KR102613662B1 - A method for providing virtualization service based on greedy/optimal algorithm and a virtualization service provision system - Google Patents

Abstract

A virtualization service provision system according to an embodiment of the present invention is a virtualization service provision system that implements a virtualization service provision method for communicating with a user's computing device to provide a cloud service to the user's computing device, comprising: A transmission/reception module that receives request information for cloud services from; A storage module that stores information necessary to implement a virtualization service provision method; and a control module that virtualizes at least some resources of the physical server based on the request information, wherein the request information includes a request to provide a cloud service for an individual resource, and the control module is configured to virtualize at least some resources of the physical server based on the request information. Only individual resources corresponding to the requested information can be virtualized.

Description

Virtualization service provision method and virtualization service provision system based on greedy/optimal algorithm {A METHOD FOR PROVIDING VIRTUALIZATION SERVICE BASED ON GREEDY/OPTIMAL ALGORITHM AND A VIRTUALIZATION SERVICE PROVISION SYSTEM}

The present invention relates to a virtualization service provision system and a virtualization service provision method. More specifically, it relates to a virtualization service provision system and a virtualization service provision method that can provide cloud services by virtualizing resources to suit the needs of users.

As Internet network technology increases and space restrictions for computer work, such as working from home, disappear, the cloud environment has recently grown rapidly. Cloud services are largely divided into those that provide virtual machines and those that provide them through containers. To provide these services, the server virtualization method creates virtual machines or containers by virtualizing all resources of the physical server through a hypervisor or Docker on the physical server. However, because this virtualization method uses all computing resources (CPU, GPU, memory, storage, etc.), it can result in indiscriminate waste of physical server resources.

The present invention is intended to solve the above-described problems, and seeks to provide a virtualization service provision system and a virtualization service provision method that can provide cloud services by individually virtualizing resources.

A virtualization service provision system according to an embodiment of the present invention is a virtualization service provision system that implements a virtualization service provision method for communicating with a user's computing device to provide a cloud service to the user's computing device, comprising: A transmission/reception module that receives request information for cloud services from; A storage module that stores information necessary to implement a virtualization service provision method; and a control module that virtualizes at least some resources of the physical server based on the request information, wherein the request information includes a request to provide a cloud service for an individual resource, and the control module is configured to virtualize at least some resources of the physical server based on the request information. Only individual resources corresponding to the requested information can be virtualized.

A virtualization service provision system according to an embodiment of the present invention is a virtualization service provision system for providing a cloud service to a user's computing device by communicating with the user's computing device, where request information for a cloud service is received from the user's computing device. A transmitting and receiving module that receives; and a control module that virtualizes at least some resources of the physical server based on the request information, wherein the request information includes a request to provide a cloud service for an individual resource, and the control module is configured to virtualize at least some resources of the physical server based on the request information. Only individual resources corresponding to the requested information can be virtualized.

Additionally, the request information may include at least one of detailed information on the central processing unit, detailed information on the graphics processing unit, detailed information on the main memory, and detailed information on the auxiliary memory.

In addition, the control module allocates the resources of the physical server according to a predetermined method and virtualizes the resources of the physical server according to the request information, and the predetermined method is used if the user requests a cloud service over a certain amount of resources. The D algorithm can be used to allocate the resources of the physical server, and if the user requests cloud services less than a certain amount of resources, the optimal algorithm can be used to allocate the physical server's resources.

In addition, the transmitting and receiving module further includes an optimal analysis module that calculates an optimal plan, which is a resource allocation plan necessary for the user, using a predetermined optimal allocation method based on operation information received from the user's computing device, and the predetermined optimal allocation method. The method analyzes the operation information to minimize an objective function, and the objective function may include a first objective function related to the user's service cost.

Additionally, the optimal analysis module can calculate the optimal solution by excluding resources that are not compatible with the user's computing device.

In addition, the control module performs virtualization in units of individual resources of the physical servers in some physical servers, and virtualization in units of all resources of the physical servers in the remaining physical servers. The predetermined optimal allocation method is performed on individual resources. This may be a method of calculating the optimal method by also considering whether to proceed with virtualization in units or in units of integrated resources.

In addition, the optimal analysis module calculates an alternative plan that is different from the optimal solution when the resource of the physical server that is the target of the optimal solution satisfies the first limit condition, and the alternative solution is the optimal solution. If the optimal method is virtualization in units of individual resources, it may be virtualization in units of integrated resources. If the optimal method is virtualization in units of integrated resources, it may be virtualization in units of individual resources.

In addition, a cost calculation module that calculates the service cost for the optimal method; and an interface module that calculates an interface provided to the user's computing device, wherein the cost calculation module calculates a service discount price for the alternative method and a normal service price for the optimal method, and the interface module It is possible to calculate the price calculated in the cost calculation module and an interface for selecting the alternative plan and the optimal plan.

A virtualization service provision method according to an embodiment of the present invention is implemented by a virtualization service provision system, and in the virtualization service provision method for providing a cloud service to a user's computing device, the user's computing device is implemented by a transmission/reception module. Receiving request information for a cloud service from a device; and virtualizing, by a control module, at least some resources of the physical server based on the request information, wherein the direct request information is information about a request from a user who has specified a necessary resource, and is a cloud service of an individual resource. It includes a provision request, and the control module can virtualize only individual resources corresponding to the direct request information according to the direct request information.

In addition, it further includes calculating, by the optimal analysis module, an optimal plan, which is a resource allocation plan necessary for the user, using a predetermined optimal allocation method based on operation information received from the user's computing device, The allocation method analyzes the operation information to minimize the objective function, and the objective function may include a first objective function related to the user's service cost.

The virtualization service provision system and virtualization service provision method implementing individual virtualization of resources according to the present invention can expand the range of choices for users.

Additionally, the resources of the physical server can be utilized efficiently.

Additionally, it can further popularize the cloud service market.

You can talk.

However, the effects of the present invention are not limited to the effects described above, and effects not mentioned can be clearly understood by those skilled in the art from this specification and the attached drawings.

1 is a relationship diagram of a virtualization service provision system according to an embodiment of the present invention.
Figure 2 is a configuration diagram of a virtualization service provision system according to an embodiment of the present invention.
Figure 3 is a configuration relationship diagram of a virtualization service provision system according to an embodiment of the present invention.
Figure 4 is a flowchart of a method for providing virtualization services according to an embodiment of the present invention.

Hereinafter, specific embodiments of the present invention will be described in detail with reference to the drawings. However, the spirit of the present invention is not limited to the presented embodiments, and those skilled in the art who understand the spirit of the present invention may add, change, or delete other components within the scope of the same spirit, or create other degenerative inventions or this invention. Other embodiments that are included within the scope of the invention can be easily proposed, but this will also be said to be included within the scope of the invention of the present application.

In addition, components having the same function within the scope of the same idea shown in the drawings of each embodiment will be described using the same reference numerals.

1 is a relationship diagram of a virtualization service provision system according to an embodiment of the present invention.

Referring to FIG. 1, the virtualization service provision system operates, maintains, and manages physical servers to smoothly provide cloud services to users using virtual machines, and can collect and transmit necessary information to users.

To this end, the virtualization service provision system may be connected to the physical server 200 and/or the user computing device 300 through a wired/wireless network.

The network in the present invention may be a core network integrated with a wired public network, wireless mobile communication network, or mobile Internet, etc., and may include TCP/IP protocols and various services existing at the upper layer thereof, such as HTTP (Hyper Text Transfer Protocol) and HTTPS. (Hyper Text Transfer Protocol Secure), Telnet, FTP (File Transfer Protocol), DNS (Domain Name System), SMTP (Simple Mail Transfer Protocol), etc., which may refer to a worldwide open computer network structure, examples of which include It comprehensively refers to a data communication network that can transmit and receive data in various forms without limitation.

The physical server in the present invention may include other components to perform the server environment. A server can include any type of device.

For example, a server may be a digital device, such as a laptop computer, notebook computer, desktop computer, web pad, or mobile phone, equipped with a processor and equipped with memory and computing power.

In one example, the server may be a web server. However, it is not limited to this, and the type of server can be changed in various ways at a level that is obvious to a person skilled in the art.

FIG. 2 is a configuration diagram of a virtualization service provision system according to an embodiment of the present invention, and FIG. 3 is a configuration diagram of a virtualization service provision system according to an embodiment of the present invention.

Referring to Figures 2 and 3, the virtualization service provision system 100 according to an embodiment of the present invention is a virtualization service provision system 100 for providing a cloud service to the user's computing device by communicating with the user's computing device. ), which may include a transmission/reception module 110 that receives request information for a cloud service from the user's computing device, and a control module 120 that virtualizes at least some resources of the physical server 200 based on the request information. You can.

In addition, the virtualization service providing system 100 performs an optimal analysis in which the transmission/reception module 110 calculates an optimal plan, which is a resource allocation plan necessary for the user, using a predetermined optimal allocation method based on operation information received from the user's computing device. It may further include a module 130, a cost calculation module 140 that calculates the service cost for the optimal method, and an interface module 150 that calculates an interface provided to the user's computing device.

In addition, the virtualization service provision system 100 implements a model creation module 160 that generates an allocation analysis model for calculating the optimal solution, a user analysis module 170 that determines the user's maliciousness, and a virtualization service provision method. It may further include a storage module 180 that stores all necessary information.

The transmitting and receiving module 110 can transmit and receive information necessary to implement a virtualization service provision method with the user's computing device and the physical server 200.

For example, the transmitting and receiving module 110 may include a cellular module, WiFi module, Bluetooth module, GNSS module, NFC module, RF module, 5G module, LTE module, NB-IOT module, and/or LoRa module.

However, it is not limited to this, and the modules included in the communication module can be modified in various ways at a level that is obvious to those skilled in the art.

The transmission/reception module 110 may receive request information and/or operation information from the user's computing device.

Request information may be generated from a computing device when a requester requests a cloud service through the computing device.

To this end, the transmission/reception module 110 may transmit the interface calculated by the interface module 150 to the requester's computing device.

Request information may include information about whether it is a direct or indirect request method, information about the desired resource in the case of a direct request, and information about the purpose of use in the case of an indirect request.

The direct request method may refer to a method in which the requester specifies and requests the resource for which he or she wishes to receive support.

For example, through the direct request method, the requester can request cloud services for only 10TB of auxiliary storage.

For example, through the direct request method, the requester can request cloud services for only 8GB of main memory.

Information on resources is at least one of detailed information on the central processing unit (CPU), detailed information on the graphics processing unit (GPU), detailed information on the main memory (RAM), and detailed information on the auxiliary storage device (Storage). Can contain one piece of information.

For example, in the case of detailed information about the central processing unit, it may include specific information about the number of cores of the CPU and CPU memory.

For example, detailed information about the graphics processing unit may include specific information about GPU speed, CPU memory, CPU cooling, and CPU clock.

For example, detailed information about an auxiliary storage device may include specific information about the type of storage and the size of the storage.

For example, in the case of detailed information about the main memory, specific information about RAM capacity may be included.

The indirect request method may refer to a method of requesting a cloud service so that the computer function desired by the requester can be implemented.

For example, through an indirect request method, a requester can request a cloud service that complements the user's computing device to facilitate video editing tasks.

A list of activities, such as document activity, video editing activity, Photoshop activity, game activity, etc., may be displayed on the requester's computing device, and the requestor may select one activity.

For example, through the indirect request method, the requester can analyze the log/metadata of the current computing device and request a cloud service that complements the user's computing device so that the computing device can operate without failure.

Operation information may be information needed to analyze the user's computing device according to an indirect request method.

Operational information may include all log data and metric data generated from the user's computing device.

Additionally, the operation information may include all information about the type of OS installed on the user's computing device, the type of application software, the specifications of the computing device, and the types and specifications of the hardware products that make up the computing device.

The transmission/reception module 110 may receive operation information including information generated as the physical server 200 operates and resource information of the physical server 200 from the physical server 200.

The operation information may include information about the types and sizes of virtual machines running on the physical server 200.

The storage module 180 stores information on all resources that the physical server 200 can provide, and this information can be transmitted to the optimal analysis module 130 at a later date.

By receiving operation information from the physical server 200, the optimal analysis module 130 can calculate available resources that the physical server 200 can provide as a cloud service.

The model creation module 160 can calculate an allocation model, which is a model that can calculate the optimal solution according to the user's request.

The model generation module 160 can calculate an allocation model using machine learning and/or deep learning.

Here, deep learning may use the Back Propagation algorithm, which is an algorithm that updates the weights of the neural network using labeled data of the output layer, but is not limited to this.

In addition, since the deep neural network and back propagation algorithm are known in the art, detailed description thereof may be omitted.

As a specific example, the model creation module 160 generates a machine based on the specifications of the user computing device 300, log/metric data, information on the user's computing usage status, and information on cloud service provision/application history from an external server. You can create an allocation model through learning/deep learning.

Specific methods of machine learning and/or deep learning utilize known technologies, and detailed descriptions thereof may be omitted.

The allocation model can calculate the method that minimizes the objective function as the optimal method.

The objective function may include a first objective function related to the user's service cost and a second objective function related to the process delay rate of the cloud service.

As the number and amount of resources provided increases, service costs may rise.

Conversely, as the number and amount of resources provided decrease, service costs may increase.

The process delay rate may change depending on the type and type of resource.

The allocation model can calculate the optimal solution based on the input constraints.

For example, constraints may include the type of resource that should not be allocated, the size of the resource, etc.

The optimal analysis module 130 can calculate the optimal solution in the case of an indirect request method using an allocation model.

The optimal method may include a method of primarily virtualizing individual resources or virtualizing integrated resources.

In the case of a method of virtualizing individual resources, the optimal method may refer to a method of virtualizing at least one of the central processing unit, graphics processing unit, main memory, and auxiliary memory to have specific detailed information.

For example, the optimal solution may be to virtualize the auxiliary storage device to a size of 40TB and provide a cloud service.

For example, the optimal solution may be to provide a cloud service by virtualizing 8GB of the main storage device and 20TB of auxiliary storage.

If the method is to virtualize integrated resources, the optimal method may be to virtualize the central processing unit, graphics processing unit, main memory, and auxiliary memory into one virtual machine.

As the number of individually virtualized resources decreases, cloud service costs can decrease and process delay rates can decrease compared to integrated virtualized resources.

However, as the number of individually virtualized resources increases, service costs may increase and process delay rates may increase compared to resources that are integratedly virtualized.

As a specific example, if only one type of resource is virtualized and all types of resources including one type of resource are virtualized, the cost and process delay rate may be lower when only one type of resource is virtualized.

On the other hand, if all types of resources are individually virtualized and all types of resources are virtualized in an integrated manner, the service cost and process delay rate may be high in the case where all types of resources are individually virtualized.

Accordingly, the optimal analysis module 130 can input the operation information and request information into the allocation model and calculate the optimal method, which is a method when the objective function is minimized.

The predetermined optimal allocation method may be a method of analyzing the motion information so that the objective function is minimized.

The predetermined optimal allocation method may be a method of calculating the optimal method by also considering whether to proceed with virtualization in individual resource units or integrated resource units.

The optimal analysis module 130 can calculate constraints and input the constraints into the allocation model.

The optimal analysis module 130 can calculate the optimal solution by excluding resources that are not compatible with the user's computing device.

The optimal analysis module 130 can set constraints for resources that are incompatible with the user's computing device and input them into the allocation model.

For example, the optimal analysis module 130 sets constraints that exclude resources of a storage type that provides a file system that is incompatible with the OS installed on the user's computing device due to the type of file system and inputs it into the allocation model. You can.

When the resources of the physical server 200, which is the target of the optimal solution, satisfy the first limit condition, the optimal analysis module 130 can calculate an alternative plan that is different from the optimal solution.

The first limit condition may be a condition in which the resource type of the physical server 200 presented as the optimal plan is available at a level below the first standard, which is a predetermined standard, in the physical server 200 permitted to use the same virtualization method as the optimal plan.

As a specific example, if the optimal solution is to provide only 10TB storage resources, the first limit condition can be satisfied if the available storage resources in the physical server 200, which is permitted to only virtualize individual resources, are 1000TB or less. there is.

The first standard may be modified in various ways depending on the type of resource and the specifications and number of physical servers 200.

For example, the first standard for the central processing unit, the first standard for the graphics processing unit, the first standard for the main memory, and the first standard for the auxiliary memory may all be different.

The optimal analysis module 130 can determine whether the first limit condition is satisfied.

An alternative method may be a method of virtualizing an integrated resource if the above optimal method is a method of virtualizing an individual resource unit.

In addition, the alternative method may be a method of virtualizing individual resources, if the optimal method is a method of virtualization in units of integrated resources.

By the control module 120, the physical server 200 is divided into a physical server 200 that individually virtualizes resources (hereinafter referred to as the first physical server 200) and a physical server 200 that virtualizes resources integratedly ( Hereinafter, it can be virtualized and managed by dividing it into a second physical server (hereinafter referred to as the second physical server 200).

That is, the control module 120 performs virtualization in units of individual resources of the physical server 200 in some of the physical servers 200, and virtualization in units of the entire resource of the physical server 200 in the remaining physical servers 200. You can proceed.

This may be to increase the resource efficiency of the physical server 200.

However, this split control method has the risk of causing a defect in the cloud service if requests are concentrated in one method.

To this end, it may be desirable to carry out the process of determining the first limit condition and calculating an alternative solution in parallel.

The overall resource unit refers to the basic unit that constitutes one computing device, and may basically include CPU, GPU, RAM, and STORAGE.

An individual resource unit refers to a detailed unit that makes up one computing device and can refer to each unit of CPU, GPU, RAM, and STORAGE.

The control module may virtualize at least some resources of the physical server based on request information. Here, the concept of virtualizing at least some resources may include both entire resource units and individual resource units.

The optimal analysis module 130 can determine whether the second limit condition is satisfied.

The second limit condition may be a condition in which the resource type of the physical server 200 presented as the optimal method is available at a level below the second standard, which is a predetermined standard, in the physical server 200 permitted to use the same virtualization method as the optimal method.

The second standard may be modified in various ways depending on the type of resource and the specifications and number of physical servers 200.

In one example, the second criterion may be lower than the first criterion.

The process of the cost calculation module 140 and the process of the interface module 150 may vary depending on whether the second limit condition is satisfied.

In the case of a direct request method, the control module 120 virtualizes the physical server 200 for directly requested resources, and in the case of an indirect request method, the control module 120 can virtualize the physical server 200 for resources such as an optimal method or an alternative method. .

The user computing device 300 can connect directly to the physical server 200 or connect to the physical server 200 through the transmission/reception module 110 to use virtualized resources.

The control module 120 can manage and virtualize the physical server 200 by distinguishing between the first physical server 200 and the second physical server 200.

The control module 120 can individually virtualize resources for the first physical server 200 in a paravirtual method.

The control module 120 may virtualize resources for the second physical server 200 using full-virtualization and/or para-virtualization.

However, it is not limited to this, and the virtualization method of the control module 120 can be modified in various ways at a level that is obvious to those skilled in the art.

The control module 120 can allocate resources of the physical server 200 according to a predetermined method and virtualize the resources of the physical server 200 according to the request information.

A predetermined method may be a method of allocating resources of the physical server 200 using a greedy algorithm if the user requests a cloud service exceeding a certain amount of resources.

Additionally, the predetermined method may be a method of allocating resources of the physical server 200 using an optimal algorithm if the user requests less than a certain amount of cloud service resources.

The greedy algorithm is a resource allocation algorithm that considers the overall resource efficiency of the physical server 200. Although the resource allocation time of the physical server 200 is long, it may be an algorithm that increases the resource allocation efficiency of the physical server 200.

The optimal algorithm is a resource allocation algorithm that selects the best according to the order of requests, and may be an algorithm that reduces the resource allocation time of the physical server 200 but reduces the resource allocation efficiency of the physical server 200.

If the user's request is a direct request, the control module 120 may determine which algorithm among predetermined methods should be used to allocate resources of the physical server 200 based on the request information.

On the other hand, when the user's request is an indirect request method, the control module 120 can determine which algorithm among predetermined methods should be used to allocate the physical server 200 resources based on the optimal method and the alternative method. .

Request information may include a request to provide a cloud service for an individual resource.

The control module 120 may virtualize only individual resources corresponding to the request information according to the request information.

The cost calculation module 140 can calculate the cloud service cost for how to provide the cloud service to the requester.

For example, the cost calculation module 140 can calculate the cloud service cost for the optimal method.

For example, the cost calculation module 140 can calculate the cloud service cost for an alternative method.

Service costs can be calculated according to a predetermined calculation method.

The more resources are used, the higher the service cost, and detailed explanations may be omitted to the extent that they overlap with known technologies.

The cost calculation module 140 can calculate the service discount price for the alternative method and the normal service price for the optimal method.

The cost calculation module 140 can calculate the price between the normal price of the alternative method and the normal price of the optimal method as the discount price of the alternative method.

Through this, users can be encouraged to choose an alternative method.

The alternative solution may be more expensive than the optimal solution, but the resources being virtualized may be larger.

By providing larger resources at a discounted price, users can be encouraged to choose an alternative method and overload of the physical server 200 can be prevented.

The cost calculation module 140 can adjust the discount rate of the alternative method by reflecting the user's malicious intent.

For example, the cost calculation module 140 may gradually lower the discount rate granted from the normal price of the alternative method as the user's malicious intent increases.

Conversely, the cost calculation module 140 can gradually increase the discount rate granted from the normal price of the alternative method as the user's malicious intent decreases.

This may be to prevent users from abusing the current discount process.

The interface module 150 can produce an interface through which a user can input request information through a computing device.

The interface module 150 can produce an interface that allows the user to check the status of the cloud service being used.

The interface module 150 can calculate an interface through which the user can accept and make payment for the recommended optimal plan.

The interface module 150 can calculate an interface that allows users to compare, select, and pay for the optimal plan and alternative plans.

The interface module 150 can calculate the price calculated by the cost calculation module 140 and an interface for selecting the alternative plan and the optimal plan.

The user analysis module 170 can analyze the user's computing device usage status information and calculate the user's malicious intent.

The usage status information may include time-series workload pattern information of the computing device, operating system installation change information of the computing device, and application program installation list information of the computing device.

The user analysis module 170 can calculate the degree of malicious intent by increasing the maliciousness if the user has a history of changing the operating system.

Most computer users use the operating system without changing it. If there is a history of changing the operating system, it may be desirable to assume that there is malicious intent to receive service with an alternative solution at the normal price of the optimal solution.

The user analysis module 170 can calculate the malicious intent by increasing the malicious intent if the user applied for the cloud service during a time when the computing device is not used.

The user analysis module 170 may calculate a time period when the user does not use the computing device based on the operation information of the user computing device 300. It may be desirable to determine the time zone when the physical server 200 is overloaded, and to judge the malicious intent as high if the application is for a computing cloud service that is not used during that time zone.

The user analysis module 170 can determine maliciousness based on the consistency of the user's application program installation list and the purpose of use requested by the user.

The user analysis module 170 can determine maliciousness to be higher as the application program installation list and usage purpose match, and as the application program installation list and usage purpose do not match, maliciousness can be judged to be lower.

If a user uses a computing device to do something related to a program that is not installed, it may be desirable to judge the maliciousness as high.

The user analysis module 170 can calculate a malicious intent calculation model that calculates malicious intent using machine learning and/or deep learning.

For this purpose, a malicious intent calculation model can be calculated through machine learning and/or deep learning on numerous data evaluating the user's computer usage status information and malicious intent, and a detailed description thereof is omitted within the scope of known technology. It can be.

The storage module 180 can store all information necessary to implement a virtualization service provision method.

In one example, the storage module may include internal memory and/or external memory.

For example, internal memory may include volatile memory (e.g., DRAM, SRAM, or SDRAM), non-volatile memory (e.g., one time programmable ROM (OTPROM), PROM, EPROM, EEPROM, mask ROM, flash ROM, flash memory, hard memory, etc. may include at least one of a drive, or solid state drive (SSD)

External memory may be a flash drive, such as compact flash (CF), secure digital (SD), Micro-SD, Mini-SD, extreme digital (xD), multi-media card (MMC), or memory stick. It may include etc.

Each of the above-described modules is connected to each other to enable wired/wireless communication, so that necessary information can be exchanged with each other.

Hereinafter, the virtualization service provision method implemented by each module will be described in detail.

Figure 4 is a flowchart of a method for providing a virtualization service according to an embodiment of the present invention.

Hereinafter, detailed description may be omitted to the extent that it overlaps with the above-described content.

Referring to FIG. 4, the virtualization service provision method according to an embodiment of the present invention is implemented by a virtualization service provision system, and in the virtualization service provision method for providing a cloud service to a user's computing device, a transmission and reception module It may include receiving direct request information or indirect request information for a cloud service from the user's computing device and virtualizing some resources of the physical server based on the request information by a control module.

In addition, the virtualization service provision method further includes calculating an optimal plan, which is a resource allocation plan required for the user, by the optimal analysis module using a predetermined optimal allocation method based on operation information received from the user's computing device. can do.

Users can request cloud services through their computing devices, and the transmission/reception module can receive request information.

If the sending/receiving module directly receives the request information, the cost calculation module directly calculates the cost of providing the cloud service according to the requested information, and the interface module is an interface that requests the user to consent to the cloud service along with the calculated cost. can be calculated.

Next, when the user accepts the service through the interface received from the transmission/reception module, the control module can virtualize the physical machine for the requested information and provide the cloud service to the user.

If the transmission/reception module receives indirect request information, the optimal analysis module can calculate the optimal solution using the request information and operation information.

Additionally, the optimization analysis module can determine whether the first limit condition is satisfied based on the operation information and the optimal solution.

If the first limit condition is not satisfied, the cost calculation module can calculate the normal price for the optimal plan, and the interface module can calculate an interface that can display the optimal plan and normal price to the user.

If the user accepts the optimal plan and pays through the provided interface, the control module can virtualize the physical machine like the optimal plan and provide cloud services to the user.

If the first limit condition is satisfied, the optimal analysis module can calculate an alternative solution.

Next, the optimal analysis module can determine whether the second limit condition is satisfied.

If the second limit condition is not satisfied, the cost calculation module can calculate the normal price of the optimal method and the discounted price of the alternative method. The interface module displays the normal price of the optimal plan and the discounted price of the alternative plan to the user and can calculate an interface that allows users to select between the optimal plan and the alternative plan.

When the user selects the optimal plan or an alternative plan through the provided interface and makes a payment, the control module can provide a cloud service to the user by virtualizing the physical machine like the selected plan.

If the user selects an alternative method, the control module can support cloud services by analyzing the time-series workload of the user's computing device and virtualizing as many resources as necessary during times when the user's workload increases.

By additionally providing these complementary cloud services, users can be encouraged to choose an alternative method.

If the user selects the optimal method, the above-mentioned complementary service may not be provided.

Whether such complementary services are provided can be displayed together when the user is informed through the interface.

If the second limit condition is satisfied, the cost calculation module can calculate the price of the optimal solution. The interface module can calculate an interface that displays the optimal plan and the price of the optimal plan.

Users can view the optimal plan and its price through the provided interface, accept it, and proceed with payment.

However, the control module can provide cloud services to users by virtualizing the physical machine based on an alternative plan, different from the approved optimal plan.

This provides better services to users at a discounted price, effectively preventing physical server overload and user complaints.

A process that proceeds when the first limit condition is satisfied may be detrimental to the cloud service provider.

Therefore, this should be a process that should be used only when the physical server is in an emergency, and cases of abuse of it need to be blocked.

Accordingly, the user analysis module can store a list of users who receive services of an alternative plan at the price of the optimal plan when the first limit condition is satisfied, and count the number of times the service is provided when the first limit condition is satisfied.

The user analysis module can calculate the degree of malicious intent for users who have received the cloud service when the first limit condition is satisfied more than a predetermined number of times.

Here, the predetermined number of times may be 3 times.

However, it is not limited to this, and the predetermined number of times can be modified in various ways at a level that is obvious to those skilled in the art.

The cost calculation module can adjust the discount rate for calculating an alternative plan according to the malicious intent when the first limit condition is satisfied and the second limit condition is not satisfied for users whose malicious intent is higher than a predetermined standard.

Through this, it is possible to limit malicious people from repeatedly receiving discount benefits.

In the attached drawings, in order to more clearly express the technical idea of the present invention, components that are unrelated or less relevant to the technical idea of the present invention are briefly expressed or omitted.

In the above, the configuration and features of the present invention have been described based on the embodiments according to the present invention, but the present invention is not limited thereto, and various changes or modifications may be made within the spirit and scope of the present invention. It is obvious to those skilled in the art, and therefore, it is stated that such changes or modifications fall within the scope of the appended patent claims.

110: collection module 120: analysis module
130: Recommendation module 140: Prediction module

Claims (10)

In a virtualization service provision system that implements a virtualization service provision method for providing cloud services to a user's computing device by communicating with the user's computing device,
A transmitting and receiving module that receives request information for cloud services from the user's computing device;
A storage module that stores information necessary to implement a virtualization service provision method; and
It includes a control module that virtualizes at least some resources of the physical server based on the request information,
The requested information is,
Includes requests to provide cloud services for individual resources,
The control module is,
The resources of the physical server are allocated according to a predetermined method, which is a method of allocating the resources of the physical server using a greedy algorithm or an optimal algorithm, and according to the request information, only individual resources corresponding to the request information are virtualized, and the request Based on the information, determine which algorithm among the predetermined methods should be used to allocate the resources of the physical server,
Virtualization service provision system.
According to paragraph 1,
The requested information is,
Containing at least one of detailed information on the central processing unit, detailed information on the graphics processing unit, detailed information on the main memory, and detailed information on the auxiliary memory,
Virtualization service provision system.
According to paragraph 2,
The predetermined method is,
If a user requests more than a certain amount of cloud service resources, the resources of the physical server are allocated using a greedy algorithm.
If the user requests less than a certain amount of cloud service resources, the optimal algorithm is used to allocate physical server resources.
Virtualization service provision system.
In a virtualization service provision system that implements a virtualization service provision method for providing cloud services to a user's computing device by communicating with the user's computing device,
A transmitting and receiving module that receives request information for cloud services from the user's computing device;
A storage module that stores information necessary to implement a virtualization service provision method;
a control module that virtualizes at least some resources of a physical server based on the request information; and
The transmitting and receiving module includes an optimal analysis module that calculates an optimal plan, which is a resource allocation plan necessary for the user, using a predetermined optimal allocation method based on operation information received from the user's computing device,
The requested information is,
Includes requests to provide cloud services for individual resources,
The control module is,
According to the request information, only individual resources corresponding to the request information are virtualized,
The predetermined optimal allocation method is,
Analyzing the operation information to minimize the objective function,
The objective function is,
Containing a first objective function related to the user's service cost,
Virtualization service provision system.
In a virtualization service provision system that implements a virtualization service provision method for providing cloud services to a user's computing device by communicating with the user's computing device,
A transmitting and receiving module that receives request information for cloud services from the user's computing device;
A storage module that stores information necessary to implement a virtualization service provision method;
a control module that virtualizes at least some resources of a physical server based on the request information; and
The transmitting and receiving module includes an optimal analysis module that calculates an optimal plan, which is a resource allocation plan necessary for the user, using a predetermined optimal allocation method based on operation information received from the user's computing device,
The requested information is,
Includes requests to provide cloud services for individual resources,
The control module is,
According to the request information, only individual resources corresponding to the request information are virtualized,
The optimal analysis module is,
Calculating the optimal solution by excluding resources that are incompatible with the user's computing device,
Virtualization service provision system.
According to paragraph 4,
The predetermined optimal allocation method is,
A method of calculating the optimal method by considering whether to proceed with virtualization in individual resource units or integrated resource units,
Virtualization service provision system.
According to any one of paragraphs 4 and 5,
The optimal analysis module is,
If the resources of the physical server that are the target of the optimal plan satisfy the first limit condition, an alternative plan that is different from the optimal plan is calculated,
The alternative method is,
If the above optimal method is a method of virtualization in individual resource units, it is a method of virtualization in integrated resource units,
If the above optimal method is a method of virtualization in units of integrated resources, it is a method of virtualization in units of individual resources,
Virtualization service provision system.
In clause 7,
A cost calculation module that calculates the service cost for the optimal method; and
It further includes an interface module that calculates an interface provided to the user's computing device,
The cost calculation module is,
Calculate the service discount price for the alternative method and the service normal price for the optimal method,
The interface module is,
Calculating an interface that allows you to select the price calculated from the cost calculation module and the alternative plan and the optimal plan,
Virtualization service provision system.
In a virtualization service provision method implemented by a virtualization service provision system and for providing cloud services to a user's computing device,
Receiving request information for a cloud service from a user's computing device by a transmission/reception module; and
Comprising: virtualizing some resources of the physical server by a control module based on the request information,
The requested information is,
Information on requests from users who have specified required resources, including requests for cloud service provision of individual resources,
The control module is,
The resources of the physical server are allocated according to a predetermined method, which is a method of allocating the resources of the physical server using a greedy algorithm or an optimal algorithm, and according to the request information, only individual resources corresponding to the request information are virtualized, and the request Based on information, determine which algorithm among predetermined methods should be used to allocate physical server resources,
How to provide virtualization services.
In a virtualization service provision method implemented by a virtualization service provision system and for providing cloud services to a user's computing device,
Receiving request information for a cloud service from a user's computing device by a transmission/reception module;
Virtualizing some resources of a physical server based on the request information by a control module; and
A step of calculating, by the optimal analysis module, an optimal plan, which is a resource allocation plan necessary for the user, using a predetermined optimal allocation method based on operation information received from the user's computing device,
The requested information is,
Information on requests from users who have specified required resources, including requests for cloud service provision of individual resources,
The control module is,
According to the request information, only individual resources corresponding to the request information are virtualized,
The predetermined optimal allocation method is,
Analyzing the operation information to minimize the objective function,
The objective function is,
Containing a first objective function related to the user's service cost,
How to provide virtualization services.

Images