CN112749071B - System and method for detecting health degree of application cluster - Google Patents
System and method for detecting health degree of application cluster Download PDFInfo
- Publication number
- CN112749071B CN112749071B CN202011609759.1A CN202011609759A CN112749071B CN 112749071 B CN112749071 B CN 112749071B CN 202011609759 A CN202011609759 A CN 202011609759A CN 112749071 B CN112749071 B CN 112749071B
- Authority
- CN
- China
- Prior art keywords
- performance data
- data
- abnormal
- application cluster
- local database
- 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.)
- Active
Links
- 230000036541 health Effects 0.000 title claims abstract description 52
- 238000000034 method Methods 0.000 title claims abstract description 22
- 238000001514 detection method Methods 0.000 claims abstract description 41
- 230000005856 abnormality Effects 0.000 claims abstract description 39
- 238000004364 calculation method Methods 0.000 claims abstract description 16
- 230000002159 abnormal effect Effects 0.000 claims description 48
- 230000003203 everyday effect Effects 0.000 claims description 8
- 208000025174 PANDAS Diseases 0.000 claims description 4
- 208000021155 Paediatric autoimmune neuropsychiatric disorders associated with streptococcal infection Diseases 0.000 claims description 4
- 240000004718 Panda Species 0.000 claims description 4
- 235000016496 Panda oleosa Nutrition 0.000 claims description 4
- 238000002372 labelling Methods 0.000 claims description 3
- 230000008520 organization Effects 0.000 claims description 3
- 230000004044 response Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 230000002547 anomalous effect Effects 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
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
- G06F11/3409—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 for performance assessment
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Quality & Reliability (AREA)
- General Physics & Mathematics (AREA)
- Computer Hardware Design (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Probability & Statistics with Applications (AREA)
- Debugging And Monitoring (AREA)
Abstract
The invention relates to a system and a method for detecting the health of an application cluster, wherein the method comprises the steps of initializing application cluster information to be monitored; the data acquisition unit acquires performance data generated by the APM tool and stores the performance data in the local database; the baseline calculation unit acquires a dynamic baseline according to the historical time sequence performance data in the local database; the abnormality detection unit detects abnormality of the real-time performance data in the local database; and the alarm unit judges the health degree of the application cluster according to the abnormality detection result of the abnormality detection unit and sends out alarm information. Compared with the prior art, the method and the device are based on the data acquisition unit, the dynamic baseline calculation unit, the anomaly detection unit, the alarm unit, the task scheduling unit and the local database, APM data of the application cluster are effectively stored, the health degree of the application cluster is obtained, the accuracy and the high efficiency of the health degree detection of the application cluster are improved, and the reliability of the health degree detection of the application cluster is improved.
Description
Technical Field
The invention relates to the field of application cluster health detection, in particular to a system and a method for detecting application cluster health.
Background
With the popularity of micro-service architecture, more and more IT projects are being developed with micro-service architecture. The integrity micro-service realizes decoupling among modules, and simultaneously meets the requirements of agile development of enterprises by the characteristics of independent deployment, rapid iteration and the like. However, with the increasing number of service modules, the call between services is more and more complex, and an application service call chain Analysis (APM) tool is needed to monitor the call condition and response performance of each application service.
Currently, more common APM tools are the Dapper, twitter zip of Pinpoint, google of Naver, the hawk eye of Naver, the CAT of the public criticizing, and so on.
Although the tool can well show the performance of each service and the calling relation among the services, the tool can alarm indexes such as transaction slow number, error reporting number and the like according to a user-defined threshold value. The following disadvantages still remain:
1. the setting of part of index alarm threshold depends on user experience and cannot be scientifically set;
2. according to the change of service pressure at different time points, partial performance indexes show a trend of dynamic change, and the existing tool lacks the capability of establishing a dynamic base line for the indexes;
3. the tolerance of the conventional threshold alarm to faults is low, and the false alarm rate is high.
Disclosure of Invention
The present invention is directed to a system and method for detecting the health of an application cluster, which overcomes the above-mentioned drawbacks of the prior art.
The aim of the invention can be achieved by the following technical scheme:
a system for detecting the health degree of an application cluster comprises a data acquisition unit, a dynamic baseline calculation unit, an anomaly detection unit, an alarm unit, a task scheduling unit and a local database,
the data acquisition unit is used for acquiring the performance data generated by the APM tool and storing the performance data into the local database,
the dynamic baseline calculation unit is used for generating a dynamic baseline according to the historical time sequence performance data in the local database,
the abnormality detection unit is used for detecting abnormality of the real-time performance data in the local database and labeling the real-time data with normal labels or abnormal labels,
the alarm unit judges the health degree of the application cluster according to the abnormal detection result of the abnormal detection unit and sends out alarm information,
the local database is used for storing performance data.
Preferably, the system further comprises a front-end display unit, wherein the front-end display unit is used for displaying the dynamic baseline and the health degree of each application cluster index in real time.
Preferably, the system further comprises a task scheduling unit for uniformly managing the tasks of data acquisition, dynamic baseline calculation, alarm polling check, data archiving and the like, and as a daemon, ensuring the normal operation of all the calculation modules.
A method for detecting the health of an application cluster, based on the system for detecting the health of the application cluster, comprising the following steps:
s1: initializing application cluster information to be monitored;
s2: the data acquisition unit acquires performance data generated by the APM tool and stores the performance data in the local database;
s3: the baseline calculation unit acquires a dynamic baseline according to the historical time sequence performance data in the local database;
s4: the abnormality detection unit detects abnormality of the real-time performance data in the local database;
s5: and the alarm unit judges the health degree of the application cluster according to the abnormality detection result of the abnormality detection unit and sends out alarm information.
Preferably, the step S1 specifically includes:
s101: synchronizing application cluster information of the accessed APM tool;
s102: and judging whether a dynamic baseline is established, if so, entering a step S2, otherwise, returning to the step S101.
Preferably, the step S2 specifically includes:
s201: acquiring an APM data source;
s201: carrying out slice statistics on the APM data source to obtain a data slice;
s202: obtaining tissue key performance index data according to the data slice;
s203: the organization key performance indicator data is stored to a local relational database.
Preferably, the step S3 specifically includes:
s301: reading historical timing performance data from a local database using a python pandas module;
s302: converting the historical time sequence performance data format into a Dataframe;
s303: judging whether the historical time sequence performance data has abnormal data or not, if so, removing the abnormal data and entering S304, otherwise, directly entering S304;
s304: calculating the mean value and the variance of the same time point every day in the historical time sequence performance data, and generating a dynamic base line according to the mean value and the variance of the same time point every day in the historical data;
s305: the dynamic baseline is written to a database.
Preferably, in the step S304, a dynamic baseline maximum value is generated by adding 2 times of variance to the average value of the historical time series performance data, and a dynamic baseline minimum value is generated by subtracting 2 times of variance from the average value of the historical time series performance data.
Preferably, the step S4 specifically includes:
s401: acquiring real-time performance data in a local database;
s402: judging whether the real-time performance data meets an abnormal rule, if so, marking an abnormal label on the real-time performance data, writing the abnormal label into a local database, and entering a step S6, otherwise, entering a step S403;
s403: judging whether the real-time performance data is abnormal or not according to an abnormality detection algorithm, if so, marking an abnormality label on the real-time performance data, writing the abnormality label into a local database, and if not, marking a normal label on the real-time performance data, writing the abnormality label into the local database.
Preferably, the step S5 specifically includes:
step S501: polling and checking all application clusters, judging whether the abnormal times of the key performance indexes in the appointed abnormal time threshold exceeds the abnormal times threshold, if so, judging that the health degree of the application clusters is abnormal and entering into S502, otherwise, judging that the health degree of the application clusters is healthy;
step S502: and generating and sending alarm information.
Preferably, the system further comprises a front-end display unit, wherein the front-end display unit is used for displaying the dynamic baseline and the health degree of each application cluster index in real time.
Preferably, the method further comprises step S6: the front end display unit displays the dynamic baseline and performance index data using an echartis chart.
The step S6 specifically comprises the following steps:
step S601: the user selects a service system and application cluster information to be checked;
step S602: selecting index information and time period information to be displayed;
step S603: the front end queries a back end database according to information input by a user, organizes data, and displays dynamic base line and abnormal point data through an echarties discount chart.
Compared with the prior art, the invention has the following advantages:
(1) The application cluster health degree detection system and method are based on the data acquisition unit, the dynamic baseline calculation unit, the anomaly detection unit, the alarm unit, the task scheduling unit and the local database, can effectively store APM data of the application clusters, realize scientific detection of the application cluster health degree, effectively improve the accuracy and the high efficiency of the application cluster health degree detection, normalize the health degree detection flow, and improve the reliability of the application cluster health degree detection;
(2) The abnormality detection unit introduces an abnormality detection algorithm, helps to establish alarm settings of various performance indexes without manual intervention, and effectively improves the accuracy and effect of abnormality detection;
(3) The invention provides a time sequence-based dynamic base line establishment, which utilizes a 2 sigma method to process historical time sequence performance data, establishes a dynamic base line, can judge and process current real-time data based on the historical time sequence performance data, and improves reliability of health judgment;
(4) According to the invention, the abnormality detection unit supports a user to formulate an alarm triggering rule according to the adjustment of the abnormality time threshold and the abnormality times threshold, thereby greatly improving the accuracy and the accuracy of the alarm and reducing the false alarm times;
(5) The invention utilizes the front-end display unit to selectively display the dynamic base line and the abnormal point data, thereby improving the operability and applicability of the system.
Drawings
FIG. 1 is a flow chart of the present invention;
FIG. 2 is a flow chart of step S2 of the present invention;
FIG. 3 is a flow chart of step S3 of the present invention;
fig. 4 is a flow chart of step S4 of the present invention.
Detailed Description
The invention will now be described in detail with reference to the drawings and specific examples. Note that the following description of the embodiments is merely an example, and the present invention is not intended to be limited to the applications and uses thereof, and is not intended to be limited to the following embodiments.
Examples
A system for detecting the health of an application cluster comprises a data acquisition unit, a dynamic baseline calculation unit, an anomaly detection unit, an alarm unit, a task scheduling unit and a local database.
Specifically, the data acquisition unit is used for acquiring performance data generated by the APM tool and storing the performance data in the local database. In this embodiment, the collection frequency and the sampling range of the performance data are set, and the data collection unit collects the historical performance data generated by the APM tool according to the formulated collection frequency and sampling range, and finally stores the historical performance data in the local database.
The dynamic baseline calculation unit is used for generating a dynamic baseline according to the historical time sequence performance data in the local database, generating the dynamic baseline according to the sampled historical time sequence data, and introducing a 2 sigma principle to compensate abnormal data so as to improve the accuracy of the baseline.
The abnormality detection unit is used for detecting abnormality of the real-time performance data in the local database and labeling normal labels or abnormal labels on the real-time data. In this embodiment, an isolated forest algorithm is used to perform anomaly detection on the sampled real-time data, and an important index for judging whether the current application cluster is healthy is generated.
The alarm unit is used for judging the health degree of the application cluster, sending alarm information according to the health degree, checking the health degree of the application cluster according to the designated health checking frequency and rule, and simultaneously counting key information of abnormal time periods of the cluster to generate alarm information to inform a user of attention.
The local database is used to store performance data.
The system also comprises a front-end display unit, wherein the front-end display unit is used for displaying the dynamic baseline and the health degree of each application cluster index in real time. In addition, the system also comprises a task scheduling unit which is used for uniformly managing the operations such as data acquisition, dynamic baseline calculation, alarm polling check, data archiving and the like and is used as a daemon to ensure the normal work of all calculation modules.
A method for detecting the health of an application cluster, based on the system for detecting the health of the application cluster, comprising the following steps:
s1: and initializing application cluster information to be monitored.
The step S1 specifically comprises the following steps:
s101: synchronizing application cluster information of the accessed APM tool;
s102: and judging whether a dynamic baseline is established, if so, entering a step S2, otherwise, returning to the step S101.
In this embodiment, whether to establish a dynamic baseline of the application cluster information is determined according to a preset dynamic baseline establishment determination rule.
S2: the data acquisition unit acquires performance data generated by the APM tool and stores the performance data in the local database.
As shown in fig. 2, step S2 specifically includes:
s201: acquiring an APM data source;
s201: carrying out slice statistics on the APM data source to obtain a data slice;
s202: obtaining tissue key performance index data according to the data slice;
s203: the organization key performance indicator data is stored to a local relational database.
In this embodiment, slice statistics is performed on APM data sources with granularity of five minutes, and key performance index data obtained according to data slicing includes a total response number, a slow number, an error number, a slow rate, an error rate, and a requested URL.
S3: the baseline calculation unit obtains a dynamic baseline according to historical time sequence performance data in the local database.
As shown in fig. 3, in step S3, the baseline calculating unit calculates a dynamic baseline according to the historical performance data of the application cluster, where the dynamic baseline is used for showing the response situation of the transaction in each period, and predicting the transaction situation at the corresponding time point of the next day, and specifically includes:
s301: reading historical timing performance data from a local database using a python pandas module;
s302: converting the historical time sequence performance data format into a Dataframe;
s303: judging whether the historical time sequence performance data has abnormal data or not, if so, removing the abnormal data and entering S304, otherwise, directly entering S304;
s304: calculating the maximum value, the minimum value and the variance of the same time point every day in the historical time sequence performance data, and generating a dynamic base line according to the maximum value, the minimum value and the variance of the same time point every day in the historical data;
s305: the dynamic baseline is written to a database.
In the step S304, a 2-fold variance is added to the average value of the historical time series performance data to generate a dynamic baseline maximum value, and a 2-fold variance is subtracted from the average value of the historical time series performance data to generate a dynamic baseline minimum value:
wherein x is max For a dynamic baseline maximum, x min The dynamic baseline minimum value is set to be,is the mean value, sigma 2 Is the variance.
S4: the abnormality detection unit performs abnormality detection on the real-time performance data in the local database.
As shown in fig. 4, S4 specifically includes:
s401: acquiring real-time performance data in a local database;
s402: judging whether the real-time performance data meets an abnormal rule, if so, marking an abnormal label on the real-time performance data, writing the abnormal label into a local database, and entering a step S6, otherwise, entering a step S403;
s403: judging whether the real-time performance data is abnormal or not according to an abnormality detection algorithm, if so, marking an abnormality label on the real-time performance data, writing the abnormality label into a local database, and if not, marking a normal label on the real-time performance data, writing the abnormality label into the local database.
In this embodiment, label values { normal ] corresponding to normal and abnormal labels are defined: 1, anomaly-1 }, and defining an anomaly rule, and judging whether the real-time performance data is anomalous or not by using an isolated forest algorithm in S403.
S5: and the alarm unit judges the health degree of the application cluster according to the abnormality detection result of the abnormality detection unit and sends out alarm information.
The step S5 specifically comprises the following steps:
step S501: polling and checking all application clusters, judging whether the abnormal times of the key performance indexes in the appointed abnormal time threshold exceeds the abnormal times threshold, if so, judging that the health degree of the application clusters is abnormal and entering into S502, otherwise, judging that the health degree of the application clusters is healthy;
step S502: and generating and sending alarm information.
In this embodiment, S5 includes:
s501: polling to check all application clusters, counting the situation that a certain index has abnormal labels for more than 2 times within the last 30 minutes, and if so, entering S502;
s502: and organizing alarm information, and informing a user of attention through channels such as mail, short message and the like.
In this embodiment, the system of the present invention further includes a front-end display unit, where the front-end display unit is configured to display, in real time, a dynamic baseline and a health degree of each application cluster index.
Correspondingly, the method of the invention further comprises the step S6: the front end display unit displays the dynamic baseline and performance index data using an echartis chart.
The step S6 specifically comprises the following steps:
step S601: the user selects a service system and application cluster information to be checked;
step S602: selecting index information and time period information to be displayed;
step S603: the front end queries a back end database according to information input by a user, organizes data, and displays dynamic base line and abnormal point data through an echarties discount chart.
The above embodiments are merely examples, and do not limit the scope of the present invention. These embodiments may be implemented in various other ways, and various omissions, substitutions, and changes may be made without departing from the scope of the technical idea of the present invention.
Claims (8)
1. A system for detecting the health degree of an application cluster is characterized by comprising a data acquisition unit, a dynamic baseline calculation unit, an abnormality detection unit, an alarm unit, a task scheduling unit and a local database,
the data acquisition unit is used for acquiring the performance data generated by the APM tool and storing the performance data into the local database,
the dynamic baseline calculation unit is used for generating a dynamic baseline according to the historical time sequence performance data in the local database,
the abnormality detection unit is used for detecting abnormality of the real-time performance data in the local database and labeling the real-time data with normal labels or abnormal labels,
the alarm unit is used for judging the health degree of the application cluster according to the abnormal detection result of the abnormal detection unit and sending out alarm information,
the local database is used to store performance data,
wherein the generation of the dynamic baseline comprises the following steps:
s301: reading historical timing performance data from a local database using a python pandas module;
s302: converting the historical time sequence performance data format into a Dataframe;
s303: judging whether the historical time sequence performance data has abnormal data or not, if so, removing the abnormal data and entering S304, otherwise, directly entering S304;
s304: calculating the mean value and the variance of the same time point every day in the historical time sequence performance data, and generating a dynamic base line according to the mean value and the variance of the same time point every day in the historical data;
s305: the dynamic baseline is written to a database,
in step S304, a dynamic baseline maximum value is generated by adding 2 times of variance to the average value of the historical time series performance data, and a dynamic baseline minimum value is generated by subtracting 2 times of variance from the average value of the historical time series performance data.
2. The system for detecting health of application clusters according to claim 1, further comprising a front-end display unit, wherein the front-end display unit is configured to display the dynamic baseline and health of each application cluster indicator in real time.
3. A method for detecting the health of an application cluster, characterized in that a system for detecting the health of an application cluster according to claim 1 is based on the steps of:
s1: initializing application cluster information to be monitored;
s2: the data acquisition unit acquires performance data generated by the APM tool and stores the performance data in the local database;
s3: the baseline calculation unit acquires a dynamic baseline according to the historical time sequence performance data in the local database;
s4: the abnormality detection unit detects abnormality of the real-time performance data in the local database;
s5: the alarm unit judges the health degree of the application cluster according to the abnormal detection result of the abnormal detection unit and sends out alarm information,
the step S3 specifically includes:
s301: reading historical timing performance data from a local database using a python pandas module;
s302: converting the historical time sequence performance data format into a Dataframe;
s303: judging whether the historical time sequence performance data has abnormal data or not, if so, removing the abnormal data and entering S304, otherwise, directly entering S304;
s304: calculating the mean value and the variance of the same time point every day in the historical time sequence performance data, and generating a dynamic base line according to the mean value and the variance of the same time point every day in the historical data;
s305: the dynamic baseline is written to a database,
in step S304, a dynamic baseline maximum value is generated by adding 2 times of variance to the average value of the historical time series performance data, and a dynamic baseline minimum value is generated by subtracting 2 times of variance from the average value of the historical time series performance data.
4. A method for detecting health of an application cluster according to claim 3, wherein said step S1 specifically comprises:
s101: synchronizing application cluster information of the accessed APM tool;
s102: and judging whether a dynamic baseline is established, if so, entering a step S2, otherwise, returning to the step S101.
5. A method for detecting health of an application cluster according to claim 3, wherein said step S2 specifically comprises:
s201: acquiring an APM data source;
s201: carrying out slice statistics on the APM data source to obtain a data slice;
s202: obtaining tissue key performance index data according to the data slice;
s203: the organization key performance indicator data is stored to a local relational database.
6. A method for detecting health of an application cluster according to claim 3, wherein said step S4 specifically comprises:
s401: acquiring real-time performance data in a local database;
s402: judging whether the real-time performance data meets an abnormal rule, if so, marking an abnormal label on the real-time performance data, writing the abnormal label into a local database, and entering a step S6, otherwise, entering a step S403;
s403: judging whether the real-time performance data is abnormal or not according to an abnormality detection algorithm, if so, marking an abnormality label on the real-time performance data, writing the abnormality label into a local database, and if not, marking a normal label on the real-time performance data, writing the abnormality label into the local database.
7. A method for detecting health of an application cluster according to claim 3, wherein said step S5 specifically comprises:
step S501: polling and checking all application clusters, judging whether the abnormal times of the key performance indexes in the appointed abnormal time threshold exceeds the abnormal times threshold, if so, judging that the health degree of the application clusters is abnormal and entering into S502, otherwise, judging that the health degree of the application clusters is healthy;
step S502: and generating and sending alarm information.
8. A method for detecting health of application clusters according to claim 3, wherein the system further comprises a front-end display unit, the front-end display unit is configured to display the dynamic baseline and health of each application cluster indicator in real time, and the method further comprises step S6: the front end display unit displays the dynamic baseline and performance index data using an echartis chart.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011609759.1A CN112749071B (en) | 2020-12-30 | 2020-12-30 | System and method for detecting health degree of application cluster |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011609759.1A CN112749071B (en) | 2020-12-30 | 2020-12-30 | System and method for detecting health degree of application cluster |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112749071A CN112749071A (en) | 2021-05-04 |
| CN112749071B true CN112749071B (en) | 2023-11-14 |
Family
ID=75649586
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011609759.1A Active CN112749071B (en) | 2020-12-30 | 2020-12-30 | System and method for detecting health degree of application cluster |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112749071B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113312234B (en) * | 2021-05-18 | 2022-07-26 | 福建天泉教育科技有限公司 | Health detection optimization method and terminal |
| CN113641566A (en) * | 2021-08-30 | 2021-11-12 | 平安资产管理有限责任公司 | System alarm method, device, computer equipment and medium based on artificial intelligence |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106209432A (en) * | 2016-06-30 | 2016-12-07 | 中国人民解放军国防科学技术大学 | Network equipment subhealth state method for early warning based on dynamic threshold and device |
| CN107943677A (en) * | 2017-10-13 | 2018-04-20 | 东软集团股份有限公司 | Application performance monitoring method, device, readable storage medium storing program for executing and electronic equipment |
| KR20180076172A (en) * | 2016-12-27 | 2018-07-05 | 주식회사 씨에스리 | Apparatus and method for detecting anomaly of database system |
| CN110768859A (en) * | 2019-09-18 | 2020-02-07 | 国网江苏省电力有限公司 | Application health automatic detection method based on time sequence data |
| WO2020125716A1 (en) * | 2018-12-21 | 2020-06-25 | 中兴通讯股份有限公司 | Method for realizing network optimization and related device |
| CN111931860A (en) * | 2020-09-01 | 2020-11-13 | 腾讯科技（深圳）有限公司 | Abnormal data detection method, device, equipment and storage medium |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9280757B2 (en) * | 2013-05-14 | 2016-03-08 | DecisionGPS, LLC | Automated inventory management |
-
2020
- 2020-12-30 CN CN202011609759.1A patent/CN112749071B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106209432A (en) * | 2016-06-30 | 2016-12-07 | 中国人民解放军国防科学技术大学 | Network equipment subhealth state method for early warning based on dynamic threshold and device |
| KR20180076172A (en) * | 2016-12-27 | 2018-07-05 | 주식회사 씨에스리 | Apparatus and method for detecting anomaly of database system |
| CN107943677A (en) * | 2017-10-13 | 2018-04-20 | 东软集团股份有限公司 | Application performance monitoring method, device, readable storage medium storing program for executing and electronic equipment |
| WO2020125716A1 (en) * | 2018-12-21 | 2020-06-25 | 中兴通讯股份有限公司 | Method for realizing network optimization and related device |
| CN110768859A (en) * | 2019-09-18 | 2020-02-07 | 国网江苏省电力有限公司 | Application health automatic detection method based on time sequence data |
| CN111931860A (en) * | 2020-09-01 | 2020-11-13 | 腾讯科技（深圳）有限公司 | Abnormal data detection method, device, equipment and storage medium |
Non-Patent Citations (3)
| Title |
|---|
| 兼顾降负荷和反弹抑制的负荷聚合商下空调集群调控策略;张天伟;王蓓蓓;贲树俊;胡楠;叶颖杰;;电力系统及其自动化学报(第03期);54-64 * |
| 分布式系统健康度实时自动化评价方法;程永新;移动通信;第42卷(第8期);91-96 * |
| 基于机器学习的动态基线性能时序数据异常检测研究与应用;马玉超;;中国金融电脑(第06期);52-60 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112749071A (en) | 2021-05-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112749071B (en) | System and method for detecting health degree of application cluster | |
| JP5324958B2 (en) | Method, program and apparatus for generating an integrated display of performance trends for multiple resources in a data processing system (integrated display of resource performance trends) | |
| US7559053B2 (en) | Program and system performance data correlation | |
| CN111475370A (en) | Operation and maintenance monitoring method, device and equipment based on data center and storage medium | |
| US20180196837A1 (en) | Root cause analysis of performance problems | |
| CN101707632A (en) | Method for dynamically monitoring performance of server cluster and alarming real-timely | |
| CN111240876B (en) | Fault positioning method and device for micro-service, storage medium and terminal | |
| CN107704387B (en) | Method, device, electronic equipment and computer readable medium for system early warning | |
| CN105979532B (en) | Performance capacity analysis early warning method and device of service processing system | |
| CN111385122A (en) | Distributed system link tracking method and device, computer equipment and storage medium | |
| CN114721912B (en) | Data analysis method, device, equipment and medium | |
| CN112286774A (en) | Operation and maintenance monitoring data display method and device, storage medium and computing equipment | |
| US20200342035A1 (en) | Data trend analysis based on real-time data aggregation | |
| CN112052134A (en) | Service data monitoring method and device | |
| CN106951360B (en) | Data statistical integrity calculation method and system | |
| CN104104734A (en) | Log analysis method and device | |
| CN113342619A (en) | Log monitoring method and system, electronic device and readable medium | |
| CN117492403B (en) | Large instrument operation monitoring system and method | |
| CN110677271A (en) | Big data alarm method, device, equipment and storage medium based on ELK | |
| CN112256548B (en) | Abnormal data monitoring method and device, server and storage medium | |
| CN112749140A (en) | MySQL slow SQL log real-time collection and optimization method and system | |
| CN114095335A (en) | Network alarm processing method and device and electronic equipment | |
| US8032302B1 (en) | Method and system of modifying weather content | |
| CN114546780A (en) | Data monitoring method, device, equipment, system and storage medium | |
| WO2010024490A1 (en) | Ubiquitous monitoring system capable of performing integral monitoring for smart objects |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |