CN109976879A - A kind of cloud computing virtual machine placement method using curve complementation based on resource - Google Patents

A kind of cloud computing virtual machine placement method using curve complementation based on resource Download PDF

Info

Publication number
CN109976879A
CN109976879A CN201910249791.4A CN201910249791A CN109976879A CN 109976879 A CN109976879 A CN 109976879A CN 201910249791 A CN201910249791 A CN 201910249791A CN 109976879 A CN109976879 A CN 109976879A
Authority
CN
China
Prior art keywords
virtual machine
machine
resource
physical
physical machine
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.)
Granted
Application number
CN201910249791.4A
Other languages
Chinese (zh)
Other versions
CN109976879B (en
Inventor
付雄
谈继凯
邓松
王俊昌
程春玲
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Nanjing Post and Telecommunication University
Original Assignee
Nanjing Post and Telecommunication University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Nanjing Post and Telecommunication University filed Critical Nanjing Post and Telecommunication University
Priority to CN201910249791.4A priority Critical patent/CN109976879B/en
Publication of CN109976879A publication Critical patent/CN109976879A/en
Application granted granted Critical
Publication of CN109976879B publication Critical patent/CN109976879B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

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
    • G06F9/44—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
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management

Landscapes

  • Engineering & Computer Science (AREA)
  • Software Systems (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

A kind of cloud computing virtual machine placement method using curve complementation based on resource, main thought is: picking out overload physical host, a virtual machine is selected in overload physical machine, predict the resource service condition at its following t time point, the resource service condition at its following t time point is predicted the physical host for migration, finding a physical host makes the resource service condition of its resource service condition and virtual machine be complementary, calculate complementary degree of the physical host with the virtual machine, then process calculates the complementary degree on overload physical host between all virtual machines and all physical hosts for migration according to this, select the maximum one group of virtual machine of complementation degree value and physical host, it will be on virtual machine (vm) migration to the physical host.If physical machine still overloads after migration, corresponding integrated complementary degree is removed from integrated complementary degree set and reselects one group of virtual machine migrated with physical host, until physical machine no longer overloads or integrated complementary degree collection is combined into sky.

Description

A kind of cloud computing virtual machine placement method using curve complementation based on resource
Technical field
The invention belongs to cloud computings and virtualization field, and in particular to a kind of cloud computing that curve complementation is used based on resource Virtual machine placement method is mainly used for reducing virtual machine (vm) migration number and improves the utilization rate of physical machine cpu resource, whole to reduce The energy consumption of a data center.
Background technique
Cloud computing is a kind of new technology for providing user service on demand, it has revolutionary shadow to IT industry It rings.The development of cloud computing has expedited the emergence of thousands of Data Node.Virtualization technology is a key technology of cloud computing, it is Cloud computing is achieved provides the basis of service on demand, and in the environment of virtualization, the running environment of software is different from traditional mould Formula operates on hardware, but operates in the environment of virtualization, and under virtualized environment, hardware resource is can be according to demand It is allocated.From the perspective of data center, virtualization technology realizes a physical machine and runs more virtual machines, thus Significantly reduce the cost of hardware.
It is to migrate online that virtualization technology, which has a key property: Jiang Yitai be currently running in virtual machine from current object It is moved on reason machine in an other physical machine.The characteristic that virtual machine migrates online has important meaning to the management of virtual machine Justice, main meaning are embodied in three aspects.First is the load balancing for being advantageously implemented physical machine.When the load of physical machine Gao Shi moves to partial virtual machine in the physical machine of load too low, realize virtual machine load too high and it is too low between it is equal Weighing apparatus；Second is easy for carrying out managing power consumption to data center.By the virtual machine (vm) migration in the physical machine of load too low to other void On quasi- machine, current physical machine is closed to realize the target for reducing energy consumption；Third is conveniently to safeguard to data center.When just Operation physical machine when something goes wrong, can be by the virtual machine (vm) migration on present physical machine to other physical machines, to protect Demonstrate,prove the normal operation of virtual machine.
An essential link is exactly the placement of virtual machine during virtual machine (vm) migration, and existing virtual machine places plan There are two types of slightly, one is the virtual machine Placement Strategy based on physical host resource utilization, refers to when virtual machine is placed, consider The loading condition of physical host after virtual machine is placed, the algorithm is to improve the utilization rate of physical host as target.Another kind is sense The virtual machine Placement for knowing the dependence between virtual machine refers to during placing virtual machine, consider between virtual machine according to Rely relationship (traffic i.e. between virtual machine), when two virtual machines are in logical on different physical hosts and between them Traffic is larger, then each communication requires to access by network, the time needed at this time completing primary communication will It is long；Effective solution scheme a kind of for this problem exactly puts the several virtual machines of (traffic is larger) of interdepending It sets on same physical host.The algorithm is based on the traffic for reducing entire data center.
For a large-scale data center, physical machine overload the case where happen occasionally, but cause overload the reason of it is more Be its load more virtual machine Centralized requests host resources caused by, for this problem of effective solution and realize reduction The purpose of energy consumption needs to migrate the virtual machine loaded in overload physical machine.And most moving method is at present It is migrated whether for physical machine overload, there is no making a concrete analysis of to the resource situation of virtual machine and physical machine, this is directly Result in time of the proving effective short and a large amount of physical machine wasting of resources of migration.
Summary of the invention
The present invention is in view of the above-mentioned problems, propose a kind of cloud computing virtual machine placement side for using curve complementation based on resource Method, this method are analyzed and are predicted virtual machine and physical machine resource service condition interior for a period of time, select in conjunction with resource complementation degree Reasonable Placement Strategy, it is ensured that the load balancing in target physical machine following a period of time subtracts while energy saving Migration number is lacked.
A kind of cloud computing virtual machine placement method being used curve complementation based on resource, is included the following steps:
Step 1, the virtual machine set V={ v in overload physical machine is obtained1,v2,v3,……vnAnd for migration physics Set P={ the p of machine1,p2,p3,……pk, wherein every virtual machine and physical machine include z class resource；
Step 2, the virtual machine v in overload virtual machine set V is obtainediIn the utilization rate matrix of the z class resource at t time point Ai；
Step 3, the virtual machine v at the following t time point is predicted with prediction techniques such as neural networksiZ class resource make With data, obtains prediction and use data matrix Ci；
Step 4, it obtains for the physical machine p in the physical machine set P of migrationjIn the utilization of the z class resource at t time point Rate matrix Bj；
Step 5, the physical machine p at the following t time point is predicted with prediction techniques such as neural networksjZ class resources left Utilization rate obtains prediction resources left utilization rate matrix Dj；
Step 6, virtual machine v is calculatediCurvature r of the upper z class resource utilization t-th of time pointizt, thus obtain void Quasi- machine viUpper z class resource utilization ciztIn the following t time point curvature riztMatrix Ri；
Step 7, physical machine p is calculatedjCurvature q of the upper z class resource utilization t-th of time pointjzt, thus obtain object Reason machine pjUpper z class resource utilization bjztIn the following t time point curvature qjztMatrix Qj；
Step 8, virtual machine v is calculatediWith physical machine pjBetween z class resource complementary degree hijz, thus obtain virtual machine viWith physical machine pjBetween all z class resources complementary degree, be combined to obtain complementary set Hij；
Step 9, virtual machine v is calculatediWith physical machine pjBetween integrated complementary degree sij, thus obtain in virtual machine set V Integrated complementary degree s in virtual machine and physical machine set P between physical machineijSet S；
Step 10, integrated complementary degree s is calculatedijMinimum value smin., obtain the corresponding the smallest virtual machine v of complementation degreeiWith Physical machine pj, by virtual machine viIt is placed into physical machine pjOn, and s is removed from set Smin；
Step 11, computation overload physical host poThe remaining utilization rate e of upper z class resourceozt, if there is ejzt> 0 and gather S is not sky, returns to step 10；Otherwise, migration terminates.
Further, in the step 2, the virtual machine v in overload virtual machine set V is obtainediIn the z class at t time point The utilization rate matrix A of resourcei, wherein aiztFor virtual machine viThe utilization rate of z class resource, resources of virtual machine at t-th of time Utilization rate matrix AiIn every a line indicate virtual machine viOn a kind of resource t time point utilization rate.
Further, in the step 3, the virtual machine at the following t time point is predicted with prediction techniques such as neural networks viZ class resource use data Ci；Wherein ciztTo predict obtained virtual machine viThe benefit of z class resource at t-th of time With rate.
Further, it in the step 4, obtains for the physical machine p in the physical machine set P of migrationjT time point Z class resource utilization rate matrix Bj, wherein bjztIt is defined as physical machine pjThe utilization rate of z class resource, object at t-th of time Reason machine resource utilization matrix BjIn every a line expression thing manage machine pjOn a kind of resource t time point utilization rate.
Further, in the step 5, the physical machine at the following t time point is predicted with prediction techniques such as neural networks pjZ class resources left utilization rate matrix Dj, wherein djztIn be defined as the obtained physical machine p of predictionjThe z at t-th of time The utilization rate of class resource, uzIndicate the utilization rate upper threshold value of z class resource.
