Equipment monitoring early warning method and device and electronic equipment

Abstract

The invention provides an equipment monitoring early warning method and device and electronic equipment, and relates to the technical field of communication base stations. The method comprises the following steps: acquiring real-time equipment data and historical equipment data of network equipment; calculating a deviation value between the real-time equipment data and the historical equipment data; if the deviation value between the real-time equipment data and the historical equipment data is smaller than a first threshold value, obtaining standard data of the network equipment; calculating fluctuation parameters of the real-time equipment data according to the real-time equipment data and the standard data; and if the fluctuation parameter meets a preset condition, generating early warning information. The method comprises the following steps: predicting possible fault information of network equipment by calculating a deviation value between real-time equipment data and historical equipment data of the network equipment; and then the fluctuation parameter of the real-time equipment data is calculated, the fluctuation parameter is comprehensively judged, the early warning information is generated in advance, and early warning is carried out on the alarm information possibly generated by the network equipment, so that adjustment is carried out in time, and the overall operation and maintenance efficiency is improved.

Description

Technical Field

[0001] The embodiments of the present application relate to the technical field of communication base stations, and in particular to a device monitoring and early warning method, device, and electronic equipment. Background Art

[0002] Base stations are hubs for information transmission and services. They can be deployed with a variety of network equipment, including servers, switches, environmental monitoring systems, power management systems, etc., to achieve information transmission in base stations. Network equipment in base stations will generate alarm information under abnormal conditions, such as power outages, low voltage disconnection, high temperature, fire alarms, water overflows, battery discharge, etc. Alarm information in base stations needs to be processed in a timely manner to ensure stable operation of the base stations and reduce the probability of accidents.

[0003] Therefore, it is necessary to monitor the alarm information in the base station in real time. The data of the network equipment in the base station can be collected regularly, and the existence of alarm information can be judged through preset algorithms or logic. When the alarm information is detected, the alarm information is uploaded to the background monitoring center for processing.

[0004] However, real-time monitoring of alarm information can only respond and process after the alarm actually occurs, and it is impossible to predict the alarm that may occur in advance. Not only is it difficult to avoid the occurrence of emergencies, but it also increases the difficulty of troubleshooting and repairing, reducing the overall operation and maintenance efficiency. Summary of the invention

[0005] The present application provides an equipment monitoring and early warning method, device and electronic equipment to solve the problem that it is impossible to predict in advance the alarms that may be generated by communication base stations, thereby reducing the overall operation and maintenance efficiency.

[0006] In a first aspect, the present application provides a device monitoring and early warning method, comprising: Acquire real-time device data and historical device data of network devices; wherein the historical device data is device data within a preset time before a failure occurs in the network device during historical operation, and the data type of the real-time device data is the same as that of the historical device data; calculate the deviation between the real-time device data and the historical device data; if the deviation between the real-time device data and the historical device data is less than a first threshold, acquire standard data of the network device; wherein the standard data is data when the network device is operating normally, and the data type of the standard data is the same as that of the real-time device data; calculate fluctuation parameters of the real-time device data based on the real-time device data and the standard data; if the fluctuation parameters meet preset conditions, generate warning information.

[0007] In the method, by calculating the deviation between the real-time device data of the network device and the historical device data of the network device that failed during its historical operation, possible fault information of the network device can be predicted; then the fluctuation parameters of the real-time device data are calculated, and by making a comprehensive judgment on the fluctuation parameters, early warning information is generated in advance, and early warning of the alarm information that may be generated by the network device is issued so that timely adjustments can be made to improve the overall operation and maintenance efficiency.

[0008] In an implementable manner of the first aspect, the fluctuation parameters of the real-time device data include the fluctuation amplitude of the real-time device data, and the fluctuation parameters of the real-time device data are calculated based on the real-time device data and the standard data, including: calculating the deviation between the real-time device data and the standard data; and determining the fluctuation amplitude of the real-time device data based on the deviation between the real-time device data and the standard data.

[0009] In the method, by calculating the fluctuation range of real-time device data, the deviation of real-time device data relative to standard data can be determined, which provides conditions for early warning judgment and improves the accuracy of equipment monitoring and early warning.

[0010] In an implementation method of the first aspect, the fluctuation parameters of the real-time device data include the fluctuation trend of the real-time device data. The fluctuation parameters of the real-time device data are calculated based on the real-time device data and the standard data, and also include: determining the fluctuation trend of the real-time device data based on the deviation amount between at least two real-time device data and the standard data among multiple real-time device data obtained at preset time intervals.

[0011] In an implementable manner of the first aspect, based on obtaining the deviation amount of at least two real-time device data from the standard data among multiple real-time device data at preset time intervals, determining the fluctuation trend of the real-time device data includes: separately judging the deviation direction of at least two real-time device data relative to the standard data; if the deviation directions of at least two real-time device data relative to the standard data are the same, marking them as the same fluctuation trend; if the deviation directions of at least two real-time device data relative to the standard data are different, marking them as different fluctuation trends.

