CN109240795A - A kind of resource regulating method of the cloud computing resources pool model suitable for super fusion IT infrastructure - Google Patents
A kind of resource regulating method of the cloud computing resources pool model suitable for super fusion IT infrastructure Download PDFInfo
- Publication number
- CN109240795A CN109240795A CN201810906122.5A CN201810906122A CN109240795A CN 109240795 A CN109240795 A CN 109240795A CN 201810906122 A CN201810906122 A CN 201810906122A CN 109240795 A CN109240795 A CN 109240795A
- Authority
- CN
- China
- Prior art keywords
- task
- resource
- virtual machine
- cloud computing
- infrastructure
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/44—Arrangements for executing specific programs
- G06F9/455—Emulation; Interpretation; Software simulation, e.g. virtualisation or emulation of application or operating system execution engines
- G06F9/45533—Hypervisors; Virtual machine monitors
- G06F9/45558—Hypervisor-specific management and integration aspects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5061—Partitioning or combining of resources
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5083—Techniques for rebalancing the load in a distributed system
- G06F9/5088—Techniques for rebalancing the load in a distributed system involving task migration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/44—Arrangements for executing specific programs
- G06F9/455—Emulation; Interpretation; Software simulation, e.g. virtualisation or emulation of application or operating system execution engines
- G06F9/45533—Hypervisors; Virtual machine monitors
- G06F9/45558—Hypervisor-specific management and integration aspects
- G06F2009/4557—Distribution of virtual machine instances; Migration and load balancing
Landscapes
- Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Multi Processors (AREA)
Abstract
The invention discloses a kind of resource regulating methods of cloud computing resources pool model suitable for super fusion IT infrastructure, by the cloud computing resources scheduling system abstract of super fusion IT infrastructure；User issues task requests, and task sequentially reaches cloud resource scheduling model, is arranged in a global task queue；Scheduler is scheduled task according to the loading condition, task type, task of each server arrival opportunity, distributes to virtual machine；If the available free resource of virtual machine of server operation, provides service immediately for user, virtual machine withdraws the resource dispensed after task execution；If the virtual machine of server operation, which can not provide, executes required by task resource, which is dropped.The present invention can more preferably be managed the resource of cloud computing, improve whole resource utilization, promote super fusion architecture and integrate performance, the O&M cost of cloud platform is effectively reduced.
Description
Technical field
The invention belongs to cloud computing resource pool fields, and in particular to a kind of cloud computing suitable for super fusion IT infrastructure
Resource pool model.
Background technique
In super emerging system, server hardware resource, as disk, memory and network need Integrated Virtual, cloud meter
Calculation platform, and the business demand that high load operation system needs higher computing resource to support high concurrent, handle up greatly.
The virtual machine that physical server can be divided into several logically independent by virtualization technology, each virtual machine use
Different operating system completes different tasks, this sufficiently to use physical resource, improve resource utilization provide it is strong
Technical guarantee.However, when virtualization technology to be introduced into the super fusion IT infrastructure environment based on cloud environment, when facing
When numerous mutually independent resource requests, it is necessary first to which solution is which physical server is selected to ask to provide these resources
Which ask, it may be assumed that select physical server to be blurred, while determining the stock number that every virtual machine should distribute.
Different from typical static virtual machine integration problem, during the super integrated environment of duration virtual machine (vm) migration, user
It is given in advance that request to virtual machine, which is with time continuity arrival cloud platform, rather than as static state deployment,.It is empty
The elementary object of quasi- machine deployment is in the case where ensureing that virtual machine obtains timely resource, so that occupied physical machine quantity reaches
To minimum, to reach raising resource utilization, the purpose of reinforcing property.For every physical server or virtual machine, money
The type in source is multidimensional, such as CPU, memory, disk, I/O.For any physical server, any type money
The exhausting of source all will lead to the physical server and be unable to satisfy new resource request, even if other kinds of resource still has richness at this time
It is remaining.
To meet multi-kind resource request, existing greedy algorithm will lead to multi-kind resource using unbalanced, occur
The phenomenon that " resource leakage "；Whole resource utilization is lower, and the integrated performance of super fusion architecture is poor, also increases the fortune of cloud platform
Tie up cost.
Summary of the invention
Goal of the invention: it is asked to solve cloud computing resource pool multi-kind resource of the existing technology using unbalanced
Topic, the present invention provide a kind of resource regulating method of cloud computing resources pool model suitable for super fusion IT infrastructure.
It is a further object of the present invention to provide a kind of cloud computing resources pool models of super fusion IT infrastructure.
Technical solution: a kind of resource regulating method of the cloud computing resources pool model suitable for super fusion IT infrastructure,
The following steps are included:
(1) server abstracts the cloud computing resource pool of super fusion IT infrastructure, the cloud computing resources after abstract
Pond includes global task queue, scheduler and virtual machine；
(2) server receives task requests, and the task is sequentially lined up in the global task queue；
(3) server command scheduler is allocated the task in global task queue, assigns the task to virtual machine
It is executed.
Further, in step (3), server command scheduler reaches opportunity according to loading condition, task type, task
Task is scheduled, virtual machine is assigned the task to.
Further, in step (3), server checks the resource service condition of virtual machine, if the available free money of virtual machine
Source then assigns the task to virtual machine and is immediately performed task, the resource dispensed is retracted to void after task execution
Quasi- machine；If virtual machine, which can not provide, executes required by task resource, which is abandoned.
Further, in step (2), it is lined up the rule for using M/M/n queuing model.
Further, in step (2), the Poisson distribution that parameter is λ is obeyed at task arrival time interval, and λ refers to the unit time
The task quantity reached in interval.
Further, in step (3), each virtual machine obeys the negative exponent that parameter is μ for the time that executes of each task
Distribution, μ are the execution time of individual task.
Further, the value of λ, μ meet
A kind of resource scheduling device of the cloud computing resources pool model suitable for super fusion IT infrastructure, including processing are single
Member, receiving module and execution module,
The processing unit is used to abstract the cloud computing resource pool of super fusion IT infrastructure, the cloud meter after abstract
Calculating resource pool includes global task queue, scheduler and virtual machine；
The receiving module sequentially arranges the task for receiving task requests in global task queue
Team；
The execution module is allocated the task in global task queue for command scheduler, assigns the task to
Virtual machine is executed.
Further, the execution module reaches opportunity according to loading condition, task type, task for command scheduler
Task is scheduled, virtual machine is assigned the task to.
Further, the execution module is used to check the resource service condition of virtual machine, if the available free money of virtual machine
Source, then be immediately performed task, and the resource dispensed is retracted to virtual machine after task execution；If virtual machine can not mention
For executing required by task resource, then the task is abandoned.
The utility model has the advantages that the present invention provides a kind of resource of cloud computing resources pool model suitable for super fusion IT infrastructure
Cloud computing resources scheduling system is combined with queue M/M/n model, realizes money by dispatching method and resource scheduling device
Source virtualization, can provide computing resource, storage resource and this service-oriented characteristic of application resource, meet dispatching requirement
Diversity is more preferably managed the resource of cloud computing, more reasonable to the scheduling of numerous application tasks, substantially increases each collection
Working efficiency of group's work in cloud computing resource pool, enables resource more efficiently and safely to provide service for application.We
Method is quantitatively portrayed according to the analysis to physical server resource service condition, and to " resource leakage ", in selection physics clothes
It is engaged in avoiding physical server from multi-kind resource occur using unbalanced phenomenon, to reduce " resource leakage " during device
The appearance of phenomenon, and then whole resource utilization is improved, it promotes super fusion architecture and integrates performance, cloud platform can be effectively reduced
O&M cost.
Detailed description of the invention
Fig. 1 is model state flow graph designed by the present invention；
Fig. 2 is the cloud resource scheduling model based on M/M/n；
Fig. 3 is service processes and operation waiting time comparison diagram in M/M/n model resource pond.
Specific embodiment
The present invention will be further explained below with reference to the attached drawings and specific examples.
A kind of resource regulating method of the cloud computing resources pool model suitable for super fusion IT infrastructure, including following step
It is rapid:
(1) server abstracts the cloud computing resource pool of super fusion IT infrastructure.Cloud resource Chi Bao after abstract
Include global task queue, scheduler, virtual machine, mutually indepedent, a server operation one or more between multiple servers
Virtual machine.Abstractdesription is as follows:
A, in the operational process in cloud resource pond, user is random sending task requests, while dispatching in cloud resource and being
There is no limit be independent from each other, task reached between the time of cloud resource scheduling system task quantity between task in system
Every being also random；
B, cloud resource scheduling system is to provide service with virtual machine for user, and a system has a multiple servers, one
Platform server can run one or more virtual machines, and the execution of task is independent between virtual machine.This shows that cloud resource is dispatched
System is Multiple server stations system, and is independent from each other for the time that each user provides service；
C, when user issues resource request, if the virtual machine in server can not provide operation required by task resource,
The request of user can be rejected, this subtask will be dropped, and not retained；If the available free resource of virtual machine in server,
Service is provided for user, virtual machine withdraws the resource dispensed after task run；
The characteristics of from the above abstractdesription, it is found that cloud resource scheduling system meets the rule of M/M/n queuing model, can adopt
Cloud resource scheduling system is modeled with M/M/n queuing model.Queuing model is by input process, queue discipline and server
It is formed in terms of structure three.
(2) server receives task requests, and task is sequentially lined up in global task queue, and queuing follows
The rule of M/M/n queuing model；
Input process is related to three concepts of time interval that total task number, task arrival pattern and task reach:
A, it total task number: in cloud computing environment, as long as the user of cloud computing system can be accessed, can act as requiring service
A side, and each user can at any time, multiple sending resource request, that is, submit task, therefore the sum of task
It is unlimited.
B, task arrival pattern: the object of cloud computing system service is the task that user submits, they are sequentially, are spaced
It is that time arrives at random and mutually indepedent.
C, the time interval distribution that task reaches: by the arrival pattern of task it is recognised that can task requests according to
The order sequence to be formed that arrives regards inlet flow as.Task reach quantity and arrival time be it is unrelated, only between task
It is related every the time.It is assumed that task arrival time spacing follows the rule of Poisson distribution within the unit time, and unit gap is arrived
The task quantity reached is λ.
(3) server command scheduler reaches opportunity to the overall situation according to the loading condition, task type, task of each server
Task in task queue is allocated, and distributes to virtual machine, and then server executes task according to the state of virtual machine.
Queue discipline meets the rule of M/M/n queuing model: if the available free resource of virtual machine of server operation, stands
As user provides service, and virtual machine withdraws the resource dispensed after task execution；If server operation is virtual
Machine, which can not provide, executes required by task resource, then the task is dropped.
: there are multiple servers in service organization in cloud computing system, every service has multiple virtual machines to provide service, and each
From autonomous working, and it is identical that each virtual machine, which provides the ability of service,.Therefore cloud computing system has n mutually independent clothes
Be engaged in mechanism.Due to the diversity of task, service time is random, the service time of each virtual machine execution individual task
Assuming that obeying the quantum condition entropy that parameter is μ, μ is the execution time of individual task.
Above-mentioned each task arrival intervals follow the Poisson distribution rule that parameter is λ, and the service time of each task follows
The quantum condition entropy rule that parameter is μ, therefore provide cloud resource scheduling model and be described as follows:
A, each task work is mutually indepedent in cloud computing resource pool, and ginseng is obeyed at the arrival time interval of each task
Number is the Poisson distribution of λ, according to the definition of Poisson distribution, in unit interval, averagely has λ task to reach；
B, after task reaches cloud resource scheduling system, if the available free resource of the virtual machine of server, task is in cloud
Be scheduled processing in resource scheduling system, and after the completion of task run, virtual machine withdraws resource, conversely, task is directly dropped.Appoint
The SO service order of business can there are many, for example prerequisite variable, first service later, most short task are preferential, Random Service, circulation clothes
Business etc., commonplace is to take first-come-first-served policy；
C, the virtual machine of n platform server provides service in cloud resource scheduling system, every server all maintains oneself
Local task queue, virtual machine for each task execute the time obey parameter be μ quantum condition entropy.
WhenWhen, there are Stationary Distributions for cloud computing resource pool.
Theoretically cloud computing resources pool model progressive can be analyzed below:
The validity and utilization rate of queuing model can be described by multiple performance index, therefore can use M/M/n
Queuing model dispatches system to analyze cloud resource, and the performance of cloud resource scheduling system is measured with this.
(1) Stationary Distribution of model
In cloud resource scheduling model, λ indicates the arrival rate parameter of each task, and μ indicates that each task receives service
Service speed, the quantity of the server of service is provided in n expression system.
Task quantity is unlimited in cloud computing resource pool, therefore cloud computing resource pool is as a birth and death process, can
The state set of energy can be expressed asThus the state flow-chart of cloud computing resource pool is as shown in Figure 1
In the resource pool state flow-chart of Fig. 2, k indicate cloud computing resource pool by operation use or be lined up service into
Number of passes, n indicate total process number of cloud computing resource pool.It is not difficult to find that cloud computing resources pool model is divided into two states:
1) as 0≤k≤n, indicate there are k service processes to be used by operation in cloud computing resource pool, remaining n-k
Service processes are at leisure；
2) as k > n, n process is all occupied by operation, and remaining k-n job queue etc. is to be serviced.
It is assumed that only allowing to there is to wait in line a queue at this time, when service processes resource service is complete idle, wait in line
Operation sequentially go to idle service processes to receive service, can be obtained by Fig. 1, can when system is in equilibrium state
K formula algebraic equation is listed, and finds out corresponding Stationary Distribution:
To 0 state, there is λ p0=μ p1, therefore p1=ρ1p0=n ρ p0；
To 1 state, there is λ p1=2 μ p2, therefore
To n-1 state, there is λ pn-1=n μ pn, therefore
To n-state, there is λ pn=n μ pn+1, therefore
To n+r-1 state, there is λ pn+r-1=n μ pn+r, therefore
It is as follows formula can be obtained according to this:
By regularity conditionsAs ρ < 1, haveThen
In waiting system, the operation of request cloud computing resource pool service can be serviced sooner or later by service processes, therefore PDamage=0.
The corresponding service ability Q=1-P of cloud computing resource poolDamage=1 (3)
The absolute service ability A=λ Q=λ (4) of cloud computing resource pool
(2) request queue is analyzed
Wait the average queue length of cloud computing resource pool service
The service processes number averagely hurried in cloud computing resource pool
The mean value of operation number in cloud computing resource pool
Wait the average queue length variance of cloud computing resource pool service
(3) response time analysis
Definition: for a queuing system, if any moment is averaged in system after it reaches statistical equilibrium state
Team leader L, average waiting queue length Lq, with average queuing latency Wq, each operation in systems it is average use time WsIt
Between have relational expression: L=λ Ws, Lq=λ WqIt sets up, then the queuing system is claimed to meet Little formula.
Average queuing latency and operation can be obtained by Little formula and use system time
The probability that the service of job request cloud computing resource pool must be waited in line
For the effect for proving M/M/n queuing model, the present embodiment passes through one M/M/n queuing model of design and n M/M1
Queuing model is compared, and calculates resource consumed by two kinds of complete whole systems of model service to observe.
In this experiment, if n=3, λ=0.3, μ=0.4, calculated result is as shown in table 1:
1 M/M/1 of table is compared with M/M/3 simulated target parameter
It can be obtained by table 1, be provided with 3 service processes windows but the queuing of only one queue M/M/3 waited in line
Than 3 M/M/1 queuing system efficiency of system significantly improve.
Formula (10) are brought into different c, λ and μ values respectively shown in Fig. 3, obtain WqAs a result the curve drawn.It can by figure
See, service processes number is more in cloud computing resource pool, and more efficient to the service of operation, the quality of service is more efficient.
The invention proposes the M/M/n models based on queueing theory, demonstrate cloud computing resource pool in only one queuing team
Working efficiency when column is better than multiple queue queues, and an appropriate number of resource need to only be integrated by finally obtaining in cloud computing resource pool
It can meet within the waiting time that operation can be born, provide cloud computing service for user.
It should be understood by those skilled in the art that, embodiments herein can provide as method, system or computer program
Product.Therefore, complete hardware embodiment, complete software embodiment or reality combining software and hardware aspects can be used in the application
Apply the form of example.Moreover, it wherein includes the computer of computer usable program code that the application, which can be used in one or more,
The computer program implemented in usable storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.) produces
The form of product.
The application is referring to method, the process of equipment (system) and computer program product according to the embodiment of the present application
Figure and/or block diagram describe.It should be understood that every one stream in flowchart and/or the block diagram can be realized by computer program instructions
The combination of process and/or box in journey and/or box and flowchart and/or the block diagram.It can provide these computer programs
Instruct the processor of general purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices to produce
A raw machine, so that being generated by the instruction that computer or the processor of other programmable data processing devices execute for real
The device for the function of being specified in present one or more flows of the flowchart and/or one or more blocks of the block diagram.
These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works, so that it includes referring to that instruction stored in the computer readable memory, which generates,
Enable the manufacture of device, the command device realize in one box of one or more flows of the flowchart and/or block diagram or
The function of being specified in multiple boxes.
These computer program instructions also can be loaded onto a computer or other programmable data processing device, so that counting
Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, thus in computer or
The instruction executed on other programmable devices is provided for realizing in one or more flows of the flowchart and/or block diagram one
The step of function of being specified in a box or multiple boxes.
The above is only the embodiment of the present invention, are not intended to restrict the invention, all in the spirit and principles in the present invention
Within, any modification, equivalent substitution, improvement and etc. done, be all contained in apply pending scope of the presently claimed invention it
It is interior.
Claims (10)
1. a kind of resource regulating method of the cloud computing resources pool model suitable for super fusion IT infrastructure, which is characterized in that
The following steps are included:
(1) server abstracts the cloud computing resource pool of super fusion IT infrastructure, the cloud computing resource pool packet after abstract
Include global task queue, scheduler and virtual machine；
(2) server receives task requests, and the task is sequentially lined up in the global task queue；
(3) server command scheduler is allocated the task in global task queue, assigns the task to virtual machine progress
It executes.
2. the scheduling of resource side of the cloud computing resources pool model according to claim 1 for being suitable for super fusion IT infrastructure
Method, which is characterized in that in step (3), server command scheduler reaches opportunity pair according to loading condition, task type, task
Task is scheduled, and assigns the task to virtual machine.
3. the scheduling of resource side of the cloud computing resources pool model according to claim 1 for being suitable for super fusion IT infrastructure
Method, which is characterized in that in step (3), server checks the resource service condition of virtual machine, if the available free resource of virtual machine,
It is then immediately performed task, the resource dispensed is retracted to virtual machine after task execution；If virtual machine can not provide
Required by task resource is executed, then is abandoned the task.
4. the scheduling of resource side of the cloud computing resources pool model according to claim 1 for being suitable for super fusion IT infrastructure
Method, which is characterized in that in step (2), be lined up the rule for using M/M/n queuing model.
5. the scheduling of resource side of the cloud computing resources pool model according to claim 1 for being suitable for super fusion IT infrastructure
Method, which is characterized in that in step (2), the Poisson distribution that parameter is λ is obeyed at task arrival time interval, and λ refers to unit interval
The task quantity of interior arrival.
6. the scheduling of resource side of the cloud computing resources pool model according to claim 5 for being suitable for super fusion IT infrastructure
Method, which is characterized in that in step (3), each virtual machine obeys the negative exponent point that parameter is μ for the time that executes of each task
Cloth, μ are the execution time of individual task.
7. the scheduling of resource side of the cloud computing resources pool model according to claim 6 for being suitable for super fusion IT infrastructure
Method, which is characterized in that the value of λ, μ meet。
8. a kind of resource scheduling device of the cloud computing resources pool model suitable for super fusion IT infrastructure, which is characterized in that
Including processing unit, receiving module and execution module,
The processing unit is used to abstract the cloud computing resource pool of super fusion IT infrastructure, the cloud computing money after abstract
Source pond includes global task queue, scheduler and virtual machine；
The task is sequentially lined up in global task queue by the receiving module for receiving task requests；
The execution module is allocated the task in global task queue for command scheduler, assigns the task to virtual
Machine is executed.
9. the scheduling of resource dress of the cloud computing resources pool model according to claim 8 for being suitable for super fusion IT infrastructure
It sets, which is characterized in that the execution module reaches opportunity pair according to loading condition, task type, task for command scheduler
Task is scheduled, and assigns the task to virtual machine.
10. the scheduling of resource of the cloud computing resources pool model according to claim 8 for being suitable for super fusion IT infrastructure
Device, which is characterized in that the execution module is used to check the resource service condition of virtual machine, if the available free money of virtual machine
Source, then be immediately performed task, and the resource dispensed is retracted to virtual machine after task execution；If virtual machine can not mention
For executing required by task resource, then the task is abandoned.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810906122.5A CN109240795A (en) | 2018-08-10 | 2018-08-10 | A kind of resource regulating method of the cloud computing resources pool model suitable for super fusion IT infrastructure |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810906122.5A CN109240795A (en) | 2018-08-10 | 2018-08-10 | A kind of resource regulating method of the cloud computing resources pool model suitable for super fusion IT infrastructure |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109240795A true CN109240795A (en) | 2019-01-18 |
Family
ID=65070297
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810906122.5A Pending CN109240795A (en) | 2018-08-10 | 2018-08-10 | A kind of resource regulating method of the cloud computing resources pool model suitable for super fusion IT infrastructure |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109240795A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110908800A (en) * | 2019-11-11 | 2020-03-24 | 广东石油化工学院 | Scheduling optimization method based on scheduling entropy in edge cloud collaborative environment |
| CN111367679A (en) * | 2020-03-31 | 2020-07-03 | 中国建设银行股份有限公司 | Artificial intelligence computing power resource multiplexing method and device |
| CN111416840A (en) * | 2020-03-02 | 2020-07-14 | 深圳供电局有限公司 | Intelligent resource allocation system and method for cloud computing platform |
| CN111767288A (en) * | 2020-07-30 | 2020-10-13 | 杭州正策信息科技有限公司 | Project declaration data processing method and device |
| CN112416495A (en) * | 2020-11-23 | 2021-02-26 | 山东乾云启创信息科技股份有限公司 | Super-fusion cloud terminal resource unified management system and method |
| CN115373804A (en) * | 2022-10-27 | 2022-11-22 | 合肥综合性国家科学中心人工智能研究院(安徽省人工智能实验室) | Virtual machine scheduling method facing network test in cloud infrastructure |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160306655A1 (en) * | 2015-04-20 | 2016-10-20 | International Business Machines Corporation | Resource management and allocation using history information stored in application's commit signature log |
| CN106951330A (en) * | 2017-04-10 | 2017-07-14 | 郑州轻工业学院 | A kind of maximized virtual machine distribution method of cloud service center service utility |
| CN107291536A (en) * | 2017-05-23 | 2017-10-24 | 南京邮电大学 | Application task stream scheduling method under a kind of cloud computing environment |
| CN108304260A (en) * | 2017-12-15 | 2018-07-20 | 上海超算科技有限公司 | A kind of virtualization job scheduling system and its implementation based on high-performance cloud calculating |
-
2018
- 2018-08-10 CN CN201810906122.5A patent/CN109240795A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160306655A1 (en) * | 2015-04-20 | 2016-10-20 | International Business Machines Corporation | Resource management and allocation using history information stored in application's commit signature log |
| CN106951330A (en) * | 2017-04-10 | 2017-07-14 | 郑州轻工业学院 | A kind of maximized virtual machine distribution method of cloud service center service utility |
| CN107291536A (en) * | 2017-05-23 | 2017-10-24 | 南京邮电大学 | Application task stream scheduling method under a kind of cloud computing environment |
| CN108304260A (en) * | 2017-12-15 | 2018-07-20 | 上海超算科技有限公司 | A kind of virtualization job scheduling system and its implementation based on high-performance cloud calculating |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110908800A (en) * | 2019-11-11 | 2020-03-24 | 广东石油化工学院 | Scheduling optimization method based on scheduling entropy in edge cloud collaborative environment |
| CN110908800B (en) * | 2019-11-11 | 2023-04-18 | 广东石油化工学院 | Scheduling optimization method based on scheduling entropy in edge cloud collaborative environment |
| CN111416840A (en) * | 2020-03-02 | 2020-07-14 | 深圳供电局有限公司 | Intelligent resource allocation system and method for cloud computing platform |
| CN111416840B (en) * | 2020-03-02 | 2023-07-11 | 深圳供电局有限公司 | Intelligent resource allocation system and method of cloud computing platform |
| CN111367679A (en) * | 2020-03-31 | 2020-07-03 | 中国建设银行股份有限公司 | Artificial intelligence computing power resource multiplexing method and device |
| CN111767288A (en) * | 2020-07-30 | 2020-10-13 | 杭州正策信息科技有限公司 | Project declaration data processing method and device |
| CN112416495A (en) * | 2020-11-23 | 2021-02-26 | 山东乾云启创信息科技股份有限公司 | Super-fusion cloud terminal resource unified management system and method |
| CN115373804A (en) * | 2022-10-27 | 2022-11-22 | 合肥综合性国家科学中心人工智能研究院(安徽省人工智能实验室) | Virtual machine scheduling method facing network test in cloud infrastructure |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Liu et al. | Online multi-workflow scheduling under uncertain task execution time in IaaS clouds | |
| CN109240795A (en) | A kind of resource regulating method of the cloud computing resources pool model suitable for super fusion IT infrastructure | |
| Ma et al. | Real-time multiple-workflow scheduling in cloud environments | |
| Cheng et al. | Cost-aware job scheduling for cloud instances using deep reinforcement learning | |
| CN102156665B (en) | Differential serving method for virtual system competition resources | |
| Djigal et al. | IPPTS: An efficient algorithm for scientific workflow scheduling in heterogeneous computing systems | |
| Polo et al. | Performance-driven task co-scheduling for mapreduce environments | |
| Zhang et al. | vGASA: Adaptive scheduling algorithm of virtualized GPU resource in cloud gaming | |
| KR20120082598A (en) | Cost based scheduling algorithm for multiple workflow in cloud computing and system of the same | |
| Sonkar et al. | A review on resource allocation and VM scheduling techniques and a model for efficient resource management in cloud computing environment | |
| CN109308212A (en) | A kind of task processing method, task processor and task processing equipment | |
| Nanda et al. | Racc: resource-aware container consolidation using a deep learning approach | |
| Rashmi et al. | Enhanced load balancing approach to avoid deadlocks in cloud | |
| Geng et al. | A task scheduling algorithm based on priority list and task duplication in cloud computing environment | |
| Tang et al. | Towards economic fairness for big data processing in pay-as-you-go cloud computing | |
| Ye et al. | Astraea: A fair deep learning scheduler for multi-tenant gpu clusters | |
| Koneru et al. | Resource allocation method using scheduling methods for parallel data processing in cloud | |
| Cheng et al. | Dynamic resource provisioning for iterative workloads on Apache Spark | |
| Ni et al. | Scalable asynchronous contact mechanics using Charm++ | |
| Grigoras et al. | Elastic management of reconfigurable accelerators | |
| Hauser et al. | Predictability of resource intensive big data and hpc jobs in cloud data centres | |
| López-Albelda et al. | FlexSched: Efficient scheduling techniques for concurrent kernel execution on GPUs | |
| Oh et al. | Job placement using reinforcement learning in GPU virtualization environment | |
| Lin et al. | Joint deadline-constrained and influence-aware design for allocating MapReduce jobs in cloud computing systems | |
| Haque et al. | A priority-based process scheduling algorithm in cloud computing |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190118 |