Further, in the step 6, virtual machine v is calculated by formula (1)iUpper z class resource utilization is at t-th The curvature r at time pointizt；
Obtain virtual machine viUpper z class resource utilization ciztIn the following t time point curvature riztMatrix Ri。
Further, in the step 7, physical machine p is calculated by formula (2)jUpper z class resource utilization is at t-th The curvature q at time pointjzt；
Obtain physical machine pjUpper z class resource utilization bjztIn the following t time point curvature qjztMatrix Qj。
Further, in the step 8, virtual machine v is calculated by formula (3)iWith physical machine pjBetween z class resource Complementary degree hijz；
Obtain virtual machine viWith physical machine pjBetween all z class resources complementary degree group be combined into complementary sets close Hij。
Hij=[hij1,hij2,…hijz]
Further, in the step 9, virtual machine v is calculated by formula (4)iWith physical machine pjBetween integrated complementary degree sij,
Obtain the integrated complementary degree s in virtual machine set V in virtual machine and physical machine set P between physical machineijSet S。
S=[s11,s12…s1k,s21…snk]
Further, in the step 10, integrated complementary degree s is calculated by formula (5)ijMinimum value smin.；
smin=min { Sij, 0 < i < n, 0 < j < k } and (5)
I, j is sminSubscript in set S, by virtual machine viIt is placed into physical machine pjOn, s is removed from set Smin；
In the step 11, computation overload physical host poThe remaining utilization rate e of upper z class resourceozt；
eozt=uzt-uz-cozt (6)
uztTo overload overall utilization of the z class resource in time t in physical machine, if there is ejzt> 0 and set S is not Sky returns to step 10；Otherwise, migration terminates.
The present invention, for the Placement Strategy of more current mainstream, main advantage is: this method analyze and predict virtual machine and The service condition of physical machine all kinds of resources interior for a period of time, it is ensured that the load in target physical machine following a period of time is equal Weighing apparatus, and resource comprehensive complementation degree is combined to select reasonable Placement Strategy so that virtual machine and target physical machine to be migrated it Between all kinds of resource utilizations it is all as complementary as possible, migration number is reduced while energy saving.
Detailed description of the invention
Fig. 1 is a kind of process based on resource using the cloud computing virtual machine placement method of curve complementation of the present invention Figure.
Specific embodiment
Technical solution of the present invention is described in further detail with reference to the accompanying drawings of the specification.
It is a kind of to be included the following steps: referring to Fig.1 based on resource using the cloud computing virtual machine placement method of curve complementation
Step 1, the virtual machine set V={ v in overload physical machine is obtained1,v2,v3,……vnAnd for migration physics Set P={ the p of machine1,p2,p3,……pk, wherein every virtual machine and physical machine include z class resource.
Step 2, the virtual machine v in overload virtual machine set V is obtainediIn the utilization rate matrix of the z class resource at t time point Ai。
In the step 2, the virtual machine v in overload virtual machine set V is obtainediIn the utilization of the z class resource at t time point Rate matrix Ai, wherein aiztFor virtual machine viThe utilization rate of z class resource at t-th of time, resources of virtual machine utilize rate matrix AiIn every a line indicate virtual machine viOn a kind of resource t time point utilization rate.
Step 3, the virtual machine v at the following t time point is predicted with prediction techniques such as neural networksiZ class resource make With data, obtains prediction and use data matrix Ci。
In the step 3, the virtual machine v at the following t time point is predicted with prediction techniques such as neural networksiZ class money The use data C in sourcei；Wherein ciztTo predict obtained virtual machine viThe utilization rate of z class resource at t-th of time.
Step 4, it obtains for the physical machine p in the physical machine set P of migrationjIn the utilization of the z class resource at t time point Rate matrix Bj。
