CN104461739B - A kind of virtual machine batch dispositions method based on cloudsim platforms - Google Patents
A kind of virtual machine batch dispositions method based on cloudsim platforms Download PDFInfo
- Publication number
- CN104461739B CN104461739B CN201410767818.6A CN201410767818A CN104461739B CN 104461739 B CN104461739 B CN 104461739B CN 201410767818 A CN201410767818 A CN 201410767818A CN 104461739 B CN104461739 B CN 104461739B
- Authority
- CN
- China
- Prior art keywords
- virtual machine
- ant
- machine
- physical machine
- cloudsim
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention discloses a kind of virtual machine batch dispositions method based on cloudsim platforms, and extended hybrid ant group algorithm simultaneously carries out the global renewal of pheromones as the strategy of virtual machine batch deployment, the hybrid ant colony using equation below：Wherein rho is the pheromones residual factor,It is Pheromone Matrixes of the virtual machine i to physical machine j；Wherein ants [k] .pheromoneDeltaMatrix represents the pheromones transformation matrices of kth ant, and antNum is ant quantity.The load balancing and resource utilization of system can be significantly improved than Greedy strategy using the dispositions method of the present invention.
Description
Technical field
The present invention relates to internet cloud calculating field, more particularly to a kind of virtual machine batch portion based on cloudsim platforms
Arranging method.
Background technology
With the made rapid progress to flourish with Internet technology of computer technology, cloud computing is as a kind of innovative
Computation schema arises at the historic moment.Infrastructure is the basis that service is cloud computing, and its core is by the computing resource of data center
Resource pool is formed by virtualization technology, and submits job specification and resource request reasonably to be distributed according to user, for
Family provides the resources such as the telescopic entity or virtual calculating of scale, storage and network.Cloud data center deploys a large amount of virtual
Machine provides a user service.
Virtual machine Placement Problems are an important research problems of cloud resource scheduling, and virtual machine is placed and aims to solve the problem that virtual machine
Mapping relations between physical machine, emphasis are the virtual machine placement schemes that optimization is found according to set Placement Strategy.
Greedy algorithm strategy can realize the optimal deployment of single virtual machine, but can not cause the deployment of whole virtual machine cluster
It is optimal.And make it that the consumption of machine more load balancing, power is more reduced, it just must take into consideration asking for global optimum
Topic.
The content of the invention
In order to solve the problems, such as that the load balancing of system and resource utilization are low, the technical solution adopted by the present invention is as follows：
A kind of virtual machine batch dispositions method based on cloudsim platforms, extended hybrid ant group algorithm and as void
The strategy of plan machine batch deployment, it is characterised in that the hybrid ant colony carries out the global renewal of pheromones using (1) formula：
Pheromone [j] [i]=pheromone [j] [i] * rho (1)
Wherein rho is the pheromones residual factor,
It is Pheromone Matrixes of the virtual machine j to physical machine i；Wherein ants [k] .pheromoneDeltaMatrix represents
The pheromones transformation matrices of k ant, antNum are ant quantity.
Further, taboo list search is added in the hybrid ant colony, the taboo list search is specially：In ant
When ant is that virtual machine distributes physical machine, physical machine i is have selected then from still untapped physical machine array if virtual machine
Remove selected physical machine i in unUsedHosts, virtual machine is to be allocated if unUsedHosts still has to be empty, past
UnUsedHosts adds all physical machine numberings.
Further, physical machine performance parameter dynamic more new strategy is added in the hybrid ant colony.
Further, the physical machine performance parameter dynamic more new strategy is specially：If ant, which is virtual machine j, have selected thing
Reason machine i, then virtual machine j corresponding normalization array is subtracted to update the cpuMips of physical machine normalization array, internal memory
Normalize the normalization array of array, the normalization array of bandwidth and hard disk size.
Virtual machine cpuMips normalization array vmCpuMipsNormalArray is calculated by (2) formula and (3) formula：
As maxVmCpuMips ≠ minVmCpuMips,
As maxVmCpuMips=minVmCpuMips,
VmCpuMipsNormalArray [i]=1 (3)
Wherein virtual machine cpuMips array elements vmCpuMipsArray [i] is virtual machine i mips and virtual machine i
The product of cpu number.MaxVmCpuMips and minVmCpuMips is virtual machine cpuMips array elements respectively
Maximum and minimum value in vmCpuMipsArray.
Physical machine cpuMips normalization array hostCpuMipsNormalArray calculating is similarly.
The normalization array vmRamNormalArray of virutal machine memory is calculated by (4) formula and (5) formula：
During maxVmRam ≠ minVmRam,
As maxVmRam=minVmRam,
VmRamNormalArray [i]=1 (5)
Wherein virtual machine Ram array elements vmRamArray [i] is virtual machine i Ram.MaxVmRam and minVmRam points
It is not the maximum and minimum value in virtual machine Ram array elements vmRamArray.
The normalization array hostRamNormalArray of physical machine internal memory calculating is similar.
The normalization array vmBwNormalArray of virtual machine bandwidth, the normalization array of main frame bandwidth
hostBwNormalArray；The normalization array vmSizeNormalArray of virtual hard disk size, host hard drive size
Normalize array hostSizeNormalArray calculating and the normalization array vmRamNormalArray of virutal machine memory
Calculate similar.
In the placement process of virtual machine, the value of matching degree is dynamic change, if virtual machine j will be deployed in physical machine
On i, then when considering physical machine i and other virtual machines matching degree, the performance parameter after physical machine i deployment virtual machines j must be used
Calculated.
Further, the probability P that physical machine i is selected by virtual machine jiCalculated by (6) formula：
Wherein τi=pheromone [j] [i],τk=pheromone [j] [k],Alpha and beta is arbitrary value, it is proposed that value is 1.0 or 5.0,
MatchDegree=(cpuMipsMatchDegreeMatrix [i] [j]2+ramMatchDegreeMatrix[i]
[j]2
+bwMatchDegreeMatrix[i][j]2+sizeMatchDegreeMatrix[i][j]2)1/2
Further, every ant after the deployment scheme of oneself is established all to pheromones transformation matrices
PheromoneDeltaMatrix is updated.
Further, described information element transformation matrices pheromoneDeltaMatrix renewal is carried out by (7) formula：
It is whole matching degree.Wherein
Further, the hybrid ant colony comprises the following steps：
S81 is initialized：Relevant parameter is transmitted to the ant colony；
S82 produces the ant of respective numbers, according to initial information element initPheromone initialization information prime matrixs
Pheromone, primary iteration number I=0；
S83 I=I+1；
S84 antNum ants perform the task of oneself, find out corresponding deployment scheme；
After S85 antNum ants complete antNum deployment scheme of all deploying virtual machines acquisitions, it is each to compare calculating
The overall matching degree cost of scheme, the optimal deployment scheme of contrast selection current iteration.
S86 fresh information prime matrixs pheromone；
S87 judges whether I is more than or equal to times, if it is not, returning to S83, next iteration is carried out, if so, then performing stopping
Iteration, optimal placement schemes bestVmToHost is exported, terminate program.
Initialization, the ant colony, including ant quantity antNum, iterative algebra times, virtual machine number are transmitted to by relevant parameter
Measure vmNum, physical machine quantity hostNum, heuristic factor alpha, expecting factor beta, pheromones residual factor rho, initial letter
Cease plain initPheromone, virtual machine cpuMips normalization array vmCpuMipsNormalArray, main frame cpuMips
Normalize array hostCpuMipsNormalArray, normalization array vmRamNormalArray, the main frame of virutal machine memory
The normalization array hostRamNormalArray of internal memory, normalization array vmBwNormalArray, the main frame of virtual machine bandwidth
The normalization array hostBwNormalArray of bandwidth, the normalization array vmSizeNormalArray of virtual hard disk size
With the normalization array hostSizeNormalArray of host hard drive size.
The initial information element of all physical machines is all initialized by an initial value initPheromone.Most starting, owning
The initial information element of physical machine is all identical.
