KR102027303B1 - Migration System and Method by Fuzzy Value Rebalance in Distributed Cloud Environment - Google Patents

Abstract

The migration system is disclosed. The migration system performs a fuzzy fuzzy and learning on a resource monitoring unit that monitors resource usage, the resource usage data monitored by the resource monitoring unit, and determines whether fuzzy readjustment is necessary based on the prediction data acquired through the learning. A purge system, and a migration management unit for determining whether to migrate in accordance with the determination of whether or not to purge the fuzzy system.

Description

Migration System and Method by Fuzzy Value Rebalance in Distributed Cloud Environment

The present invention relates to a migration system and method, and more particularly to a system and method for predicting the state of the virtual machine through the fuzzy value readjustment in a distributed cloud environment, and performing the migration.

In recent years, energy usage has increased due to the increase in data centers.However, in a distributed cloud environment, there is a way to continuously receive existing services from a new geographically close data center even if a user moving from one data center moves to another. need.

The migration technology for managing resources can locate the virtual machine on a physical resource so that the workload can be executed most efficiently by identifying the characteristics of the workload to be performed when the virtual machine (VM) allocation is required. In addition, the company utilizes migration technology to improve performance and low power operation.

On the other hand, the purpose of the existing migration techniques is to reduce the overall migration time, and the service latency is not taken into account. Therefore, the performance of the application cannot be accurately predicted and the resources cannot be dynamically allocated in a situation where the system load is large. I have this. In particular, since a physical machine has a hotspot problem that degrades performance if it does not have enough resources according to the time of the allocated virtual machines, the CPU, memory, and network resource requirements of the virtual machine can be dynamically allocated to the service. What is needed is a system and method that can.

SUMMARY OF THE INVENTION An object of the present invention is to provide a migration system and method for guaranteeing a continuous service to a user and improving QoS so that a user can efficiently use resources in a distributed data center.

The migration system according to an embodiment of the present invention is a resource monitoring unit for monitoring the resource usage, performing fuzzy fuzzy and learning on the resource usage data monitored through the resource monitoring unit, fuzzy based on the prediction data obtained through the learning It may include a fuzzy system for determining whether re-adjustment is necessary, and a migration management unit for determining whether to migrate in accordance with the determination of whether to purge the fuzzy system.

The resource monitoring unit may include a workload analysis unit that analyzes a workload to be provided to a user based on the resource usage data, and a metric about the resource usage data to be fuzzy based on an analysis result of the workload. It may include a metric analysis unit for selecting the.

Here, the workload analyzer may analyze the pattern of the resource usage data of the workload and perform clustering on the resource usage data based on the analyzed pattern of the resource usage data.

Here, the fuzzy system is a fuzzy equalizer, which is a set of fuzzy equalizers and control rules that perform fuzzy through scale mapping for changing a range of resource usage data values into a corresponding universe of discourse. Decision-Making Logic to determine a rule based on a rule generation unit for generating and managing a rule (Fuzzy Rule), resource usage data purged through the fuzzy equalizer and fuzzy rules generated by the rule generator A fuzzy inference unit for performing a), and a depurifier for performing the depuration through the scale mapping to the discussion area corresponding to the range of the result value of the fuzzy inference unit.

The fuzzy system may further include a learning unit configured to perform learning on the resource use data purged through the fuzzy unit.

The apparatus may further include a readjustment determiner configured to determine whether the fuzzy readjustment is necessary based on the prediction data acquired through the learner.

Here, the readjustment determination unit may determine whether the fuzzy readjustment is necessary by comparing the QoS value of the prediction data with a preset threshold value.

Here, if it is determined that the fuzzy readjustment is necessary according to the readjustment determining unit, the rule generator may generate a new fuzzy rule.

The migration method according to an embodiment of the present invention comprises the steps of (a) monitoring resource usage, (b) performing fuzzy and learning on the resource usage data monitored through the step (a), (c) Determining whether fuzzy readjustment is necessary based on the prediction data obtained through step (b), and (d) determining whether to migrate according to whether to purge readjustment of step (c). have.

Here, the step (a) is (a-1) performing the analysis on the workload to be provided to the user based on the resource usage data, and (a-2) purge based on the analysis result for the workload The method may further include selecting a metric regarding the resource usage data to be converted.

Here, the step (b) includes the step of (b-1) performing fuzzy with respect to the resource usage data, and (b-2) with the resource usage data purged through the step (b-1). The method may further include performing learning and obtaining prediction data.

Here, the step (b) may further include (b-3) performing re-clustering on the purged resource usage data.

Here, in step (c), it may be determined whether a fuzzy readjustment is necessary by comparing the QoS value of the prediction data with a preset threshold value.

If it is determined that purge readjustment is necessary through step (c), steps (b) to (c) may be repeatedly performed until it is determined that purge readjustment is not necessary.

According to an embodiment of the present invention, it is possible to efficiently utilize resources and improve performance by utilizing migration in a distributed cloud environment, and to ensure an improved service in a distributed cloud environment.

In addition, the values of the indicators used in the migration can be fuzzy, and the values through the fuzzy re-adjustment can be reflected to adjust the factors that may affect the migration and to increase the resource efficiency in the migration.

1 illustrates an example of a cloud data center system to which the present invention can be applied.
2 is a block diagram of a migration system according to an embodiment of the present invention.
3 is a block diagram of a resource monitoring unit.
4 is a flowchart illustrating a migration method according to an embodiment of the present invention.
5 is a graph showing the results before and after learning for fuzzy readjustment.
6 is a graph illustrating an example of the result of the fuzzy readjustment.
7 illustrates a comparison of the accuracy of a migration system and method according to an embodiment of the present invention with an existing algorithm.

Specific structural or functional descriptions of the embodiments according to the inventive concept disclosed herein are merely illustrated for the purpose of describing the embodiments according to the inventive concept, and the embodiments according to the inventive concept. These may be embodied in various forms and are not limited to the embodiments described herein.

Embodiments according to the inventive concept may be variously modified and have various forms, so embodiments are illustrated in the drawings and described in detail herein. However, this is not intended to limit the embodiments in accordance with the concept of the present invention to specific embodiments, and includes modifications, equivalents, or substitutes included in the spirit and scope of the present invention.

Terms such as first or second may be used to describe various components, but the components should not be limited by the terms. The terms are only for the purpose of distinguishing one component from another component, for example, without departing from the scope of the rights according to the inventive concept, the first component may be called a second component, Similarly, the second component may also be referred to as the first component.

When a component is referred to as being "connected" or "connected" to another component, it may be directly connected to or connected to that other component, but it may be understood that other components may be present in between. Should be. On the other hand, when a component is said to be "directly connected" or "directly connected" to another component, it should be understood that there is no other component in between. Expressions describing relationships between components, such as "between" and "immediately between" or "directly neighboring", should be interpreted as well.

The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. Singular expressions include plural expressions unless the context clearly indicates otherwise. As used herein, the terms "comprise" or "having" are intended to designate that the stated feature, number, step, operation, component, part, or combination thereof is present, but one or more other features or numbers, It is to be understood that it does not exclude in advance the possibility of the presence or addition of steps, actions, components, parts or combinations thereof.

Unless defined otherwise, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art. Terms such as those defined in the commonly used dictionaries should be construed as having meanings consistent with the meanings in the context of the related art, and are not construed in ideal or excessively formal meanings unless expressly defined herein. Do not. Hereinafter, exemplary embodiments will be described in detail with reference to the accompanying drawings.

1 illustrates an example of a cloud data center system to which the present invention can be applied.

Referring to FIG. 1, the cloud data center system 1 may be a software-defined networking (SDN) -based system. In this case, the cloud data center system 1 may include a data center 10, an SDN 20, and the like. Migration system 30.

The data center 10 estimates the state of the virtual machine in consideration of the transmission / reception unit connected to the outside, the service recognition unit recognizing the service requested by the user, the resource monitoring unit monitoring the resource usage, and the priority, and performs the migration. It may include a virtual machine management unit for determining the virtual machine.

SDN 20 extends the virtual network to control and manage the cloud data center 10 to be interconnected. The SDN 20 may include a controller that checks an API, converts it into an interface that can be understood by the network device, and then transfers the controller to the network device and a service recognizer that recognizes the service requested by the user. Meanwhile, the SDN controller manages open flow switches constituting a physical network and open virtual switches (OvS: Open Virtual Switch) constituting a virtual network. Such OvSs may allow virtual machines created on the physical machine to be connected to the network.

A virtual machine connected to a network through OvS refers to a machine that is virtually created and operated based on the resources of the physical machine. The virtual machines may operate as if they were separate computing devices by operating an operating system (OS) separately.

At this time, the system in one virtual machine may be migrated to another virtual machine. Migration means migrating a system, application, or module from one environment to another. In this case, the existing environment where the system and the like existed and the new environment may not be the same. For example, system resources (CPU, memory, etc.) provided to the existing virtual machine and system resources provided to the new virtual machine may be different from each other.

On the other hand, it is apparent that the migration system 30 according to an embodiment of the present invention to be described below is applicable to other network environments as well as the SDN-based network environment described as an example.

2 is a block diagram of a migration system according to an embodiment of the present invention.

Referring to FIG. 2, the migration system 30 is a system for migrating a system in one of the virtual machines to another virtual machine, and includes a transceiver 310, a resource monitoring unit 330, and a fuzzy system 350. And the migration management unit 370.

The transceiver 310 exchanges data with the data center 10 through the SDN 20.

The resource monitoring unit 330 monitors the state of the virtual machine and / or resources provided to the virtual machine. More specifically, the resource monitoring unit 330 acquires data on the state of the virtual machine or the resource usage provided to the virtual machine by monitoring the CPU usage of the virtual machine, memory usage such as RAM, and / or network resource status. can do. In addition, the resource monitoring unit 330 may be a time (wait time) that the virtual machine waits, a time (execution time) the operation of the virtual machine, a period in which the operation of the virtual machine is terminated, and / or interruption of power supply. It is also possible to monitor the frequency and so on.

The monitoring result of the resource monitoring unit 330 may be transferred to the fuzzy system 350. In this case, the resource monitoring unit 330 may transmit the monitoring result to the purge system 350 periodically or continuously.

Referring to FIG. 3, which shows a block diagram of a resource monitoring unit, the resource monitoring unit 330 may include a workload analyzer and a metric analyzer.

The workload analyzer analyzes the workload according to the service to be provided to the user based on the resource usage data monitored by the resource monitor 330. More specifically, the workload analysis unit analyzes the pattern of the resource usage data monitored by the resource monitoring unit 330, performs clustering analysis on the resource usage data by clustering based on the analyzed resource usage pattern data. In this case, the K-means algorithm may be used as the clustering algorithm used for cluster analysis, but various algorithms may be used without being limited thereto.

In addition, the workload analysis unit may perform re-clustering according to the resource usage data purged through the fuzzy control unit 351.

The metric analyzer performs an analysis on the metric and selects a metric regarding the resource usage data to be fuzzy. The metric analyzer may compare metrics based on the purpose of the service recognized by the service recognizer and clustered resource usage data, and select a metric for improving migration efficiency.

Table 1 below is an example of a metric according to the purpose of the service.

Service purpose goal Metrics Performance efficiency Minimizing time Transferred pages Network traffic Bandwidth Waiting time Number of migration VM execution time VM RAM workload Increasing resource utilization Resource utilization
Response time Load balancing Resource utilization Improving Reliability Scalability Throughput Response time Power consumption Increasing resource utilization Numberof migration Running server / VM Resource utilization Power consumption Energy consumption frequency Reducing bottleneck Resource utilization Bandwidth

The fuzzy system 350 performs learning of the monitored resource usage data through the resource monitoring unit 330, or purges the resource usage data of the selected metric based on the monitoring result and the learning result and performs a fuzzy rule. Can be generated. The purge system 350 includes a purge controller 351, a learner 353, and a readjustment determiner 355.

The fuzzy control unit 351 may purge the resource usage data of the selected metric based on the resource monitoring result and the learning result and generate a fuzzy rule. The purge control unit 351 includes a purge unit 351a, a rule generator 351d, a purge inference unit 351b, and a depurator 351c.

The fuzzy unit 351a may perform fuzzy by converting an input variable, which is an average value of the monitored resource usage data, into a predetermined value at which the command can be realized. That is, the fuzzy unit 351a purges the input variable through scale mapping, which changes the range of the value of the input variable into a corresponding universe of discourse.

The rule generator 351d records and manages a set of control rules. Meanwhile, the rule generation unit 351d may generate a new rule when the fuzzy re-adjustment is necessary according to the re-adjustment determination unit 355 to be described later.

The fuzzy inference unit 351b may perform decision-making logic that determines a rule based on the fuzzy input and the fuzzy rule generated by the rule generator 351d. The resultant value of the purge is transferred to the depurifier 351c.

The depurator 351c performs a scale mapping operation of converting an output variable into a desired range and converting it into a discussion area. The diffused result value according to the scale mapping may be transmitted to the resource monitoring unit 330.

The learner 353 performs machine learning on fuzzy resource usage data. Machine learning can be implemented using any machine learning algorithm. Machine learning algorithms include, for example, deep neural networks (DNNs), convolutional neural networks (CNNs), recurrent neural networks (RNNs), and deep trust neural networks (DBNs). And deep Q-Networks (Deep Q-Networks) may be implemented using at least one, but the machine learning algorithm that can be implemented is not limited thereto.

The learning unit 353 may check the change of the resource state by performing the learning based on the fuzzy resource usage data, and re-install according to the learning result (that is, according to the change of the resource state) in the fuzzy control unit 351. By doing fuzzy, you can reflect the exact use of resources.

The readjustment determiner 355 determines whether fuzzy reconditioning is necessary based on whether the QoS is satisfied based on the prediction data acquired through the learner 353. More specifically, the readjustment determination unit 355 determines whether the QoS is satisfied by using the prediction data, which may be determined by comparing the QoS value of the prediction data with a preset threshold value.

)이 기 설정된 임계값(

) 보다 작다면, QoS를 만족하는 것으로 판단할 수 있다.As an example, if the service is to improve the performance efficiency, the QoS value defined by Equation 1 below (

) Is the preset threshold (

If it is smaller than), it can be determined that the QoS is satisfied.

)이 기 설정된 임계값(

) 보다 작다면 마이그레이션 실행 시간을 최소화하는 목적에 대한 QoS를 만족하는 것으로 보아 퍼지 재조정을 할 필요가 없는 것으로 판단할 수 있다.That is, the QoS value (

) Is the preset threshold (

Less than), it is determined that there is no need for fuzzy rebalancing because it satisfies QoS for the purpose of minimizing migration execution time.

)이 기 설정된 임계값(

) 보다 작다면, QoS를 만족하는 것으로 판단할 수 있다.As another example, if the service is to improve performance efficiency, the QoS value defined by Equation 2 below (

) Is the preset threshold (

If it is smaller than), it can be determined that the QoS is satisfied.

이다. 즉, 트래픽 수요와 관련된 평균제곱오차(MSE)값인 QoS값(

)이 기 설정된 임계값(

) 보다 작다면 수요 예측이 오차 범위 내에 이루어진 것으로 보아 퍼지 재조정을 할 필요가 없는 것으로 판단할 수 있다.here,

to be. That is, the QoS value (MSE) value related to traffic demand (

) Is the preset threshold (

Less than), the demand forecast is within the margin of error, indicating that no fuzzy readjustment is necessary.

That is, the readjustment determination unit 355 may determine whether the QoS is satisfied to determine whether to re-adjust the fuzzy, and transmit a signal for fuzzy reconditioning to the fuzzy system 350 if the QoS is not satisfied.

On the other hand, the QoS value for determining whether or not to re-adjust fuzzy is not limited to the above embodiment, it is obvious that it may vary depending on the service purpose and metrics provided to the user.

The migration manager 370 determines whether to migrate according to whether to purge the fuzzy system 350 again. If it is determined that the fuzzy readjustment is no longer necessary, the migration manager 370 may determine whether to migrate according to the predicted state of the virtual machine through the virtual machine manager.

4 is a flowchart illustrating a migration method according to an embodiment of the present invention. Hereinafter, a description of a portion overlapping with the above-described portion will be omitted.

Referring to FIG. 4, step S410 performs analysis on the workload. In step S410 analyzes the pattern of the resource usage data monitored by the resource monitoring unit 330, clustering based on the analyzed pattern to perform cluster analysis on the resource usage data of the workload. To this end, the step of monitoring the resources provided to the virtual machine and / or the virtual machine through the resource monitoring unit 330 may be performed prior to step S410.

In step S420, the metric is analyzed according to the resource usage data clustered in step S410, and a metric for improving migration efficiency (that is, for guaranteeing QoS) is selected. In operation S420, a score indicating a degree of importance for metric selection may be additionally performed. On the other hand, depending on the purpose of the service, a number of different metrics can be used simultaneously.

Step S430a performs fuzzy on resource usage data related to the selected metric based on the monitored resource usage data. Purge is performed through purge system 350. On the other hand, if it is determined that the fuzzy re-adjustment is necessary through the steps S440 to S470 to be described later, re-fuzzy based on the monitored resource usage data and the learned resource usage data may be reflected to reflect the state of the resource. (S430b)

In step S440, re-clustering is performed on the purged resource usage data. That is, clustering of the fuzzy resource usage data is performed again to perform cluster analysis and reflect the state of resources.

In operation S450, learning about resource usage data is performed to predict a change in resource usage. In operation S450, the change in resource usage may be predicted using the trained model, and based on the determination, the fuzzy readjustment may be determined.

Step S460 determines whether or not to purge. The readjustment is determined by comparing the QoS value for the resource usage data predicted through the step S450 with a preset threshold value, and the preset threshold value may vary depending on the service purpose and the selected metric.

If it is determined in step S460 that the predetermined QoS value is satisfied (S470), the state of the virtual machine is predicted (S480), and it is determined whether to migrate according to the prediction result (S490).

On the other hand, if it is determined in step S460 that the predetermined QoS value is not satisfied (S470), it may be considered that fuzzy re-adjustment is necessary and re-fuzzy may be performed (S430b).

The following describes an embodiment of the present inventors migration system 30 and method.

<Example>

According to an embodiment of the present invention, learning is performed on any resource usage data to determine whether to re-fuzzy.

Referring to FIG. 5, which shows the results before and after the training for fuzzy rebalancing, it is possible to know the change in the fuzzy resource usage data (CPU usage and RAM usage) through the training, and to predict the change in resource usage. You can create a new fuzzy rule based on this.

Table 2 below shows the newly generated fuzzy rules.

Power Resource Utilization Number of VM Waiting time One Very high Very high Very high Very high 2 Very high Very low Very low Very low 3 Very low Very high Very low Very low 4 Very low Very low Very low Very low 5 Very low Very low Very high Very low 6 Very low Very low Very low Very high 7 Very low Very low Very low Very low

That is, a new fuzzy rule for each metric is generated and the state of the virtual machine is predicted according to each newly generated fuzzy rule.

Referring to FIG. 6, which shows an example of the result of the fuzzy readjustment, it is possible to predict the state (energy consumption) of the virtual machine according to each newly generated fuzzy rule.

7 illustrates a comparison of the accuracy of a migration system and method according to an embodiment of the present invention with an existing algorithm.

Referring to FIG. 7, the horizontal axis represents time intervals T1: ~ 3h, T2: 3-6h, T3: 7-12h, and T4: 13-24h, and the vertical axis represents MSE for the predicted state of the virtual machine. That is, it can be seen that the prediction of the virtual machine according to the present invention exhibits an improved prediction rate compared to the conventional prediction algorithm in most time intervals.

As a result, in the case of using the present invention, it is possible to improve the migration efficiency through fuzzy readjustment according to the user's requirements and the purpose of the service in a distributed cloud environment.

The apparatus described above may be implemented as a hardware component, a software component, and / or a combination of hardware components and software components. For example, the devices and components described in the embodiments may be, for example, processors, controllers, arithmetic logic units (ALUs), digital signal processors, microcomputers, field programmable arrays (FPAs), It may be implemented using one or more general purpose or special purpose computers, such as a programmable logic unit (PLU), microprocessor, or any other device capable of executing and responding to instructions. The processing device may execute an operating system (OS) and one or more software applications running on the operating system. The processing device may also access, store, manipulate, process, and generate data in response to the execution of the software. For convenience of explanation, one processing device may be described as being used, but one of ordinary skill in the art will appreciate that the processing device includes a plurality of processing elements and / or a plurality of types of processing elements. It can be seen that it may include. For example, the processing device may include a plurality of processors or one processor and one controller. In addition, other processing configurations are possible, such as parallel processors.

The software may include a computer program, code, instructions, or a combination of one or more of the above, and configure the processing device to operate as desired, or process it independently or collectively. You can command the device. Software and / or data may be any type of machine, component, physical device, virtual equipment, computer storage medium or device in order to be interpreted by or to provide instructions or data to the processing device. Or may be permanently or temporarily embodied in a signal wave to be transmitted. The software may be distributed over networked computer systems so that they may be stored or executed in a distributed manner. Software and data may be stored on one or more computer readable recording media.

The method according to the embodiment may be embodied in the form of program instructions that can be executed by various computer means and recorded in a computer readable medium. The computer readable medium may include program instructions, data files, data structures, etc. alone or in combination. The program instructions recorded on the media may be those specially designed and constructed for the purposes of the embodiments, or they may be of the kind well-known and available to those having skill in the computer software arts. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tape, optical media such as CD-ROMs, DVDs, and magnetic disks, such as floppy disks. Magneto-optical media, and hardware devices specifically configured to store and execute program instructions, such as ROM, RAM, flash memory, and the like. Examples of program instructions include not only machine code generated by a compiler, but also high-level language code that can be executed by a computer using an interpreter or the like. The hardware device described above may be configured to operate as one or more software modules to perform the operations of the embodiments, and vice versa.

Although the embodiments have been described with reference to the accompanying drawings as described above, various modifications and variations are possible to those skilled in the art from the above description. For example, the described techniques may be performed in a different order than the described method, and / or components of the described systems, structures, devices, circuits, etc. may be combined or combined in a different form than the described method, or other components. Or even if replaced or substituted by equivalents, an appropriate result can be achieved.

Therefore, other implementations, other embodiments, and equivalents to the claims are within the scope of the claims that follow.

Claims (14)

A resource monitoring unit for monitoring resource usage;
A fuzzy system performing fuzzy and learning on the resource usage data monitored by the resource monitoring unit and determining whether fuzzy readjustment is necessary based on the predicted data obtained through the learning; And
It includes a migration management unit for determining whether to migrate in accordance with the determination of whether or not to re-adjust the fuzzy system,
The purge system
A fuzzy equalizer for performing fuzzy through scale mapping for changing a range of the resource usage data value into a corresponding universe of discourse;
A rule generator for generating and managing a fuzzy rule, which is a set of control rules;
A fuzzy inference unit that performs decision-making logic to determine a rule based on the resource usage data purged through the fuzzy unit and the fuzzy rule generated by the rule generator;
A depurifier for performing depurification through scale mapping to change into a discussion area corresponding to a range of result values of the fuzzy inference unit;
A learning unit that learns the resource usage data purged through the fuzzy unit; And
And a readjustment determination unit determining whether a fuzzy readjustment is necessary based on the prediction data acquired through the learning unit.
And the readjustment determination unit determines whether a fuzzy readjustment is necessary by comparing a QoS value with respect to the predicted data and a preset threshold value.
The method of claim 1,
The resource monitoring unit
A workload analyzer configured to analyze a workload to be provided to a user based on the resource usage data; And
And a metric analyzer configured to select a metric for the resource usage data to be fuzzy based on the analysis result of the workload.
The method of claim 2,
The workload analysis unit analyzes the pattern of the resource usage data of the workload, and performs a clustering of the resource usage data based on the analyzed pattern of the resource usage data.
delete delete delete delete The method of claim 1,
And the rule generation unit generates a new fuzzy rule when it is determined that fuzzy readjustment is necessary according to the readjustment determining unit.
The migration method performed by the migration system,
(a) monitoring resource usage;
(b) performing fuzzy and learning on the resource usage data monitored through step (a);
(c) determining whether fuzzy readjustment is necessary based on the prediction data obtained through step (b); And
(d) determining whether to migrate according to whether to re-fuzzy in step (c);
Step (b) is
(b-1) performing fuzzy through scale mapping to change the range of resource usage data values into corresponding discussion areas;
(b-2) performing learning on the resource usage data purged through step (b-1) and obtaining prediction data; And
(b-3) performing re-clustering on the fuzzy resource usage data,
The step (c) is a migration method for determining whether the fuzzy re-adjustment is necessary by comparing the QoS value and the predetermined threshold value for the prediction data.
The method of claim 9,
Step (a) is
(a-1) performing analysis on the workload to be provided to the user based on the resource usage data; And
(a-2) selecting a metric for the resource usage data to be fuzzy based on the analysis result for the workload.
delete delete delete The method of claim 9,
If it is determined that the purge readjustment is necessary through the step (c), the step (b) to (c) is repeatedly performed until it is determined that the purge readjustment is not necessary.

Images