220, a first flow rate of the main path at a future time is predicted.

[0051] In some embodiments, predicting the first flow of the main path at a future time includes: inputting the flow data of the main path at a historical time into a second prediction model, and obtaining the first flow of the main path at a future time predicted and output by the second prediction model. The historical time may include one or more collection cycles. The future time may include one collection cycle.

[0052] In some embodiments, predicting the first flow of the main path at a future time includes: inputting the flow data and performance data of the main path at a historical time into a second prediction model, and obtaining the first flow of the main path at a future time predicted by the second prediction model. The historical time may include one or more collection cycles. The future time may include one collection cycle.

[0053] The second prediction model is obtained based on an artificial intelligence model. The artificial intelligence model includes but is not limited to a machine learning model such as a LightGBM (Light Gradient Boosting Machine) model. The second prediction model is also called a traffic prediction model.

[0054] In some embodiments, obtaining a second prediction model based on an artificial intelligence model includes: inputting the traffic data of a certain path at a first time into the artificial intelligence model, comparing the predicted traffic of the path at a second time predicted by the artificial intelligence model with the actual traffic of the path at the second time to determine the prediction deviation, continuously updating the parameters of the artificial intelligence model according to the prediction deviation until the prediction deviation is small enough to meet the business requirements, and using the trained artificial intelligence model as the second prediction model. The second time is later than the first time. The first time may include one or more acquisition cycles.

[0055] In some embodiments, obtaining a second prediction model based on an artificial intelligence model includes: inputting the traffic data and performance data of a path at a first time into the artificial intelligence model, comparing the predicted traffic of the path at a second time predicted by the artificial intelligence model with the actual traffic of the path at the second time to determine the prediction deviation, continuously updating the parameters of the artificial intelligence model according to the prediction deviation until the prediction deviation is small enough to meet the business requirements, and using the trained artificial intelligence model as the second prediction model. The second time is later than the first time. The first time may include one or more acquisition cycles.

[0056] In step 230, the second traffic of each backup path at the future time is predicted.

[0057] In some embodiments, predicting the second flow of each backup path at the future time includes: inputting the flow data of each backup path at the historical time into a second prediction model, and obtaining the second flow of each backup path at the future time predicted and output by the second prediction model. The historical time may include one or more collection cycles. The future time may include one collection cycle.

[0058] In some embodiments, predicting the second flow of each backup path at the future time includes: inputting the flow data and performance data of each backup path at the historical time into a second prediction model, and obtaining the second flow of each backup path at the future time predicted and output by the second prediction model. The historical time may include one or more collection cycles. The future time may include one collection cycle.

[0059] The second prediction model is obtained based on an artificial intelligence model. The artificial intelligence model includes but is not limited to a machine learning model such as a LightGBM (Light Gradient Boosting Machine) model. The method for obtaining the second prediction model based on the artificial intelligence model is described above and will not be repeated here.

[0060] In step 240, the first flow of the main path at the future time is superimposed on the second flow of each backup path at the future time, and traffic simulation is performed to obtain the third flow of each backup path at the future time.

[0061] In step 250, the congestion status of the third traffic of each backup path at the future time is determined.

[0062] In some embodiments, the congestion of the third traffic of each backup path at the future time is determined by comparing the third traffic of each backup path at the future time with the dynamic traffic congestion threshold value. If the third traffic of a backup path at the future time is greater than the dynamic traffic congestion threshold value of the backup path at the future time, the backup path is determined to be congested at the future time; otherwise, the backup path is determined to be not congested at the future time.

[0063] The dynamic traffic congestion threshold is not fixed, and the dynamic traffic congestion threshold of each backup path at the future time is dynamically determined according to the historical data of each backup path. The subsequent embodiments will specifically describe the method for determining the dynamic traffic congestion threshold. The determined dynamic traffic congestion threshold is, for example, 0.9, but is not limited to this example.

[0064] The actual congestion situation of the path can be determined more accurately based on the dynamic traffic congestion threshold.

