CN114531365B - Cloud resource automatic operation and maintenance method under multi-cloud environment - Google Patents
Cloud resource automatic operation and maintenance method under multi-cloud environment Download PDFInfo
- Publication number
- CN114531365B CN114531365B CN202210433207.2A CN202210433207A CN114531365B CN 114531365 B CN114531365 B CN 114531365B CN 202210433207 A CN202210433207 A CN 202210433207A CN 114531365 B CN114531365 B CN 114531365B
- Authority
- CN
- China
- Prior art keywords
- maintenance
- field
- maintenance field
- cloud
- potential energy
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/142—Network analysis or design using statistical or mathematical methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/11—Complex mathematical operations for solving equations, e.g. nonlinear equations, general mathematical optimization problems
- G06F17/12—Simultaneous equations, e.g. systems of linear equations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/08—Configuration management of networks or network elements
- H04L41/0876—Aspects of the degree of configuration automation
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/147—Network analysis or design for predicting network behaviour
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Computational Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Algebra (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Probability & Statistics with Applications (AREA)
- Operations Research (AREA)
- Automation & Control Theory (AREA)
- Computing Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a method for cloud resource automation operation and maintenance under a cloudy environment, which comprises the following steps of forming an initial data matrix according to all operation and maintenance QoS attribute values in each operation and maintenance field of cloud resources under the cloudy environment, and carrying out dimensionless operation on the initial data matrix to obtain a normalized matrix code Mc: calculating the operation and maintenance center P of the multi-operation and maintenance field set C based on the normalized matrix code McOAnd polar boundary PeObtaining the maximum operation and maintenance distance d of all operation and maintenance fieldsmaxAnd a minimum operation and maintenance distance dminCalculating the distance difference delta r between the energy levels of the multi-operation-dimension field; determining the operation and maintenance field actually divided by each operation and maintenance process based on a single operation and maintenance classification algorithm, and estimating the index value i of the operation and maintenance field where each operation and maintenance process is locatedf(ii) a Forming an operation and maintenance field set S ordered according to potential energy values according to the potential energy value of each operation and maintenance field in the multi-operation and maintenance field set C, and calculating the total migration delay ratio of the two operation and maintenance fields; and predicting the behavior pattern during the migration of the operation and maintenance field by using an autoregressive prediction model.
Description
Technical Field
The invention relates to the technical field of cloud resource operation and maintenance, in particular to a cloud resource automatic operation and maintenance method in a multi-cloud environment.
Background
As cloud technologies are continuously applied to the business field, management problems related to cloud resources are becoming a focus of attention in academic and industrial fields, and a series of cloud resource management technologies are emerging. The resource management technologies mainly concern the problem of realizing the maximum utilization of cloud resources on the premise of meeting the requirements of users.
The cloud and the environment thereof are dynamically changed, which brings a series of problems for cloud management, and in the actual management process, the mainstream method is to provide operation and maintenance for users based on the elastic resource management capability of the cloud. Currently, a great deal of researchers solve the problem from different perspectives, wherein the main trend is to realize dynamic allocation of cloud resources by means of operation and maintenance quality, so that management of QoS becomes an important component in cloud management, which is a relevant standard scale for providing decisions for cloud implementation of flexible management, load balance management and resource optimization.
Aiming at dynamic multi-cloud operation and user requirements, the core problem of multi-cloud operation and maintenance management is how to effectively converge and organize multi-cloud operation and maintenance according to changed operation and maintenance, and independently and transparently provide operation and maintenance according to the change of operation and maintenance and the user requirements, so that continuous and stable operation of applications is ensured. The management method of the multi-cloud operation and maintenance should have the characteristics of autonomy (sensing changes and deciding behaviors of the multi-cloud operation and maintenance), flexibility (adapting to operation and maintenance and demand changes), utility optimization (rapidly and accurately providing operation and maintenance), and the like.
Disclosure of Invention
The invention provides a method for cloud resource automatic operation and maintenance in a multi-cloud environment, which comprises the following steps:
step 1, forming an initial data matrix according to all operation and maintenance QoS attribute values in each operation and maintenance field of cloud resources under a multi-cloud environment, and carrying out dimensionless operation on the initial data matrix to obtain a normalized matrix code Mc:
each line of the normalized matrix code Mc represents n operation and maintenance QoS attribute values in one operation and maintenance field, and the normalized matrix code Mc has k operation and maintenance fields;
step 2, calculating the operation and maintenance center P of the multi-operation and maintenance field set C based on the normalized matrix code McOAnd polar boundary PeObtaining the maximum operation and maintenance distance d of all operation and maintenance fieldsmaxAnd a minimum operation and maintenance distance dminCalculating the distance difference delta r between the energy levels of the multi-operation-dimension field;
step 3, determining the operation and maintenance field actually divided by each operation and maintenance process based on a single operation and maintenance classification algorithm, and estimating the index value i of the operation and maintenance field of each operation and maintenance processf;
Step 4, forming an operation and maintenance field set S = { S } ordered according to potential energy values according to the potential energy value of each operation and maintenance field in the multi-operation and maintenance field set C1,s2,…,sj,…};
and 6, predicting the behavior pattern during the migration of the operation and maintenance field by using an autoregressive prediction model.
Further, in the step 2, the operation and maintenance center POExpressed as:
PO=(min[p1], min[p2],…,min[pk]);
wherein [ p ]1]Then a one-dimensional matrix composed of n operation and maintenance QoS attribute values representing the first operation and maintenance field, [ p ]k]Representing a one-dimensional matrix formed by n operation and maintenance QoS attribute values of the kth operation and maintenance field;
the polar boundary PeIs represented as;
Pe=(max[p1], max[p2],…,max[pk]);
calculating all operation and maintenance distance vectors d in the multi-operation and maintenance field set Cs:
WhereinIs the ith QoS attribute value of the operation and maintenance field s;is the ith QoS attribute value of the operation and maintenance field center; n denotes n QoS attribute values of one operation and maintenance field.
Further, the single operation and maintenance classification algorithm comprises the following steps:
step 3.1, operation and maintenance distance d based on operation and maintenance field ssCalculating operation and maintenance potential energy Eps ;
Wherein, the first and the second end of the pipe are connected with each other,potential energy parameters;
Calculate the ithfThe contraction and expansion potential values of the operation and maintenance fieldAnd,
wherein, the first and the second end of the pipe are connected with each other,is the ithfThe operation and maintenance radius of each operation and maintenance field;
step 3.2, potential energy E of cloud resource spsAnd a firstAverage potential energy of individual operation and maintenance fieldHigh energy level valueAnd low energy levelAnd comparing, determining the index value of the cloud resource s to be divided into the operation and maintenance field,
step 3.2, potential energy E of the operation and maintenance field spsAnd the ithfAverage potential energy and shrinkage potential energy values of individual operation and maintenance fieldAnd expansion potential energy valueComparing and determining an index value of the operation and maintenance field s;
and 3.3, updating the average potential energy of the operation and maintenance field s with the determined index value.
Further, in the step 5, the convergence coefficient of the real-time operation and maintenance field migration is determinedDefined as the total migration delay ratio of the two operation and maintenance fields:
wherein, T1And T2Respectively the migration duration, V, of the two operation and maintenance fields1And V2The data volume transmitted in unit time of the two operation and maintenance fields is respectively.
Further, in step 6, the number m of visits to the operation and maintenance field is determined by a group of times m within the time p1,m2,…,mpLinearly combining with white noise of time t to obtain a predicted value m of the access times of the operation and maintenance field of the period tt:
Wherein, the first and the second end of the pipe are connected with each other,in order to be a linear least squares estimate,to estimate the parameters;
according to the least square estimation method of the linear model, the linear equation set is converted into the following three vectors:
Further, a regression model is fitted using sample data of length N, assuming M0Is the sum of the squares of the residuals of a one-dimensional regression model, M1Is the squared remainder of the one-dimensional regression model, the regression model distribution F is as follows:
sample data of length N follows an F distribution.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the description below are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a schematic flow chart of a cloud resource automation operation and maintenance method in a cloud environment according to the present invention;
FIG. 2 is a schematic flow chart of a single operation and maintenance classification algorithm of the present invention;
FIG. 3 is a schematic diagram of the migration structure of the operation and maintenance field of the present invention;
FIG. 4 is a diagram illustrating the migration and migration times of the operation and maintenance field predicted by the regression model according to the present invention.
Detailed Description
In order to make the embodiments of the present application better understood, the technical solutions in the embodiments of the present application will be clearly described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only some embodiments of the present application, but not all embodiments.
In the drawings of the embodiments of the present invention, in order to better and more clearly describe the working principle of each element in the system, the connection relationship of each part in the apparatus is shown, only the relative position relationship between each element is clearly distinguished, and the restriction on the signal transmission direction, the connection sequence, and the size, the dimension, and the shape of each part structure in the element or structure cannot be formed.
As shown in fig. 1, a schematic flow chart of the method for cloud resource automation operation and maintenance in a cloud environment of the present invention includes the following steps:
step 1, extracting operation and maintenance QoS information in a multi-operation and maintenance field set C of cloud resources in a multi-cloud environment, and acquiring a normalized matrix code Mc of the operation and maintenance QoS information.
The QoS (Quality of Service) refers to that a cloud resource can provide better Service capability for specified network communication by using various basic technologies, is a security mechanism for the cloud resource, and is a technology for solving problems such as cloud resource delay and blocking.
Under normal circumstances, if the cloud resources are only used for a specific application system without time limitation, no QoS is required, such as Web application, or E-mail setting, etc. But is essential for critical and multimedia applications. When cloud resources are overloaded or congested, QoS can ensure that important traffic is not delayed or discarded, while ensuring efficient operation of the cloud resources. Often, the service functions provided by different cloud resources are different, and even among cloud resources providing similar service functions, their QoS is different due to various reasons (e.g., different technical modes and distribution locations).
And forming an initial data matrix according to the actual factor values of the operation and maintenance fields of the cloud resources in the multi-cloud environment, and carrying out non-dimensionalization on the initial data matrix to obtain a normalized matrix code Mc, wherein the normalized matrix code Mc comprises all operation and maintenance QoS attribute values in the operation and maintenance fields.
Each row of the normalized matrix code Mc represents n operation and maintenance QoS attribute values in one operation and maintenance field, and the normalized matrix code Mc of the above formula has k operation and maintenance fields.
Step 2, calculating the operation and maintenance center P of the multi-operation and maintenance field set C based on the normalized matrix code McO:
PO=(min[p1], min[p2],…,min[pk]) (1) ;
Wherein [ p ]1]Then the one-dimensional matrix of n operation and maintenance QoS attribute values representing the first operation and maintenance field, i.e. the first row of the normalized matrix code Mc, [ p ]k]The k-th row of the normalized matrix code Mc is the one-dimensional matrix formed by the n operation and maintenance QoS attribute values of the k-th operation and maintenance field.
Operation and maintenance center PORefers to the central point of the multi-operation field set C, around which the operation field of the cloud resource in all the multi-cloud environments is created, and is represented as a k-tuple vector, where each element represents the minimum value of all the operation QoS attribute values in the operation field.
Calculating the polar boundary P of the multi-operation and maintenance field set Ce;
Pe=(max[p1], max[p2],…,max[pk]) (2);
Polar boundary P of multi-operation and maintenance field set CeThe boundary of the outermost layer of the operation and maintenance field of the cloud resources in the cloud environment represents the last stage of operation and maintenance energy level. It is also represented as a k-tuple vector, where each element represents the maximum of the QoS attribute values of all the operations in the operation field.
Calculating all operation and maintenance distance vectors d in the multi-operation and maintenance field set Cs:
Operation and maintenance distance vector dsIs the QoS vector P of the operation and maintenance field ssAnd operation and maintenance center P0The distance of (c). It is an important index for determining the operation and maintenance energy level, whereinIs the ith QoS attribute value of the operation and maintenance field s;is the ith QoS attribute value of the operation and maintenance field center; n denotes n QoS attribute values of one operation and maintenance field.
Simultaneously obtaining the maximum operation and maintenance distance d of all the operation and maintenance fields in the operation and maintenance fieldmaxAnd a minimum operation and maintenance distance dmin(ii) a Calculating the distance difference Delta r of the operation and maintenance energy level:
the difference in distance between the operational levels is the width of the operational field, which describes the distance change between two adjacent operational levels, whereinIs the number of operation and maintenance fields.
And step 3, determining operation and maintenance fields where all operation and maintenance processes are located. Determining the operation and maintenance field actually divided by each operation and maintenance process based on a single operation and maintenance classification algorithm, and estimating the index value i of the operation and maintenance field where each operation and maintenance process is locatedf。
The single operation and maintenance classification algorithm divides each operation and maintenance process into related operation and maintenance fields in a multi-cloud environment, compares the potential energy of the operation and maintenance process with the value of the energy level of a certain operation and maintenance field, and determines the operation and maintenance field where the operation and maintenance process is located, as shown in fig. 2, the method specifically comprises the following steps:
step 3.1, operation and maintenance distance d based on operation and maintenance field ssCalculating operation and maintenance potential energy Eps ;
Wherein, the first and the second end of the pipe are connected with each other,is a potential energy parameter.
The operation and maintenance potential energy is an indicated value of the operation and maintenance state of the operation and maintenance field, describes an actual calculation method of the energy level of the operation and maintenance field, and simultaneously converts the operation and maintenance state into a value which can be calculated by the operation and maintenance field.
Potential energy difference of operation and maintenanceRepresents the ithfThe maximum difference value between two energy levels of each operation and maintenance field;
calculate the ithfThe contraction and expansion potential values of the operation and maintenance fieldAndeach of which represents the i-th groupfHigh and low energy levels of the operation and maintenance field:
wherein, the first and the second end of the pipe are connected with each other,is the ithfThe operation and maintenance radius of each operation and maintenance field.
Step 3.2, potential energy E of the operation and maintenance field spsAnd the ithfAverage potential energy and shrinkage potential energy values of individual operation and maintenance fieldAnd expansion potential energy valueThe comparison is made and then the index value of the operation and maintenance field s is determined.
And 3.3, updating the average potential energy of the operation and maintenance field s with the determined index value.
Step 4, forming an operation and maintenance field set S = { S } ordered according to potential energy values according to the potential energy value of each operation and maintenance field in the multi-operation and maintenance field set C1,s2,…,sj,…}。
Service interruption is most likely to trigger migration of an operation and maintenance field in a fault, and in the embodiment, an automatic migration decision step of the operation and maintenance field in a cloud environment is adopted, so that high performance and good load balance of cloud resource operation and maintenance automation in the cloud environment are achieved.
For a given deployment of the operation and maintenance farm in a cloudy environment, in order to maintain the operation and maintenance farm in a relatively stable environment and avoid the occurrence of high failure rates, the resources of the operation and maintenance farm have their own stability thresholds, which is an upper limit for the operation and maintenance utilization in the cloudy environment. If once the established threshold is exceeded, some appropriate operation and maintenance field migration scheduling must be performed and the operation and maintenance field with the relatively short migration time is selected for migration.
wherein, T1And T2The migration durations, V, of the two operation and maintenance fields respectively1And V2The data volume transmitted in unit time of the two operation and maintenance fields is respectively.
For a given operation and maintenance field, the size of the migration duration of each operation and maintenance field and the amount of data transferred per unit time are fixed. Therefore, if the convergence factor is largeSmaller, the convergence of the operation and maintenance field migration is faster. Convergence coefficient with smaller operation and maintenance field migrationThe operation and maintenance field can help to reduce the overhead time in the cloud environment when the operation and maintenance field is migrated.
In a cloudy environment, in order to maintain the operation and maintenance field to operate in a relatively stable cloudy environment and avoid the occurrence of a high failure rate, the resources of the operation and maintenance field have their own stability threshold, which is an upper limit for stable utilization of cloud resources.
As shown in fig. 3, three operation and maintenance fields S1、S2、S3Migration Structure for example, three operation and maintenance fields S1、S2、S3The stability threshold value of the system is increased in sequence when the operation and maintenance field S is used1When the stability reaches a threshold value, the migration of the operation and maintenance field is realized, namely the operation and maintenance field S1Migrate to operation and maintenance site S2。
And 6, introducing an autoregressive prediction model to predict a behavior mode during the migration of the operation and maintenance field, namely the use condition and the access times of the operation and maintenance field.
If the operation and maintenance field utilization rate and the access times within the specific time period T are high, the probability that the two indexes are kept unchanged or increased in the next period is high. To a certain extent, the usage rate and the access times of the operation and maintenance field in a certain period T can be predicted through the usage condition of the operation and maintenance field in the previous period and the change of the access times of the operation and maintenance field by the user.
By a collected set of discretesAnd using the data to match the autoregressive model. Access times m of a group of operation and maintenance fields in passing time p1,m2,…,mpThe linear combination of the time t and white noise can obtain the predicted value m of the access times of the operation and maintenance field of the period ttThe following were used:
wherein the content of the first and second substances,is a linear least-squares estimate of the value,to estimate the parameters.
The time series parameters are assumed to be determined and the estimated parameters are taken into account. According to the least square estimation method of the linear model, the linear equation set is converted into the following three vectors:
In a cloudy environment, because there are many samples of the storage utilization rate in the operation and maintenance field, in this embodiment, the regression model is fitted with sample data of length N, assuming that M is the number of samples0Is the sum of the residual squares of the one-dimensional regression model. M1Is the squared remainder of the one-dimensional regression model, the regression model distribution F is as follows:
sample data of length N follows an F distribution. Fig. 4 is a diagram showing a distribution of migration times and migration times of the operation and maintenance field predicted according to the regression model.
In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, cause the processes or functions described in accordance with the embodiments of the application to occur, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored on or transmitted over a computer-readable storage medium. The computer-readable storage medium may be any available medium that can be accessed by a computer or a data storage device, such as an integrated maintenance machine, data center, etc., that includes one or more available media. The usable medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a magnetic tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a Solid State Disk (SSD)), among others.
While the invention has been described with reference to specific embodiments, the scope of the invention is not limited thereto, and those skilled in the art can easily conceive various equivalent modifications or substitutions within the technical scope of the invention. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (6)
1. The method for cloud resource automatic operation and maintenance in the cloud environment is characterized by comprising the following steps:
step 1, forming an initial data matrix according to all operation and maintenance QoS attribute values in each operation and maintenance field of cloud resources under a multi-cloud environment, and carrying out dimensionless operation on the initial data matrix to obtain a normalized matrix code Mc:
wherein, each line of the normalization matrix code Mc represents n operation and maintenance QoS attribute values in one operation and maintenance field, and the normalization matrix code Mc has k operation and maintenance fields in total;
step 2, calculating the operation and maintenance center P of the multi-operation and maintenance field set C based on the normalized matrix code McOAnd polar boundary PeObtaining the maximum operation and maintenance distance d of all operation and maintenance fieldsmaxAnd a minimum operation and maintenance distance dminCalculating the distance difference delta r between the energy levels of the multi-operation-dimension field;
step 3, determining the operation and maintenance field actually divided by each operation and maintenance process based on a single operation and maintenance classification algorithm, and estimating the index value i of the operation and maintenance field of each operation and maintenance processf;
Step 4, forming an operation and maintenance field set S = { S } according to the potential energy value of each operation and maintenance field in the multi-operation and maintenance field set C1,s2,…,sj,…};
Step 5, calculating the total migration delay ratio of the two operation and maintenance fields;
and 6, predicting a behavior mode during the migration of the operation and maintenance field by using an autoregressive prediction model.
2. The method for cloud resource automation operation and maintenance in the multi-cloud environment according to claim 1, wherein in the step 2, the operation and maintenance center P isOExpressed as:
PO=(min[p1], min[p2],…,min[pk]);
wherein [ p ]1]Then a one-dimensional matrix composed of n operation and maintenance QoS attribute values representing the first operation and maintenance field, [ p ]k]A one-dimensional matrix formed by n operation and maintenance QoS attribute values representing the kth operation and maintenance field;
the polar boundary PeIs represented as;
Pe=(max[p1], max[p2],…,max[pk]);
calculating all operation and maintenance distance vectors d in the multi-operation and maintenance field set Cs:
3. The method for cloud resource automation operation and maintenance in the multi-cloud environment according to claim 2, wherein the single operation and maintenance classification algorithm includes the following steps:
step 3.1, operation and maintenance distance d based on operation and maintenance field ssCalculating operation and maintenance potential energy Eps ;
Calculate the ithfThe contraction and expansion potential values of the operation and maintenance fieldAnd,
wherein the content of the first and second substances,is the ithfThe operation and maintenance radius of each operation and maintenance field;
step 3.2, potential energy E of the operation and maintenance field spsAnd ithfAverage potential energy and shrinkage potential energy values of individual operation and maintenance fieldAnd expansion potential energy valueComparing and determining an index value of the operation and maintenance field s;
and 3.3, updating the average potential energy of the operation and maintenance field s with the determined index value.
4. The method for automation operation and maintenance of cloud resources in a cloudy environment according to claim 1, wherein in the step 5, a convergence coefficient of a real-time operation and maintenance field is migratedDefined as the total migration delay ratio of the two operation and maintenance fields:
wherein, T1And T2Respectively the migration duration, V, of the two operation and maintenance fields1And V2The data volume transmitted in unit time of the two operation and maintenance fields is respectively.
5. The method for cloud resource automation operation and maintenance in the multi-cloud environment according to claim 4, wherein in the step 6, the number m of times of access to the operation and maintenance field is counted in a group of time p1,m2,…,mpLinearly combining with white noise of time t to obtain a predicted value m of the access times of the operation and maintenance field of the period tt:
Wherein the content of the first and second substances,is a linear least-squares estimate of the value,to estimate the parameters;
according to the least square estimation method of the linear model, the linear equation set is converted into the following three vectors:
6. The method of claim 5, wherein the regression model is fitted using sample data with length N, assuming M0Is the residual sum of squares, M, of the one-dimensional regression model1Is the squared remainder of the one-dimensional regression model, the regression model distribution F is as follows:
sample data of length N follows an F distribution.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210433207.2A CN114531365B (en) | 2022-04-24 | 2022-04-24 | Cloud resource automatic operation and maintenance method under multi-cloud environment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210433207.2A CN114531365B (en) | 2022-04-24 | 2022-04-24 | Cloud resource automatic operation and maintenance method under multi-cloud environment |
Publications (2)
Publication Number | Publication Date |
---|---|
CN114531365A CN114531365A (en) | 2022-05-24 |
CN114531365B true CN114531365B (en) | 2022-07-15 |
Family
ID=81627991
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210433207.2A Active CN114531365B (en) | 2022-04-24 | 2022-04-24 | Cloud resource automatic operation and maintenance method under multi-cloud environment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114531365B (en) |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106453546A (en) * | 2016-10-08 | 2017-02-22 | 电子科技大学 | Distributed storage scheduling method |
WO2017045211A1 (en) * | 2015-09-16 | 2017-03-23 | 国云科技股份有限公司 | Cloud computing task scheduling method constrained by multiple quality-of-service requirements |
CN110138612A (en) * | 2019-05-15 | 2019-08-16 | 福州大学 | A kind of cloud software service resource allocation methods based on QoS model self-correcting |
CN112988381A (en) * | 2021-02-26 | 2021-06-18 | 北京百度网讯科技有限公司 | Method and device for generating optimization information for cloud resources and electronic equipment |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103973803B (en) * | 2014-05-19 | 2017-10-13 | 英华达(上海)科技有限公司 | High in the clouds resource allocation system, method |
-
2022
- 2022-04-24 CN CN202210433207.2A patent/CN114531365B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2017045211A1 (en) * | 2015-09-16 | 2017-03-23 | 国云科技股份有限公司 | Cloud computing task scheduling method constrained by multiple quality-of-service requirements |
CN106453546A (en) * | 2016-10-08 | 2017-02-22 | 电子科技大学 | Distributed storage scheduling method |
CN110138612A (en) * | 2019-05-15 | 2019-08-16 | 福州大学 | A kind of cloud software service resource allocation methods based on QoS model self-correcting |
CN112988381A (en) * | 2021-02-26 | 2021-06-18 | 北京百度网讯科技有限公司 | Method and device for generating optimization information for cloud resources and electronic equipment |
Non-Patent Citations (1)
Title |
---|
一种多云管理平台的设计与实现;何锡点等;《网络安全技术与应用》;20200115(第01期);全文 * |
Also Published As
Publication number | Publication date |
---|---|
CN114531365A (en) | 2022-05-24 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Ismaeel et al. | Proactive dynamic virtual-machine consolidation for energy conservation in cloud data centres | |
He et al. | QoE-driven content-centric caching with deep reinforcement learning in edge-enabled IoT | |
CN105159751B (en) | The virtual machine migration method of energy efficient in a kind of cloud data center | |
US8010447B2 (en) | Operational risk control apparatus and method for data processing | |
CN112988398B (en) | Micro-service dynamic scaling and migration method and device | |
JP4977762B2 (en) | Dynamic network selection using the kernel | |
TWI725744B (en) | Method for establishing system resource prediction and resource management model through multi-layer correlations | |
JPWO2008102739A1 (en) | Virtual server system and physical server selection method | |
CN103986766A (en) | Self-adaptation load balancing job task scheduling method and device | |
Cai et al. | SARM: service function chain active reconfiguration mechanism based on load and demand prediction | |
Saxena et al. | Workload forecasting and resource management models based on machine learning for cloud computing environments | |
Tu et al. | An optimized cluster storage method for real-time big data in Internet of Things | |
Wei et al. | Dynamic network slice reconfiguration by exploiting deep reinforcement learning | |
CN115858155A (en) | Dynamic capacity expansion and contraction method and device for application resources of computing power network platform | |
CN115834587A (en) | Method and device for selecting target storage server and electronic equipment | |
Mahan et al. | A novel resource productivity based on granular neural network in cloud computing | |
CN114531365B (en) | Cloud resource automatic operation and maintenance method under multi-cloud environment | |
CN113254146A (en) | Cloud platform service trust value calculation, task scheduling and load balancing system and method | |
Zhang et al. | L-qoco: learning to optimize cache capacity overloading in storage systems | |
CN116643844A (en) | Intelligent management system and method for automatic expansion of power super-computing cloud resources | |
US10594620B1 (en) | Bit vector analysis for resource placement in a distributed system | |
CN106790485B (en) | Online service request scheduling method based on cost consideration in hybrid cloud mode | |
WO2019186243A1 (en) | Global data center cost/performance validation based on machine intelligence | |
Jing et al. | An energy efficient and resource‐constrained scheduling framework for smart city application | |
CN112199153A (en) | Virtual network function VNF instance deployment method and device |
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 |