[0012] In the method, by calculating the fluctuation trend of at least two real-time device data, it can be determined whether the deviation of the device data is accidental or continuous, thereby avoiding the situation where an early warning is generated when the real-time device data accidentally deviates, and reducing the probability of false alarms.

[0013] In an implementable manner of the first aspect, the fluctuation parameters of the real-time device data include the duration of the fluctuation of the real-time device data. The fluctuation parameters of the real-time device data are calculated based on the real-time device data and the standard data, and also include: obtaining the fluctuation trends of at least two real-time device data among multiple real-time device data; if the fluctuation trends are the same, determining the duration of the fluctuation based on the time interval for obtaining at least two real-time device data with the same fluctuation trend, and the duration of the fluctuation is obtained by adding the time interval for obtaining at least two real-time device data with the same fluctuation trend.

[0014] In the method, the duration of the real-time equipment data with the same fluctuation trend is calculated to obtain the duration of the fluctuation, and whether an early warning is needed is determined according to the duration of the fluctuation, thereby improving the accuracy of the equipment monitoring and early warning method.

[0015] In an implementation method of the first aspect, the fluctuation parameters of the real-time device data include the similarity of the fluctuation trends of the real-time device data. The fluctuation parameters of the real-time device data are calculated based on the real-time device data and the standard data, and also include: obtaining a first fluctuation trend of the real-time device data, and obtaining a second fluctuation trend of the historical device data; calculating the similarity of the first fluctuation trend and the second fluctuation trend to obtain the similarity of the fluctuation trends of the real-time device data.

[0016] In the method, by calculating the similarity of fluctuation trends, the fluctuation trend of real-time device data can be compared with the fluctuation trend of historical device data, and whether the current device needs an early warning can be analyzed based on historical early warning situations, thereby improving the accuracy of the device monitoring early warning method.

[0017] In an implementable manner of the first aspect, the preset conditions include at least one of the following: the fluctuation amplitude is greater than the amplitude threshold; the fluctuation trends are the same; the fluctuation duration is greater than the time threshold; the fluctuation trend similarity is greater than the similarity threshold; if the fluctuation parameter meets the preset conditions, a warning message is generated, including: if the fluctuation parameter meets all the preset conditions, a warning message is generated, or, if the fluctuation parameter meets at least one of the preset conditions, the number and parameter values ​​of the fluctuation parameters that meet the preset conditions are obtained; if the number of fluctuation parameters that meet the preset conditions is greater than the second threshold, and the parameter values ​​of the fluctuation parameters that meet the preset conditions are greater than the third threshold, a warning message is generated.

[0018] In the method, by comprehensively judging multiple different preset conditions, it is possible to judge whether an early warning is needed in two situations: when the real-time device data meets all the preset conditions or when the real-time device data only meets some of the preset conditions, thereby improving the comprehensiveness of the equipment monitoring early warning method.

[0019] In an implementation method of the first aspect, if the fluctuation parameter meets the preset conditions, after the step of generating early warning information, it also includes: sending the early warning information to the monitoring center; controlling the monitoring center to generate a processing strategy based on the early warning information, and sending the processing strategy to the terminal device.

[0020] In the method, when a possible failure of a network device is detected and a warning message is issued, in order to improve the timeliness of the failure processing, the warning message can be sent to the monitoring center and a processing strategy can be generated to reduce the probability of the network device actually failing.

[0021] In the second aspect, the present application provides an equipment monitoring and early warning device, comprising: a data acquisition module, configured to: acquire real-time equipment data of a network device and historical equipment data of the network device; wherein the historical equipment data is equipment data within a preset time before a failure occurs in the historical operation of the network device, and the data type of the real-time equipment data is the same as that of the historical equipment data; a deviation calculation module, configured to: calculate the deviation between the real-time equipment data and the historical equipment data; a judgment module, configured to: acquire standard data of the network device if the deviation between the real-time equipment data and the historical equipment data is less than a first threshold; wherein the standard data is data when the network device is operating normally, and the data type of the standard data is the same as that of the real-time equipment data; a fluctuation parameter calculation module, configured to: calculate the fluctuation parameters of the real-time equipment data based on the real-time equipment data and the standard data; an early warning information generation module, configured to: generate early warning information if the fluctuation parameters meet the preset conditions.

[0022] In a third aspect, the present application provides an electronic device comprising: one or more processors; and a memory configured to store one or more programs; wherein, when the one or more programs are executed by one or more processors, the one or more processors implement any one of the device monitoring and early warning methods in the first aspect.

[0023] It should be understood that the beneficial effects that can be achieved by the technical solutions of the second and third aspects provided above can be referred to the beneficial effects of the first aspect and any possible implementation thereof, and will not be repeated here.

[0024] It can be seen from the above technical scheme that the present application provides an equipment monitoring and early warning method, device and electronic device, the method comprising: obtaining real-time equipment data and historical equipment data of a network device; wherein the historical equipment data is equipment data within a preset time before a failure occurs in a historical operation of the network device, and the data type of the real-time equipment data is the same as that of the historical equipment data; calculating the deviation between the real-time equipment data and the historical equipment data; if the deviation between the real-time equipment data and the historical equipment data is less than a first threshold, obtaining standard data of the network device; wherein the standard data is data when the network device is operating normally, and the data type of the standard data is the same as that of the real-time equipment data; calculating fluctuation parameters of the real-time equipment data based on the real-time equipment data and the standard data; if the fluctuation parameters meet the preset conditions, generating early warning information.

[0025] In the method, by calculating the deviation between the real-time device data of the network device and the historical device data of the network device that failed during its historical operation, possible fault information of the network device can be predicted; then the fluctuation parameters of the real-time device data are calculated, and by making a comprehensive judgment on the fluctuation parameters, early warning information is generated in advance, and early warning of the alarm information that may be generated by the network device is issued so that timely adjustments can be made to improve the overall operation and maintenance efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the technical solution of the present application, the drawings required for use in the embodiments are briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0027] Figure 1 A schematic diagram of the working process of the equipment monitoring system provided in the embodiment of the present application; Figure 2 A schematic diagram of a device monitoring and early warning system provided in an embodiment of the present application; Figure 3 A schematic diagram of a process flow of a device monitoring and early warning method provided in an embodiment of the present application; Figure 4 A schematic diagram of a method for determining fluctuation trends of two real-time device data provided in an embodiment of the present application; Figure 5 A schematic diagram of the structure of the equipment monitoring and early warning device provided in an embodiment of the present application; Figure 6 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0028] The following embodiments are described in detail, and examples thereof are shown in the accompanying drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The implementations described in the following embodiments do not represent all implementations consistent with the present application. They are only examples of systems and methods consistent with some aspects of the present application as detailed in the claims.

[0029] It should be noted that the brief description of terms in this application is only for the convenience of understanding the embodiments described below, and is not intended to limit the embodiments of this application. Unless otherwise specified, these terms should be understood according to their ordinary and common meanings.

[0030] The terms "first", "second", "third", etc. in the specification and claims of this application and the above drawings are used to distinguish similar or similar objects or entities, and do not necessarily mean to limit a specific order or sequence, unless otherwise noted. It should be understood that the terms used in this way can be interchangeable under appropriate circumstances.

[0031] In order to facilitate the understanding of the technical solution of the application, the relevant technologies involved in this application are first explained below.

[0032] Communication base stations are the core nodes of information transmission and services in modern communication networks, carrying the task of data transmission. Various network devices can be deployed in communication base stations, including but not limited to high-performance servers, precision communication equipment, environmental monitoring systems, and power management systems. These network devices work together to ensure that the base station can stably and efficiently perform various tasks of information transmission and meet the communication needs of users.

[0033] During the operation of the base station, various network devices may trigger abnormal working conditions due to various external or internal factors, thus generating alarm information, including but not limited to power outages caused by power failures, equipment out of working condition due to low voltage, high temperature warnings caused by poor heat dissipation, potential fire risks, water overflows caused by failure of waterproof measures, and deep discharge of battery packs due to long-term power supply, etc. These alarm information directly affects the stable operation of the base station. If not handled in time, it may cause communication interruption, equipment damage, and even safety accidents.

[0034] In order to deal with the risks caused by abnormal working status of network equipment, it is necessary to monitor the alarm information in the base station in real time. Therefore, an equipment monitoring system should be established in the communication base station. Figure 1 The following is a schematic diagram of the working process of the equipment monitoring system. Figure 1As shown, the equipment monitoring system first executes step S101: regularly obtain equipment data, and collect key operating data of all network devices in the base station at regular time intervals. Then execute step S102: parse the data message, and parse the acquired equipment data to obtain equipment data that is convenient for comparative analysis. Secondly, use a preset algorithm or logical judgment mechanism to analyze the parsed equipment data to determine whether an alarm is required. If an alarm is required, execute step S103: send the alarm information to the monitoring center, and then execute step S104: process the warning, and the monitoring center processes the alarm information; if an alarm is not required, continue to execute step S101: regularly obtain equipment data to play a role in real-time monitoring.

[0035] However, although the equipment monitoring system can respond quickly after an alarm occurs, its limitation is that it cannot predict possible alarms in advance, which increases the probability of emergencies and makes troubleshooting and repair more difficult, thus affecting the overall operation and maintenance efficiency.

[0036] To solve the above problems, the embodiments of the present application provide an equipment monitoring and early warning method, device and electronic device. By calculating the deviation between the real-time equipment data of the network equipment and the historical equipment data of the network equipment that has failed during its historical operation, it is possible to predict the possible fault information of the network equipment; then calculate the fluctuation parameters of the real-time equipment data, and generate early warning information by making a comprehensive judgment on the fluctuation parameters, so as to provide early warning for the alarm information that may be generated by the network equipment, so as to make timely adjustments and improve the overall operation and maintenance efficiency.

[0037] The equipment monitoring and early warning method can be applied to the equipment monitoring and early warning system to achieve overall monitoring and early warning of equipment in a communication base station. Figure 2 Schematic diagram of the equipment monitoring and early warning system provided in the embodiment of the present application. Figure 2 As shown, the equipment monitoring and early warning system includes multiple network devices (such as switches, routers, transceivers, etc.), monitoring equipment, and a monitoring center. Among them, the network equipment can realize the functions of signal reception and transmission, data forwarding, network interconnection, protocol conversion, etc. of the communication base station, and is a key device in the communication base station; the monitoring equipment is used to realize the monitoring and early warning function of the network equipment in the system, communicates with multiple network devices through the communication interface, receives the real-time device data of the network equipment, analyzes the real-time device data, and warns of possible faults of the network equipment, and sends the warning information to the monitoring center; the monitoring center processes the received warning information, generates a processing strategy, and then sends the processing strategy to the terminal equipment outside the system for the operation and maintenance personnel to view and deal with the network equipment that may fail in time.

[0038] Next, the specific implementation method of the equipment monitoring and early warning method is introduced. Figure 3 A flow chart of a device monitoring and early warning method provided in an embodiment of the present application is shown in FIG. Figure 3 As shown, the monitoring and early warning method includes steps S100-S500, which are as follows: S100: Acquire real-time device data and historical device data of network devices.

[0039] In some embodiments, the network equipment in the communication base station will generate a variety of data during operation, including performance indicator parameters of the network equipment, operation status information, various physical quantity values ​​during operation, operation behavior records, and operation feedback data of internal components, etc., which can reflect the operation status and working conditions of the equipment. When the network equipment is about to fail, the real-time equipment data of the network equipment may fluctuate compared with the equipment data in the normal state. Therefore, by obtaining the real-time equipment data of the network equipment and analyzing the data, it is possible to promptly discover the situation where the network equipment may fail.

[0040] Exemplarily, if the communication base station includes a first network device, a second network device, and a third network device, the AC voltage, DC voltage, AC current, DC current, temperature and other data of the first network device, the second network device, and the third network device are obtained as the real-time device data of each network device. Taking the first network device as a transceiver as an example, the real-time device data of the first network device includes AC voltage 220V, DC voltage 48V, AC current 10A, DC current 100A, and temperature 20 degrees Celsius (℃).

[0041] It should be noted that the device data of the network device is not limited to the above data and the above values, but also includes other data related to the device operating status and other values, which are not specifically limited in the embodiments of the present application.

[0042] In some embodiments, in order to improve the timeliness of the device monitoring and early warning method and achieve the purpose of real-time monitoring of network devices, real-time device data of network devices can be obtained at regular intervals.

[0043] Exemplarily, a real-time acquisition program is set to obtain real-time device data of network devices according to a predetermined time plan. The predetermined time plan is to obtain data every 30 seconds (S). For example, a communication base station includes a first network device, a second network device, and a third network device, and the AC voltage, DC voltage, AC current, DC current, and temperature of the above three network devices are obtained every 30 seconds.

[0044] It should be noted that other methods may be used to periodically obtain real-time device data of network devices, which are not limited to the method of setting a real-time acquisition program, and are not specifically limited in the embodiments of the present application.

[0045] In some embodiments, the operation data of the network device may be abnormal within a preset time before a failure occurs. Therefore, to facilitate subsequent judgment of the abnormal state of the network device, the device data of the network device within a preset time before a failure occurs during historical operation, i.e., historical device data, may be stored.

[0046] Specifically, before the first network device fails, the real-time device data of the first network device is regularly acquired and stored. When the first network device fails, the real-time device data stored within a preset time before the first network device fails is marked as historical device data.

[0047] Exemplarily, the preset time is set to 10 minutes. When the first network device has failed, the real-time device data obtained within 10 minutes before the failure of the first network device is used as the historical device data of the first network device, including AC voltage 200V, DC voltage 44V, AC current 8A, DC current 80A, and temperature 18°C.

[0048] It should be noted that since the method for obtaining real-time device data of network devices is periodic acquisition, multiple sets of real-time device data can be obtained within a preset time before a network device failure occurs, and any set of real-time device data can be used as historical device data of the network device, which is not specifically limited in the embodiments of the present application.

[0049] S200: Calculate the deviation between the real-time device data and the historical device data.

[0050] In some embodiments, in order to preliminarily determine whether there is an abnormality in the real-time device data, the real-time device data of the same network device can be compared with the historical device data. It should be noted that the device data of the network device includes multiple types such as AC voltage, DC voltage, AC current, DC current and temperature. Therefore, in order to ensure the accuracy of the comparison result, it is necessary to compare the real-time device data of the same type with the historical device data. Specifically, the real-time device data of the same type and the historical device data are compared by calculating the deviation between the two.