[0065] In step 260, a risk assessment of a service level agreement (SLA) indicator of each backup path at the future time is determined.

[0066] In some embodiments, if step 250 determines that a backup path is not congested at the future time, step 260 can be continued to be executed to further determine the risk assessment status of the service level agreement indicator at the future time; if step 250 determines that a backup path is congested at the future time, there is no need to continue to execute step 260, and the candidacy of the backup path can be directly cancelled.

[0067] In some embodiments, by comparing the bandwidth utilization of each backup path at the future time with the preset service level agreement bandwidth utilization, the risk assessment of the service level agreement indicator of each backup path at the future time is determined. If the bandwidth utilization of a backup path at the future time is greater than the preset service level agreement bandwidth utilization, it is determined that the service level agreement indicator of the backup path at the future time has a risk; otherwise, it is determined that the service level agreement indicator of the backup path at the future time does not have a risk.

[0068] In step 270, the target backup path is determined according to the congestion of the third traffic of each backup path at the future time, or in combination with the risk assessment of the service level agreement indicators of each backup path at the future time.

[0069] In some embodiments, the target backup path is determined based on the congestion of the third traffic of each backup path at the future time and the risk assessment of the service level agreement indicator. The backup path with no congestion and no risk of the third traffic at the future time is determined as a candidate backup path, and the target backup path is determined based on the candidate backup path. Wherein, in the case of multiple candidate backup paths, the shortest candidate backup path is determined as the target backup path. In the case of one candidate backup path, the candidate backup path is determined as the target backup path.

[0070] In step 280, if the primary path fails at the future time, the service of the primary path is switched to the target backup path.

[0071] The disclosed embodiment predicts the first traffic of the main path and each backup path at the future time, and then superimposes the first traffic of the main path at the future time on the basis of the second traffic of each backup path at the future time to obtain the third traffic of each backup path at the future time. According to the congestion of the third traffic of each backup path at the future time, the target backup path can also be determined in combination with the risk assessment of the service level agreement indicators of each backup path at the future time; so that if the main path fails at the future time, the business of the main path can be switched to the target backup path in time. Thereby avoiding the congestion problem caused by the backup path. Not only can the timely switching of the main path traffic be guaranteed, but also the performance of the backup path after the traffic switching can be effectively guaranteed.

[0072] Figure 3 A flowchart of a method for determining a dynamic traffic congestion threshold value according to some embodiments of the present disclosure is shown.

[0073] like Figure 3 As shown, the method for determining the dynamic traffic congestion threshold value of this embodiment includes: steps 310-320.

[0074] In step 310, based on the historical data of each backup path, the maximum number of data packets transmitted by each backup path at the future time is predicted.

[0075] In some embodiments, step 310 includes steps 311 - 312 .

[0076] In step 311, historical data of each backup path is obtained, where the historical data of each backup path includes the maximum number of data packets transmitted by each backup path in a historical time.

[0077] In step 312, the maximum number of data packets transmitted by each backup path at a historical time is input into a first prediction model to obtain the maximum number of data packets transmitted by each backup path at the future time predicted and output by the first prediction model.

[0078] In some embodiments, the historical time may include one or more collection periods, and the future time may include one collection period.

[0079] The first prediction model is obtained based on an artificial intelligence model. The artificial intelligence model includes but is not limited to a machine learning model such as a LightGBM model. The first prediction model is also called a data packet quantity prediction model.

[0080] In some embodiments, obtaining a first prediction model based on an artificial intelligence model includes: inputting the maximum number of packets transmitted by a path at a first time into the artificial intelligence model, comparing the predicted value of the maximum number of packets transmitted by the path at a second time predicted by the artificial intelligence model with the actual value of the maximum number of packets transmitted by the path at the second time to determine the prediction deviation, continuously updating the parameters of the artificial intelligence model according to the prediction deviation until the prediction deviation is small enough to meet business requirements, and using the trained artificial intelligence model as the first prediction model. Wherein, the second time is later than the first time, the first time may include one or more acquisition cycles, and the second time may include one acquisition cycle.

[0081] In step 320, a dynamic traffic congestion threshold value of each backup path at the future time is determined according to the maximum number and length of data packets transmitted by each backup path at the future time.

[0082] In some embodiments, step 320 includes steps 321 - 322 .

[0083] In step 321, the maximum number of bytes transmitted by each backup path at the future time (set as B) is determined based on the product of the maximum number of data packets transmitted by each backup path at the future time (set as Ni) and the data packet length (set as L).

[0084] The formula is: B=Ni×L.

[0085] In step 322, based on the maximum number of bytes transmitted by each backup path at the future time, a dynamic traffic congestion threshold value of each backup path at the future time is determined.

[0086] In one embodiment, based on a conversion formula, such as 8bit = 1Byte, 1024Byte = 1KB, 1024KB = 1MB, the unit of Ni is converted into kb or MB or others, and the converted Ni is the dynamic traffic congestion threshold value.

[0087] In the above embodiment, the dynamic traffic congestion threshold is not fixed. The dynamic traffic congestion threshold of the backup path at the future time is dynamically determined according to the historical data of the backup path. The actual congestion of the path can be determined more accurately based on the dynamic traffic congestion threshold.

[0088] Figure 4 A schematic diagram showing the structure of a path determination device according to some embodiments of the present disclosure.

[0089] like Figure 4 As shown, the path determination device 400 of this embodiment includes: various modules for executing the path determination method.

[0090] The data acquisition module 410 is configured to acquire traffic prediction related data. The data acquisition module 410 is configured to acquire traffic prediction related data such as configuration data, traffic data and performance data of the primary path and the backup path in response to the path switching solution verification request.

[0091] The configuration data of the path includes, for example, but is not limited to, information of the head-end device and the terminal device of the path, and other information that can represent the path or its directionality.

[0092] The flow data of the path includes, for example, but is not limited to, the flow data of each collection period of the path in the historical time. The collection period is set according to business needs, for example, the collection period can be 5 minutes, 1 hour, 1 day, etc., but is not limited to the examples given.

[0093] The performance data of the path includes, but is not limited to, data such as delay and jitter that can characterize the performance of the path.

[0094] The primary path and the backup path may include, for example, but are not limited to, an SRv6 path.

[0095] The data preprocessing module 420 is configured to perform preprocessing such as data cleaning on the data acquired by the data acquisition module 410. Through data cleaning, erroneous, incomplete, erroneous or redundant data in the acquired data is deleted or corrected. Data cleaning can not only correct errors, but also enhance the consistency between different data from each individual device or path segment.

[0096] The data storage module 430 is configured to store the pre-processed mass data efficiently and quickly in a certain format. The storage of mass data can refer to the relevant big data storage technology, for example.

[0097] The path traffic prediction module 440 is configured to predict the first traffic of the main path at a future time.

[0098] In some embodiments, predicting the first flow of the main path at a future time includes: inputting the flow data of the main path at a historical time into a second prediction model, and obtaining the first flow of the main path at a future time predicted and output by the second prediction model. The historical time may include one or more collection cycles. The future time may include one collection cycle.

[0099] In some embodiments, predicting the first flow of the main path at a future time includes: inputting the flow data and performance data of the main path at a historical time into a second prediction model, and obtaining the first flow of the main path at a future time predicted by the second prediction model. The historical time may include one or more collection cycles. The future time may include one collection cycle.

[0100] The second prediction model is obtained based on an artificial intelligence model. The artificial intelligence model includes but is not limited to the LightGBM model.

[0101] The path traffic prediction module 440 is configured to predict the second traffic of each backup path at the future time.

[0102] In some embodiments, predicting the second flow of each backup path at the future time includes: inputting the flow data of each backup path at the historical time into a second prediction model, and obtaining the second flow of each backup path at the future time predicted and output by the second prediction model. The historical time may include one or more collection cycles. The future time may include one collection cycle.

[0103] In some embodiments, predicting the second flow of each backup path at the future time includes: inputting the flow data and performance data of each backup path at the historical time into a second prediction model, and obtaining the second flow of each backup path at the future time predicted and output by the second prediction model. The historical time may include one or more collection cycles. The future time may include one collection cycle.

[0104] The path traffic simulation module 450 is configured to perform traffic simulation by superimposing the first traffic of the main path at the future time on the basis of the second traffic of each backup path at the future time to obtain the third traffic of each backup path at the future time.

[0105] The path traffic congestion evaluation module 460 is configured to determine the congestion status of the third traffic of each backup path at the future time.

[0106] In some embodiments, the congestion of the third traffic of each backup path at the future time is determined by comparing the third traffic of each backup path at the future time with the dynamic traffic congestion threshold value. If the third traffic of a backup path at the future time is greater than the dynamic traffic congestion threshold value of the backup path at the future time, the backup path is determined to be congested at the future time; otherwise, the backup path is determined to be not congested at the future time.

[0107] The SLA indicator risk assessment module 470 is configured to determine the SLA indicator risk assessment status of each backup path at the future time.

[0108] In some embodiments, if module 460 determines that a backup path is not congested at the future time, module 470 can continue to be executed to further determine the risk assessment status of the service level agreement indicator at the future time; if module 460 determines that a backup path is congested at the future time, there is no need to continue to execute module 470, and the candidacy of the backup path can be directly cancelled.

[0109] In some embodiments, by comparing the bandwidth utilization of each backup path at the future time with the preset service level agreement bandwidth utilization, the risk assessment of the service level agreement indicator of each backup path at the future time is determined. If the bandwidth utilization of a backup path at the future time is greater than the preset service level agreement bandwidth utilization, it is determined that the service level agreement indicator of the backup path at the future time has a risk; otherwise, it is determined that the service level agreement indicator of the backup path at the future time does not have a risk.

[0110] The backup path determination module 480 is configured to determine the target backup path according to the congestion of the third traffic of each backup path at the future time, or in combination with the risk assessment of the service level agreement indicators of each backup path at the future time.

[0111] In some embodiments, the target backup path is determined based on the congestion of the third traffic of each backup path at the future time and the risk assessment of the service level agreement indicator. The backup path with no congestion and no risk of the third traffic at the future time is determined as a candidate backup path, and the target backup path is determined based on the candidate backup path. Wherein, in the case of multiple candidate backup paths, the shortest candidate backup path is determined as the target backup path. In the case of one candidate backup path, the candidate backup path is determined as the target backup path.

[0112] Figure 5 A schematic diagram showing the structure of a path determination device according to some embodiments of the present disclosure.

[0113] like Figure 5 As shown, the path determination device 500 of this embodiment includes: a memory 510 and a processor 520 coupled to the memory 510 , and the processor 520 is configured to execute the path determination method in any of some embodiments based on the instructions stored in the memory 510 .

[0114] The path determination device 500 may further include an input / output interface 530 , a network interface 540 , a storage interface 550 , etc. These interfaces 530 , 540 , 550 , the memory 510 , and the processor 520 may be connected, for example, via a bus 560 .

[0115] The memory 510 may include, for example, a system memory, a fixed non-volatile storage medium, etc. The system memory may store, for example, an operating system, an application program, a boot loader, and other programs.

[0116] The processor 520 may be implemented by a general purpose processor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistors and other discrete hardware components.

[0117] Among them, the input and output interface 530 provides a connection interface for input and output devices such as a display, a mouse, a keyboard, and a touch screen. The network interface 540 provides a connection interface for various networked devices. The storage interface 550 provides a connection interface for external storage devices such as SD cards and USB flash drives. The bus 560 can use any bus structure among a variety of bus structures. For example, the bus structure includes but is not limited to the Industry Standard Architecture (ISA) bus, the Micro Channel Architecture (MCA) bus, and the Peripheral Component Interconnect (PCI) bus.

