CN114168444A - Dynamic operation and maintenance repair reporting model based on monitoring big data - Google Patents
Dynamic operation and maintenance repair reporting model based on monitoring big data Download PDFInfo
- Publication number
- CN114168444A CN114168444A CN202111530596.2A CN202111530596A CN114168444A CN 114168444 A CN114168444 A CN 114168444A CN 202111530596 A CN202111530596 A CN 202111530596A CN 114168444 A CN114168444 A CN 114168444A
- Authority
- CN
- China
- Prior art keywords
- monitoring
- data
- monitoring item
- item
- historical
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 185
- 238000012423 maintenance Methods 0.000 title claims abstract description 40
- 230000008439 repair process Effects 0.000 title claims abstract description 20
- 238000012549 training Methods 0.000 claims abstract description 21
- 238000012360 testing method Methods 0.000 claims abstract description 19
- 230000002159 abnormal effect Effects 0.000 claims abstract description 17
- 238000004458 analytical method Methods 0.000 claims abstract description 7
- 230000005856 abnormality Effects 0.000 claims abstract description 4
- 238000009499 grossing Methods 0.000 claims description 22
- 238000000034 method Methods 0.000 claims description 16
- 230000001932 seasonal effect Effects 0.000 claims description 8
- 101001095088 Homo sapiens Melanoma antigen preferentially expressed in tumors Proteins 0.000 claims description 5
- 102100037020 Melanoma antigen preferentially expressed in tumors Human genes 0.000 claims description 5
- 238000002790 cross-validation Methods 0.000 claims description 5
- 230000008569 process Effects 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims description 2
- 238000012300 Sequence Analysis Methods 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000007429 general method Methods 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/34—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment
- G06F11/3447—Performance evaluation by modeling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/34—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment
- G06F11/3452—Performance evaluation by statistical analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/34—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment
- G06F11/3466—Performance evaluation by tracing or monitoring
- G06F11/3476—Data logging
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/34—Recording or statistical evaluation of computer activity, e.g. of down time, of input/output operation ; Recording or statistical evaluation of user activity, e.g. usability assessment
- G06F11/3466—Performance evaluation by tracing or monitoring
- G06F11/3495—Performance evaluation by tracing or monitoring for systems
Landscapes
- Engineering & Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Hardware Design (AREA)
- Quality & Reliability (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Probability & Statistics with Applications (AREA)
- Debugging And Monitoring (AREA)
- Alarm Systems (AREA)
Abstract
The invention discloses a dynamic operation and maintenance repair reporting model based on monitoring big data, which comprises the following steps: s1) acquiring historical monitoring data of the monitoring items, wherein the historical monitoring data is divided into a training set and a test set; s2) establishing a Holt-Winters model of the monitoring item by using the historical monitoring data; s3) predicting future data according to the Holt-Winters model of the monitoring item, and determining an alarm threshold value interval of the monitoring item; s4) carrying out threshold analysis on the actual monitoring data based on the alarm threshold interval of the monitoring item, and judging whether the monitoring item is abnormal or not; and if the abnormality occurs, sending alarm information to the system. The dynamic operation and maintenance repair reporting model based on the big monitoring data predicts and dynamically adjusts the threshold value based on the historical data, and solves the problems that the existing operation and maintenance system scheme is poor in timeliness and difficult to dynamically adjust the alarm threshold value according to the actual situation due to the fact that the fixed threshold value is set based on manual experience.
Description
Technical Field
The invention relates to the technical field of system operation and maintenance, in particular to a dynamic operation, maintenance and repair model based on monitoring big data.
Background
The system operation and maintenance pay attention to guarantee the normal operation of the system, and the system operation and maintenance has two meanings of operation and maintenance. With the rapid development of various hardware and software, the system structure is more and more complex, the operation and maintenance difficulty is more and more high, and the requirements on operation and maintenance personnel are higher and higher. At present, the operation and maintenance of the system also depend on the experience of operation and maintenance personnel seriously, and for the operation and maintenance personnel with insufficient experience, configuration errors are easy to occur, and missing reports and false reports occur, so that great loss is caused.
In view of the above problems, a dynamic operation and maintenance repair reporting model based on big monitoring data is needed.
Disclosure of Invention
The invention aims to provide a dynamic operation and maintenance repair reporting model based on big monitoring data, which predicts and dynamically adjusts a threshold value based on historical data and solves the problems that the existing operation and maintenance system scheme sets a fixed threshold value based on manual experience, has poor timeliness and is difficult to dynamically adjust an alarm threshold value according to actual conditions.
In order to achieve the purpose, the invention provides the following scheme:
a dynamic operation and maintenance repair reporting model based on monitoring big data comprises the following steps:
s1) obtaining historical monitoring data of the monitoring items, wherein the historical monitoring data is divided into a training set and a testing set;
s2) establishing a Holt-Winters model of the monitoring item by utilizing the historical monitoring data;
s3) predicting future data according to the Holt-Winters model of the monitoring item, and determining an alarm threshold interval of the monitoring item;
s4) carrying out threshold analysis on the actual monitoring data based on the alarm threshold interval of the monitoring item, and judging whether the monitoring item is abnormal or not; and if the abnormality occurs, sending alarm information to the system.
Optionally, in step S1), the obtaining of the historical monitoring data of the monitoring item, where the historical monitoring data is divided into training set data and test set data, specifically includes:
s101) determining a required monitoring host and a monitoring item of the monitoring host, and acquiring a key value and a monitoring item ID corresponding to the monitoring item;
s102) judging the historical data type corresponding to the monitoring item, and inquiring a data table corresponding to the data type in a Zabbix database through the name of the monitoring host and a key value to obtain the historical data of the monitoring item;
s103) dividing the acquired historical data of the monitoring item into a training set and a test set, wherein the test set is the data of the latest h hour, and the rest data is the training set.
Optionally, in step S2), establishing a Holt-Winters model of the monitoring item by using the historical monitoring data specifically includes:
s201) initializing a horizontal smoothing value L0Trend smoothed value P0And seasonal smooth value SkThe calculation formulas are respectively as follows:
wherein: t is the season length; y (i) is the data value of the monitoring item at the moment i; y (T + i) is a data value of the monitoring item at the moment i in the next season; s is the number of seasons,n is the number of the historical time sequence data of the monitoring item;
s202) fitting a Holt-Winters model of a monitoring item by using training set data, setting initial values of a horizontal smoothing coefficient alpha, a trend smoothing coefficient beta and a seasonal smoothing coefficient gamma, and obtaining an optimal smoothing parameter by using an average absolute percentage error MAPE as an index by adopting a cross-validation method;
s203) inputting the optimal smooth parameters, generating an optimal Holt-Winters model of the monitoring item, fixing the model parameters and storing the optimal Holt-Winters model of the current monitoring item.
Optionally, in step S3), the predicting future data according to the Holt-Winters model of the monitoring item, and determining the alarm threshold interval of the monitoring item specifically include:
s301) calculating monitoring item prediction data at each moment in a fixed time interval by using an optimal Holt-Winters model;
s302) establishing a confidence interval of the monitoring item prediction data at each moment by using a Brutlag algorithm:
wherein: m is a scale factor; d predicting deviation; y istIs a predicted value at the time t;respectively an upper confidence bound and a lower confidence bound at the time t;
wherein: y ist-T、Respectively a predicted value and an actual value of the monitoring item data at the T-T moment;
s303) setting the created confidence interval as an alarm threshold interval for triggering the monitoring item.
Optionally, after step S303), the method further includes:
s304) re-executing the steps S301) to S303) for the next time interval, and obtaining the alarm threshold interval of the monitoring item at each moment in the next time interval.
Optionally, in step S4), performing threshold analysis on the actual monitoring data based on the alarm threshold interval of the monitoring item, and determining whether the monitoring item is abnormal specifically includes: when the value of the actual monitoring data is in a threshold interval, judging that the monitoring item is not abnormal; and when the value of the actual monitoring data exceeds the threshold interval, judging that the monitoring item is abnormal.
Optionally, the monitoring items include available memory in Zabbix, CPU idle time, CPU user utilization, free disk space, free index nodes, incoming network work traffic eth0, number of processes, processor load per second, and used disk space.
According to the specific embodiment provided by the invention, the invention discloses the following technical effects: the dynamic operation, maintenance and repair reporting model based on the big monitoring data, provided by the invention, comprises the steps of firstly obtaining historical monitoring index data from a Zabbix monitoring platform, and dividing each historical monitoring index data into a training set and a test set; secondly, using training set data as input of a Holt-Winters model, initializing a horizontal smooth value, a trend smooth value and a season smooth value of the Holt-Winters, calculating an optimal horizontal smooth coefficient, a trend smooth coefficient and a season smooth coefficient through cross validation, establishing the optimal Holt-Winters model, inputting a test set into the established model, and evaluating the accuracy of the model; finally, predicting data in a certain time period according to the selected optimal Holt-Winters model, dynamically determining a threshold interval of a monitoring index by using a predicted value and an algorithm of the model, judging the data exceeding the threshold interval as an abnormal value, and sending alarm information to a system; according to the invention, time sequence analysis is carried out according to the monitoring historical information, and a historical information model is established for realizing reasonable monitoring alarm threshold setting and dynamic updating of the threshold, improving the problem of false alarm and missing alarm of a visual operation and maintenance system and relieving the defect of serious dependence on operation and maintenance personnel; the algorithm provided by the invention combines a large amount of historical information obtained by Zabbix monitoring, analyzes a time sequence based on a Holt-Winters model, dynamically determines and updates a monitoring item threshold in real time, and gives an alarm to operation and maintenance personnel aiming at abnormal conditions; in a word, the invention solves the problems that the existing operation and maintenance system scheme sets a fixed threshold based on manual experience, has poor timeliness and is difficult to dynamically adjust the alarm threshold according to the actual situation.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings without inventive exercise.
Fig. 1 is a flowchart of a method for monitoring a dynamic operation, maintenance and repair reporting model based on big data according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The invention aims to provide a dynamic operation and maintenance repair reporting model based on big monitoring data, which predicts and dynamically adjusts a threshold value based on historical data and solves the problems that the existing operation and maintenance system scheme sets a fixed threshold value based on manual experience, has poor timeliness and is difficult to dynamically adjust an alarm threshold value according to actual conditions.
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in further detail below.
Exponential smoothing is a classical prediction method framework that can generate reliable prediction results quickly and is applicable to a wide range of time series, and based on this great advantage, plays an important role in industrial applications, thus also motivating some very successful prediction methods. Based on the framework, students Holt and Winters expand the exponential smoothing method for multiple times, and a Holt-Winters model is provided for further capturing seasonal factors in time series prediction and improving prediction precision. The Holt-Winters model comprises a prediction equation and three smoothing equations, namely a horizontal smoothing equation, a trend smoothing equation and a seasonal smoothing equation, which jointly form a model for time series modeling.
Zabbix is a highly sophisticated network monitoring solution that can monitor numerous network parameters and the health and integrity of servers. Zabbix uses a flexible alert mechanism that allows users to configure email-based alerts for almost any event, allowing users to quickly respond to server problems. The ZabbixAPI provides a programming interface for Zabbix, is used for batch operation, third-party software integration and the like, and can conveniently acquire monitoring history information. In the basic Zabbix scheme, an alarm mechanism mainly depends on a manually set threshold or condition, the adaptability is limited, the dependence on manual experience is strong, and the existence of a Zabbix programming interface provides possibility for a user to perform data analysis modeling based on monitoring historical information and construct an automatic and intelligent alarm method.
As shown in fig. 1, the dynamic operation and maintenance repair model based on big monitoring data provided in the embodiment of the present invention includes the following steps:
s1) obtaining historical monitoring data of the monitoring items, wherein the historical monitoring data is divided into a training set and a testing set; in the embodiment, 10004 pieces of historical data are shared, wherein 9884 pieces of training set data and 120 pieces of test set data are shared;
s2) establishing a Holt-Winters model of the monitoring item by utilizing the historical monitoring data;
s3) predicting future data according to the Holt-Winters model of the monitoring item, and determining an alarm threshold interval of the monitoring item;
s4) carrying out threshold analysis on the actual monitoring data based on the alarm threshold interval of the monitoring item, and judging whether the monitoring item is abnormal or not; and if the abnormality occurs, sending alarm information to the system.
Step S1), the obtaining of the historical monitoring data of the monitoring item, the historical monitoring data being divided into training set data and test set data, specifically includes:
s101) determining a required monitoring host and a monitoring item of the monitoring host, and acquiring a key value and a monitoring item ID corresponding to the monitoring item;
s102) judging the historical data type corresponding to the monitoring item, and inquiring a data table corresponding to the data type in a Zabbix database through the name of the monitoring host and a key value to obtain the historical data of the monitoring item;
s103) dividing the acquired historical data of the monitoring item into a training set and a test set, wherein the test set is the data of the latest h hour, and the rest data is the training set.
Step S2), establishing a Holt-Winters model of the monitoring item by using the historical monitoring data, specifically comprising:
s201) initializing a horizontal smoothing value L0Trend smoothed value P0And seasonal smooth value SkThe Holt-Winters algorithm needs to set an initial value when a first round of prediction is started, the initial value has a large influence on the initial stage of a time sequence, and the influence of the initial value on the prediction is gradually reduced after iteration of a plurality of time step lengths, and a general method for selecting the initial value is as follows:
wherein: t is the season length, wherein the value of T is 180; y (i) is the data value of the monitoring item at the moment i; y (T + i) is a data value of the monitoring item at the moment i in the next season; s is the number of seasons,n is the number of the historical time sequence data of the monitoring item, wherein the value of n is 9884;
s202) fitting a Holt-Winters model of a monitoring item by using training set data, setting a horizontal smoothing coefficient alpha, setting initial values of a trend smoothing coefficient beta and a seasonal smoothing coefficient gamma as [0,0,0], setting a value range as (0, 1), obtaining an optimal smoothing parameter by using an average absolute percentage error MAPE as an index by adopting a cross-over cross-validation method, wherein the obtained index value of the MAPE is 2.66%, and the optimized smoothing systems are respectively alpha-0.0148, beta-0.0007 and gamma-0.2589;
s203) inputting the optimal smooth parameters, generating an optimal Holt-Winters model of the monitoring item, fixing the model parameters and storing the optimal Holt-Winters model of the current monitoring item; inputting 120 pieces of test set data into the model, outputting a predicted value, and comparing the predicted value with the prediction precision of other method models, and the result shows that as shown in table 1: the model is utilized to calculate the MAPE index value to be 2.54 percent, and the verification model has higher precision.
TABLE 1 Holt-Winters vs. prediction accuracy of other method models
Step S3), predicting future data according to the Holt-Winters model of the monitoring item, and determining an alarm threshold interval of the monitoring item, wherein the step S3) specifically comprises the following steps:
s301) calculating monitoring item prediction data at each moment in a fixed time interval by using an optimal Holt-Winters model; the fixed time interval here is 2 hours, totaling 120 pieces of data;
s302) establishing a confidence interval of the monitoring item prediction data at each moment by using a Brutlag algorithm:
wherein: m is a scale factor, wherein the value of m is 1.96; d predicting deviation; y istIs a predicted value at the time t;respectively representing a confidence upper bound and a confidence lower bound at the moment t;
wherein: y ist-T、Respectively a predicted value and an actual value of the monitoring item data at the T-T moment;
s303) confidence interval to be createdThe alarm threshold interval set as the trigger monitoring item is, for example, t 9885, and the threshold interval is calculated as (68.46, 76.89).
Optionally, after step S303), the method further includes:
s304) updating historical data by using 120 actual monitoring data corresponding to the current round of prediction, replacing 120 pieces of data with the earliest time in the historical data, and using the data for the next round of updating of the model parameters, namely re-executing the steps S301) to S303) aiming at the next time interval to obtain the alarm threshold interval of the monitoring item at each moment in the next time interval.
In step S4), the performing threshold analysis on the actual monitoring data based on the alarm threshold interval of the monitoring item to determine whether the monitoring item is abnormal specifically includes: when the value of the actual monitoring data is in a threshold interval, judging that the monitoring item is not abnormal; and when the value of the actual monitoring data exceeds the threshold interval, judging that the monitoring item is abnormal.
The monitoring items comprise available memory in Zabbix, CPU idle time, CPU user utilization rate, free disk space, free index nodes, incoming network work flow eth0, process number, processor load per second and used disk space.
The dynamic operation, maintenance and repair reporting model based on the big monitoring data, provided by the invention, comprises the steps of firstly obtaining historical monitoring index data from a Zabbix monitoring platform, and dividing each historical monitoring index data into a training set and a test set; secondly, using training set data as input of a Holt-Winters model, initializing a horizontal smooth value, a trend smooth value and a season smooth value of the Holt-Winters, calculating an optimal horizontal smooth coefficient, a trend smooth coefficient and a season smooth coefficient through cross validation, establishing the optimal Holt-Winters model, inputting a test set into the established model, and evaluating the accuracy of the model; finally, predicting data in a certain time period according to the selected optimal Holt-Winters model, dynamically determining a threshold interval of a monitoring index by using a predicted value and an algorithm of the model, judging the data exceeding the threshold interval as an abnormal value, and sending alarm information to a system; according to the invention, time sequence analysis is carried out according to the monitoring historical information, and a historical information model is established for realizing reasonable monitoring alarm threshold setting and dynamic updating of the threshold, improving the problem of false alarm and missing alarm of a visual operation and maintenance system and relieving the defect of serious dependence on operation and maintenance personnel; the algorithm provided by the invention combines a large amount of historical information obtained by Zabbix monitoring, analyzes a time sequence based on a Holt-Winters model, dynamically determines and updates a monitoring item threshold in real time, and gives an alarm to operation and maintenance personnel aiming at abnormal conditions; in a word, the invention solves the problems that the existing operation and maintenance system scheme sets a fixed threshold based on manual experience, has poor timeliness and is difficult to dynamically adjust the alarm threshold according to the actual situation.
The principles and embodiments of the present invention have been described herein using specific examples, which are provided only to help understand the method and the core concept of the present invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, the specific embodiments and the application range may be changed. In view of the above, the present disclosure should not be construed as limiting the invention.
Claims (7)
1. A dynamic operation and maintenance repair reporting model based on monitoring big data is characterized by comprising the following steps:
s1) obtaining historical monitoring data of the monitoring items, wherein the historical monitoring data is divided into a training set and a testing set;
s2) establishing a Holt-Winters model of the monitoring item by utilizing the historical monitoring data;
s3) predicting future data according to the Holt-Winters model of the monitoring item, and determining an alarm threshold interval of the monitoring item;
s4) carrying out threshold analysis on the actual monitoring data based on the alarm threshold interval of the monitoring item, and judging whether the monitoring item is abnormal or not; and if the abnormality occurs, sending alarm information to the system.
2. The monitoring big data-based dynamic operation, maintenance and repair reporting model according to claim 1, wherein step S1) is performed to obtain historical monitoring data of the monitoring item, and the historical monitoring data is divided into training set data and test set data, which specifically includes:
s101) determining a required monitoring host and a monitoring item of the monitoring host, and acquiring a key value and a monitoring item ID corresponding to the monitoring item;
s102) judging the historical data type corresponding to the monitoring item, and inquiring a data table corresponding to the data type in a Zabbix database through the name of the monitoring host and a key value to obtain the historical data of the monitoring item;
s103) dividing the acquired historical data of the monitoring item into a training set and a test set, wherein the test set is the data of the latest h hour, and the rest data is the training set.
3. The monitoring big data-based dynamic operation, maintenance and repair reporting model according to claim 2, wherein step S2) of establishing a Holt-Winters model of a monitoring item by using the historical monitoring data specifically comprises:
s201) initializing a horizontal smoothing value L0Trend smoothed value P0And seasonal smooth value SkThe calculation formulas are respectively as follows:
wherein: t is the season length; y (i) is the data value of the monitoring item at the moment i; y (T + i) is a data value of the monitoring item at the moment i in the next season; s is the number of seasons,n is the number of the historical time sequence data of the monitoring item;
s202) fitting a Holt-Winters model of a monitoring item by using training set data, setting initial values of a horizontal smoothing coefficient alpha, a trend smoothing coefficient beta and a seasonal smoothing coefficient gamma, and obtaining an optimal smoothing parameter by using an average absolute percentage error MAPE as an index by adopting a cross-validation method;
s203) inputting the optimal smooth parameters, generating an optimal Holt-Winters model of the monitoring item, fixing the model parameters and storing the optimal Holt-Winters model of the current monitoring item.
4. The monitoring big data-based dynamic operation and maintenance repair reporting model according to claim 3, wherein step S3) includes predicting future data according to the Holt-Winters model of the monitoring item, and determining an alarm threshold interval of the monitoring item, specifically including:
s301) calculating monitoring item prediction data at each moment in a fixed time interval by using an optimal Holt-Winters model;
s302) establishing a confidence interval of the monitoring item prediction data at each moment by using a Brutlag algorithm:
wherein: m is a scale factor; d predicting deviation; y istIs a predicted value at the time t;respectively an upper confidence bound and a lower confidence bound at the time t;
wherein: y ist-T、Respectively a predicted value and an actual value of the monitoring item data at the T-T moment;
s303) setting the created confidence interval as an alarm threshold interval for triggering the monitoring item.
5. The dynamic operation and maintenance repair reporting model based on big monitoring data as claimed in claim 4, further comprising after step S303):
s304) re-executing the steps S301) to S303) for the next time interval, and obtaining the alarm threshold interval of the monitoring item at each moment in the next time interval.
6. The monitoring big data-based dynamic operation, maintenance and repair reporting model according to claim 4, wherein in step S4), the alarm threshold interval based on the monitoring item performs threshold analysis on the actual monitoring data to determine whether the monitoring item is abnormal, specifically including: when the value of the actual monitoring data is in a threshold interval, judging that the monitoring item is not abnormal; and when the value of the actual monitoring data exceeds the threshold interval, judging that the monitoring item is abnormal.
7. The monitoring big data-based dynamic operation and maintenance repair reporting model according to any one of claims 1-6, wherein the monitoring items comprise available memory in Zabbix, CPU idle time, CPU user utilization, free disk space, free index nodes, incoming network work traffic eth0, number of processes, processor load per second, and used disk space.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111530596.2A CN114168444B (en) | 2021-12-14 | 2021-12-14 | Dynamic operation maintenance report repairing method based on monitoring big data |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111530596.2A CN114168444B (en) | 2021-12-14 | 2021-12-14 | Dynamic operation maintenance report repairing method based on monitoring big data |
Publications (2)
Publication Number | Publication Date |
---|---|
CN114168444A true CN114168444A (en) | 2022-03-11 |
CN114168444B CN114168444B (en) | 2024-06-04 |
Family
ID=80486601
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111530596.2A Active CN114168444B (en) | 2021-12-14 | 2021-12-14 | Dynamic operation maintenance report repairing method based on monitoring big data |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114168444B (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114915542A (en) * | 2022-04-28 | 2022-08-16 | 远景智能国际私人投资有限公司 | Data abnormity warning method, device, equipment and storage medium |
CN115096359A (en) * | 2022-06-17 | 2022-09-23 | 北京航空航天大学 | Metal roof health monitoring system and method |
CN115311829A (en) * | 2022-10-12 | 2022-11-08 | 山东未来网络研究院(紫金山实验室工业互联网创新应用基地) | Accurate alarm method and system based on mass data |
CN115358430A (en) * | 2022-09-14 | 2022-11-18 | 哈尔滨菲桐匠心科技有限公司 | Operation and maintenance information management system and method based on big data |
CN115766513A (en) * | 2022-10-25 | 2023-03-07 | 中邮科通信技术股份有限公司 | Anomaly detection method and device |
CN117559633A (en) * | 2023-11-03 | 2024-02-13 | 华能国际电力股份有限公司河北清洁能源分公司 | Power operation and maintenance regulation and control system based on energy efficiency abnormality |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105844543A (en) * | 2016-04-07 | 2016-08-10 | 国网天津市电力公司 | Automation operation management system for power enterprise information system |
CN109491289A (en) * | 2018-11-15 | 2019-03-19 | 国家计算机网络与信息安全管理中心 | A kind of dynamic early-warning method and device for data center's dynamic environment monitoring |
CN110782045A (en) * | 2019-10-17 | 2020-02-11 | 成都四方伟业软件股份有限公司 | Method and device for generating dynamic threshold of operation and maintenance alarm system |
CN111082998A (en) * | 2019-12-30 | 2020-04-28 | 上海数熙科技有限公司 | Architecture system of operation and maintenance monitoring campus convergence layer |
CN112926749A (en) * | 2020-12-30 | 2021-06-08 | 国网宁夏电力有限公司信息通信公司 | Intelligent power grid information equipment monitoring system and method |
-
2021
- 2021-12-14 CN CN202111530596.2A patent/CN114168444B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105844543A (en) * | 2016-04-07 | 2016-08-10 | 国网天津市电力公司 | Automation operation management system for power enterprise information system |
CN109491289A (en) * | 2018-11-15 | 2019-03-19 | 国家计算机网络与信息安全管理中心 | A kind of dynamic early-warning method and device for data center's dynamic environment monitoring |
CN110782045A (en) * | 2019-10-17 | 2020-02-11 | 成都四方伟业软件股份有限公司 | Method and device for generating dynamic threshold of operation and maintenance alarm system |
CN111082998A (en) * | 2019-12-30 | 2020-04-28 | 上海数熙科技有限公司 | Architecture system of operation and maintenance monitoring campus convergence layer |
CN112926749A (en) * | 2020-12-30 | 2021-06-08 | 国网宁夏电力有限公司信息通信公司 | Intelligent power grid information equipment monitoring system and method |
Non-Patent Citations (1)
Title |
---|
司占军;肖桐;: "校园网络舆情监控平台的设计与实现", 电子世界, no. 14, 30 July 2014 (2014-07-30) * |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114915542A (en) * | 2022-04-28 | 2022-08-16 | 远景智能国际私人投资有限公司 | Data abnormity warning method, device, equipment and storage medium |
CN115096359A (en) * | 2022-06-17 | 2022-09-23 | 北京航空航天大学 | Metal roof health monitoring system and method |
CN115358430A (en) * | 2022-09-14 | 2022-11-18 | 哈尔滨菲桐匠心科技有限公司 | Operation and maintenance information management system and method based on big data |
CN115311829A (en) * | 2022-10-12 | 2022-11-08 | 山东未来网络研究院(紫金山实验室工业互联网创新应用基地) | Accurate alarm method and system based on mass data |
CN115311829B (en) * | 2022-10-12 | 2023-02-03 | 山东未来网络研究院(紫金山实验室工业互联网创新应用基地) | Accurate alarm method and system based on mass data |
CN115766513A (en) * | 2022-10-25 | 2023-03-07 | 中邮科通信技术股份有限公司 | Anomaly detection method and device |
CN117559633A (en) * | 2023-11-03 | 2024-02-13 | 华能国际电力股份有限公司河北清洁能源分公司 | Power operation and maintenance regulation and control system based on energy efficiency abnormality |
Also Published As
Publication number | Publication date |
---|---|
CN114168444B (en) | 2024-06-04 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN114168444A (en) | Dynamic operation and maintenance repair reporting model based on monitoring big data | |
CN111459778B (en) | Operation and maintenance system abnormal index detection model optimization method, device and storage medium | |
CN108199795B (en) | A kind of monitoring method and device of equipment state | |
CN110095744B (en) | Error prediction method for electronic transformer | |
Girard et al. | Gaussian process priors with uncertain inputs application to multiple-step ahead time series forecasting | |
CN106886481B (en) | Static analysis and prediction method and device for system health degree | |
CN112862012A (en) | Operation and maintenance system abnormity early warning method, device and equipment based on LSTM model | |
CN111143102A (en) | Abnormal data detection method and device, storage medium and electronic equipment | |
US12092269B2 (en) | Method for troubleshooting potential safety hazards of compressor in smart gas pipeline network and internet of things system thereof | |
CN112734128A (en) | 7-day power load peak value prediction method based on optimized RBF | |
CN113486584B (en) | Method and device for predicting equipment failure, computer equipment and computer readable storage medium | |
CN114997607A (en) | Anomaly assessment early warning method and system based on engineering detection data | |
CN111624986A (en) | Case base-based fault diagnosis method and system | |
CN111176953A (en) | Anomaly detection and model training method thereof, computer equipment and storage medium | |
CN113469570A (en) | Information quality evaluation model construction method, device, equipment and storage medium | |
CN116187552A (en) | Abnormality detection method, computing device, and computer storage medium | |
CN114338348A (en) | Intelligent alarm method, device, equipment and readable storage medium | |
CN109409786A (en) | Method and system for evaluating reliability of power distribution network | |
CN112836843B (en) | Base station out-of-service alarm prediction method and device | |
CN111783883A (en) | Abnormal data detection method and device | |
CN116757352A (en) | Integrated platform health monitoring method, device, equipment and medium | |
CN108664696B (en) | Method and device for evaluating running state of water chiller | |
CN113486583B (en) | Method and device for evaluating health of equipment, computer equipment and computer readable storage medium | |
WO2023044019A1 (en) | Method and system for managing model updates for process models | |
CN115146997A (en) | Evaluation method and device based on power data, electronic equipment and storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
TA01 | Transfer of patent application right | ||
TA01 | Transfer of patent application right |
Effective date of registration: 20240509 Address after: Room B8110-1, Building 1, No. 43 Yanyang Road, Nankai District, Tianjin, 300000 Applicant after: Tianjin Zhuoyue xinzhongxin Longteng Technology Development Co.,Ltd. Country or region after: China Address before: No.9, 13th Street, economic and Technological Development Zone, Binhai New Area, Tianjin Applicant before: TIANJIN University OF SCIENCE AND TECHNOLOGY Country or region before: China |
|
GR01 | Patent grant | ||
GR01 | Patent grant |