[0051] In some embodiments, the deviation between the real-time device data and the historical device data of the same type can be calculated by subtracting them and calculating the absolute value. Exemplarily, the real-time device data of the first network device is obtained as AC voltage 220V, DC voltage 44.5V, AC current 10A, DC current 100A, and temperature 20°C. The historical device data of the first network device is AC voltage 200V, DC voltage 44V, AC current 8A, DC current 80A, and temperature 18°C. The absolute values ​​of the differences of AC voltage, DC voltage, AC current, DC current and temperature are calculated to be 20, 0.5, 2, and 20, respectively, which are the deviations of each type of data. After obtaining the deviation between the real-time device data and the historical device data, it can be judged whether the first network device may be abnormal based on the numerical value of the deviation.

[0052] S300: If the deviation between the real-time device data and the historical device data is less than a first threshold, acquiring standard data of the network device.

[0053] In some embodiments, after obtaining the deviation between the real-time device data and the historical device data, it is determined whether the deviation is less than a first threshold value. If the deviation is less than the first threshold value, it means that the current real-time device data of the network device is close to the historical device data before the failure occurred in the historical operation process, and there is a possibility of failure. At this time, it is necessary to obtain the standard data of the network device during normal operation, and make further judgments based on the standard data.

[0054] It should be noted that different first thresholds need to be set for different network devices and different types of device data of the same network device to improve the accuracy of judging abnormal device status. As long as any type of device data meets the condition that the deviation is less than the first threshold, it is judged that the network device has the possibility of failure.

[0055] Exemplarily, the first threshold of the DC voltage of the first network device is set to 1, and the DC voltage deviation between the real-time device data and the historical device data of the first network device is 0.5, which is less than the set first threshold. Therefore, the first network device has the possibility of failure. Therefore, the standard data of the first network device is obtained: AC voltage 220V, DC voltage 48V, AC current 10A, DC current 100A, temperature 20°C, for subsequent early warning judgment.

[0056] S400: Calculating fluctuation parameters of the real-time device data according to the real-time device data and the standard data.

[0057] In some embodiments, in order to improve the accuracy and comprehensiveness of the equipment monitoring and early warning method, the same type of real-time equipment data and historical equipment data can be used to calculate the fluctuation parameters of the real-time equipment data, and the degree of abnormality of the real-time equipment data can be judged based on the fluctuation parameters to determine whether an early warning is needed.

[0058] In some embodiments, the fluctuation parameters of the real-time device data include the fluctuation amplitude of the real-time device data, and the fluctuation amplitude is calculated by calculating the deviation between the real-time device data and the standard data, and determining the fluctuation amplitude of the real-time device data based on the deviation between the real-time device data and the standard data.

[0059] For example, taking the first network device as an example, the real-time device data of the first network device is AC voltage 220V, DC voltage 44.5V, AC current 10A, DC current 100A, and temperature 20° C. The standard data of the first network device is AC voltage 220V, DC voltage 48V, AC current 10A, DC current 100A, and temperature 20° C. The deviation of each type of device data is calculated respectively, and the AC voltage fluctuation amplitude is 0, the DC voltage fluctuation amplitude is 3.5, the AC current fluctuation amplitude is 0, the DC current fluctuation amplitude is 0, and the temperature fluctuation amplitude is 0.

[0060] In some embodiments, the fluctuation parameter of the real-time device data also includes the fluctuation trend of the real-time device data, and the fluctuation trend indicates the change trend of multiple real-time device data continuously acquired within a period of time relative to the standard data of the same type. When judging the fluctuation trend, firstly, the deviation amount of at least two real-time device data from the multiple real-time device data and the standard data is obtained at a preset time interval; then the deviation direction of at least two real-time device data relative to the standard data is judged respectively; if the deviation directions of at least two real-time device data relative to the standard data are the same, it is marked as the same fluctuation trend; if the deviation directions of at least two real-time device data relative to the standard data are different, it is marked as different fluctuation trends. Among them, the deviation direction indicates the positive or negative value obtained by subtracting the real-time device data from the standard data of the same type. For example, if the DC voltage of the real-time device data is 44V and the DC voltage of the standard data is 48V, the difference between the two is -4, which is a negative value, indicating that the deviation direction is negative; in contrast, if the value obtained by subtracting the two is a positive value, it indicates that the deviation direction is positive.

[0061] Exemplarily, the preset time interval is set to 30S. Taking the DC voltages in two real-time device data of the first network device as an example, the standard DC voltage in the standard data is 48V. The DC voltage of the real-time device data obtained for the first time is 44V, which is marked as the first DC voltage. After 30S, the DC voltage of the real-time device data is obtained again, which is 42V, which is marked as the second DC voltage. Figure 4The following is a schematic diagram of the method for determining the fluctuation trend of two real-time device data. Figure 4 As shown, the first DC voltage and the second DC voltage are obtained in a time interval of 30S; the first difference of the first DC voltage relative to the standard DC voltage in the standard data is calculated to be -4, and the first difference of the second DC voltage relative to the standard DC voltage in the standard data is -2; since the first difference and the second difference are both negative values, indicating that the deviation directions of the first DC voltage and the second DC voltage are the same, the fluctuation trends of the DC voltage of the first network device are marked as the same.

[0062] For example Figure 4 As shown, a first DC voltage of 44V and a second DC voltage of 52V are obtained in a time interval of 30S; the first difference of the first DC voltage relative to the standard DC voltage is calculated to be -4, and the first difference of the second DC voltage relative to the standard DC voltage in the standard data is 4V; since the first difference is a negative value and the second difference is a positive value, indicating that the deviation directions of the first DC voltage and the second DC voltage are different, the fluctuation trend of the DC voltage of the first network device is marked as different.

[0063] In some embodiments, the fluctuation parameter of the real-time device data also includes the duration of the fluctuation of the real-time device data, which is related to the fluctuation trend and indicates the duration of time during which the fluctuation trend remains unchanged. When calculating the duration of the fluctuation, the fluctuation trends of multiple real-time device data are first obtained. If the fluctuation trends of multiple real-time device data are the same, the time intervals used to obtain the multiple real-time device data are added together to obtain the duration of the fluctuation.

[0064] Exemplarily, the preset time interval is set to 30S, and the DC voltage of the first network device is obtained every 30S. Three DC voltages of 42V, 43V, and 44V are obtained continuously. If the standard DC voltage is 48V, the differences of the three DC voltages relative to the standard DC voltage are all negative values, and the deviation directions are all the same, so the fluctuation trends are the same. It should be understood that it takes two time intervals to continuously obtain three DC voltages. The two time intervals of 30S are added together to obtain a fluctuation duration of 60S.

[0065] In some embodiments, the fluctuation parameter of the real-time device data also includes the fluctuation trend similarity of the real-time device data, and the fluctuation trend similarity is calculated by: obtaining a first fluctuation trend of the real-time device data and a second fluctuation trend of the historical device data; calculating the similarity of the first fluctuation trend and the second fluctuation trend to obtain the fluctuation trend similarity of the real-time device data. The real-time device data and the historical device data can be device data of two network devices of the same type but different loads, respectively, to improve the universality of the reference data.

[0066] For example, taking DC voltage as an example, the DC voltage in the real-time device data of the first network device decreases from 44V to 38V within 60S, which is equivalent to a decrease of 0.1V per second, and the DC voltage in the historical device data of the second network device of the same type as the first network device decreases from 22V to 16V within 60S, which is equivalent to a decrease of 0.1V per second. Therefore, the fluctuation trend similarity of the DC voltage of the first network device is 100%.

[0067] S500: If the fluctuation parameter meets the preset conditions, a warning message is generated.

[0068] In some embodiments, the severity of the abnormality in the operating status of the network device can be determined based on the fluctuation parameters of the real-time device data.

[0069] Specifically, it is determined whether the fluctuation parameter exceeds a reasonable range by setting preset conditions. The preset conditions include at least one of the following: the fluctuation amplitude is greater than the amplitude threshold; the fluctuation trend is the same; the fluctuation duration is greater than the time threshold; the fluctuation trend similarity is greater than the similarity threshold.

[0070] In some embodiments, if the fluctuation parameters of the real-time device data meet all the above preset conditions, it means that the real-time device data of the network device has produced abnormally high fluctuations, the network device is likely to fail, and early warning information needs to be generated.

[0071] Exemplarily, if the DC voltage fluctuation amplitude of the first network device is 12, which is greater than the amplitude threshold of 10; the fluctuation trend is the same; the fluctuation duration is 80S, which is greater than the time threshold of 60S; the fluctuation trend similarity is 65%, which is greater than the similarity threshold of 60%, then a warning message is generated.

[0072] In some embodiments, if the fluctuation parameter satisfies at least one of the preset conditions, a comprehensive judgment needs to be made based on the number and specific values ​​of the fluctuation parameters that meet the preset conditions. Specifically, the number and parameter values ​​of the fluctuation parameters that meet the preset conditions are obtained; if the number of fluctuation parameters that meet the preset conditions is greater than the second threshold, and the parameter values ​​of the fluctuation parameters that meet the preset conditions are greater than the third threshold, a warning message is generated.

[0073] It should be noted that, since the device data includes multiple types, the third threshold is set according to different types of device data and is not completely the same.

[0074] Exemplarily, the second threshold is set to 2. If the fluctuation amplitude of the DC voltage of the first network device is 18, which is greater than the amplitude threshold of 10; the fluctuation trends are different; the fluctuation duration is 100S, which is greater than the time threshold of 60S; the fluctuation trend similarity is 80%, which is greater than the similarity threshold of 60%, then the fluctuation parameters that meet the preset conditions include the fluctuation amplitude, the fluctuation duration and the fluctuation trend similarity, and the number is 3, which is greater than the second threshold of 2; and the third thresholds of the fluctuation amplitude, the fluctuation duration and the fluctuation trend similarity are set to 15, 80S, and 70%, respectively. The fluctuation parameters that meet the preset conditions in the DC current of the first network device are all greater than their respective third thresholds. After comprehensive judgment, the warning conditions are met, and thus a warning message is generated.