In the step 4, obtain for the physical machine p in the physical machine set P of migrationjIn the z class resource at t time point Utilization rate matrix Bj, wherein bjztIt is defined as physical machine pjThe utilization rate of z class resource at t-th of time, physical machine resource Utilization rate matrix BjIn every a line expression thing manage machine pjOn a kind of resource t time point utilization rate.
Step 5, the physical machine p at the following t time point is predicted with prediction techniques such as neural networksjZ class resources left Utilization rate obtains prediction resources left utilization rate matrix Dj。
In the step 5, the physical machine p at the following t time point is predicted with prediction techniques such as neural networksjZ class money Source residue utilization rate matrix Dj, wherein djztIn be defined as the obtained physical machine p of predictionjThe benefit of z class resource at t-th of time With rate, uzIndicate the utilization rate upper threshold value of z class resource.
Step 6, virtual machine v is calculatediCurvature r of the upper z class resource utilization t-th of time pointizt, thus obtain void Quasi- machine viUpper z class resource utilization ciztIn the following t time point curvature riztMatrix Ri。
In the step 6, virtual machine v is calculated by formula (1)iSong of the upper z class resource utilization t-th of time point Rate rizt；
Obtain virtual machine viUpper z class resource utilization ciztIn the following t time point curvature riztMatrix Ri。
Step 7, physical machine p is calculatedjCurvature q of the upper z class resource utilization t-th of time pointjzt, thus obtain object Reason machine pjUpper z class resource utilization bjztIn the following t time point curvature qjztMatrix Qj。
In the step 7, physical machine p is calculated by formula (2)jSong of the upper z class resource utilization t-th of time point Rate qjzt；
Obtain physical machine pjUpper z class resource utilization bjztIn the following t time point curvature qjztMatrix Qj。
Step 8, virtual machine v is calculatediWith physical machine pjBetween z class resource complementary degree hijz, thus obtain virtual machine viWith physical machine pjBetween all z class resources complementary degree, be combined to obtain complementary set Hij。
In the step 8, virtual machine v is calculated by formula (3)iWith physical machine pjBetween z class resource complementary degree hijz；
Obtain virtual machine viWith physical machine pjBetween all z class resources complementary degree group be combined into complementary sets close Hij。
Hij=[hij1,hij2,…hijz]
Step 9, virtual machine v is calculatediWith physical machine pjBetween integrated complementary degree sij, thus obtain in virtual machine set V Integrated complementary degree s in virtual machine and physical machine set P between physical machineijSet S.
In the step 9, virtual machine v is calculated by formula (4)iWith physical machine pjBetween integrated complementary degree sij,
Obtain the integrated complementary degree s in virtual machine set V in virtual machine and physical machine set P between physical machineijSet S。
S=[s11,s12…s1k,s21…snk]
Step 10, integrated complementary degree s is calculatedijMinimum value smin, the corresponding the smallest virtual machine v of complementation degree is obtainediWith Physical machine pj, by virtual machine viIt is placed into physical machine pjOn, and s is removed from set Smin。
In the step 10, integrated complementary degree s is calculated by formula (5)ijMinimum value smin.；
smin=min { Sij, 0 < i < n, 0 < j < k } and (5)
I, j is sminSubscript in set S, by virtual machine viIt is placed into physical machine pjOn, s is removed from set Smin。
Step 11, computation overload physical host poThe remaining utilization rate e of upper z class resourceozt, if there is ejzt> 0 and gather S is not sky, returns to step 10；Otherwise, migration terminates.
In the step 11, computation overload physical host poThe remaining utilization rate e of upper z class resourceozt；
eozt=uzt-uz-cozt (6)
uztTo overload overall utilization of the z class resource in time t in physical machine, if there is ejzt> 0 and set S is not Sky returns to step 10；Otherwise, migration terminates.
The foregoing is merely better embodiment of the invention, protection scope of the present invention is not with above embodiment Limit, as long as those of ordinary skill in the art's equivalent modification or variation made by disclosure according to the present invention, should all be included in power In the protection scope recorded in sharp claim.

Claims (10)

1. a kind of cloud computing virtual machine placement method for using curve complementation based on resource, characterized by the following steps:
Step 1, the virtual machine set V={ v in overload physical machine is obtained1,v2,v3,……vnAnd for migration physical machine Set P={ p1,p2,p3,……pk, wherein every virtual machine and physical machine include z class resource；
Step 2, the virtual machine v in overload virtual machine set V is obtainediIn the utilization rate matrix A of the z class resource at t time pointi；
Step 3, the virtual machine v at the following t time point is predicted with prediction techniques such as neural networksiZ class resource use number According to obtaining prediction using data matrix Ci；
Step 4, it obtains for the physical machine p in the physical machine set P of migrationjIn the utilization rate square of the z class resource at t time point Battle array Bj；
Step 5, the physical machine p at the following t time point is predicted with prediction techniques such as neural networksjZ class resources left utilize Rate obtains prediction resources left utilization rate matrix Dj；
Step 6, virtual machine v is calculatediCurvature r of the upper z class resource utilization t-th of time pointizt, thus obtain virtual machine vi Upper z class resource utilization ciztIn the following t time point curvature riztMatrix Ri；
Step 7, physical machine p is calculatedjCurvature q of the upper z class resource utilization t-th of time pointjzt, thus obtain physical machine pj Upper z class resource utilization bjztIn the following t time point curvature qjztMatrix Qj；
Step 8, virtual machine v is calculatediWith physical machine pjBetween z class resource complementary degree hijz, thus obtain virtual machine viWith Physical machine pjBetween all z class resources complementary degree, be combined to obtain complementary set Hij；
Step 9, virtual machine v is calculatediWith physical machine pjBetween integrated complementary degree sij, thus obtain virtual machine in virtual machine set V And the integrated complementary degree s in physical machine set P between physical machineijSet S；
Step 10, integrated complementary degree s is calculatedijMinimum value smin., obtain the corresponding the smallest virtual machine v of complementation degreeiAnd physical machine pj, by virtual machine viIt is placed into physical machine pjOn, and s is removed from set Smin；
Step 11, computation overload physical host poThe remaining utilization rate e of upper z class resourceozt, if there is ejzt> 0 and set S is not Sky returns to step 10；Otherwise, migration terminates.
2. a kind of cloud computing virtual machine placement method for using curve complementation based on resource according to claim 1, special Sign is: in the step 2, obtaining the virtual machine v in overload virtual machine set ViIn the utilization of the z class resource at t time point Rate matrix Ai, wherein aiztFor virtual machine viThe utilization rate of z class resource at t-th of time, resources of virtual machine utilize rate matrix AiIn every a line indicate virtual machine viOn a kind of resource t time point utilization rate.
3. a kind of cloud computing virtual machine placement method for using curve complementation based on resource according to claim 1, special Sign is: in the step 3, the virtual machine v at the following t time point is predicted with prediction techniques such as neural networksiZ class resource Use data Ci；Wherein ciztTo predict obtained virtual machine viThe utilization rate of z class resource at t-th of time.
4. a kind of cloud computing virtual machine placement method for using curve complementation based on resource according to claim 1, special Sign is: in the step 4, obtaining for the physical machine p in the physical machine set P of migrationjIn the z class resource at t time point Utilization rate matrix Bj, wherein bjztIt is defined as physical machine pjThe utilization rate of z class resource at t-th of time, physical machine resource Utilization rate matrix BjIn every a line expression thing manage machine pjOn a kind of resource t time point utilization rate.
5. a kind of cloud computing virtual machine placement method for using curve complementation based on resource according to claim 1, special Sign is: in the step 5, the physical machine p at the following t time point is predicted with prediction techniques such as neural networksjZ class resource Remaining utilization rate matrix Dj, wherein djztIn be defined as the obtained physical machine p of predictionjThe utilization of z class resource at t-th of time Rate, uzIndicate the utilization rate upper threshold value of z class resource.
6. a kind of cloud computing virtual machine placement method for using curve complementation based on resource according to claim 1, special Sign is: in the step 6, calculating virtual machine v by formula (1)iSong of the upper z class resource utilization t-th of time point Rate rizt；
Obtain virtual machine viUpper z class resource utilization ciztIn the following t time point curvature riztMatrix Ri。
7. a kind of cloud computing virtual machine placement method for using curve complementation based on resource according to claim 1, special Sign is: in the step 7, calculating physical machine p by formula (2)jSong of the upper z class resource utilization t-th of time point Rate qjzt；
Obtain physical machine pjUpper z class resource utilization bjztIn the following t time point curvature qjztMatrix Qj。
8. a kind of cloud computing virtual machine placement method for using curve complementation based on resource according to claim 1, special Sign is: in the step 8, calculating virtual machine v by formula (3)iWith physical machine pjBetween z class resource complementary degree hijz；
Obtain virtual machine viWith physical machine pjBetween all z class resources complementary degree group be combined into complementary sets close Hij。
Hij=[hij1,hij2,…hijz]
9. a kind of cloud computing virtual machine placement method for using curve complementation based on resource according to claim 1, special Sign is: in the step 9, calculating virtual machine v by formula (4)iWith physical machine pjBetween integrated complementary degree sij,
Obtain the integrated complementary degree s in virtual machine set V in virtual machine and physical machine set P between physical machineijSet S.
S=[s11,s12…s1k,s21…snk]
10. a kind of cloud computing virtual machine placement method for using curve complementation based on resource according to claim 1, special Sign is: in the step 10, calculating integrated complementary degree s by formula (5)ijMinimum value smin.；
smin=min { Sij, 0 < i < n, 0 < j < k } and (5)
I, j is sminSubscript in set S, by virtual machine viIt is placed into physical machine pjOn, s is removed from set Smin；
In the step 11, computation overload physical host poThe remaining utilization rate e of upper z class resourceozt；
eozt=uzt-uz-cozt (6)
uztTo overload overall utilization of the z class resource in time t in physical machine, if there is ejzt> 0 and set S is not sky, Return to step 10；Otherwise, migration terminates.
CN201910249791.4A 2019-03-29 2019-03-29 Cloud computing virtual machine placement method based on resource usage curve complementation Active CN109976879B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910249791.4A CN109976879B (en) 2019-03-29 2019-03-29 Cloud computing virtual machine placement method based on resource usage curve complementation

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910249791.4A CN109976879B (en) 2019-03-29 2019-03-29 Cloud computing virtual machine placement method based on resource usage curve complementation

Publications (2)

Publication Number Publication Date
CN109976879A true CN109976879A (en) 2019-07-05
CN109976879B CN109976879B (en) 2022-09-16

Family

ID=67081602

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910249791.4A Active CN109976879B (en) 2019-03-29 2019-03-29 Cloud computing virtual machine placement method based on resource usage curve complementation

Country Status (1)

Country Link
CN (1) CN109976879B (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110399203A (en) * 2019-07-25 2019-11-01 南京邮电大学 A kind of cloud computing virtual machine migration method based on Fu Leixie distance
WO2021180056A1 (en) * 2020-03-09 2021-09-16 华为技术有限公司 Method for resource migration, system and device
CN113742090A (en) * 2021-11-08 2021-12-03 苏州浪潮智能科技有限公司 Load balancing method and device for virtual machine and storage medium

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104008018A (en) * 2014-05-22 2014-08-27 南京邮电大学 Virtual machine online migration method in cloud computing environment
US8990805B2 (en) * 2011-12-01 2015-03-24 Tunghai University Method of dynamic resource allocation for a virtual machine cluster
CN106125888A (en) * 2016-06-23 2016-11-16 河海大学常州校区 The efficient power-economizing method of the utilization of resources based on virtual machine (vm) migration in cloud data center

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8990805B2 (en) * 2011-12-01 2015-03-24 Tunghai University Method of dynamic resource allocation for a virtual machine cluster
CN104008018A (en) * 2014-05-22 2014-08-27 南京邮电大学 Virtual machine online migration method in cloud computing environment
CN106125888A (en) * 2016-06-23 2016-11-16 河海大学常州校区 The efficient power-economizing method of the utilization of resources based on virtual machine (vm) migration in cloud data center

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
陈驹洲: "云计算环境下网络感知的虚拟机迁移研究", 《硕士电子期刊》 *

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110399203A (en) * 2019-07-25 2019-11-01 南京邮电大学 A kind of cloud computing virtual machine migration method based on Fu Leixie distance
WO2021180056A1 (en) * 2020-03-09 2021-09-16 华为技术有限公司 Method for resource migration, system and device
CN113742090A (en) * 2021-11-08 2021-12-03 苏州浪潮智能科技有限公司 Load balancing method and device for virtual machine and storage medium
CN113742090B (en) * 2021-11-08 2022-03-08 苏州浪潮智能科技有限公司 Load balancing method and device for virtual machine and storage medium

Also Published As

Publication number Publication date
CN109976879B (en) 2022-09-16

Similar Documents

Publication Publication Date Title
CN108829494B (en) Container cloud platform intelligent resource optimization method based on load prediction
CN102724277B (en) The method of live migration of virtual machine and deployment, server and group system
CN104102543B (en) The method and apparatus of adjustment of load in a kind of cloud computing environment
CN105446979B (en) Data digging method and node
CN104008018B (en) The online moving method of virtual machine under cloud computing environment
CN109976879A (en) A kind of cloud computing virtual machine placement method using curve complementation based on resource
CN110347498B (en) Load dynamic migration method in container and virtual machine mixed cloud environment
Rajabzadeh et al. Energy-aware framework with Markov chain-based parallel simulated annealing algorithm for dynamic management of virtual machines in cloud data centers
CN103677960B (en) Game resetting method for virtual machines capable of controlling energy consumption
CN106528270A (en) Automatic migration method and system of virtual machine based on OpenStack cloud platform
CN104216784A (en) Hotspot balance control method and related device
CN110362388A (en) A kind of resource regulating method and device
Gomathi et al. Multi-objective optimization of energy aware virtual machine placement in cloud data center
CN106686039A (en) Resource scheduling method and device in cloud computing system
CN106598693B (en) Delay strategy-based energy consumption and load sensitive virtual machine integration method
Devi et al. SLAV mitigation and energy-efficient VM allocation technique using improvised grey wolf optimization algorithm for cloud computing
CN104778088A (en) Method and system for optimizing parallel I/O (input/output) by reducing inter-progress communication expense
CN105373451B (en) The method and device that a kind of virtual machine is placed
CN107423114A (en) A kind of dynamic migration of virtual machine method based on classification of service
CN110399203A (en) A kind of cloud computing virtual machine migration method based on Fu Leixie distance
Jayasena et al. Multi-objective energy efficient resource allocation using virus colony search (VCS) algorithm
CN106227600B (en) A kind of multidimensional virtual resource allocation method based on Energy-aware
Talukder et al. Dual threshold load balancing in SDN environment using process migration
Guo et al. Handling data skew at reduce stage in Spark by ReducePartition
Quan et al. Energy usage and carbon emission optimization mechanism for federated data centers

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant