Re-routing method and system, electronic equipment and readable storage medium

Through high-risk site prediction model and routing pooling technology, the optimal path is calculated in real time, which solves the problem of slow response of the existing re-routing mechanism under high traffic volume, and achieves rapid network recovery.

CN119094423AInactive Publication Date: 2024-12-06FIBERHOME TELECOMMUNICATION TECHNOLOGIES CO LTD
View PDF 8 Cites 0 Cited by

Patent Information

Application Number
CN202411128315.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-16
Publication Date
2024-12-06
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

The existing rerouting mechanism cannot respond to network interrupts in real time when the traffic volume is large, resulting in an extended network recovery time.

Method used

By building a high-risk site prediction model, a routing pool is created to record the business and available path mapping relationship of high-risk sites, monitor the link status in real time, and use the shortest path algorithm to calculate the real-time optimal path and update the routing information table to achieve fast routing path allocation.

Benefits of technology

It greatly shortens the pathfinding time when high-risk site business interruption, improves rerouting efficiency and network recovery speed, and can respond to massive link interrupt messages in a timely manner.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119094423A_ABST
    Figure CN119094423A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of communication transmission networks, and discloses a rerouting method and system, electronic equipment and a readable storage medium, and the method comprises the steps: obtaining current network alarm data, and predicting whether a network site is a high-risk site or not through employing a trained high-risk site prediction model; creating a routing pool, adding the predicted high-risk sites into the routing pool, and recording a mapping relationship between the service of each high-risk site and an available path; the link state of the high-risk site is monitored in real time, when the service of the high-risk site is interrupted, an available path set is searched in the routing pool according to the service ID, and real-time optimal path information is calculated; and updating a routing information table according to the real-time optimal path information, and realizing routing path distribution of the high-risk site by using the updated routing information table. Aiming at a large number of link interruption conditions, the rerouting method provided by the invention is utilized to realize rapid rerouting, so that the path finding time is shortened, and the network recovery speed is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of communication transmission network technology, and in particular to a rerouting method, system, electronic device and readable storage medium. Background Art

[0002] As more and more businesses and fields rely on communication networks, high availability and self-healing capabilities of networks are becoming key goals in building communication networks. Depending on the business configuration requirements, static tunnels and dynamic tunnels can be configured on the network management system. When network links and device nodes fail, dynamic tunnels can automatically detect the failure, recalculate routes, converge routes again, and restore network traffic. The routes and forwarding labels of static tunnels are specified by the network management system. If they cannot perceive network changes, they do not have self-healing capabilities.

[0003] Network management system rerouting is a method for static tunnel failure recovery. For non-returnable services, when the LSP path is interrupted, the first node calculates the best path for service recovery, and then establishes a new LSP through signaling. The new LSP transmits the service and deletes the original LSP. For returnable services, the original LSP will not be deleted after rerouting. If the original LSP link failure is restored, the service will be automatically migrated to the original path and the reroute will be deleted. Therefore, the recovery of static tunnels and services after network failure depends on the rerouting performance. The existing rerouting mechanism calculates a new path in real time after receiving the link interruption message. When the business volume is small, the path can be found quickly, but as the business volume increases dramatically, it may cause path finding lags and fail to respond to each interrupted service in real time, thereby increasing the network interruption time. Summary of the invention

[0004] The object of the present invention is to provide a rerouting method, system, electronic device and readable storage medium, which can quickly respond to a large number of interrupted services and shorten the network interruption time.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] A first aspect of the present invention provides a rerouting method, comprising:

[0007] Obtain current network alarm data and use the trained high-risk site prediction model to predict whether a network site is a high-risk site;

[0008] Create a routing pool, add the predicted high-risk sites to the routing pool, and record the mapping relationship between the services of each high-risk site and the available paths;

[0009] Monitor the link status of high-risk sites in real time. When the service of a high-risk site is interrupted, search the available path set in the routing pool according to the service ID and calculate the real-time optimal path information.

[0010] The routing information table is updated according to the real-time optimal path information, and the updated routing information table is used to implement routing path allocation for high-risk sites.

[0011] Furthermore, before obtaining the current network alarm data, it also includes: collecting historical alarm data in the network site database, the historical alarm data is the number of different types of alarms reported by each network site in the past at least three years; preprocessing the historical alarm data to construct a data set; establishing an initial prediction model, and using the data set to train the initial prediction model to obtain the optimal model parameters of the high-risk site prediction model.

[0012] Furthermore, the alarm types in the historical alarm data include but are not limited to link alarms, pcep alarms, bgp alarms and laser port alarms.

[0013] Furthermore, the link status of the high-risk site is monitored in real time, including: when an alarm of link signal loss is received, setting the corresponding link to an interrupted state; when the alarm of link signal loss disappears, setting the corresponding link to a connected state.

[0014] Furthermore, the available path set is searched in the routing pool according to the service ID, and the real-time optimal path information is calculated, including: traversing all available paths in the routing pool according to the service ID, first querying whether the current link status is connected, if so, calculating whether the current link is the real-time optimal path, otherwise querying the next path.

[0015] Furthermore, the shortest path algorithm is used to calculate the real-time optimal path.

[0016] Furthermore, it also includes: determining whether the source and sink network elements of the interrupted links are the same; if so, grouping the links with the same source and sink into one group, and synchronously searching for an available path set in the routing pool.

[0017] A second aspect of the present invention provides a rerouting system, comprising:

[0018] The prediction module is used to obtain the current network alarm data and use the trained high-risk site prediction model to predict whether the network site is a high-risk site;

[0019] A creation module is used to create a routing pool, add the predicted high-risk sites to the routing pool, and record the mapping relationship between the services of each high-risk site and the available paths;

[0020] The path-finding module is used to monitor the link status of high-risk sites in real time. When the service of a high-risk site is interrupted, it searches for a set of available paths in the routing pool according to the service ID and calculates the real-time optimal path information.

[0021] The updating module is used to update the routing information table according to the real-time optimal path information, and use the updated routing information table to implement routing path allocation for high-risk sites.

[0022] Based on the same inventive concept, an embodiment of the present invention further provides an electronic device, comprising: a memory and a processor; the processor is used to read and execute a computer program stored in the memory to implement the aforementioned rerouting method.

[0023] Based on the same inventive concept, an embodiment of the present invention further provides a computer storage medium, wherein the computer storage medium stores computer executable instructions, and the computer executable instructions implement the aforementioned rerouting method when executed.

[0024] The technical effects and advantages of the present invention are as follows: Since the services of high-risk sites are frequently interrupted, a high-risk site prediction model is constructed, and a routing pool is created for the predicted high-risk sites. The mapping relationship between the services of each high-risk site and the available paths is recorded in the routing pool. Whenever the services are interrupted, only the relevant available path set needs to be obtained in the routing pool according to the service ID, which greatly reduces the time spent on real-time path finding of high-risk sites, improves the efficiency of rerouting, and quickly restores communication. Even for massive link interruption messages, the rerouting method provided by the present invention can respond in time and improve the network recovery speed.

[0025] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures pointed out in the description, claims and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0027] Figure 1 is a schematic flow chart of a rerouting method in a first embodiment of the present invention;

[0028] Figure 2 is a flow chart of a rerouting method in a second embodiment of the present invention;

[0029] Figure 3 It is a schematic diagram of the structure of the high-risk site prediction model in the second embodiment of the present invention;

[0030] Figure 4 is a schematic diagram of the structure of a rerouting system in a third embodiment of the present invention;

[0031] Prediction module 100; creation module 101; path finding module 102; update module 103. DETAILED DESCRIPTION

[0032] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0033] To solve the problem of slow network recovery caused by large-scale business interruption in existing technologies, such as Figure 1 As shown, the first embodiment of the present invention discloses a rerouting method, comprising the following steps:

[0034] Step S1: obtaining current network alarm data, and using a trained high-risk site prediction model to predict whether a network site is a high-risk site;

[0035] Step S2: Create a routing pool, add the predicted high-risk sites to the routing pool, and record the mapping relationship between the services of each high-risk site and the available paths;

[0036] Step S3: monitor the link status of the high-risk site in real time. When the service of the high-risk site is interrupted, search the available path set in the routing pool according to the service ID and calculate the real-time optimal path information;

[0037] Step S4: update the routing information table according to the real-time optimal path information, and use the updated routing information table to implement routing path allocation for high-risk sites.

[0038] Since services at high-risk sites are frequently interrupted, the embodiment of the present invention creates a routing pool for predicted high-risk sites. Whenever services are interrupted, it is only necessary to obtain a set of related available paths in the routing pool according to the service ID. This greatly reduces the time spent on real-time path finding when services at high-risk sites are interrupted, improves the efficiency of rerouting, and quickly restores communications.

[0039] like Figure 2 As shown, according to the second embodiment of the present invention, before predicting high-risk sites according to current network alarm data, step S10 is required to construct a high-risk site prediction model.

[0040] The method of building a high-risk site prediction model is as follows:

[0041] 1. Collect historical alarm data in the network site database;

[0042] You can select the number of different types of alarms reported by each network site in the past three or five years. The alarm types reported by the network site include but are not limited to: link alarm (network port connection failure alarm), pcep alarm (equipment fiber connection status alarm), bgp alarm (equipment channel alarm), laser port alarm (laser failure alarm);

[0043] Table 1 shows the historical alarm data obtained from the network site database (1 indicates a high-risk site, 0 indicates a non-high-risk site)

[0044]

[0045] Table 1

[0046] 2. Preprocess historical alarm data and construct a data set;

[0047] First, the historical alarm data is cleaned, including removing outliers and filling missing data. Then, the cleaned data is standardized, for example, using the mean or standard deviation for standardization. The constructed data set can be a data set for a binary classification problem, including features (number of alarms of different types) and reliability labels (whether it is a high-risk site, 1 indicates a high-risk site, 0 indicates a non-high-risk site).

[0048] Table 2 shows the historical alarm data obtained after processing with the mean value (900)

[0049]

[0050] Table 2

[0051] 3. Establish an initial prediction model and use the data set to train the initial prediction model to obtain the optimal model parameters of the high-risk site prediction model;

[0052] The steps are as follows: select a suitable network model, such as a convolutional neural network model, first define the input and output of the initial model, the input is feature data, namely the number of link alarms, the number of pcep alarms, the number of bgp alarms, and the number of laser port alarms, and the output is the reliability label of the network site; then determine the structure of the initial model, such as Figure 3 As shown, the input layer is used to input feature data, the hidden layer is a fully connected layer of one or more layers, and the activation function is in the hidden layer to introduce nonlinear relationships. The activation function used in the embodiment of the present invention is the Sigmoid function. Map the output value of the output layer to [0,1], where 1 represents a high-risk site and 0 represents a non-high-risk site; initialize the weights and biases of the model; divide the data set into a training set and a test set, use the training set to train the initial prediction model, and obtain the prediction results of the model by inputting feature data and calculating according to the defined model structure; select an appropriate loss function, such as mean square error (MSE), to measure the difference between the predicted value and the true value; use the stochastic gradient descent method based on the loss function Update the weights and biases of the prediction model, i.e. Figure 3 W11, w21, w12, w22, w13, w23, w14, w24 (weights) and b1, b2, b3 (biases) are used to reduce the value of the loss function. The learning rate μ is a constant used to adjust the training speed. L is the loss of the entire network. Repeat the above steps until the maximum number of iterations is reached or the loss function converges. Use the test set to evaluate the trained model, and adjust the model parameters or network structure according to the evaluation results to obtain the optimal model parameters and further improve the performance of the prediction model.

[0053] According to the above steps, a high-risk site prediction model with good accuracy and generalization ability is finally constructed, which can predict whether the network site is a high-risk site based on the current alarm data of the network site. Through step S20, the current network alarm data is obtained to predict high-risk sites. The current network alarm data can be understood as the above four types of alarm frequency information collected by the network site database within this year or within a predetermined time period. These data are processed according to the above preprocessing method and then imported into the trained high-risk site prediction model. The output result can predict whether the network site is a high-risk site. In an embodiment of the present invention, due to the frequent service interruptions of high-risk sites, a routing pool is created for the high-risk sites, and the routing pool is used to achieve rapid rerouting of high-risk sites.

[0054] Step S30: add all predicted high-risk sites to the routing pool, and record the mapping relationship between the services of each high-risk site and the available paths; by pre-finding all available paths of the service tunnel and storing them in the routing pool, one service ID may correspond to multiple paths;

[0055] Step S40, real-time monitoring and maintenance of the network system status; when the system starts, the alarm of the signal loss of the current existing link is obtained and the corresponding link is set to an interrupted state. If it is an SR tunnel, it includes a FlexE virtual link, and the signal loss alarm reported by the device link is monitored at the same time.

[0056] In this embodiment, the link status of the high-risk site is monitored in real time. When an alarm of link signal loss is received, the corresponding link is set to an interrupted state; when the alarm of link signal loss disappears, the corresponding link is set to a connected state.

[0057] Step S41, determine whether the link is interrupted;

[0058] Specifically, when the fiber connection is judged to be in an interrupted state according to the signal loss alarm on the line receiving side, the attribute of the link object is set to interrupted, thereby triggering a rerouting operation. When the alarm signal disappears, it is judged that the fiber connection is restored, and the attribute of the link object is set to connected.

[0059] When the link interruption of the high-risk site causes service interruption, step S50, traverse all available paths in the routing pool according to the service ID; step S51, query whether the current path status is connected; if so, calculate whether the current path is the real-time optimal path according to step S52; otherwise, query the next path.

[0060] Traverse the path set in the routing pool to determine the status of the current escape path; if the current escape path is in the up state, determine whether the current escape path is the real-time optimal path; if the current escape path is in the down state, query the next path.

[0061] According to a preferred embodiment, the real-time optimal path is calculated using the shortest path algorithm. Taking into account various factors such as the link connectivity of the current network, the QoS value of the link (such as the network delay between service routers, etc.), the congestion state of the network element, the congestion state of the service router, the activation state of the service capability, the forwarding cost of the service router, and the SLA (service level), the real-time optimal path is calculated using the shortest path algorithm, such as the Dijkstra algorithm.

[0062] In a communication network, a source network element is a network node that sends data, and a sink network element is a network node that receives data. Preferably, before path finding, it is determined whether the source and sink network elements of the interrupted link are the same. If so, the same source and sink links are grouped together, and the available path set is searched synchronously in the routing pool. For example, if the source network element and sink network element of link A and link B are the same, link A and link B are considered as a group, and the same source and sink links only need to search for an available path once in the routing pool, saving time.

[0063] In addition, the routes can be segmented to find the source and destination of fiber interruption on a link, and only perform route search for the services with fiber interruption, so as to reuse existing link resources to the greatest extent and reduce unnecessary losses caused by repeated creation.

[0064] Step S60: updating the routing information table according to the real-time optimal path information;

[0065] Step S61: Send the updated routing information table to the device to implement routing path allocation for high-risk sites.

[0066] In an embodiment of the present invention, the real-time optimal path information may include a preset number of routing information with the highest priority. The locally stored routing information table is updated according to the real-time optimal path information, and the updated routing information table is then sent to the device, so that the service router of the high-risk site selects the most suitable routing path to forward the service message according to the updated routing information table, thereby realizing dynamic routing decision-making.

[0067] According to the embodiment of the present invention, the high-risk site prediction model is trained using the historical alarm data in the network site database, and a routing pool is created for the predicted high-risk sites. Whenever the high-risk site service is interrupted, only the relevant available path set needs to be obtained in the routing pool according to the service ID, which greatly reduces the time spent on real-time path finding for the interrupted service, improves the efficiency of rerouting of the high-risk site, and thus quickly restores communication. Even for a large number of link interruption messages, the rerouting method provided by the present invention can respond in a timely manner, shorten the path finding time, and improve the network recovery speed.

[0068] The third embodiment of the present invention also provides a rerouting system, such as Figure 4 As shown, the system includes:

[0069] The prediction module 100 is used to obtain the current network alarm data and use the trained high-risk site prediction model to predict whether the network site is a high-risk site;

[0070] A creation module 101 is used to create a routing pool, add the predicted high-risk sites to the routing pool, and record the mapping relationship between the services of each high-risk site and the available paths;

[0071] The path finding module 102 is used to monitor the link status of the high-risk site in real time. When the service of the high-risk site is interrupted, the available path set is searched in the routing pool according to the service ID, and the real-time optimal path information is calculated;

[0072] The updating module 103 is used to update the routing information table according to the real-time optimal path information, and use the updated routing information table to implement routing path allocation for high-risk sites.

[0073] Regarding the system in the above embodiment, the specific manner in which each unit module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0074] Based on the same inventive concept, an embodiment of the present invention further provides an electronic device, comprising: a memory and a processor, wherein the processor is used to read and execute a computer program stored in the memory to implement the aforementioned rerouting method.

[0075] Based on the same inventive concept, an embodiment of the present invention further provides a computer storage medium, wherein the computer storage medium stores computer executable instructions, and the computer executable instructions implement the aforementioned rerouting method when executed.

[0076] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or modules, which can be electrical, mechanical or other forms.

[0077] The modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical modules, that is, they may be located in one place, or they may be distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, the functional modules in the various embodiments of the present invention may be integrated into a processing module, or each module may exist physically separately, or two or more modules may be integrated into one module. The above-mentioned integrated modules may be implemented in the form of hardware or in the form of software functional modules.

[0078] If the integrated module is implemented in the form of a software function module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0079] It should be noted that, for the convenience of description, the aforementioned method embodiments are all described as a series of action combinations, but those skilled in the art should be aware that the present invention is not limited by the described action sequence, because according to the present invention, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present invention.

[0080] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0081] Finally, it should be noted that the above is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, it is still possible for those skilled in the art to modify the technical solutions described in the aforementioned embodiments or to make equivalent substitutions for some of the technical features therein. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A rerouting method, It is characterized in that The method comprises: Obtain current network alarm data and use the trained high-risk site prediction model to predict whether a network site is a high-risk site; Create a routing pool, add the predicted high-risk sites to the routing pool, and record the mapping relationship between the services of each high-risk site and the available paths; Monitor the link status of high-risk sites in real time. When the service of the high-risk site is interrupted, search for an available path set in the routing pool according to the service ID and calculate the real-time optimal path information; The routing information table is updated according to the real-time optimal path information, and the updated routing information table is used to implement routing path allocation for high-risk sites.

2. The method according to claim 1, It is characterized in that Before obtaining the current network alarm data, it also includes: Collecting historical alarm data in a network site database, the historical alarm data being the number of different types of alarms reported by each network site in the past at least three years; Preprocessing the historical alarm data to construct a data set; An initial prediction model is established, and the initial prediction model is trained using the data set to obtain optimal model parameters of the high-risk site prediction model.

3. The method according to claim 2, It is characterized in that The alarm types in the historical alarm data include but are not limited to link alarms, pcep alarms, bgp alarms and laser port alarms.

4. The method according to claim 1, It is characterized in that The real-time monitoring of the link status of the high-risk site includes: When receiving an alarm of link signal loss, set the corresponding link to an interrupted state; When the link signal loss alarm disappears, the corresponding link is set to a connected state.

5. The method according to claim 4, It is characterized in that The searching for an available path set in the routing pool according to the service ID and calculating real-time optimal path information includes: All available paths in the routing pool are traversed according to the service ID, and first the current link status is queried whether it is connected. If so, whether the current link is a real-time optimal path is calculated, otherwise the next path is queried.

6. The method according to claim 5, It is characterized in that The real-time optimal path is calculated using a shortest path algorithm.

7. The method according to claim 5, It is characterized in that The method further comprises: Before path finding, determine whether the source and sink network elements of the interrupted link are the same; If so, the links with the same source and sink are grouped together and a set of available paths is searched synchronously in the routing pool.

8. A rerouting system, It is characterized in that The system comprises: The prediction module is used to obtain the current network alarm data and use the trained high-risk site prediction model to predict whether the network site is a high-risk site; A creation module is used to create a routing pool, add the predicted high-risk sites to the routing pool, and record the mapping relationship between the services of each high-risk site and the available paths; A path finding module is used to monitor the link status of high-risk sites in real time. When the service of a high-risk site is interrupted, the module searches for a set of available paths in the routing pool according to the service ID and calculates the real-time optimal path information. The updating module is used to update the routing information table according to the real-time optimal path information, and use the updated routing information table to implement routing path allocation for high-risk sites.

9. An electronic device, It is characterized in that include: Memory, processor; The processor is used to read and execute the computer program stored in the memory to implement the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, It is characterized in that The computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions, when executed, implement the method according to any one of claims 1 to 7.

Citation Information

Patent Citations

  • Re-routing method, system and network deivce

    CN103959723A

  • Construction method of deep neural network model and fault diagnosis method and system

    CN111342997A

  • Alarm prediction method and system

    CN111475804A

  • End-to-end service alarm state monitoring method and system

    CN112003715A

  • Service recovery method and device, electronic equipment and storage medium

    CN112866833A