[0118] The embodiments of the present disclosure provide a non-transitory computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the steps of the path determination method in any of the embodiments are implemented.

[0119] (1) A path determination method, comprising:

[0120] Predicting the first flow of the main path at a future time;

[0121] Predicting the second flow of each backup path at the future time;

[0122] Superimposing the first flow of the primary path at the future time on the basis of the second flow of each backup path at the future time, to obtain a third flow of each backup path at the future time;

[0123] A target backup path is determined according to the congestion status of the third traffic on each backup path at the future time.

[0124] (2) According to (1), it also includes: determining the congestion status of the third traffic of each backup path at the future time by comparing the third traffic of each backup path at the future time with the dynamic traffic congestion threshold value, wherein the dynamic traffic congestion threshold value of each backup path at the future time is determined based on the historical data of each backup path.

[0125] (3) According to (2), further comprising: predicting the maximum number of data packets transmitted by each backup path at the future time based on the historical data of each backup path;

[0126] According to the maximum number and length of the data packets transmitted by each backup path at the future time, a dynamic traffic congestion threshold value of each backup path at the future time is determined.

[0127] (4) According to (3), the historical data of each backup path includes the maximum number of data packets transmitted by each backup path at a historical time; wherein, predicting the maximum number of data packets transmitted by each backup path at the future time includes: inputting the maximum number of data packets transmitted by each backup path at a historical time into a first prediction model, and obtaining the maximum number of data packets transmitted by each backup path at the future time predicted by the first prediction model, wherein the first prediction model is obtained based on an artificial intelligence model.

[0128] (5) According to (3), determining the dynamic traffic congestion threshold value of each backup path at the future time includes: determining the maximum number of bytes transmitted by each backup path at the future time based on the product of the maximum number of data packets transmitted by each backup path at the future time and the data packet length; and determining the dynamic traffic congestion threshold value of each backup path at the future time based on the maximum number of bytes transmitted by each backup path at the future time.

[0129] (6) According to (1-5), determining the target backup path includes: determining the target backup path according to the congestion status of the third traffic of each backup path at the future time and the risk assessment status of the service level agreement indicator.

[0130] (7) According to (6), determining the target backup path includes: determining a backup path that is free of congestion and risk for the third traffic at the future time as a candidate backup path, and determining the target backup path based on the candidate backup path.

[0131] (8) According to (7), determining the target backup path based on the candidate backup paths includes: when there are multiple candidate backup paths, determining the shortest candidate backup path as the target backup path.

[0132] (9) According to (6-8), it also includes: determining the service level agreement indicator risk assessment status of each backup path at the future time by comparing the bandwidth utilization of each backup path at the future time with the preset service level agreement bandwidth utilization.

[0133] (10) According to (1-9), predicting the first flow of the main path at a future time includes: inputting the flow data of the main path at a historical time into a second prediction model, and obtaining the first flow of the main path at a future time predicted by the second prediction model, wherein the second prediction model is obtained based on an artificial intelligence model.

[0134] (11) According to (1-10), predicting the second flow of each backup path at the future time includes: inputting the flow data of each backup path at the historical time into a second prediction model, and obtaining the second flow of each backup path at the future time predicted by the second prediction model, wherein the second prediction model is obtained based on an artificial intelligence model.

[0135] (12) According to (1-11), it also includes: if the primary path fails at the future time, switching the service of the primary path to the target backup path.

[0136] (13) According to (1-12), the primary path and the backup path are SRv6 paths.

[0137] Those skilled in the art will appreciate that the embodiments of the present disclosure may be provided as methods, systems, or computer program products. Therefore, the present disclosure may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present disclosure may take the form of a computer program product implemented on one or more non-transient computer-readable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer program code.

[0138] The present disclosure is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present disclosure. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0139] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0140] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0141] The above description is only a preferred embodiment of the present disclosure and is not intended to limit the present disclosure. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present disclosure should be included in the protection scope of the present disclosure.

Claims

1. A path determination method, characterized in that: include: Predicting the first flow of the main path at a future time; Predicting the second flow of each backup path at the future time; Superimposing the first flow of the primary path at the future time on the basis of the second flow of each backup path at the future time, to obtain a third flow of each backup path at the future time; A target backup path is determined according to the congestion status of the third traffic on each backup path at the future time.

2. The method according to claim 1, characterized in that Also includes: By comparing the third flow of each backup path at the future time with the dynamic flow congestion threshold, the congestion condition of the third flow of each backup path at the future time is determined, The dynamic traffic congestion threshold value of each backup path at the future time is determined according to the historical data of each backup path.

3. The method according to claim 2, characterized in that Also includes: predicting, based on the historical data of each backup path, the maximum number of data packets transmitted by each backup path at the future time; According to the maximum number and length of the data packets transmitted by each backup path at the future time, a dynamic traffic congestion threshold value of each backup path at the future time is determined.

4. The method according to claim 3, characterized in that The historical data of each backup path includes the maximum number of data packets transmitted by each backup path at a historical time; Among them, predicting the maximum number of data packets transmitted by each backup path at the future time includes: inputting the maximum number of data packets transmitted by each backup path at a historical time into a first prediction model, and obtaining the maximum number of data packets transmitted by each backup path at the future time predicted by the first prediction model, wherein the first prediction model is obtained based on an artificial intelligence model.

5. The method according to claim 3, characterized in that: Determining the dynamic traffic congestion threshold value of each backup path at the future time includes: Determine the maximum number of bytes transmitted by each backup path at the future time based on the product of the maximum number of data packets transmitted by each backup path at the future time and the length of the data packet; Based on the maximum number of bytes transmitted by each backup path at the future time, a dynamic traffic congestion threshold value of each backup path at the future time is determined.

6. The method according to any one of claims 1 to 5, characterized in that: Determining the target backup path includes: The target backup path is determined according to the congestion condition of the third traffic of each backup path at the future time and the risk assessment condition of the service level agreement indicator.

7. The method according to claim 6, characterized in that Determining the target backup path includes: A backup path without congestion and risk for the third traffic at the future time is determined as a candidate backup path, and a target backup path is determined based on the candidate backup path.

8. The method according to claim 7, characterized in that Determining the target backup path based on the candidate backup paths includes: When there are multiple candidate backup paths, the shortest candidate backup path is determined as the target backup path.

9. The method according to claim 6, characterized in that Also includes: By comparing the bandwidth utilization of each backup path at the future time with the preset service level agreement bandwidth utilization, the service level agreement indicator risk assessment status of each backup path at the future time is determined.

10. The method according to any one of claims 1 to 5, characterized in that: Predicting the first flow of the main path at a future time includes: The flow data of the main path at historical time is input into a second prediction model to obtain the first flow of the main path at a future time predicted and output by the second prediction model, and the second prediction model is obtained based on an artificial intelligence model.

11. The method according to any one of claims 1 to 5, characterized in that: Predicting the second traffic of each backup path at the future time includes: The flow data of each backup path at historical time is input into a second prediction model to obtain the second flow of each backup path at a future time predicted and output by the second prediction model, wherein the second prediction model is obtained based on an artificial intelligence model.

12. The method according to any one of claims 1 to 5, characterized in that: Also includes: If the primary path fails at the future time, the services of the primary path are switched to the target backup path.

13. The method according to any one of claims 1 to 5, characterized in that: The primary and backup paths are segment routing (SRv6) paths based on Internet Protocol version 6.

14. A path determination device, comprising: Memory; as well as A processor coupled to the memory, the processor being configured to execute the method of any one of claims 1-13 based on instructions stored in the memory.

15. A path determination device, comprising: A module for executing the method of any one of claims 1-13.

16. A non-transitory computer-readable storage medium having a computer program stored thereon, wherein when the program is executed by a processor, the steps of the method according to any one of claims 1 to 13 are implemented.

Images