A 5G communication network router fault detection method, system and electronic device

Abstract

The present invention discloses a 5G communication network router fault detection method, system and electronic device, and relates to the field of data processing technology. The method includes: obtaining a first temperature change curve of a target router, the first temperature change curve is used to characterize the temperature change of the target router during the process of increasing the network load from zero to the target network load and maintaining the target duration; according to the first temperature change curve, determining the temperature variability of the target router, the temperature variability is used to characterize the degree of temperature change of the target router when the network load is stable; increasing the network load of the target router, and obtaining the second temperature change curve of the target router; according to the temperature variability and the second temperature change curve, determining the first failure probability of the target router; when the first failure probability is greater than the preset probability threshold, determining that the target router has failed. The present invention can accurately determine the failure probability of the router and improve the accuracy of fault detection.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a 5G communication network router fault detection method, system and electronic equipment. Background Art

[0002] Routers are widely used in 5G communication networks and serve as a bridge between 5G networks and terminal devices. Routers extend the advantages of 5G networks such as high speed and large capacity to various terminals, enabling terminal devices to smoothly access the network to obtain services, and play a key role in connecting the entire communication link. If a router fails, serious packet loss and network delays may occur, which greatly affects the user experience. Therefore, it is very important to perform fault detection on the router.

[0003] In existing methods, the temperature of the router is usually directly compared with a preset threshold to determine whether the router is faulty.

[0004] However, this method only focuses on whether the temperature of the router exceeds a preset threshold, and ignores the temperature change trend and fluctuation of the router, resulting in low accuracy of router fault detection. Summary of the invention

[0005] The embodiments of the present invention provide a 5G communication network router fault detection method, system and electronic device, which can improve the accuracy of router fault detection.

[0006] A first aspect of an embodiment of the present invention provides a 5G communication network router fault detection method, comprising:

[0007] Obtaining a first temperature change curve of the target router, where the first temperature change curve is used to characterize the temperature change of the target router during a process in which the network load increases from zero to a target network load and is maintained for a target duration;

[0008] Determining the temperature variability of the target router according to the first temperature variation curve, where the temperature variability is used to characterize the degree of temperature variation of the target router when the network load is stable;

[0009] Increasing the network load of the target router to obtain a second temperature change curve of the target router, where the second temperature change curve is used to characterize the temperature change of the target router during the process of increasing the target network load;

[0010] Determining a first failure probability of the target router according to the temperature variability and the second temperature variation curve;

[0011] When the first failure probability is greater than a preset probability threshold, it is determined that a failure occurs on the target router.

[0012] A second aspect of an embodiment of the present invention provides a 5G communication network router fault detection system, including:

[0013] A curve acquisition module, used to acquire a first temperature change curve of a target router, the first temperature change curve being used to characterize the temperature change of the target router during a process in which the network load increases from zero to a target network load and is maintained for a target duration;

[0014] A curve analysis module, used to determine the temperature variability of the target router according to the first temperature change curve, where the temperature variability is used to characterize the degree of temperature change of the target router when the network load is stable;

[0015] The curve acquisition module is further used to increase the network load of the target router to obtain a second temperature change curve of the target router, where the second temperature change curve is used to characterize the temperature change of the target router during the process of increasing the target network load;

[0016] A probability determination module, used to determine a first failure probability of a target router according to the temperature variability and the second temperature variation curve;

[0017] The fault judgment module is used to determine that a target router has a fault when the first fault probability is greater than a preset probability threshold.

[0018] According to a third aspect of an embodiment of the present invention, a 5G communication network router fault detection electronic device is provided, the device comprising: a memory and a program or instruction stored in the memory and executable on a processor, wherein when the program or instruction is executed by the processor, a 5G communication network router fault detection method as provided in any one of the above-mentioned embodiments of the present application is implemented.

[0019] In the 5G communication network router fault detection method provided by an embodiment of the present invention, a first temperature change curve is obtained that characterizes the temperature change of the target router during the process of increasing the network load from zero to the target network load and maintaining the target duration. Then, based on the first temperature change curve, the temperature variability that characterizes the degree of temperature change of the target router when the network load is stable is determined. Then, the network load of the target router is increased to obtain the second temperature change curve of the target router. Thus, based on the temperature variability and the second temperature change curve, the first failure probability of the target router is determined. When the first failure probability is greater than the preset probability threshold, it is determined that the target router has failed. In this way, the present invention analyzes the temperature change trend and fluctuation of the router during the network load change process based on the first temperature change curve and the second temperature change curve, so that the failure probability of the router can be accurately determined, and the accuracy of router fault detection can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. 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 paying creative work.

[0021] Figure 1 A schematic flow chart of a first 5G communication network router fault detection method provided by an embodiment of the present invention;

[0022] Figure 2 A schematic flow chart of a second 5G communication network router fault detection method provided by an embodiment of the present invention;

[0023] Figure 3 A schematic flow chart of a third 5G communication network router fault detection method provided by an embodiment of the present invention;

[0024] Figure 4 A schematic diagram of the structure of a 5G communication network router fault detection system provided by an embodiment of the present invention;

[0025] Figure 5 A schematic structural diagram of a 5G communication network router fault detection electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0026] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of the specific implementation, structure, features and effects of a 5G communication network router fault detection method, system and electronic device proposed by the present invention in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0027] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0028] It should be noted that the acquisition, storage, use, and processing of data in the technical solution of the present invention are in compliance with the relevant provisions of laws and regulations.

[0029] It should be noted that in the embodiments of the present invention, certain software, components, models and other existing solutions in the industry may be mentioned, which should be regarded as exemplary. Their purpose is only to illustrate the feasibility of implementing the technical solution of the present invention, but it does not mean that the applicant has or will necessarily use the solution.

[0030] Routers are widely used in 5G communication networks and serve as a bridge between 5G networks and terminal devices. Routers extend the advantages of 5G networks such as high speed and large capacity to various terminals, enabling terminal devices to smoothly access the network to obtain services, and play a key role in connecting the entire communication link. If a router fails, serious packet loss and network delays may occur, which greatly affects the user experience. Therefore, it is very important to perform fault detection on the router.

[0031] In existing methods, the temperature of the router is usually directly compared with a preset threshold to determine whether the router is faulty. However, this method only focuses on whether the temperature of the router exceeds the preset threshold, ignoring the temperature change trend and fluctuation of the router, resulting in low accuracy of router fault detection.

[0032] The object of the present invention is to provide a 5G communication network router fault detection method, system and electronic device. In the 5G communication network router fault detection method provided by the embodiment of the present invention, a first temperature change curve is obtained to characterize the temperature change of the target router during the process of increasing the network load from zero to the target network load and maintaining the target duration. Then, according to the first temperature change curve, the temperature variability characterizing the degree of temperature change of the target router when the network load is stable is determined. Then, the network load of the target router is increased to obtain the second temperature change curve of the target router. Thus, according to the temperature variability and the second temperature change curve, the first failure probability of the target router is determined. When the first failure probability is greater than the preset probability threshold, it is determined that the target router fails. In this way, the present invention analyzes the temperature change trend and fluctuation of the router during the network load change process according to the first temperature change curve and the second temperature change curve, so that the failure probability of the router can be accurately determined and the accuracy of router fault detection can be improved.

[0033] The following describes a specific embodiment of a 5G communication network router fault detection method, system and electronic device provided by an embodiment of the present invention.

[0034] The following first introduces a 5G communication network router fault detection method provided by an embodiment of the present invention.

[0035] Figure 1A flow chart of a 5G communication network router fault detection method is provided. The 5G communication network router fault detection method can be applied to a server. The 5G communication network router fault detection method can include the following S101 to S105.

[0036] S101, obtaining a first temperature change curve of a target router, where the first temperature change curve is used to characterize a temperature change of the target router during a process in which a network load of the target router increases from zero to a target network load and is maintained for a target duration.

[0037] In this embodiment, the target router includes multiple areas. For example, the target router may include a computing core, a cache area, and the like.

[0038] The target network load is a preset network load threshold. For example, the target network load may be 50% of the rated network load.

[0039] As an example, the server increases the network load of the target router from zero to 50% of the rated network load, and maintains the target duration at 50% of the rated network load.

[0040] During the period when the target router's network load increases from zero to 50% of the rated network load and maintains the target duration, the server uses a high-precision temperature sensor to collect temperature values ​​of each area in the target router at a preset collection frequency. The server calculates the average temperature value of each area at each moment as the temperature value of the target router at the corresponding moment.

[0041] Finally, the temperature values ​​of the target router at each moment are used to generate a first temperature change curve of the target router in chronological order, wherein the horizontal axis of the first temperature change curve is the network load size at the corresponding moment, and the vertical axis of the first temperature change curve is the temperature value of the target router at the corresponding moment.

[0042] S102: Determine the temperature variability of the target router according to the first temperature variation curve, where the temperature variability is used to characterize the degree of temperature variation of the target router when the network load is stable.

[0043] In this embodiment, the temperature variability is used to reflect the temperature fluctuation degree of the target router in the first temperature variation curve when the network load is stable.

[0044] As an example, the server obtains the temperature value of the target router at each time during the network load stability period from the first temperature change curve.

[0045] Then, by calculating the temperature standard deviation or coefficient of variation of the temperature values ​​of the target router at each moment during the network load stability period, the temperature variability of the target router is quantified.

[0046] S103, increasing the network load of the target router, and obtaining a second temperature change curve of the target router, where the second temperature change curve is used to characterize the temperature change of the target router during the process of increasing the target network load.

[0047] In this embodiment, the server continues to increase the network load of the target router from 50% of the rated network load, increasing the rated network load by 2% each time until it increases to 70% of the rated network load.

[0048] During the period when the target router's rated network load increases from 50% to 70%, the server collects the temperature values ​​of each area in the target router through a high-precision temperature sensor at a preset collection frequency. The server calculates the average value of the temperature values ​​of each area at each moment as the temperature value of the target router at the corresponding moment.

[0049] Finally, the temperature values ​​of the target router at each moment are used to generate a second temperature change curve of the target router in chronological order, wherein the horizontal axis of the second temperature change curve is the network load size at the corresponding moment, and the vertical axis of the second temperature change curve is the temperature value of the target router at the corresponding moment.

[0050] S104: Determine a first failure probability of the target router according to the temperature variability and the second temperature variation curve.

[0051] In this embodiment, the first failure probability is used to characterize the probability of a failure of the target router.

[0052] As an example, the server trains the preset model through the historical temperature variability and the historical second temperature change curve corresponding to the routers that have failed in the past to obtain a fault prediction model. The fault prediction model can predict the failure probability of the router according to the temperature variability and the second temperature change curve of the router.

[0053] Then, the temperature variability of the target router and the second temperature variation curve are input into the fault prediction model, and the fault prediction model outputs a first failure probability of the target router.

[0054] S105: When the first failure probability is greater than a preset probability threshold, determine that a failure occurs in the target router.

[0055] In this embodiment, the preset probability threshold is used to represent a preset acceptable failure risk level.

[0056] As an example, the server compares the calculated first failure probability with a preset probability threshold. If the first failure probability is greater than the preset probability threshold, it is considered that the target router has failed and corresponding maintenance or replacement measures need to be taken; if the first failure probability is less than or equal to the preset probability threshold, it is considered that the target router has not failed.

[0057] Through this embodiment, a first temperature change curve is obtained that characterizes the temperature change of the target router during the process of increasing the network load from zero to the target network load and maintaining the target duration. Then, based on the first temperature change curve, the temperature variability that characterizes the degree of temperature change of the target router when the network load is stable is determined. Then, the network load of the target router is increased to obtain the second temperature change curve of the target router. Thus, based on the temperature variability and the second temperature change curve, the first failure probability of the target router is determined. When the first failure probability is greater than the preset probability threshold, it is determined that the target router has failed. In this way, the present invention analyzes the temperature change trend and fluctuation of the router during the network load change process based on the first temperature change curve and the second temperature change curve, so that the failure probability of the router can be accurately determined, and the accuracy of router fault detection can be improved.

[0058] As an optional embodiment, Figure 2 As shown, S102 may specifically include the following S201 to S205.

[0059] S201, performing first-order difference on each temperature value in the first temperature change curve to obtain a difference sequence corresponding to the first temperature change curve;

[0060] S202, clustering the difference data in the difference sequence to obtain a clustering result;

[0061] S203, dividing the first temperature change curve into a first sub-curve and a second sub-curve according to the clustering result, the first sub-curve is used to characterize the temperature change during the temperature rising period, and the second sub-curve is used to characterize the temperature change during the temperature stable period;

[0062] S204, determining the temperature stability of the target router according to the second sub-curve, where the temperature stability is used to characterize the temperature stability of the target router when the network load is stable;

[0063] S205 , determining the temperature variability of the target router according to the first sub-curve, the second sub-curve, and the temperature stability.

[0064] In this embodiment, the first sub-curve is used to characterize the temperature change of the target router during a period of rapid temperature growth, and the second sub-curve is used to characterize the temperature change of the target router during a period of relatively stable temperature.

[0065] The temperature stability is used to reflect the degree to which the temperature of the target router in the second sub-curve is maintained stable.

[0066] As an example, the server first obtains the temperature values ​​of the target router at each time from the first temperature change curve to form a temperature value sequence. Then, the temperature value sequence is subjected to first-order difference processing, that is, the difference between two adjacent temperature values ​​is calculated. For example, if the temperature value sequence is T={T1, T2, …, Tn}, the difference sequence is D={T2−T1, T3−T2, …, Tn−Tn−1}.

[0067] Then, according to the characteristics and requirements of the differential data in the differential sequence, a suitable clustering algorithm is selected, such as K-means, DBSCAN, etc. The selected clustering algorithm is applied to cluster the differential data in the differential sequence to obtain the clustering result.

[0068] Then, according to the clustering result, the differential data is mapped back to the original temperature change curve to determine the cluster to which each temperature value belongs. According to the cluster to which the temperature value belongs, the temperature change curve is divided into two sub-curves: a first sub-curve in the temperature rising period and a second sub-curve in the temperature stable period.

[0069] Then, the second sub-curve is analyzed to calculate the temperature stability index, such as the standard deviation and variance of the temperature fluctuation. These temperature stability indexes reflect the degree of temperature fluctuation during the temperature stability period. According to the temperature stability index, the temperature stability of the target router is comprehensively evaluated. The smaller the temperature stability index, the more stable the temperature, and the greater the temperature stability.

[0070] Finally, the temperature variability of the target router is comprehensively evaluated by combining the first sub-curve, the second sub-curve, and the temperature stability. Specifically, the server calculates the temperature variability index, such as the amplitude of the overall temperature change, the temperature change rate, etc., based on the first sub-curve and the second sub-curve. The temperature variability of the target router is evaluated based on the temperature variability index and the temperature stability. The larger the temperature variability index, the greater the temperature variability; the smaller the temperature stability, the greater the temperature variability.

[0071] Through this embodiment, each temperature value in the first temperature change curve is clustered, so that the first temperature change curve is divided into a first sub-curve and a second sub-curve. Then, the temperature variability of the target router is evaluated according to the first sub-curve and the second sub-curve. In this way, the temperature variability of the target router can be accurately determined, thereby improving the accuracy of router fault detection.

[0072] As an optional embodiment, S204 may specifically include:

[0073] According to the second sub-curve, determining a segmentation time at which the first sub-curve changes into the second sub-curve and a curve slope of the second sub-curve;

[0074] Multiply the segmented time by the curve slope of the second sub-curve and take the inverse of the inverse to obtain a first calculation result;

[0075] An exponential function operation is performed on the first calculation result to obtain the temperature stability of the target router.

[0076] In this embodiment, the temperature stability of the target router can be specifically determined by the following formula 1:

[0077] Formula 1;

[0078] In formula 1, It is used to characterize the temperature stability of the target router, and s is used to characterize the segmentation time from the first sub-curve to the second sub-curve, that is, the starting time of the second sub-curve. The slope of the second sub-curve, Used to characterize exponential function operations.

[0079] Among them, the smaller the value of the segmented time is, the earlier the first sub-curve changes to the second sub-curve, that is, the earlier the temperature stabilizes, so the temperature stability is greater; the smaller the slope of the second sub-curve is, the smaller the temperature change in the second sub-curve is, so the temperature stability is greater.

[0080] The greater the temperature stability of the target router, the smaller the temperature change of the target router, and the smaller the temperature variability of the target router.

[0081] Through this embodiment, the temperature stability of the target router is accurately evaluated according to the segmented time when the first sub-curve changes to the second sub-curve and the curve slope of the second sub-curve. This helps to accurately evaluate the temperature variability of the target router according to the temperature stability of the target router, thereby improving the accuracy of router fault detection.

[0082] As an optional embodiment, S205 may specifically include:

[0083] Obtaining a first temperature change value of the target router according to the temperature value at the start time of the first sub-curve and the temperature value at the end time of the second sub-curve;

[0084] Performing an exponential function operation on the inverse number of the temperature stability to obtain a second calculation result;

[0085] The second calculation result, the first temperature change value, and the curve slope of the first sub-curve are multiplied to obtain the temperature variability of the target router.

[0086] In this embodiment, the first temperature change value is used to characterize the absolute value of the difference between the temperature value at the start time of the first sub-curve and the temperature value at the end time of the second sub-curve in the target router, that is, how much the temperature of the target router increases from zero network load to target network load and maintains the target duration.

[0087] As an example, the temperature variability of the target router may be specifically determined by the following formula 2:

[0088] Formula 2;

[0089] In formula 2, A is used to characterize the temperature variability of the target router. Used to characterize the slope of the first sub-curve. It is used to represent the temperature value at the end of the second sub-curve. Used to characterize the temperature value at the beginning of the first sub-curve. Used to characterize the temperature stability of the target router, Used to characterize exponential function operations.

[0090] The smaller the slope of the first sub-curve is, the smaller the temperature change in the first sub-curve is, and thus the smaller the temperature variability is; It is used to characterize how much the temperature of the target router increases after the network load increases from zero to the target network load and maintains the target time. The smaller it is, the less the temperature rises, and therefore the smaller the temperature variability is; the greater the temperature stability of the target router, the smaller the temperature change of the target router, and therefore the smaller the temperature variability of the target router is.

[0091] During the normal operation of the target router, as the power is turned on and the network load is connected, various components inside the target router start to work, and the current passing through various components will generate heat. The temperature of the target router will quickly rise from room temperature to a relatively stable low temperature state within a few minutes after startup. After that, during the stable operation period of the target router, when the network load and ambient temperature remain unchanged, the temperature of the target router will usually remain in a relatively stable range.

[0092] Therefore, the greater the temperature variability of the target router, the greater the temperature of the target router is usually not maintained in a relatively stable range, that is, the greater the possibility of abnormal temperature rise of the target router, the greater the possibility of failure of the target router.

[0093] Through this embodiment, the temperature variability of the target router is determined by comprehensive evaluation based on the first sub-curve, the second sub-curve and the temperature stability. This helps to accurately evaluate the first fault probability of the target router according to the temperature variability of the target router, thereby improving the accuracy of router fault detection.

[0094] As an optional embodiment, S104 may specifically include:

[0095] Determine, according to the second temperature change curve, a second temperature change value of the target router, the number of first temperature extreme value points, and a network load change value;

[0096] The product of the second temperature change value and the number of the first temperature extreme value points is divided by the network load change value to obtain a third calculation result;

[0097] The temperature variability, the third calculation result, and the slope of the second temperature variation curve are multiplied to obtain a first failure probability of the target router.

[0098] In this embodiment, the second temperature change value is used to characterize the difference between the maximum temperature and the minimum temperature in the second temperature change curve, that is, the temperature change amplitude in the second temperature change curve.

[0099] The number of first temperature extreme value points is used to characterize the number of extreme value points in the second temperature change curve, that is, the number of temperature changes in the second temperature change curve.

[0100] The network load change value is used to characterize the difference between the maximum value and the minimum value of the network load in the second temperature change curve, that is, the change amplitude of the network load in the second temperature change curve.

[0101] As an example, the first failure probability of the target router may be determined by the following formula 3:

[0102] Formula 3;

[0103] In Formula 3, B is used to characterize the first failure probability of the target router, A is used to characterize the temperature variability of the target router. k3 is used to characterize the slope of the second temperature change curve, j is used to characterize the second temperature change value of the target router, and m is used to characterize the number of first temperature extreme points of the target router. f1 is used to characterize the maximum value of the network load in the second temperature change curve. Used to characterize the minimum value of the network load in the second temperature variation curve.

[0104] Among them, the greater the temperature variability of the target router, the greater the possibility that the temperature of the target router increases abnormally, and the greater the possibility that the target router fails; the greater the slope of the second temperature change curve, the faster the temperature increases, that is, the greater the possibility that the temperature of the target router increases abnormally, and the greater the possibility that the target router fails; It is used to characterize the temperature stability of the target router during the increase of network load. The network load has a certain range of variation. The smaller the range, the greater the temperature variation. The more times the temperature changes, the lower the temperature stability and the more likely the target router is to fail.

[0105] Through this embodiment, the first failure probability of the target router is accurately evaluated according to the second temperature change value of the target router, the number of first temperature extreme value points, the network load change value and the temperature variability. In this way, by accurately evaluating the first failure probability of the target router failing, the accuracy of router fault detection can be improved.

[0106] As an optional embodiment, Figure 3 As shown, after S104, the 5G communication network router fault detection method may also include the following S301 to S303.

[0107] S301, according to the temperature difference of each area in the target router under the same network load, correct the first failure probability to obtain a second failure probability of the target router;

[0108] S302, reducing the network load of the target router, and obtaining a third temperature change value and the number of second temperature extreme value points during the process of reducing the network load of the target router;

[0109] S303, correcting the second failure probability according to the third temperature change value and the number of second temperature extreme value points to obtain a target failure probability of the target router;

[0110] S105 may specifically include:

[0111] When the target failure probability is greater than a preset probability threshold, it is determined that the target router fails.

[0112] In this embodiment, the target router is a complex integrated circuit composed of multiple functional units. If a fault occurs in a local area, such as a core computing unit is damaged, then when the network load increases, the current and power consumption changes in this area will be different from normal, causing a large amount of heat to accumulate in this local area, resulting in obvious temperature differences in different parts of the target router. The temperature of the local overheating area is extremely high, and the local overheating phenomenon will be more obvious, while the temperature of other relatively normal areas will also increase due to the overall heat conduction, but it is far less obvious than the temperature change of the local overheating area. Therefore, the fault probability can be corrected according to the temperature difference between different areas in the target router.

[0113] At the same time, if the target router fails, then when its network load decreases, the temperature will not decrease synchronously with the decrease of the network load, but will maintain the original high temperature or continue to increase. Therefore, the failure probability can also be corrected according to the third temperature change value and the number of second temperature extreme points during the process of reducing the network load of the target router.

[0114] The third temperature change value is used to characterize the difference between the maximum temperature and the minimum temperature during the process of reducing the network load of the target router, that is, the temperature change amplitude during the process of reducing the network load of the target router.

[0115] The second temperature extreme value point quantity is used to characterize the extreme value point quantity during the process of reducing the network load of the target router, that is, the number of temperature changes during the process of reducing the network load of the target router.

[0116] As an example, the server adjusts the first failure probability through a preset probability correction model according to the temperature difference of each area in the target router under the same network load to obtain the second failure probability.

[0117] Then, the network load of the target router is reduced. During the process of reducing the network load, the temperature of the target router is continuously monitored to obtain the third temperature change value and the number of second temperature extreme points during the process of reducing the network load of the target router. A correction factor is set according to the relationship between the third temperature change value and the number of second temperature extreme points and the failure probability. The second failure probability is adjusted using the correction factor to obtain the target failure probability of the target router.

[0118] Finally, the calculated target failure probability is compared with the preset probability threshold. If the target failure probability is greater than the preset probability threshold, the target router is considered to have failed and corresponding maintenance or replacement measures need to be taken; if the target failure probability is less than or equal to the preset probability threshold, the target router is considered to have not failed.

[0119] Through this embodiment, according to the temperature difference of each area in the target router under the same network load, and the third temperature change value and the number of second temperature extreme points in the process of reducing the network load of the target router, the first failure probability of the target router is corrected to obtain the target failure probability. Therefore, according to the target failure probability, it is possible to accurately evaluate whether the target router has a failure, which can improve the accuracy of router fault detection.

[0120] As an optional embodiment, S301 may specifically include:

[0121] For each area of ​​the target router in the second temperature change curve under each network load, respectively perform: accumulating the temperature difference value between the target area and each area other than the target area to obtain the temperature difference accumulation value, the target area is any area in the target router;

[0122] The accumulated values ​​of temperature differences of each area under each network load are added up and divided by the number of network loads to obtain the average temperature difference;

[0123] For each area in the target router, respectively perform: accumulating the difference values ​​of the temperature change amplitudes of the target area and other areas except the target area to obtain an amplitude difference accumulation value;

[0124] The amplitude difference accumulation values ​​of each region are accumulated to obtain the total amplitude difference;

[0125] The first failure probability, the temperature difference mean, and the total amplitude difference are multiplied to obtain a second failure probability of the target router.

[0126] In this embodiment, the second failure probability of the target router can be specifically determined by the following formula 4:

[0127] Formula 4;

[0128] In Formula 4, C is used to characterize the second failure probability of the target router, and B is used to characterize the first failure probability of the target router. w is used to characterize the number of network loads in the second temperature variation curve, and q is used to characterize the number of regions in the target router. It is used to represent the accumulated temperature difference between the lth area and other areas under the i-th network load. It is used to characterize the accumulated value of the amplitude difference of the lth region, that is, the accumulated value of the difference between the temperature change amplitudes of the lth region and other regions.

[0129] in, It is used to represent the average value of the accumulated temperature difference between each area and other areas under all network loads. The larger the value of is, the more obvious the local overheating feature of the target router is, and the greater the second failure probability of the target router is; It represents the cumulative value of the difference in temperature variation between the lth area and other areas during the entire load change process. The larger the value of , the greater the difference in temperature variation between each area and other areas, that is, the more obvious the local overheating feature of the target router is, and the greater the second failure probability of the target router is.

[0130] Through this embodiment, the first fault probability is corrected according to the temperature difference of each area in the target router under the same network load, thereby obtaining the second fault probability. In this way, it is possible to more accurately evaluate whether the target router has a fault according to the second fault probability, thereby improving the accuracy of router fault detection.

[0131] As an optional embodiment, S303 may specifically include:

[0132] Perform an exponential function operation on the third temperature change value and the inverse of the accumulated value of the preset coefficient to obtain a fourth calculation result;

[0133] The second failure probability, the fourth calculation result, and the number of second temperature extreme value points are multiplied to obtain a target failure probability of the target router.

[0134] In this embodiment, the target failure probability of the target router can be specifically determined by the following formula 5:

[0135] Formula 5;

[0136] In formula 5, Used to characterize the target failure probability of the target router, Used to characterize the second failure probability of the target router. It is used to characterize the maximum temperature of the target router during the process of network load reduction. This is used to indicate the minimum temperature during the process of reducing the network load of the target router. It is used to characterize the number of the second temperature extreme points, that is, the number of extreme points in the process of reducing the network load of the target router. Used to characterize exponential function operations.

[0137] in, The smaller the value is, the less the temperature decreases during the process of reducing the network load of the target router, which means that the target router is more likely to fail, and the greater the target failure probability is; the more extreme points there are in the process of reducing the network load of the target router, that is, the more mutations the temperature value has, the greater the target failure probability is.

[0138] Through this embodiment, the second fault probability is corrected according to the third temperature change value and the number of second temperature extreme points, thereby obtaining a target fault probability. In this way, it is possible to more accurately evaluate whether a target router has a fault according to the target fault probability, thereby improving the accuracy of router fault detection.

[0139] Based on the 5G communication network router fault detection method. Accordingly, the present invention also provides a specific embodiment of a 5G communication network router fault detection system.

[0140] Figure 4 A structural schematic diagram of a 5G communication network router fault detection system provided in an embodiment of the present application is shown. The 5G communication network router fault detection system 400 may include a curve acquisition module 410, a curve analysis module 420, a probability determination module 430 and a fault judgment module 440.

[0141] The curve acquisition module 410 is used to acquire a first temperature change curve of the target router, where the first temperature change curve is used to characterize the temperature change of the target router during the process of increasing the network load from zero to the target network load and maintaining the target time length;

[0142] The curve analysis module 420 is used to determine the temperature variability of the target router according to the first temperature change curve, and the temperature variability is used to characterize the degree of temperature change of the target router when the network load is stable;

[0143] The curve acquisition module 410 is further used to increase the network load of the target router and acquire a second temperature change curve of the target router, where the second temperature change curve is used to characterize the temperature change of the target router during the process of increasing the target network load;

[0144] A probability determination module 430, configured to determine a first failure probability of a target router according to the temperature variability and the second temperature variation curve;

[0145] The fault judgment module 440 is used to determine that a fault occurs on the target router when the first fault probability is greater than a preset probability threshold.

[0146] In the 5G communication network router fault detection system provided by an embodiment of the present invention, a first temperature change curve is obtained that characterizes the temperature change of the target router during the process of increasing the network load from zero to the target network load and maintaining the target duration. Then, based on the first temperature change curve, the temperature variability that characterizes the degree of temperature change of the target router when the network load is stable is determined. Then, the network load of the target router is increased to obtain the second temperature change curve of the target router. Thus, based on the temperature variability and the second temperature change curve, the first failure probability of the target router is determined. When the first failure probability is greater than the preset probability threshold, it is determined that the target router has failed. In this way, the present invention analyzes the temperature change trend and fluctuation of the router during the network load change process according to the first temperature change curve and the second temperature change curve, so that the failure probability of the router can be accurately determined, and the accuracy of router fault detection can be improved.

[0147] Based on the 5G communication network router fault detection method. Accordingly, the present invention also provides a specific embodiment of a 5G communication network router fault detection electronic device.

[0148] Figure 5 A schematic diagram of the hardware structure of a 5G communication network router fault detection electronic device provided in an embodiment of the present invention is shown.

[0149] The 5G communication network router fault detection electronic device may include a processor 501 and a memory 502 storing computer program instructions.

[0150] Specifically, the processor 501 may include a central processing unit, or a specific integrated circuit, or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0151] The memory 502 may include a large capacity memory for data or instructions. By way of example and not limitation, the memory 502 may include a hard disk drive, a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus drive, or a combination of two or more of these. Where appropriate, the memory 502 may include a removable or non-removable (or fixed) medium. Where appropriate, the memory 502 may be inside or outside the integrated gateway disaster recovery device. In a particular embodiment, the memory 502 is a non-volatile solid-state memory.

[0152] The memory 502 may include read-only memory, random access memory, magnetic disk storage media devices, optical storage media devices, flash memory devices, electrical, optical or other physical / tangible memory storage devices. Thus, typically, the memory 502 includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the method according to an aspect of the present disclosure.

[0153] The processor 501 implements any one of the 5G communication network router fault detection methods in the above embodiments by reading and executing computer program instructions stored in the memory 502.

[0154] In one example, the digital twin model building device in a complex scenario may further include a communication interface 503 and a bus 510. Figure 5 As shown, the processor 501, the memory 502, and the communication interface 503 are connected via a bus 510 and communicate with each other.

[0155] The communication interface 503 is mainly used to implement communication between each module, device, unit and / or equipment in the embodiment of the present application.

[0156] Bus 510 includes hardware, software or both, and couples the components of 5G communication network router fault detection electronic equipment to each other. For example, but not limitation, the bus may include accelerated graphics port or other graphics bus, enhanced industrial standard architecture bus, front-end bus, hypertransport interconnect, industrial standard architecture bus, infinite bandwidth interconnect, low pin count bus, memory bus, micro channel architecture bus, peripheral component interconnect bus, serial advanced technology attachment bus, video electronics standard association local bus or other suitable bus or two or more of these combinations. Where appropriate, bus 510 may include one or more buses. Although the present application embodiment describes and shows a specific bus, the present application considers any suitable bus or interconnect.

[0157] It should be clear that the present invention is not limited to the specific configuration and processing described above and shown in the figures. For the sake of simplicity, a detailed description of the known method is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present invention is not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order between the steps after understanding the spirit of the present invention.

[0158] It should also be noted that the exemplary embodiments mentioned in the present invention describe some methods or systems based on a series of steps or devices. However, the present invention is not limited to the order of the above steps, that is, the steps can be performed in the order mentioned in the embodiments, or in a different order from the embodiments, or several steps can be performed simultaneously.

[0159] The above is only a specific implementation of the present invention. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working process of the system, module and unit described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here. It should be understood that the protection scope of the present invention is not limited to this. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present invention, and these modifications or replacements should be covered within the protection scope of the present invention.

Claims

1. A 5G communication network router fault detection method, characterized in that: The method comprises: Acquire a first temperature change curve of the target router, where the first temperature change curve is used to characterize the temperature change of the target router during a process in which the network load increases from zero to a target network load and is maintained for a target duration; Determining the temperature variability of the target router according to the first temperature change curve, wherein the temperature variability is used to characterize the degree of temperature change of the target router when the network load is stable; Increasing the network load of the target router to obtain a second temperature change curve of the target router, where the second temperature change curve is used to characterize the temperature change of the target router during the process of increasing the target network load; Determining a first failure probability of the target router according to the temperature variability and the second temperature variation curve; When the first failure probability is greater than a preset probability threshold, determining that a failure occurs on the target router; The determining, according to the temperature variability and the second temperature variation curve, a first failure probability of the target router includes: Determine, according to the second temperature change curve, a second temperature change value, a number of first temperature extreme value points, and a network load change value of the target router; The product of the second temperature change value and the number of the first temperature extreme value points is divided by the network load change value to obtain a third calculation result; The temperature variability, the third calculation result, and the slope of the second temperature variation curve are multiplied to obtain a first failure probability of the target router.

2. The 5G communication network router fault detection method according to claim 1, characterized in that: Determining the temperature variability of the target router according to the first temperature change curve includes: Performing a first-order difference on each temperature value in the first temperature change curve to obtain a difference sequence corresponding to the first temperature change curve; Clustering the differential data in the differential sequence to obtain a clustering result; According to the clustering result, the first temperature change curve is divided into a first sub-curve and a second sub-curve, the first sub-curve is used to characterize the temperature change during the temperature rising period, and the second sub-curve is used to characterize the temperature change during the temperature stable period; Determining the temperature stability of the target router according to the second sub-curve, wherein the temperature stability is used to characterize the temperature stability of the target router when the network load is stable; The temperature variability of the target router is determined according to the first sub-curve, the second sub-curve, and the temperature stability.

3. The 5G communication network router fault detection method according to claim 2, characterized in that: Determining the temperature stability of the target router according to the second sub-curve includes: According to the second sub-curve, determining a segmentation time at which the first sub-curve changes into the second sub-curve and a curve slope of the second sub-curve; Multiply the segment time by the curve slope of the second sub-curve and take the inverse of the result to obtain a first calculation result; An exponential function operation is performed on the first calculation result to obtain the temperature stability of the target router.

4. The 5G communication network router fault detection method according to claim 2, characterized in that: The determining the temperature variability of the target router according to the first sub-curve, the second sub-curve and the temperature stability includes: Obtaining a first temperature change value of the target router according to a temperature value at a start time of the first sub-curve and a temperature value at an end time of the second sub-curve; Performing an exponential function operation on the inverse number of the temperature stability to obtain a second calculation result; The second calculation result, the first temperature change value, and the curve slope of the first sub-curve are multiplied to obtain the temperature variability of the target router.

5. The 5G communication network router fault detection method according to any one of claims 1 to 4, characterized in that: After determining the first failure probability of the target router according to the temperature variability and the second temperature change curve, the method further includes: According to the temperature difference of each area in the target router under the same network load, the first failure probability is corrected to obtain a second failure probability of the target router; Reducing the network load of the target router, and obtaining a third temperature change value and a number of second temperature extreme value points during the process of reducing the network load of the target router; Correcting the second failure probability according to the third temperature change value and the number of the second temperature extreme value points to obtain a target failure probability of the target router; The step of determining that a failure occurs on the target router when the first failure probability is greater than a preset probability threshold comprises: When the target failure probability is greater than a preset probability threshold, it is determined that the target router fails.

6. The 5G communication network router fault detection method according to claim 5, characterized in that: The step of correcting the first failure probability according to the temperature difference between the areas in the target router under the same network load to obtain the second failure probability of the target router includes: For each area of ​​the target router in the second temperature change curve under each network load, respectively performing: accumulating the temperature difference value between the target area and each area other than the target area to obtain a temperature difference accumulation value, wherein the target area is any area in the target router; The accumulated values ​​of the temperature differences of the various regions under various network loads are accumulated and divided by the number of the network loads to obtain a mean value of the temperature differences; For each area in the target router, respectively: accumulating the difference values ​​of the temperature change amplitudes of the target area and other areas except the target area to obtain an amplitude difference accumulation value; Accumulating the amplitude difference accumulated values ​​of the respective regions to obtain a total amplitude difference; The first failure probability, the temperature difference mean, and the total amplitude difference are multiplied to obtain a second failure probability of the target router.

7. The 5G communication network router fault detection method according to claim 5, characterized in that: The step of correcting the second failure probability according to the third temperature change value and the number of the second temperature extreme value points to obtain a target failure probability of the target router includes: Perform an exponential function operation on the third temperature change value and the inverse of the accumulated value of the preset coefficient to obtain a fourth calculation result; The second failure probability, the fourth calculation result, and the number of the second temperature extreme value points are multiplied to obtain a target failure probability of the target router.

8. A 5G communication network router fault detection system, characterized in that: The system comprises: A curve acquisition module, used to acquire a first temperature change curve of a target router, wherein the first temperature change curve is used to characterize the temperature change of the target router during a process in which the network load of the target router increases from zero to a target network load and is maintained for a target duration; A curve analysis module, used to determine the temperature variability of the target router according to the first temperature change curve, wherein the temperature variability is used to characterize the degree of temperature change of the target router when the network load is stable; The curve acquisition module is further used to increase the network load of the target router to obtain a second temperature change curve of the target router, wherein the second temperature change curve is used to characterize the temperature change of the target router during the process of increasing the target network load; A probability determination module, configured to determine a first failure probability of the target router according to the temperature variability and the second temperature variation curve; A fault judgment module, configured to determine that a fault occurs on the target router when the first fault probability is greater than a preset probability threshold; The determining, according to the temperature variability and the second temperature variation curve, a first failure probability of the target router includes: Determine, according to the second temperature change curve, a second temperature change value, a number of first temperature extreme value points, and a network load change value of the target router; The product of the second temperature change value and the number of the first temperature extreme value points is divided by the network load change value to obtain a third calculation result; The temperature variability, the third calculation result, and the slope of the second temperature variation curve are multiplied to obtain a first failure probability of the target router.

9. A 5G communication network router fault detection electronic device, characterized in that: The device comprises: a processor and a memory storing computer program instructions; When the processor executes the computer program instructions, it implements the 5G communication network router fault detection method as described in any one of claims 1-7.

Images