Further, in the step S84 ant perform the task of oneself find out corresponding to deployment scheme include following step
Suddenly：
S91 initializes to the ant：Relevant parameter is transmitted to the ant by ant colony；
S92 calculates cpuMips matching degree matrix cpuMipsMatchDegreeMatrix, the matching degree matrix of internal memory
RamMatchDegreeMatrix, the matching degree matrix bwMatchDegreeMatrix of bandwidth and hard disk size matching degree square
Battle array sizeMatchDegreeMatrix；
S93 initialization information element transformation matrices pheromoneDeltaMatrix is 0, still untapped physical machine array
UnUsedHosts, the mapping array of virtual machine to physical machine；
S94 is passed to virtual machine numbering j and Pheromone Matrix pheromone, checks whether unUsedHosts arrays are sky,
If otherwise calculate the selected probability P of physical machine that numbering is i in unUsedHosts arraysiIf then toward unUsedHosts
All physical machine numberings are added in array and calculate the selected probability P of physical machine that numbering is i againi；
One physical machine i of S95 roulette selections；
S96 renewals physical machine i cpuMips normalization array, the normalization array of bandwidth, the normalization array of internal memory and
The normalization array of hard disk size, remove selected physical machine i from unUsedHosts arrays；
S97 checks whether that also virtual machine is unallocated, if then returning to S92, if it is not, then ant fresh information element change
Then matrix pheromoneDeltaMatrix stops the task of oneself.
During initialization by ant colony by the quantity vmNum of virtual machine, the quantity hostNum of main frame, heuristic factor alpha,
Expecting factor is beta, virtual machine cpuMips normalization array vmCpuMipsNormalArray, main frame cpuMips return
One changes array hostCpuMipsNormalArray, the normalization array vmRamNormalArray of virutal machine memory, in main frame
Normalization array hostRamNormalArray, normalization array vmBwNormalArray, the host tape of virtual machine bandwidth deposited
Wide normalization array hostBwNormalArray,
The normalization array vmSizeNormalArray of virtual hard disk size, the normalization array of host hard drive size
HostSizeNormalArray is transmitted to the ant.
The computational methods of matching degree matrix are to subtract virtual machine with the normalization array of physical machine to normalize array accordingly.
Roulette selection is more commonly used in system of selection.The selected probability of the bigger individual of fitness is bigger, this
Sample is very helpful to the quality for improving solution.
Roulette selection in the present invention is in detail
The probability selectProb of one (0,1) is randomly generated first, makes sum=0.0,
If for i from 0 to hostNum, sum is smaller than selectProb, then acquiescence selects the first of unUsedHosts arrays
Individual element is selected physical machine.
Further, a kind of virtual machine batch dispositions method based on cloudsim platforms of the invention includes：
CreateVmsInDatacenter functions in cloudsim datacenterbrokerAco check whether there is
The virtual machine set not created, if so, the message for creating virtual machine is then sent to datacenterAco, what transmission to be created
Virtual machine set；
ProcessVmCreate functions in datacenterAco receive the virtual machine set sent, call virtual
AllocateHostForVmList functions in machine distribution class VmAllocationPolicyAco,
In allocateHostForVmList functions physical machine is distributed according to the hybrid ant colony for virtual machine set.
A kind of virtual machine batch dispositions method based on cloudsim platforms of the present invention uses cloud emulation platform
Cloudsim is as test simulation instrument.By to the management virtual machine placement method in VmAllocationPolicyAco classes
AllocateHostForVmList functions are write, and realize virtual machine Placement, and change Vm and Datacenter simultaneously
Class.
Beneficial effects of the present invention：Use a kind of virtual machine batch deployment side based on cloudsim platforms of the present invention
Method, than the load balancing and resource utilization that existing greedy algorithm and Basic Ant Group of Algorithm can be obviously improved system.
Brief description of the drawings
Fig. 1 is the overall flow figure of the embodiment of the present invention.
Fig. 2 is the hybrid ant colony flow chart of the embodiment of the present invention.
Fig. 3 is the physical machine performance parameter schematic diagram of the embodiment of the present invention.
Fig. 4 is the virtual machine performance parameter schematic diagram of the embodiment of the present invention.
Fig. 5 is the cloud task length schematic diagram of the embodiment of the present invention.
Fig. 6 is the hybrid ant colony ant colony parameter setting schematic diagram of the embodiment of the present invention.
