CN114168409A - Service system running state monitoring and early warning method and system - Google Patents
Service system running state monitoring and early warning method and system Download PDFInfo
- Publication number
- CN114168409A CN114168409A CN202111424577.1A CN202111424577A CN114168409A CN 114168409 A CN114168409 A CN 114168409A CN 202111424577 A CN202111424577 A CN 202111424577A CN 114168409 A CN114168409 A CN 114168409A
- Authority
- CN
- China
- Prior art keywords
- data
- running state
- data set
- state data
- early warning
- 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.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/30—Monitoring
- G06F11/3003—Monitoring arrangements specially adapted to the computing system or computing system component being monitored
- G06F11/302—Monitoring arrangements specially adapted to the computing system or computing system component being monitored where the computing system component is a software system
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Quality & Reliability (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Biology (AREA)
- Probability & Statistics with Applications (AREA)
- Computer Hardware Design (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a service system running state monitoring and early warning method and a system, wherein the method comprises the following steps: collecting working condition information of the operation state of a service system to be detected, and storing the working condition information as a first operation state data set; performing quality exploration and characteristic analysis on the first operation state data set to obtain a second operation state data set; preprocessing the second running state data set to obtain a third running state data set; performing similarity measurement on the third running state data set to obtain a similarity distance of the running state data; performing mode mining processing on the third running state data set to obtain a data association rule; generating a first combination model based on the similarity distance and the data association rule; and (4) carrying out real-time monitoring and early warning based on the data change trend predicted by the first combined model. The invention can visually reflect each service operation index of the data center in real time, ensure the availability of the system, prevent the occurrence of emergency and improve the operation efficiency and safe operation of the system.
Description
Technical Field
The invention relates to the field of artificial intelligence, in particular to a service system running state monitoring and early warning method and system.
Background
The data center is used as a central place for storing and processing business data inside, and the safe operation in aspects of power, environment, security protection, network, equipment and the like of the data center is related to the operation of a global system. Therefore, the data center safety monitoring is used as an important component of operation, and has important effects on ensuring the safe operation of company business, improving the operation efficiency of daily work and the like.
Traditional data center maintenance work mainly depends on that the computer lab staff attends to on duty, however manual monitoring has very big limitation. Firstly, the requirement of the maintenance of a data center of a machine room on the professional degree of managers is high, and the problem cannot be found at the first time when equipment fails due to blind spots in manual operation; secondly, the data center equipment works all day long, so that a large amount of labor cost is required to be invested for watching, and all-day manual monitoring is difficult to realize; finally, the traditional manual on-duty monitoring has poor real-time performance of alarm and low response efficiency, and is not beneficial to the high-efficiency operation and maintenance of the data center. Once a system or equipment fails, the economic loss caused by the system or equipment is immeasurable, so that real-time intelligent monitoring management of the data center is very important.
With the development of technologies such as big data and artificial intelligence, the creation of an 'unattended' data center with high intelligence is a new development of a data center environment control system.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides the service system operation state monitoring and early warning method and the service system operation state monitoring and early warning system, which can intuitively reflect each service operation index of the data center in real time, ensure the availability of the system, prevent the occurrence of an emergency and improve the operation efficiency and the safe operation of the system.
In a first aspect, the present invention provides a method for monitoring and warning an operation state of a service system, including the following steps:
s101, collecting working condition information of the running state of a service system to be detected, and storing the working condition information as a first running state data set;
step S103, performing quality exploration and characteristic analysis on the first operation state data set to obtain a second operation state data set;
step S105, preprocessing the second running state data set to obtain a third running state data set;
step S107, carrying out similarity measurement on the third running state data set to obtain a similarity distance of the running state data;
step S109, performing pattern mining processing on the third running state data set to obtain a data association rule;
step S111, generating a first combination model based on the similarity distance and a data association rule;
and S113, carrying out real-time monitoring and early warning based on the first combined model prediction data change trend.
Wherein, the quality exploration and feature analysis in the step S103 at least include data missing, abnormal value analysis, overall distribution of data, statistic analysis and correlation analysis.
Wherein the preprocessing in the step S105 includes: data cleansing, data standardization, data reduction and data discretization.
Wherein the data normalization comprises:
wherein, XjFor the values of the data objects in the original data set,
value, X, normalized for the data objectmaxIs the maximum value, X, in the data objectminIs the minimum value in the data object.
Wherein the data reduction specifically comprises:
wherein the content of the first and second substances,
the data object is subjected to data reduction to obtain a value, and the original data set with the original length of N is finally converted into the data set with the length of N in a segmented and aggregated manner
Wherein the data discretization comprises:
wherein the content of the first and second substances,
the data object is subjected to data discretization, and finally, a time-series data set is converted into a character string set { u, l, d } according to the data change trend, wherein t is a fluctuation threshold of the data.
Wherein, the step S107 specifically includes:
and according to the third running state data set and aiming at different index data of the working condition information, acquiring a template subsequence in the period of hours, days, weeks and months respectively, calculating the similar distance between the current time subsequence of the same index data and the template subsequence, and predicting the data change in the future time.
Wherein, the step S109 specifically includes:
step S1091, mining a frequent mode of the business system for operating each index data according to the third operation state data set;
step S1093, mining the frequent mode of the business system running different index data according to the frequent mode of each index data;
and S1095, generating an association rule of the third operation state data set according to the frequent mode among the different index data.
Wherein, the step S111 specifically includes:
and generating the first combined model in a weighted mode based on the similarity distance and the prediction result of the association rule.
In a second aspect, the present invention further provides a service system operation state monitoring and early warning system, including:
the data acquisition module is used for acquiring the working condition information of the running state of the service system to be detected and storing the working condition information as a first running state data set;
the data exploration module is used for carrying out quality exploration and characteristic analysis on the first running state data set to obtain a second running state data set;
the data preprocessing module is used for preprocessing the second running state data set to obtain a third running state data set;
the sequence matching module is used for carrying out similarity measurement on the third running state data set to obtain the similarity distance of the running state data;
the pattern mining module is used for carrying out pattern mining processing on the third running state data set to obtain a data association rule;
the model optimization module generates a first combination model based on the similarity distance and the data association rule;
and the monitoring and early warning module is used for carrying out real-time monitoring and early warning based on the first combined model prediction data change trend.
The invention provides a service system running state monitoring and early warning method and system based on artificial intelligence, which can realize uninterrupted identification and early warning of abnormal states within 7-24 hours, reduce the working intensity of data center operators, greatly improve the accuracy and timeliness of fault finding while reducing the labor cost, and improve the stability and real-time performance of data center operation and maintenance work, thereby further improving the running efficiency of internal systems of companies.
Drawings
The above and other objects, features and advantages of exemplary embodiments of the present disclosure will become readily apparent from the following detailed description read in conjunction with the accompanying drawings. Several embodiments of the present disclosure are illustrated by way of example, and not by way of limitation, in the figures of the accompanying drawings and in which like reference numerals refer to similar or corresponding parts and in which:
fig. 1 is a flowchart illustrating a method for monitoring and warning an operation state of a service system according to an embodiment of the present invention;
FIG. 2 is a schematic diagram illustrating pretreatment according to an embodiment of the present invention;
FIG. 3 is a flow diagram illustrating a pattern mining process according to an embodiment of the present invention;
fig. 4 is a schematic diagram illustrating a service system operation state monitoring and early warning system according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention clearer, the present invention will be described in further detail with reference to the accompanying drawings, and it is apparent that the described embodiments are only a part of the embodiments of the present invention, 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 terminology used in the embodiments of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in the examples of the present invention and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise, and "a plurality" typically includes at least two.
It is also noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that an article or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such article or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in the article or device in which the element is included.
Alternative embodiments of the present invention are described in detail below with reference to the accompanying drawings.
The first embodiment,
As shown in fig. 1, the present invention discloses a service system operation state monitoring and early warning method, which comprises the following steps:
s101, collecting working condition information of the running state of a service system to be detected, and storing the working condition information as a first running state data set;
step S103, performing quality exploration and characteristic analysis on the first operation state data set to obtain a second operation state data set;
step S105, preprocessing the second running state data set to obtain a third running state data set;
s107, carrying out similarity measurement on the third running state data set to obtain the similarity distance of the running state data;
step S109, performing pattern mining processing on the third running state data set to obtain a data association rule;
step S111, generating a first combination model based on the similarity distance and the data association rule;
and S113, carrying out real-time monitoring and early warning based on the data change trend of the first combined model prediction.
Example II,
As shown in fig. 1, the present invention provides a service system operation state monitoring and early warning method, which includes the following steps:
s101, collecting working condition information of the running state of a service system to be detected, and storing the working condition information as a first running state data set; the service system comprises a plurality of machines, wherein the service system comprises a plurality of pieces of service information, and the service information comprises monitoring index data information of running states of the machines in the service system, and specifically comprises a CPU utilization rate, a memory utilization rate, a disk utilization rate, a CPU idle rate, a buffer area utilization rate, a total file system utilization rate, a disk IO (input/output) waiting time, a response time, a network average total flow per second flowing out/flowing in and the like;
step S103, performing quality exploration and characteristic analysis on the first operation state data set to obtain a second operation state data set; the step is to search data aiming at the collected operation information data set of the service system, and know the gross quality, the size, the characteristics, the sample number, the data type, the probability distribution of the data and the like of the data set so as to better know the data characteristics of the data set;
step S105, preprocessing the second running state data set to obtain a third running state data set;
s107, carrying out similarity measurement on the third running state data set to obtain the similarity distance of the running state data; the method comprises the steps that sequence matching is carried out on related information in a single monitoring index of a monitored system, on a third running state data set, aiming at different index data, a subsequence of a template is obtained in a time angle by taking an hour period, a day period, a week period and a month period respectively, and the similar distance between the subsequence at the current moment and the subsequence of the template is calculated;
step S109, performing pattern mining processing on the third running state data set to obtain a data association rule; the step of pattern mining is a process of searching information hidden in a large amount of equipment operation data through an algorithm;
step S111, generating a first combination model based on the similarity distance and the data association rule;
and S113, carrying out real-time monitoring and early warning based on the data change trend of the first combined model prediction.
The embodiment of the present invention is further described in order to facilitate understanding of the quality exploration and the feature analysis in step S103. The quality exploration in this embodiment aims to check the correctness and validity of data, and its main task is to check whether dirty data exists in the original data, where dirty data generally refers to data that does not meet the requirements and cannot be directly analyzed accordingly.
In a practical application scenario, the quality exploration and feature analysis mentioned in step S103 of the present embodiment at least include data missing, abnormal value analysis, overall distribution of data, statistic analysis and correlation analysis.
To further understand data loss, outlier analysis, overall distribution of data, statistics analysis, and correlation analysis, they are further described below.
Data loss generally refers to both observed loss and loss of variable values in observations.
Outliers are those data that are incorrectly entered and contain unreasonable data, and are typically individual values in a sample whose values deviate significantly from the rest of the observations. In most cases, the variables are not allowed to have negative values, i.e., the negative values are abnormal values.
For abnormal value analysis, certain business background knowledge can be combined to find abnormality from the value taking condition of the variable, so as to judge whether data processing errors exist. The 3-sigma principle (if the data obeys a normal distribution, under the 3-sigma principle, an abnormal value is defined as a value that deviates from the mean by more than three times the standard deviation in a set of measured values), IQR (an abnormal value is generally defined as a value smaller than Q)Ll.5IQR or greater than QuValue of +1.5IQR, QLCalled the lower quartile, QuCalled upper quartile, IQR called quartile spacing, is QuUpper quartile sum QLThe difference between the lower quartile, which includes half of the total observed value. ) And analyzing whether the data are abnormal or not by using a statistical method.
The overall distribution of the data can be observed by a drawing mode, such as a histogram and a frequency chart, the shape and the distribution trend of the data distribution.
The statistic analysis is descriptive statistics on data, and can analyze data conditions such as variable value range, deviation degree and the like.
The most common statistics are the maximum and minimum, which are used to determine whether the value of this variable is outside a reasonable range. Statistics such as mean, mode, quantile, standard deviation, variance, etc. may also be calculated.
The correlation analysis is used for analyzing the strength of linear correlation degree between two continuous variables and can be analyzed by calculating a Pearson correlation coefficient. The formula is as follows:
wherein E () is desired, μXDesired E (X), μ for XYRepresenting the desired E (Y) of Y, the pearson correlation coefficient ρ of two consecutive variables (X, Y)X,YEqual to the product of the covariance cov (X, Y) between them divided by their respective standard deviations (σ)X,σY)。
Example III,
On the basis of the above embodiment, the present embodiment may further include the following:
as shown in fig. 2, the preprocessing of the second operation state data set in step S105 may include: data cleansing, data standardization, data reduction and data discretization.
The pretreatment process in this embodiment is further described below to facilitate better understanding of the pretreatment process by those skilled in the art.
The data normalization of the present embodiment may include:
wherein XjFor the values of the data objects in the original data set,
value, X, normalized for the data objectmaxIs the maximum value, X, in the data objectminIs the minimum value.
The data reduction processing is applied to the data after the data normalization, which may specifically include:
wherein
The data object is subjected to data reduction to obtain a value, and the original data set with the original length of N is finally converted into the data set with the length of N in a segmented and aggregated manner
The data discretization of the reduced data may specifically include:
wherein the content of the first and second substances,
the data object is subjected to data discretization, and finally, a time-series data set is converted into a character string set { u, l, d } according to the data change trend, wherein t is a fluctuation threshold of the data.
The data cleaning of the present embodiment adopts methods of filling missing values, replacing invalid data, removing noise in data, and the like, and in order to make clear the difference between the data cleaning and the quality exploration and feature analysis performed by the present embodiment, the difference is further described. The quality exploration and analysis of data of the present embodiment mainly focuses on the discovery of dirty data, and particularly, the main task is to check whether dirty data exists in original data, and the dirty data generally refers to data which is not qualified and cannot be directly analyzed correspondingly. While data cleansing is the correction or discarding of such dirty data.
Example four,
On the basis of the above embodiment, the present embodiment may further include the following:
in this embodiment, the performing the similarity measurement on the preprocessed third operation state data set may specifically include, in step S107:
and according to the third running state data set and aiming at different index data of the working condition information, acquiring a template subsequence in the period of hours, days, weeks and months respectively, calculating the similar distance between the current time subsequence of the same index data and the template subsequence, and predicting the data change in the future time.
For the convenience of understanding the content of step S107 in the present embodiment, some of the content will be described in detail. The index data of the operation state of the service system in this embodiment includes a CPU usage rate, a memory usage rate, a disk usage rate, an access amount, and the like of the operation of the service system.
In this embodiment, when acquiring a template subsequence, random selection is performed based on the template sequence, a subsequence with a period of hours, days, weeks, and months is selected, and the randomly selected sequence is used as the template subsequence.
Example V,
On the basis of the above embodiment, the present embodiment may further include the following:
in this embodiment, in addition to performing the similarity measurement on the third operation state data set, the third operation state data set needs to be subjected to the pattern mining process, specifically, as shown in fig. 3, step S109 of this embodiment may include:
step S1091, mining a frequent mode of the business system for operating each index data according to the third operation state data set;
step S1093, mining the frequent mode of the business system running different index data according to the frequent mode of each index data;
and S1095, generating an association rule of a third operation state data set according to the frequent mode among different index data.
The pattern mining algorithm mainly includes Apriori, FP-tres, and the like, and in the present embodiment, it is preferable to perform pattern mining using Apriori algorithm. For step S1091, the specific method may include:
firstly, the maximum length of the mode is set to be k, and the minimum support threshold of the frequent mode is set to be min.
And mining a frequent pattern of the preprocessed third running state data set by using an association analysis Apriori algorithm, firstly, obtaining a frequent pattern with the length of 2 by connecting every two of the frequent patterns based on a sequence frequent pattern with the size of 1, namely, the frequent pattern is composed of symbols u, l and d in a character string set { u, l and d }, obtaining the frequency of the frequent pattern by completely scanning the discretized data set once, namely, obtaining the frequency of the frequent pattern, namely, the number of times of the support count, and recording a position list of the pattern in the data set, wherein the position list comprises an initial position and an end position of the pattern, filtering the frequent pattern, and reserving the frequent pattern which is greater than a minimum support threshold value min to obtain the frequent pattern set with the length of 2. Repeating the above process to obtain a length-3 frequent pattern set, a position list of the pattern occurrence, a length-3 frequent pattern set, …, a length-k pattern set, a position list of the pattern occurrence, and a length-k frequent pattern set.
For step S1093, the embodiment performs pattern mining on the service system running between different index data by using Apriori association analysis algorithm. The specific method comprises the following steps:
first, the maximum length of the mode is set to k2, the minimum support threshold of the frequent mode is set to min2, and the maximum support threshold of the frequent mode is set to max 2.
Randomly selecting a certain index data operated by a service system, starting a frequent mode 1 in the sequence, connecting the frequent modes in the frequent mode in the sequence with other sequences in pairs to generate a candidate frequent mode with the length of 2 between the sequences; generating a position list of the candidate frequent patterns with the length of 2 among the sequences through the position list of the candidate frequent patterns in the sequences, judging whether the length of the position list is between the minimum support degree min2 and the maximum support degree max2, and if so, adding the candidate frequent patterns with the length of 2 among the sequences into a frequent pattern set among the sequences; otherwise, deleting the inter-sequence candidate frequent pattern with the length of 2; by analogy, two frequent patterns with the length of k2-1 are used for generating the candidate frequent patterns with the length of k2 among the sequences; generating a new position list through the position lists of the two candidate frequent patterns in the sequence, judging whether the length of the new position list is between the minimum support metric min2 and the maximum support metric max2, and if so, adding the candidate frequent patterns with the length of k2 between the sequences into the inter-sequence frequent pattern set; otherwise, deleting the inter-sequence candidate frequent patterns with the length of k2 until the lengths of the frequent patterns in the inter-sequence frequent pattern set reach the set maximum length of k 2.
For step S1095, the method may include:
firstly, setting a minimum confidence threshold of a rule to be min3, generating an association rule of a service system running state data set according to a frequency mode between the excavated different index data, and screening the generated association rule according to the set minimum confidence threshold min3 to obtain a final association rule.
Example six,
On the basis of the above embodiment, the present embodiment may further include the following:
in this embodiment, the generating the first combined model based on the similarity distance and the data association rule in step S111 may specifically include:
generating a first combination model in a weighting mode based on the similarity distance and the prediction result of the association rule;
and according to the experimental result, adjusting parameters and optimizing the first combined model, adjusting the similarity distance and the weight of the output result of the data association rule, and optimizing the first combined model.
In this embodiment, after obtaining the optimized first combination model, the step S113 is adopted to perform real-time monitoring and early warning, which may specifically include:
calculating by the similar distance between the template subsequence and the current time sequence, predicting the change trend of the future set time data by taking the real sequence data as experimental data, and judging that the change trend is abnormal if the change trend exceeds a certain threshold value.
According to the association rule among the mined data, the change rule of another data can be obtained according to a certain data, and when the real data trend does not accord with the predicted data change rule, the abnormal data is judged.
And combining results between the single sequence and the data sequence, and comprehensively judging the abnormal possibility of the single sequence and the data sequence so as to carry out monitoring and early warning.
In the embodiment, after data analysis and processing, various index data of the operation state data of the service system can be displayed on one graph to perform comprehensive dynamic monitoring, so that managers can conveniently master the operation state of the data center equipment.
Example seven,
As shown in fig. 4, an embodiment of the present invention further provides a service system operation state monitoring and early warning system, which includes:
the data acquisition module is used for acquiring the working condition information of the running state of the service system to be detected and storing the working condition information as a first running state data set;
the data exploration module is used for carrying out quality exploration and characteristic analysis on the first running state data set to obtain a second running state data set;
the data preprocessing module is used for preprocessing the second running state data set to obtain a third running state data set;
the sequence matching module is used for carrying out similarity measurement on the third running state data set to obtain the similarity distance of the running state data;
the pattern mining module is used for carrying out pattern mining processing on the third running state data set to obtain a data association rule;
the model optimization module generates a first combination model based on the similarity distance and the data association rule;
and the monitoring and early warning module is used for carrying out real-time monitoring and early warning based on the first combined model prediction data change trend.
Example eight,
The disclosed embodiments provide a non-volatile computer storage medium having stored thereon computer-executable instructions that may perform the method steps of the above embodiments.
It should be noted that the computer readable medium in the present disclosure can be a computer readable signal medium or a computer readable storage medium or any combination of the two. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In contrast, in the present disclosure, a computer readable signal medium may comprise a propagated data signal with computer readable program code embodied therein, either in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, optical cables, RF (radio frequency), etc., or any suitable combination of the foregoing.
The computer readable medium may be embodied in the electronic device; or may exist separately without being assembled into the electronic device.
Computer program code for carrying out operations for aspects of the present disclosure may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + +, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local Area Network (AN) or a Wide Area Network (WAN), or the connection may be made to AN external computer (for example, through the internet using AN internet service provider).
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The units described in the embodiments of the present disclosure may be implemented by software or hardware. Where the name of an element does not in some cases constitute a limitation on the element itself.
The foregoing describes preferred embodiments of the present invention, and is intended to provide a clear and concise description of the spirit and scope of the invention, and not to limit the same, but to include all modifications, substitutions, and alterations falling within the spirit and scope of the invention as defined by the appended claims.
Claims (10)
1. A monitoring and early warning method for the operation state of a service system is characterized by comprising the following steps:
s101, collecting working condition information of the running state of a service system to be detected, and storing the working condition information as a first running state data set;
step S103, performing quality exploration and characteristic analysis on the first operation state data set to obtain a second operation state data set;
step S105, preprocessing the second running state data set to obtain a third running state data set;
step S107, carrying out similarity measurement on the third running state data set to obtain a similarity distance of the running state data;
step S109, performing pattern mining processing on the third running state data set to obtain a data association rule;
step S111, generating a first combination model based on the similarity distance and a data association rule;
and S113, carrying out real-time monitoring and early warning based on the first combined model prediction data change trend.
2. The method of claim 1, wherein the quality exploration and feature analysis in step S103 at least includes data missing, outlier analysis, overall distribution of data, statistics analysis, and correlation analysis.
3. The method according to claim 1, wherein the preprocessing in step S105 comprises: data cleansing, data standardization, data reduction and data discretization.
4. The method of claim 3, wherein the data normalization comprises:
wherein, XjFor the values of the data objects in the original data set,
value, X, normalized for the data objectmaxIs the maximum value, X, in the data objectminIs the minimum value in the data object.
5. The method of claim 4, wherein the data reduction specifically comprises:
wherein the content of the first and second substances,
the data object is subjected to data reduction to obtain a value, and the original data set with the original length of N is finally converted into the data set with the length of N in a segmented and aggregated manner
6. The method of claim 5, wherein the discretizing of the data comprises:
wherein the content of the first and second substances,
is the value of the data object after data discretization, and finally, the time series number is obtained according to the data change trendThe data set is converted into a character string set { u, l, d }, wherein t is a fluctuation threshold of the data.
7. The method according to claim 6, wherein the step S107 specifically includes:
and according to the third running state data set and aiming at different index data of the working condition information, acquiring a template subsequence in the period of hours, days, weeks and months respectively, calculating the similar distance between the current time subsequence of the same index data and the template subsequence, and predicting the data change in the future time.
8. The method according to claim 7, wherein the step S109 specifically includes:
step S1091, mining a frequent mode of the business system for operating each index data according to the third operation state data set;
step S1093, mining the frequent mode of the business system running different index data according to the frequent mode of each index data;
and S1095, generating an association rule of the third operation state data set according to the frequent mode among the different index data.
9. The method according to claim 8, wherein the step S111 specifically includes:
and generating the first combined model in a weighted mode based on the similarity distance and the prediction result of the association rule.
10. The utility model provides a business system running state monitoring early warning system which characterized in that includes:
the data acquisition module is used for acquiring the working condition information of the running state of the service system to be detected and storing the working condition information as a first running state data set;
the data exploration module is used for carrying out quality exploration and characteristic analysis on the first running state data set to obtain a second running state data set;
the data preprocessing module is used for preprocessing the second running state data set to obtain a third running state data set;
the sequence matching module is used for carrying out similarity measurement on the third running state data set to obtain the similarity distance of the running state data;
the pattern mining module is used for carrying out pattern mining processing on the third running state data set to obtain a data association rule;
the model optimization module generates a first combination model based on the similarity distance and the data association rule;
and the monitoring and early warning module is used for carrying out real-time monitoring and early warning based on the first combined model prediction data change trend.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111424577.1A CN114168409A (en) | 2021-11-26 | 2021-11-26 | Service system running state monitoring and early warning method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111424577.1A CN114168409A (en) | 2021-11-26 | 2021-11-26 | Service system running state monitoring and early warning method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114168409A true CN114168409A (en) | 2022-03-11 |
Family
ID=80481395
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111424577.1A Pending CN114168409A (en) | 2021-11-26 | 2021-11-26 | Service system running state monitoring and early warning method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114168409A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117131110A (en) * | 2023-10-27 | 2023-11-28 | 南京中鑫智电科技有限公司 | Method and system for monitoring dielectric loss of capacitive equipment based on correlation analysis |
-
2021
- 2021-11-26 CN CN202111424577.1A patent/CN114168409A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117131110A (en) * | 2023-10-27 | 2023-11-28 | 南京中鑫智电科技有限公司 | Method and system for monitoring dielectric loss of capacitive equipment based on correlation analysis |
| CN117131110B (en) * | 2023-10-27 | 2024-01-23 | 南京中鑫智电科技有限公司 | Method and system for monitoring dielectric loss of capacitive equipment based on correlation analysis |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111459778B (en) | Operation and maintenance system abnormal index detection model optimization method, device and storage medium | |
| CN110498314B (en) | Health assessment method and system for elevator door system, electronic device and storage medium | |
| CN114267178B (en) | Intelligent operation maintenance method and device for station | |
| US20220179393A1 (en) | Machine tool evaluation method, machine tool evaluation system and medium | |
| US20230019404A1 (en) | Data Processing for Industrial Machine Learning | |
| CN112199252B (en) | Abnormality monitoring method and device and electronic equipment | |
| CN111241683A (en) | Equipment working condition fault prediction method and system based on dynamic time warping | |
| CN117055502A (en) | Intelligent control system based on Internet of things and big data analysis | |
| CN116457802A (en) | Automatic real-time detection, prediction and prevention of rare faults in industrial systems using unlabeled sensor data | |
| CN117439256A (en) | Power station equipment management method and system based on Internet of things | |
| KR101960755B1 (en) | Method and apparatus of generating unacquired power data | |
| CN114168409A (en) | Service system running state monitoring and early warning method and system | |
| CN114548493A (en) | Method and system for predicting current overload of electric energy meter | |
| CN113778766A (en) | Hard disk failure prediction model establishing method based on multi-dimensional characteristics and application thereof | |
| CN110796282A (en) | Industry fluctuation period monitoring method based on correlation coefficient | |
| CN116611813A (en) | Intelligent operation and maintenance management method and system based on knowledge graph | |
| CN116956174B (en) | Classification model for cold head state classification detection and life prediction and generation method of prediction model | |
| CN113591266A (en) | Method and system for analyzing fault probability of electric energy meter | |
| CN117808157B (en) | Intelligent identification-based unreported outage behavior prediction analysis system | |
| CN115018366B (en) | Energy storage system working state monitoring method and device, storage medium and electronic equipment | |
| CN117952318A (en) | Industrial garden carbon emission data management system and method based on big data | |
| CN116822788A (en) | Method for analyzing overall operation efficiency of dispatching command business | |
| CN117709587A (en) | Digital management and control method and system based on quantitative fee prediction and analysis | |
| CN118132321A (en) | Learning-based database abnormal root cause SQL diagnosis method and diagnosis device thereof | |
| CN117974155A (en) | User complaint pre-processing method, device and equipment |
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 |