[0075] It should be noted that the above-mentioned amplitude threshold, time threshold, similarity threshold, second threshold and third threshold can all be set to other values, and the preset condition of the fluctuation trend can also be set to be greater than a fixed value, which is not specifically limited in the embodiments of the present application.

[0076] In some embodiments, after the warning information is generated, the warning information can also be sent to a monitoring center, and the monitoring center generates a processing strategy based on the warning information, and then sends the processing strategy to the terminal device for processing by operation and maintenance personnel.

[0077] Exemplarily, when the fluctuation parameter of the real-time device data of the first network device meets the preset condition, the early warning information of the first network device is generated. At this time, the early warning information of the first network device is sent to the monitoring center, and the monitoring center generates a work order for equipment maintenance of the first network device and sends it to the terminal device of the operation and maintenance personnel. After receiving the work order, the operation and maintenance personnel can perform maintenance on the first network device, and can solve the problem of abnormal operation status before the first network device actually fails.

[0078] The present application also provides an equipment monitoring and early warning device, Figure 5 This is a schematic diagram of the structure of the equipment monitoring and early warning device provided in the embodiment of the present application. Figure 5As shown, the equipment monitoring and early warning device includes: a data acquisition module 501, which is configured to: acquire real-time equipment data of network equipment and historical equipment data of network equipment; wherein the historical equipment data is the equipment data within a preset time before a failure occurs in the historical operation of the network equipment, and the data type of the real-time equipment data is the same as that of the historical equipment data; a deviation calculation module 502, which is configured to: calculate the deviation between the real-time equipment data and the historical equipment data; a judgment module 503, which is configured to: if the deviation between the real-time equipment data and the historical equipment data is less than a first threshold, then acquire standard data of the network equipment; wherein the standard data is the data when the network equipment is operating normally, and the data type of the standard data is the same as that of the real-time equipment data; a fluctuation parameter calculation module 504, which is configured to: calculate the fluctuation parameter of the real-time equipment data according to the real-time equipment data and the standard data; and a warning information generation module 505, which is configured to: generate warning information if the fluctuation parameter meets the preset conditions.

[0079] An embodiment of the present application further provides an electronic device, comprising: a memory for storing a computer program; and a processor for executing the computer program to implement the steps of any one of the methods in the first aspect. Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Figure 6 As shown, the electronic device includes a processor 601, at least one communication bus 602, a user interface 603, at least one external communication interface 604 and a memory 605. The communication bus 602 is configured to realize the connection and communication between these components. The user interface 603 may include a display screen, and the external communication interface 604 may include a standard wired interface and a wireless interface. The memory 605 stores a computer program. The processor 601 is used to execute the computer program stored in the memory 605.

[0080] It can be seen from the above technical scheme that the present application provides an equipment monitoring and early warning method, device and electronic device, the method comprising: obtaining real-time equipment data and historical equipment data of a network device; wherein the historical equipment data is equipment data within a preset time before a failure occurs in a historical operation of the network device, and the data type of the real-time equipment data is the same as that of the historical equipment data; calculating the deviation between the real-time equipment data and the historical equipment data; if the deviation between the real-time equipment data and the historical equipment data is less than a first threshold, obtaining standard data of the network device; wherein the standard data is data when the network device is operating normally, and the data type of the standard data is the same as that of the real-time equipment data; calculating fluctuation parameters of the real-time equipment data based on the real-time equipment data and the standard data; if the fluctuation parameters meet the preset conditions, generating early warning information.

[0081] In the method, by calculating the deviation between the real-time device data of the network device and the historical device data of the network device that failed during its historical operation, possible fault information of the network device can be predicted; then the fluctuation parameters of the real-time device data are calculated, and by making a comprehensive judgment on the fluctuation parameters, early warning information is generated in advance, and early warning of the alarm information that may be generated by the network device is issued so that timely adjustments can be made to improve the overall operation and maintenance efficiency.

[0082] Similar parts between the embodiments provided in this application can be referenced to each other. The specific implementation methods provided above are only a few examples under the general concept of this application and do not constitute a limitation on the protection scope of this application. For those skilled in the art, any other implementation methods expanded based on the scheme of this application without creative work belong to the protection scope of this application.

Claims

1. A device monitoring and early warning method, characterized in that: The method comprises: Acquire real-time device data and historical device data of a network device; wherein the historical device data is device data within a preset time before a failure occurs in the historical operation of the network device, and the data types of the real-time device data and the historical device data are the same; Calculating the deviation between the real-time device data and the historical device data; If the deviation between the real-time device data and the historical device data is less than a first threshold, acquiring standard data of the network device; wherein the standard data is data when the network device operates normally, and the data type of the standard data is the same as that of the real-time device data; Calculating a fluctuation parameter of the real-time device data according to the real-time device data and the standard data; If the fluctuation parameter meets the preset conditions, a warning message is generated.

2. The equipment monitoring and early warning method according to claim 1 is characterized in that: The fluctuation parameter of the real-time device data includes the fluctuation amplitude of the real-time device data, and the calculation of the fluctuation parameter of the real-time device data according to the real-time device data and the standard data includes: Calculating the deviation between the real-time device data and the standard data; Based on the deviation between the real-time device data and the standard data, the fluctuation range of the real-time device data is determined.

3. The equipment monitoring and early warning method according to claim 2 is characterized in that: The fluctuation parameter of the real-time device data includes the fluctuation trend of the real-time device data, and the calculation of the fluctuation parameter of the real-time device data according to the real-time device data and the standard data further includes: Based on obtaining the deviation amount between at least two of the plurality of real-time device data and the standard data at preset time intervals, the fluctuation trend of the real-time device data is determined.

4. The equipment monitoring and early warning method according to claim 3 is characterized in that: The determining the fluctuation trend of the real-time device data based on obtaining the deviation between at least two of the plurality of real-time device data and the standard data at a preset time interval comprises: respectively determining the deviation directions of the at least two real-time device data relative to the standard data; If the deviation directions of the at least two real-time device data relative to the standard data are the same, it is marked as the same fluctuation trends; If the deviation directions of the at least two real-time device data relative to the standard data are different, it is marked as the fluctuation trends are different.

5. The equipment monitoring and early warning method according to claim 4 is characterized in that: The fluctuation parameter of the real-time device data includes the duration of the fluctuation of the real-time device data, and the calculation of the fluctuation parameter of the real-time device data according to the real-time device data and the standard data further includes: Acquire fluctuation trends of at least two of the real-time device data among the plurality of real-time device data; If the fluctuation trends are the same, the fluctuation duration is determined based on the time interval for obtaining at least two real-time device data with the same fluctuation trend, and the fluctuation duration is obtained by adding the time interval for obtaining at least two real-time device data with the same fluctuation trend.

6. The equipment monitoring and early warning method according to claim 5 is characterized in that: The fluctuation parameter of the real-time device data includes the fluctuation trend similarity of the real-time device data, and the calculation of the fluctuation parameter of the real-time device data according to the real-time device data and the standard data further includes: Acquire a first fluctuation trend of the real-time device data, and acquire a second fluctuation trend of the historical device data; The similarity between the first fluctuation trend and the second fluctuation trend is calculated to obtain the fluctuation trend similarity of the real-time device data.

7. The equipment monitoring and early warning method according to claim 6 is characterized in that: The preset condition includes at least one of the following: The fluctuation amplitude is greater than the amplitude threshold; The fluctuation trends are the same; The duration of the fluctuation is greater than the time threshold; The fluctuation trend similarity is greater than a similarity threshold; If the fluctuation parameter meets the preset condition, generating warning information includes: If the fluctuation parameter satisfies all the preset conditions, the warning information is generated; or, if the fluctuation parameter satisfies at least one of the preset conditions, the number and parameter values ​​of the fluctuation parameters that have satisfied the preset conditions are obtained; If the number of the fluctuation parameters that have satisfied the preset condition is greater than a second threshold, and the parameter value of the fluctuation parameters that have satisfied the preset condition is greater than a third threshold, the warning information is generated.

8. The equipment monitoring and early warning method according to claim 1 is characterized in that: After the step of generating warning information if the fluctuation parameter meets the preset condition, the method further includes: Sending the warning information to a monitoring center; The monitoring center is controlled to generate a processing strategy according to the early warning information, and the processing strategy is sent to the terminal device.

9. An equipment monitoring and early warning device, characterized in that: include: A data acquisition module is configured to: acquire real-time device data of a network device and historical device data of the network device; wherein the historical device data is device data of the network device within a preset time before a failure occurs during a historical operation, and the real-time device data and the historical device data have the same data type; The deviation calculation module is configured to: calculate the deviation between the real-time device data and the historical device data; The judgment module is configured to: if the deviation between the real-time device data and the historical device data is less than a first threshold, obtain the standard data of the network device; wherein the standard data is the data when the network device is operating normally, and the data type of the standard data is the same as that of the real-time device data; A fluctuation parameter calculation module is configured to: calculate the fluctuation parameter of the real-time device data according to the real-time device data and the standard data; The warning information generation module is configured to generate warning information if the fluctuation parameter meets the preset conditions.

10. An electronic device, characterized in that: include: one or more processors; a memory configured to store one or more programs; Wherein, when the one or more programs are executed by the one or more processors, the one or more processors implement the equipment monitoring and early warning method according to any one of claims 1-8.

Images