Fig. 7 is the design sketch using the virtual machine batch dispositions method of the present invention.
Fig. 8 is the design sketch using the virtual machine batch dispositions method of the present invention.
Fig. 9 is the design sketch using the cloudsim Greedy strategies carried.
Figure 10 is the design sketch using the cloudsim Greedy strategies carried.
Embodiment
As shown in figure 1, a kind of virtual machine based on cloudsim platforms of the present invention is apparent that by the flow chart
The overall flow of batch dispositions method.
A kind of virtual machine batch dispositions method overall flow based on cloudsim platforms of the present invention is as follows：
CreateVmsInDatacenter functions in cloudsim datacenterbrokerAco check whether there is
The virtual machine set not created, if so, the message for creating virtual machine is then sent to datacenterAco, what transmission to be created
Virtual machine set；
ProcessVmCreate functions in datacenterAco receive the virtual machine set sent, call virtual
AllocateHostForVmList functions in machine distribution class VmAllocationPolicyAco,
In allocateHostForVmList functions physical machine is distributed according to hybrid ant colony for virtual machine set.
As shown in Fig. 2 the handling process of hybrid ant colony is apparent that by the flow chart.
Hybrid ant colony handling process of the present invention comprises the following steps：
S81 is initialized：Relevant parameter is transmitted to the ant colony；
S82 produces the ant of respective numbers, according to initial information element initPheromone initialization information prime matrixs
Pheromone, primary iteration number I=0；
S83 I=I+1；
S84 antNum ants perform the task of oneself, find out corresponding deployment scheme；
After S85 antNum ants complete antNum deployment scheme of all deploying virtual machines acquisitions, it is each to compare calculating
The overall matching degree cost of scheme, the optimal deployment scheme of contrast selection current iteration.
S86 fresh information prime matrixs pheromone；
S87 judges whether I is more than or equal to times, if it is not, returning to S83, next iteration is carried out, if so, then performing stopping
Iteration, optimal placement schemes bestVmToHost is exported, terminate program.
Wherein, step S84 includes in detail：
S91 initializes to the ant：Relevant parameter is transmitted to the ant by ant colony；
S92 calculates cpuMips matching degree matrix cpuMipsMatchDegreeMatrix, the matching degree matrix of internal memory
RamMatchDegreeMatrix, the matching degree matrix bwMatchDegreeMatrix of bandwidth and hard disk size matching degree square
Battle array sizeMatchDegreeMatrix；
S93 initialization information element transformation matrices pheromoneDeltaMatrix is 0, still untapped physical machine array
UnUsedHosts, the mapping array of virtual machine to physical machine；
S94 is passed to virtual machine numbering j and Pheromone Matrix pheromone, checks whether unUsedHosts arrays are sky,
If otherwise calculate the selected probability P of physical machine that numbering is i in unUsedHosts arraysiIf then toward unUsedHosts
All physical machine numberings are added in array and calculate the selected probability P of physical machine that numbering is i againi；
One physical machine i of S95 roulette selections；
S96 renewals physical machine i cpuMips normalization array, the normalization array of bandwidth, the normalization array of internal memory and
The normalization array of hard disk size, remove selected physical machine i from unUsedHosts arrays；
S97 checks whether that also virtual machine is unallocated, if then returning to S92, if it is not, then ant fresh information element change
Then matrix pheromoneDeltaMatrix stops the task of oneself.
For the effect of virtual machine batch dispositions method more of the invention and the cloudsim Greedy strategy carried, this hair
It is bright to have carried out Computer Simulation.
The quantity of physical machine is 5 in artificial tasks, and the performance parameter of each physical machine is as shown in Figure 3；The quantity of virtual machine
For 10, the performance parameter of each virtual machine is as shown in Figure 4；Cloud task quantity is 16, and cloud task length is as shown in Figure 5；Ant colony is joined
Number sets as shown in Figure 6.Using the present invention dispositions method simulation result as shown in Figure 7 and Figure 8, carried using cloudsim
Greedy strategy result as shown in Figure 9 and Figure 10.
From Fig. 7 and Fig. 8, using the present invention dispositions method when, mipsDifference standardizing standard differences are
0.096609175, ramDifference standardizing standard difference is that 0.39440534, bwDifference standardizing standard differences are
0.42309853, sizeDifference standardizing standard difference is 0.8940959, and total standardizing standard difference is 1.0692.
From Fig. 9 and Figure 10, during the Greedy strategy carried using cloudsim, mipsDifference standardizing standards
Difference is that 0.2228109, ramDifference standardizing standards difference is that 0.39440534, bwDifference standardizing standards are poor
It is 0.9358696 for 0.5784185, sizeDifference standardizing standards difference, total standardizing standard difference is
1.1896675。
From contrast above, using the dispositions method of the present invention than the Greedy strategy that cloudsim is carried in itself,
This 4 standardizing standard differences of mipsDifference, ramDifference, bwDifference, sizeDifference have
Different degrees of reduction, total standardizing standard difference reduce 10%, and the load balancing and resource utilization of system obtain substantially
Improve.
Claims (9)
1. a kind of virtual machine batch dispositions method based on cloudsim platforms, extended hybrid ant group algorithm and as virtual
The strategy of machine batch deployment, it is characterised in that the hybrid ant colony carries out the global renewal of pheromones using equation below：
Pheromone [j] [i]=pheromone [j] [i] * rho
Wherein rho is the pheromones residual factor,
It is Pheromone Matrixes of the virtual machine j to physical machine i；Wherein ants [k] .pheromoneDeltaMatrix represents kth only
The pheromones transformation matrices of ant, antNum are ant quantity；
The probability P that physical machine i is selected by virtual machine jiCalculated by below equation：
Wherein τi=pheromone [j] [i],
τk=pheromone [j] [k],Alpha and beta is arbitrary value,
MatchDegree=(cpuMipsMatchDegreeMatrix [i] [j]2+ramMatchDegreeMatrix[i][j]2
+bwMatchDegreeMatrix[i][j]2+sizeMatchDegreeMatrix[i][j]2)1/2。
A kind of 2. virtual machine batch dispositions method based on cloudsim platforms according to claim 1, it is characterised in that
Taboo list search is added in the hybrid ant colony, the taboo list search is specially：Distributed in ant for virtual machine
During physical machine, if virtual machine have selected physical machine i then remove from still untapped physical machine array unUsedHosts it is selected
The physical machine i selected, if unUsedHosts still has to be empty, virtual machine is to be allocated, and all physics is added toward unUsedHosts
Machine is numbered.
3. a kind of virtual machine batch dispositions method based on cloudsim platforms according to claim 1 or 2, its feature exist
In the addition physical machine performance parameter dynamic more new strategy in the hybrid ant colony.
A kind of 4. virtual machine batch dispositions method based on cloudsim platforms according to claim 3, it is characterised in that
Dynamically more new strategy is specially the physical machine performance parameter：If ant, which is virtual machine j, have selected physical machine i, subtract virtual
Machine j corresponding normalization array updates the cpuMips of physical machine normalization array, the normalization array of internal memory, bandwidth
Normalize the normalization array of array and hard disk size.
A kind of 5. virtual machine batch dispositions method based on cloudsim platforms according to claim 1, it is characterised in that
Every ant is all carried out more after the deployment scheme of oneself is established to pheromones transformation matrices pheromoneDeltaMatrix
Newly.
A kind of 6. virtual machine batch dispositions method based on cloudsim platforms according to claim 5, it is characterised in that
Described information element transformation matrices pheromoneDeltaMatrix renewal is entered as follows
WhereinIt is overall
With degree, wherein hostNum is physical machine quantity.
A kind of 7. virtual machine batch dispositions method based on cloudsim platforms according to claim 6, it is characterised in that
The hybrid ant colony comprises the following steps：
S81 is initialized：Relevant parameter is transmitted to the ant colony；
S82 produces the ant of respective numbers, according to initial information element initPheromone initialization information prime matrixs
Pheromone, primary iteration number I=0；
S83 I=I+1；
S84 antNum ants perform the task of oneself, find out corresponding deployment scheme；
After S85 antNum ants complete antNum deployment scheme of all deploying virtual machines acquisitions, compare and calculate each scheme
Overall matching degree cost, contrast selection current iteration optimal deployment scheme；
S86 fresh information prime matrixs pheromone；
S87 judges whether I is more than or equal to times, if it is not, returning to S83, carries out next iteration, is changed if so, then performing stopping
In generation, optimal placement schemes bestVmToHost is exported, terminate program, wherein times is iterative algebra.
A kind of 8. virtual machine batch dispositions method based on cloudsim platforms according to claim 7, it is characterised in that
In the step S84 ant perform the task of oneself find out corresponding to deployment scheme comprise the following steps：
S91 initializes to the ant：Relevant parameter is transmitted to the ant by ant colony；
S92 calculates cpuMips matching degree matrix cpuMipsMatchDegreeMatrix, the matching degree matrix of internal memory
RamMatchDegreeMatrix, the matching degree matrix bwMatchDegreeMatrix of bandwidth and hard disk size matching degree square
Battle array sizeMatchDegreeMatrix；
S93 initialization information element transformation matrices pheromoneDeltaMatrix is 0, still untapped physical machine array
UnUsedHosts, the mapping array of virtual machine to physical machine；
S94 is passed to virtual machine numbering j and Pheromone Matrix pheromone, checks whether unUsedHosts arrays are sky, if not
Then calculate the selected probability P of physical machine that numbering is i in unUsedHosts arraysiIf then toward unUsedHosts arrays
All physical machine numberings of middle addition calculate the selected probability P of physical machine that numbering is i againi；
One physical machine i of S95 roulette selections；
S96 renewal physical machines i cpuMips normalization array, the normalization array of bandwidth, the normalization array of internal memory and hard disk
The normalization array of size, remove selected physical machine i from unUsedHosts arrays；
S97 checks whether that also virtual machine is unallocated, if then returning to S92, if it is not, the then ant fresh information element transformation matrices
Then pheromoneDeltaMatrix stops the task of oneself.
9. a kind of virtual machine batch dispositions method based on cloudsim platforms according to claim 7 or 8, its feature exist
In methods described includes：
CreateVmsInDatacenter functions in cloudsim datacenterbrokerAco, which check whether there is, not to be created
The virtual machine set built, if so, then sending the message for creating virtual machine to datacenterAco, transmission to be created virtual
Machine set；
ProcessVmCreate functions in datacenterAco receive the virtual machine set sent, call virtual machine point
With the allocateHostForVmList functions in class VmAllocationPolicyAco,
In allocateHostForVmList functions physical machine is distributed according to the hybrid ant colony for virtual machine set.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410767818.6A CN104461739B (en) | 2014-12-15 | 2014-12-15 | A kind of virtual machine batch dispositions method based on cloudsim platforms |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410767818.6A CN104461739B (en) | 2014-12-15 | 2014-12-15 | A kind of virtual machine batch dispositions method based on cloudsim platforms |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104461739A CN104461739A (en) | 2015-03-25 |
| CN104461739B true CN104461739B (en) | 2017-12-05 |
Family
ID=52907837
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410767818.6A Active CN104461739B (en) | 2014-12-15 | 2014-12-15 | A kind of virtual machine batch dispositions method based on cloudsim platforms |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104461739B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104572251B (en) * | 2015-01-30 | 2018-01-26 | 中国联合网络通信集团有限公司 | Virtual machine deployment method and device |
| CN104915557B (en) * | 2015-06-04 | 2017-09-01 | 中山大学 | A kind of cloud method for allocating tasks based on Bi-objective ant group algorithm |
| CN108108224B (en) * | 2017-12-05 | 2019-10-01 | 西南交通大学 | Virtual machine placement method in cloud data center based on ant colony optimization algorithm |
| CN109240805B (en) * | 2018-09-28 | 2020-10-20 | 北京邮电大学 | Virtual machine allocation method and device |
| CN110851230B (en) * | 2019-06-26 | 2023-08-15 | 湘潭大学 | Virtual machine placement method based on reinforcement learning in cloud computing |
| CN111240804A (en) * | 2020-01-12 | 2020-06-05 | 桂林理工大学 | Cloud data center cost optimization method based on resource management |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103067524A (en) * | 2013-01-18 | 2013-04-24 | 浪潮电子信息产业股份有限公司 | Ant colony optimization computing resource distribution method based on cloud computing environment |
| CN103488539A (en) * | 2013-09-23 | 2014-01-01 | 北京交通大学 | Data center energy saving method based on central processing unit (CPU) dynamic frequency modulation technology |
| CN103970609A (en) * | 2014-04-24 | 2014-08-06 | 南京信息工程大学 | Cloud data center task scheduling method based on improved ant colony algorithm |
| CN104063261A (en) * | 2014-04-01 | 2014-09-24 | 杭州电子科技大学 | Multi-objective optimization virtual machine placing method under cloud environment |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8296711B2 (en) * | 2010-09-30 | 2012-10-23 | Synopsys, Inc. | Method and apparatus for using entropy in ant colony optimization circuit design from high level synthesis |
-
2014
- 2014-12-15 CN CN201410767818.6A patent/CN104461739B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103067524A (en) * | 2013-01-18 | 2013-04-24 | 浪潮电子信息产业股份有限公司 | Ant colony optimization computing resource distribution method based on cloud computing environment |
| CN103488539A (en) * | 2013-09-23 | 2014-01-01 | 北京交通大学 | Data center energy saving method based on central processing unit (CPU) dynamic frequency modulation technology |
| CN104063261A (en) * | 2014-04-01 | 2014-09-24 | 杭州电子科技大学 | Multi-objective optimization virtual machine placing method under cloud environment |
| CN103970609A (en) * | 2014-04-24 | 2014-08-06 | 南京信息工程大学 | Cloud data center task scheduling method based on improved ant colony algorithm |
Non-Patent Citations (1)
| Title |
|---|
| 基于多目标蚁群改进算法的虚拟机放置策略;张莉莉 等;《中国科技论文在线》;20141204;正文第95-110行、第168-190行、第230-233行 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104461739A (en) | 2015-03-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104461739B (en) | A kind of virtual machine batch dispositions method based on cloudsim platforms | |
| Zheng et al. | Virtual machine consolidated placement based on multi-objective biogeography-based optimization | |
| WO2019196127A1 (en) | Cloud computing task allocation method and apparatus, device, and storage medium | |
| CN107491341B (en) | A kind of virtual machine distribution method based on particle group optimizing | |
| US9116181B2 (en) | Method, apparatus, and system for virtual cluster integration | |
| CN105975340A (en) | Deployment algorithm of application distribution of virtual machine | |
| CN104881322B (en) | A kind of cluster resource dispatching method and device based on vanning model | |
| CN107346264A (en) | A kind of method, apparatus and server apparatus of virtual machine load balance scheduling | |
| CN112073452B (en) | Mobile edge computing task allocation method with effective energy and limited resources | |
| CN111064633A (en) | Cloud-edge cooperative power information communication equipment automated testing resource allocation method | |
| CN110321198B (en) | Container cloud platform computing resource and network resource cooperative scheduling method and system | |
| WO2013165354A1 (en) | Determining virtual machine placement | |
| CN108427602B (en) | Distributed computing task cooperative scheduling method and device | |
| CN115454612A (en) | Cloud platform task scheduling method based on dimension learning strategy and wolf optimization | |
| CN106412124A (en) | Task allocation system and task allocation method for parallel ordering cloud service platform | |
| CN102420850B (en) | Resource scheduling method and system thereof | |
| CN104572251A (en) | Virtual machine deploying method and device | |
| CN109976879B (en) | Cloud computing virtual machine placement method based on resource usage curve complementation | |
| CN116366658B (en) | Cloud computing load balancing method and system | |
| Zhuang et al. | Impact of instance seeking strategies on resource allocation in cloud data centers | |
| Jayasena et al. | Multi-objective energy efficient resource allocation using virus colony search (VCS) algorithm | |
| Tang | Load balancing optimization in cloud computing based on task scheduling | |
| Zhang et al. | Repeatable multi-dimensional virtual network embedding in cloud service platform | |
| US11768760B2 (en) | Testing of a resource manager of an application management system | |
| Su et al. | A power-aware virtual machine mapper using firefly optimization |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |