CN116107630B - Multi-platform adaptation method for big data operation and maintenance monitoring - Google Patents
Multi-platform adaptation method for big data operation and maintenance monitoring Download PDFInfo
- Publication number
- CN116107630B CN116107630B CN202310391635.8A CN202310391635A CN116107630B CN 116107630 B CN116107630 B CN 116107630B CN 202310391635 A CN202310391635 A CN 202310391635A CN 116107630 B CN116107630 B CN 116107630B
- Authority
- CN
- China
- Prior art keywords
- platform
- commonality
- adaptation
- functional
- components
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F8/00—Arrangements for software engineering
- G06F8/70—Software maintenance or management
- G06F8/76—Adapting program code to run in a different environment; Porting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F8/00—Arrangements for software engineering
- G06F8/30—Creation or generation of source code
- G06F8/36—Software reuse
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Biophysics (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Train Traffic Observation, Control, And Security (AREA)
Abstract
The invention discloses a multi-platform adaptation method for big data operation and maintenance monitoring, which comprises the following steps: performing cluster analysis on a group of sample platforms according to the functional components to obtain a plurality of platform sets, and performing adaptive commonality analysis on the functional components in the plurality of platform sets to obtain adaptive commonality components of each platform set; and learning and training the platform functional characteristics and the adaptation commonality components in the platform set by utilizing the BP neural network to obtain a commonality adaptation model. According to the invention, the operation and maintenance relations between the platforms and the components are constructed, a unified operation and maintenance monitoring view angle is generated by using the model, and reasonable adaptation is established between different platforms, so that the dilemma that each component is difficult to integrate at the operation and maintenance level, is repeatedly built and has low automation degree is avoided, and the integrated operation and maintenance management of the large data platform can be realized.
Description
Technical Field
The invention relates to the technical field of operation and maintenance monitoring, in particular to a multi-platform adaptation method for big data operation and maintenance monitoring.
Background
Ambari, like Hadoop et al open source software, is also an item in Apache software Foundation and is the top level item. In terms of Ambari, it is the creation, management, and monitoring of a cluster of hadoops, where hadoops are meant in a broad sense to refer to the entire ecological circle of hadoops (e.g., hive, hbase, sqoop, zookeeper, etc.), and not just to refer to hadoops. In one sentence, ambari is a tool to make Hadoop and related big data software easier to use. Ambari is used as a top-level open source project for large data operation and maintenance monitoring, and is widely applied to large data platform construction and operation and maintenance. However, official ambari by default only supports the x86 cpu architecture, and the centos and ubuntu operating systems, cannot run on domestic operating systems.
Traditional big data operation and maintenance platform components are complex in variety and generally comprise various open source technical products, such as: hadoop, elasticSearch, HBase, phoenix, etc., and involves a number of types of components, such as: containers, middleware, databases, etc. Because there is no unified operation and maintenance interface between different components, the operation and maintenance management is generally performed by adopting the native interfaces, the big data operation and maintenance management platform built by the mode is discrete, the operation and maintenance between the systems and between the components is split, the unified operation and maintenance monitoring view angle is lacking, the reasonable adaptation between different platforms cannot be established, the integration difficulty, the repeated construction and the low automation degree of each component at the operation and maintenance level are difficult, and the integrated operation and maintenance management of the big data platform is difficult to realize.
Disclosure of Invention
The invention aims to provide a multi-platform adaptation method for large data operation and maintenance monitoring, which aims to solve the technical problems that in the prior art, discrete operation and maintenance among systems and among components is split, a unified operation and maintenance monitoring view angle is lacked, reasonable adaptation among different platforms cannot be established, the components are difficult to integrate at the operation and maintenance level, repeated construction and low in automation degree, and integrated operation and maintenance management of a large data platform is difficult to realize.
In order to solve the technical problems, the invention specifically provides the following technical scheme:
a multi-platform adaptation method for big data operation and maintenance monitoring comprises the following steps:
s1, splitting operation and maintenance monitoring functional components to obtain operation and maintenance monitoring functional characteristics of each functional component;
s2, selecting a group of sample platforms, acquiring platform function characteristics of each sample platform, and marking the functional components used by the sample platforms;
step S3, carrying out cluster analysis on a group of sample platforms according to the functional components to obtain a plurality of platform sets, and carrying out adaptive commonality analysis on the functional components in the plurality of platform sets to obtain adaptive commonality components of each platform set;
and S4, learning and training the platform functional characteristics and the adaptation commonality components in the platform set by utilizing the BP neural network to obtain a commonality adaptation model so as to realize multi-platform autonomous adaptation of big data operation and maintenance monitoring.
As a preferred aspect of the present invention, the operation and maintenance monitoring function features include a component input data type, a component output data type, and a component monitoring function type.
As a preferred embodiment of the present invention, the platform function features include a platform input data type, a platform output data type, and a platform monitoring target type.
As a preferable scheme of the invention, the clustering analysis is carried out on a group of sample platforms according to the functional components to obtain a plurality of platform sets, and the method comprises the following steps:
vectorizing all operation and maintenance monitoring functional features corresponding to all functional components of each sample platform to serve as feature vectors of each sample platform;
and performing cluster analysis on the group of sample platforms based on the feature vectors to divide the group of sample platforms into a plurality of platform sets.
As a preferred solution of the present invention, the performing an adaptive commonality analysis on a functional component in a plurality of platform sets to obtain an adaptive commonality component of each platform set includes:
taking the functional components corresponding to all sample platforms in each platform set as each component set; quantifying an adaptation commonality of each functional component in each component set, the function expression of the adaptation commonality being:
wherein P is k For the adaptation commonality of the kth functional component in each component set, X k Monitoring the functional characteristics, X, of the operation and maintenance of the kth functional component in each component set i For the first of each component setiThe operation and maintenance of the individual functional components monitors the functional characteristics, n being the total number of functional components in each component set, k,ito count variable, |X k -X i I is X k And X i Is the euclidean distance of (2);
setting a screening threshold value of the adaptation commonality, and taking a functional component corresponding to the adaptation commonality lower than the screening threshold value in each component set as an adaptation commonality component of each component set;
the adaptation commonality component of each component set is mapped to an adaptation commonality component of each platform component.
As a preferable scheme of the invention, the learning training of the platform functional characteristics and the adaptation commonality components in the platform set by using the BP neural network to obtain the commonality adaptation model comprises the following steps:
taking the platform function characteristics of the sample platform in each platform set as an input item of the BP neural network, and taking the adaptive commonality component of each platform set as an output item of the BP neural network;
performing convolution training on an input item of the BP neural network and an output item of the BP neural network by using the BP neural network to obtain the commonality adaptation model;
the model expression of the commonality adaptation model is as follows:
S=BP(Y);
in the formula, S is an adaptive commonality component, Y is a platform functional characteristic, and BP is a BP neural network.
As a preferred scheme of the present invention, the method further comprises a process of adapting the platform to be adapted, including:
obtaining platform function characteristics of a platform to be adapted, and obtaining an adaptation commonality component of the platform to be adapted by using a commonality adaptation model;
when the operation and maintenance monitoring functional characteristics corresponding to the adaptation commonality components of the platform to be adapted comprise all the platform functional characteristics of the platform to be adapted, taking the adaptation commonality components of the platform to be adapted as the operation and maintenance monitoring components of the platform to be adapted;
and when the operation and maintenance monitoring functional characteristics corresponding to the adaptive commonality components of the platform to be matched do not contain all the platform functional characteristics of the platform to be matched, the platform functional characteristics which are not contained in the operation and maintenance monitoring functional characteristics are subjected to artificial calibration functional components, and the adaptive commonality components and the artificial calibration functional components of the platform to be matched are used as the operation and maintenance monitoring components of the platform to be matched.
As a preferable scheme of the invention, the platform function characteristics and the operation and maintenance monitoring function characteristics are normalized before calculation.
As a preferable scheme of the invention, the clustering analysis algorithm comprises a Kmeans algorithm, a hierarchical clustering method and a spatial clustering algorithm based on density.
As a preferred embodiment of the present invention, the set of platforms includes at least one sample platform.
Compared with the prior art, the invention has the following beneficial effects:
according to the invention, a group of sample platforms are subjected to clustering analysis according to the functional components to obtain a plurality of platform sets, the functional components are subjected to adaptive commonality analysis in the plurality of platform sets to obtain adaptive commonality components of each platform set, the BP neural network is utilized to learn and train the platform functional characteristics and the adaptive commonality components in the platform sets to obtain a commonality adaptation model, the operation and maintenance relevance between the platforms and between the components is constructed, the model is utilized to generate a uniform operation and maintenance monitoring view angle, reasonable adaptation is established between different platforms, the dilemma that the integration difficulty, repeated construction and low automation degree of each component in the operation and maintenance level are avoided, and the integrated operation and maintenance management of a large data platform can be realized.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below. It will be apparent to those of ordinary skill in the art that the drawings in the following description are exemplary only and that other implementations can be obtained from the extensions of the drawings provided without inventive effort.
Fig. 1 is a flowchart of a multi-platform adaptation method for big data operation and maintenance monitoring according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Traditional big data operation and maintenance platform components are complex in variety and generally comprise various open source technical products, such as: hadoop, elasticSearch, HBase, phoenix, etc., and involves a number of types of components, such as: containers, middleware, databases, etc. Because there is no unified operation and maintenance interface between different components, the operation and maintenance management is generally carried out by adopting the native interfaces, the big data operation and maintenance management platform built by the method is discrete, the operation and maintenance between the platforms and the components is relatively split, the unified operation and maintenance monitoring view angle is lacking, the reasonable adaptation between different platforms cannot be established, the integration difficulty, the repeated construction and the low automation degree of each component at the operation and maintenance level are low, and the integrated operation and maintenance management of the big data platform is difficult to realize.
As shown in fig. 1, the present invention provides a multi-platform adaptation method for monitoring big data operation and maintenance, which comprises the following steps:
s1, splitting operation and maintenance monitoring functional components to obtain operation and maintenance monitoring functional characteristics of each functional component;
s2, selecting a group of sample platforms, acquiring platform function characteristics of each sample platform, and marking functional components used by the sample platforms;
step S3, carrying out cluster analysis on a group of sample platforms according to the functional components to obtain a plurality of platform sets, and carrying out adaptive commonality analysis on the functional components in the plurality of platform sets to obtain adaptive commonality components of each platform set;
and S4, learning and training the platform functional characteristics and the adaptation commonality components in the platform set by utilizing the BP neural network to obtain a commonality adaptation model so as to realize multi-platform autonomous adaptation of big data operation and maintenance monitoring.
Carrying out cluster analysis on a group of sample platforms according to functional components to obtain a plurality of platform sets, carrying out adaptive commonality analysis on the functional components in the plurality of platform sets to obtain adaptive commonality components of each platform set, carrying out learning training on the functional characteristics of the platform and the adaptive commonality components in the platform sets by utilizing a BP neural network to obtain a commonality adaptation model, constructing operation and maintenance relations between the platforms and the components, generating uniform operation and maintenance monitoring view angles by utilizing the model, establishing reasonable adaptation between different platforms, avoiding the dilemma of difficult operation and maintenance layer integration, repeated construction and low automation degree between the components, and realizing the integrated operation and maintenance management of a large data platform.
The operation and maintenance monitoring function features comprise a component input data type, a component output data type and a component monitoring function type, or operation and maintenance monitoring function features of other data types are selected according to actual scenes.
The platform function features comprise platform input data types, platform output data types and platform monitoring target types, or platform function features of other data types are selected according to actual scenes.
In order to avoid the problem that operation and maintenance between platforms and between the components are split due to discrete characteristics of a big data operation and maintenance management platform and lack of a unified operation and maintenance monitoring view angle, the invention provides a method for constructing operation and maintenance relativity between the platforms and between the components, namely, each platform utilizes operation and maintenance monitoring function characteristics of used functional components to cluster, so that the platforms with the same component use characteristics are classified into the same platform set, the used components among the platforms are known to have commonality attribute, the operation and maintenance relativity among the platforms is constructed, and the operation and maintenance split attribute among the platforms can be reduced according to the reference of the combination of the functional components among the platforms in one platform set, and the method comprises the following steps:
performing cluster analysis on a group of sample platforms according to the functional components to obtain a plurality of platform sets, wherein the method comprises the following steps:
vectorizing all operation and maintenance monitoring functional features corresponding to all functional components of each sample platform to serve as feature vectors of each sample platform;
and performing cluster analysis on the group of sample platforms based on the feature vectors to divide the group of sample platforms into a plurality of platform sets.
The invention maps the relevance between pure platforms to the relevance between the platforms and the functional components, builds the adaptation commonality to screen out the commonality functional components of each platform in the adaptation platform set, builds the operation and maintenance relevance between each platform and the functional components, adopts the relatively similar functional components to execute similar operation and maintenance monitoring functions with all platforms belonging to the same platform set, reduces the operation and maintenance splitting attribute between the platforms and the components, and is concretely as follows:
performing adaptive commonality analysis on the functional components in a plurality of platform sets to obtain adaptive commonality components of each platform set, including:
taking the functional components corresponding to all sample platforms in each platform set as each component set; quantifying the adaptation commonality of each functional component in each component set, wherein the function expression of the adaptation commonality is as follows:
wherein P is k For the adaptation commonality of the kth functional component in each component set, X k Monitoring the functional characteristics, X, of the operation and maintenance of the kth functional component in each component set i For the first of each component setiThe operation and maintenance of the individual functional components monitors the functional characteristics, n being the total number of functional components in each component set, k,ito count variable, |X k -X i I is X k And X i Is the euclidean distance of (2);
setting a screening threshold value of the adaptation commonality, and taking a functional component corresponding to the adaptation commonality lower than the screening threshold value in each component set as an adaptation commonality component of each component set;
the adaptation commonality component of each component set is mapped to an adaptation commonality component of each platform component.
The feature data balance is utilized to construct the adaptation commonality, the higher the adaptation commonality is, the larger the difference between the operation and maintenance monitoring function features of the functional component in the component set and the operation and maintenance monitoring function features of other functional components is, the characteristic of the outstanding individualization is realized, the operation and maintenance monitoring function features of the functional component are outstanding in individualization requirements of the platform because the component set is mapped by the platform set, the lower the adaptation commonality is, the smaller the difference between the operation and maintenance monitoring function features of the functional component in the component set and the operation and maintenance monitoring function features of the other functional components is, the characteristic of the outstanding commonality is realized, and the operation and maintenance monitoring function features of the functional component are outstanding in the commonality requirements of the platform are outstanding because the component set is mapped by the platform set.
The invention builds the adaptation commonality to screen the adaptation commonality components, builds the operation and maintenance association between each platform and the functional components, and reduces the operation and maintenance splitting attribute between the platform and the components.
In order to uniformly establish an operation and maintenance monitoring view angle according to the platform functional characteristics, avoid the dilemma that each component is difficult to integrate in an operation and maintenance layer, repeatedly construct and has low automation degree, realize the integrated operation and maintenance management of a large data platform, construct a common adaptation model by using a BP neural network, and establish the mapping relation between the platform functional characteristics and the adaptive common components, so that the adaptive common components are directly obtained according to the platform functional characteristics, realize the modeling construction of the operation and maintenance monitoring view angle, and have no subjective participation, and concretely comprise the following steps:
learning and training the platform functional characteristics and the adaptation commonality components in the platform set by utilizing the BP neural network to obtain a commonality adaptation model, wherein the method comprises the following steps:
taking the platform function characteristics of the sample platform in each platform set as an input item of the BP neural network, and taking the adaptive commonality component of each platform set as an output item of the BP neural network;
performing convolution training on an input item of the BP neural network and an output item of the BP neural network by using the BP neural network to obtain a commonality adaptation model;
the model expression of the commonality adaptation model is:
S=BP(Y);
in the formula, S is an adaptive commonality component, Y is a platform functional characteristic, and BP is a BP neural network.
The method also comprises the process of adapting the platform to be adapted, and comprises the following steps:
obtaining platform function characteristics of a platform to be adapted, and obtaining an adaptation commonality component of the platform to be adapted by using a commonality adaptation model;
when the operation and maintenance monitoring functional characteristics corresponding to the adaptation commonality components of the platform to be adapted comprise all the platform functional characteristics of the platform to be adapted, taking the adaptation commonality components of the platform to be adapted as the operation and maintenance monitoring components of the platform to be adapted;
and when the operation and maintenance monitoring functional characteristics corresponding to the adaptive commonality components of the platform to be matched do not contain all the platform functional characteristics of the platform to be matched, the platform functional characteristics which are not contained in the operation and maintenance monitoring functional characteristics are subjected to artificial calibration functional components, and the adaptive commonality components and the artificial calibration functional components of the platform to be matched are used as the operation and maintenance monitoring components of the platform to be matched.
The platform functional characteristics and the operation and maintenance monitoring functional characteristics are normalized before calculation.
The clustering analysis algorithm comprises a Kmeans algorithm, a hierarchical clustering method and a density-based spatial clustering algorithm.
The platform set comprises at least one sample platform.
According to the invention, a group of sample platforms are subjected to clustering analysis according to the functional components to obtain a plurality of platform sets, the functional components are subjected to adaptive commonality analysis in the plurality of platform sets to obtain adaptive commonality components of each platform set, the BP neural network is utilized to learn and train the platform functional characteristics and the adaptive commonality components in the platform sets to obtain a commonality adaptation model, the operation and maintenance relevance between the platforms and between the components is constructed, the model is utilized to generate a uniform operation and maintenance monitoring view angle, reasonable adaptation is established between different platforms, the dilemma that the integration difficulty, repeated construction and low automation degree of each component in the operation and maintenance level are avoided, and the integrated operation and maintenance management of a large data platform can be realized.
The above embodiments are only exemplary embodiments of the present application and are not intended to limit the present application, the scope of which is defined by the claims. Various modifications and equivalent arrangements may be made to the present application by those skilled in the art, which modifications and equivalents are also considered to be within the scope of the present application.
Claims (6)
1. A multi-platform adaptation method for big data operation and maintenance monitoring is characterized in that: the method comprises the following steps:
s1, splitting operation and maintenance monitoring functional components to obtain operation and maintenance monitoring functional characteristics of each functional component;
s2, selecting a group of sample platforms, acquiring platform function characteristics of each sample platform, and marking the functional components used by the sample platforms;
step S3, carrying out cluster analysis on a group of sample platforms according to the functional components to obtain a plurality of platform sets, and carrying out adaptive commonality analysis on the functional components in the plurality of platform sets to obtain adaptive commonality components of each platform set;
s4, learning and training the platform functional characteristics and the adaptation commonality components in the platform set by utilizing the BP neural network to obtain a commonality adaptation model so as to realize multi-platform autonomous adaptation of big data operation and maintenance monitoring;
the operation and maintenance monitoring function characteristics comprise a component input data type, a component output data type and a component monitoring function type;
the platform functional characteristics comprise a platform input data type, a platform output data type and a platform monitoring target type;
performing adaptive commonality analysis on the functional components in the plurality of platform sets to obtain adaptive commonality components of each platform set, including:
taking the functional components corresponding to all sample platforms in each platform set as each component set; quantifying an adaptation commonality of each functional component in each component set, the function expression of the adaptation commonality being:
wherein P is k For the adaptation commonality of the kth functional component in each component set, X k Monitoring the functional characteristics, X, of the operation and maintenance of the kth functional component in each component set i For the first of each component setiThe operation and maintenance of the individual functional components monitors the functional characteristics, n being the total number of functional components in each component set, k,ito count variable, |X k -X i I is X k And X i Is the euclidean distance of (2);
setting a screening threshold value of the adaptation commonality, and taking a functional component corresponding to the adaptation commonality lower than the screening threshold value in each component set as an adaptation commonality component of each component set;
mapping the adaptation commonality component of each component set into an adaptation commonality component of each platform component;
the learning training is carried out on the platform functional characteristics and the adaptation commonality components in the platform set by utilizing the BP neural network to obtain a commonality adaptation model, and the method comprises the following steps:
taking the platform function characteristics of the sample platform in each platform set as an input item of the BP neural network, and taking the adaptive commonality component of each platform set as an output item of the BP neural network;
performing convolution training on an input item of the BP neural network and an output item of the BP neural network by using the BP neural network to obtain the commonality adaptation model;
the model expression of the commonality adaptation model is as follows:
S=BP(Y);
in the formula, S is an adaptive commonality component, Y is a platform functional characteristic, and BP is a BP neural network.
2. The multi-platform adaptation method for big data operation and maintenance monitoring according to claim 1, wherein the method comprises the following steps: the step of performing cluster analysis on a group of sample platforms according to the functional components to obtain a plurality of platform sets comprises the following steps:
vectorizing all operation and maintenance monitoring functional features corresponding to all functional components of each sample platform to serve as feature vectors of each sample platform;
and performing cluster analysis on the group of sample platforms based on the feature vectors to divide the group of sample platforms into a plurality of platform sets.
3. The multi-platform adaptation method for big data operation and maintenance monitoring according to claim 1, further comprising a process of adapting a platform to be adapted, comprising:
obtaining platform function characteristics of a platform to be adapted, and obtaining an adaptation commonality component of the platform to be adapted by using a commonality adaptation model;
when the operation and maintenance monitoring functional characteristics corresponding to the adaptation commonality components of the platform to be adapted comprise all the platform functional characteristics of the platform to be adapted, taking the adaptation commonality components of the platform to be adapted as the operation and maintenance monitoring components of the platform to be adapted;
and when the operation and maintenance monitoring functional characteristics corresponding to the adaptive commonality components of the platform to be matched do not contain all the platform functional characteristics of the platform to be matched, the platform functional characteristics which are not contained in the operation and maintenance monitoring functional characteristics are subjected to artificial calibration functional components, and the adaptive commonality components and the artificial calibration functional components of the platform to be matched are used as the operation and maintenance monitoring components of the platform to be matched.
4. The multi-platform adaptation method for big data operation and maintenance monitoring according to claim 1, wherein the platform functional characteristics and the operation and maintenance monitoring functional characteristics are normalized before calculation.
5. The multi-platform adaptation method for big data operation and maintenance monitoring according to claim 2, wherein the algorithm of the cluster analysis comprises a Kmeans algorithm, a hierarchical clustering method and a spatial clustering algorithm based on density.
6. The multi-platform adaptation method for big data operation and maintenance monitoring according to claim 2, wherein the platform set comprises at least one sample platform.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310391635.8A CN116107630B (en) | 2023-04-13 | 2023-04-13 | Multi-platform adaptation method for big data operation and maintenance monitoring |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310391635.8A CN116107630B (en) | 2023-04-13 | 2023-04-13 | Multi-platform adaptation method for big data operation and maintenance monitoring |
Publications (2)
Publication Number | Publication Date |
---|---|
CN116107630A CN116107630A (en) | 2023-05-12 |
CN116107630B true CN116107630B (en) | 2023-06-20 |
Family
ID=86264174
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310391635.8A Active CN116107630B (en) | 2023-04-13 | 2023-04-13 | Multi-platform adaptation method for big data operation and maintenance monitoring |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116107630B (en) |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108446200A (en) * | 2018-02-07 | 2018-08-24 | 福建星瑞格软件有限公司 | Server intelligence O&M method based on big data machine learning and computer equipment |
CN114168152A (en) * | 2021-12-06 | 2022-03-11 | 国网河北省电力有限公司信息通信分公司 | Business application development and business operation and maintenance management system based on machine learning |
CN114372145A (en) * | 2021-12-23 | 2022-04-19 | 国网山东省电力公司信息通信公司 | Operation and maintenance resource dynamic allocation scheduling method based on knowledge graph platform |
WO2023272851A1 (en) * | 2021-06-29 | 2023-01-05 | 未鲲(上海)科技服务有限公司 | Anomaly data detection method and apparatus, device, and storage medium |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20190095478A1 (en) * | 2017-09-23 | 2019-03-28 | Splunk Inc. | Information technology networked entity monitoring with automatic reliability scoring |
US11584020B2 (en) * | 2018-12-04 | 2023-02-21 | Cloudminds Robotics Co., Ltd. | Human augmented cloud-based robotics intelligence framework and associated methods |
CN115699050A (en) * | 2019-11-05 | 2023-02-03 | 强力价值链网络投资组合2019有限公司 | Value chain network control tower and enterprise management platform |
-
2023
- 2023-04-13 CN CN202310391635.8A patent/CN116107630B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108446200A (en) * | 2018-02-07 | 2018-08-24 | 福建星瑞格软件有限公司 | Server intelligence O&M method based on big data machine learning and computer equipment |
WO2023272851A1 (en) * | 2021-06-29 | 2023-01-05 | 未鲲(上海)科技服务有限公司 | Anomaly data detection method and apparatus, device, and storage medium |
CN114168152A (en) * | 2021-12-06 | 2022-03-11 | 国网河北省电力有限公司信息通信分公司 | Business application development and business operation and maintenance management system based on machine learning |
CN114372145A (en) * | 2021-12-23 | 2022-04-19 | 国网山东省电力公司信息通信公司 | Operation and maintenance resource dynamic allocation scheduling method based on knowledge graph platform |
Non-Patent Citations (5)
Title |
---|
An end-to-end model-based approach to support big data analytics development;Hourieh Khalajzadeh等;Journal of Computer Languages;第58卷;第1-20页 * |
Orfeon: An AIOps framework for the goal-driven operationalization of distributed analytical pipelines;Josu Díaz-de-Arcaya等;Future Generation Computer Systems;第140卷;第18-35页 * |
基于Hadoop的大数据信息安全监控云平台设计与研究;张帅 等;计算机测量与控制;第25卷(第09期);第72-74+78页 * |
基于云计算的大数据运维系统的设计与实现;李鹏;中国优秀硕士学位论文全文数据库 信息科技辑(第9期);I138-166 * |
基于云计算的综合运维管理平台关键技术研究;王志浩;中国博士学位论文全文数据库 信息科技辑(第3期);I139-1 * |
Also Published As
Publication number | Publication date |
---|---|
CN116107630A (en) | 2023-05-12 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111242282B (en) | Deep learning model training acceleration method based on end edge cloud cooperation | |
CN109299284B (en) | Knowledge graph representation learning method based on structural information and text description | |
CN103559504B (en) | Image target category identification method and device | |
Sun et al. | A new surrogate-assisted interactive genetic algorithm with weighted semisupervised learning | |
WO2018058821A1 (en) | Disease and insect pest forecasting method and apparatus based on planting equipment | |
WO2021051987A1 (en) | Method and apparatus for training neural network model | |
CN113868366B (en) | Streaming data-oriented online cross-modal retrieval method and system | |
CN107451230A (en) | A kind of answering method and question answering system | |
CN112115967A (en) | Image increment learning method based on data protection | |
CN116719917A (en) | Knowledge question-answering system, method and storage medium combining large model with external knowledge | |
CN112180471A (en) | Weather forecasting method, device, equipment and storage medium | |
CN113761220A (en) | Information acquisition method, device, equipment and storage medium | |
CN111861231A (en) | Flight training special situation intelligent generation method based on decision tree | |
CN114463596A (en) | Small sample image identification method, device and equipment of hypergraph neural network | |
CN116107630B (en) | Multi-platform adaptation method for big data operation and maintenance monitoring | |
CN110110628A (en) | A kind of detection method and detection device of frequency synthesizer deterioration | |
CN108090564A (en) | Based on network weight is initial and the redundant weighting minimizing technology of end-state difference | |
CN113221913A (en) | Agriculture and forestry disease and pest fine-grained identification method and device based on Gaussian probability decision-level fusion | |
CN110221839A (en) | A kind of hardware accelerator VerilogHDL code automatic generation method | |
CN115588487A (en) | Medical image data set making method based on federal learning and generation countermeasure network | |
CN112015854B (en) | Heterogeneous data attribute association method based on self-organizing mapping neural network | |
CN107122472A (en) | Extensive unstructured data extracting method, its system, DDM platform | |
CN113239034A (en) | Big data resource integration method and system based on artificial intelligence and cloud platform | |
CN112766356A (en) | Prediction method and system based on dynamic weight D-XGboost model | |
CN111882441A (en) | User prediction interpretation Treeshap method based on financial product recommendation scene |
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 |