CN106227600B - A kind of multidimensional virtual resource allocation method based on Energy-aware - Google Patents
A kind of multidimensional virtual resource allocation method based on Energy-aware Download PDFInfo
- Publication number
- CN106227600B CN106227600B CN201610592975.7A CN201610592975A CN106227600B CN 106227600 B CN106227600 B CN 106227600B CN 201610592975 A CN201610592975 A CN 201610592975A CN 106227600 B CN106227600 B CN 106227600B
- Authority
- CN
- China
- Prior art keywords
- physical machine
- resource
- machine
- physical
- virtual 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 18
- 238000013508 migration Methods 0.000 claims abstract description 28
- 230000005012 migration Effects 0.000 claims abstract description 27
- 238000005265 energy consumption Methods 0.000 claims abstract description 24
- 230000008447 perception Effects 0.000 claims description 8
- 238000005259 measurement Methods 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 2
- 238000010187 selection method Methods 0.000 claims description 2
- 238000013468 resource allocation Methods 0.000 abstract description 7
- 238000007726 management method Methods 0.000 abstract description 4
- 238000004422 calculation algorithm Methods 0.000 description 16
- 238000010586 diagram Methods 0.000 description 5
- 238000002474 experimental method Methods 0.000 description 3
- 239000002699 waste material Substances 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- 241000136406 Comones Species 0.000 description 1
- 238000001816 cooling Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000004134 energy conservation Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000009705 shock consolidation Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
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
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5061—Partitioning or combining of resources
- G06F9/5077—Logical partitioning of resources; Management or configuration of virtualized 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
- G06F9/48—Program initiating; Program switching, e.g. by interrupt
- G06F9/4806—Task transfer initiation or dispatching
- G06F9/4843—Task transfer initiation or dispatching by program, e.g. task dispatcher, supervisor, operating system
- G06F9/485—Task life-cycle, e.g. stopping, restarting, resuming execution
- G06F9/4856—Task life-cycle, e.g. stopping, restarting, resuming execution resumption being on a different machine, e.g. task migration, virtual machine migration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2209/00—Indexing scheme relating to G06F9/00
- G06F2209/50—Indexing scheme relating to G06F9/50
- G06F2209/504—Resource capping
-
- 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)
- Debugging And Monitoring (AREA)
- Power Sources (AREA)
Abstract
The multidimensional virtual resource allocation method based on Energy-aware that the invention discloses a kind of ties up resource status model by establishing D, has introduced physical machine range index;Comprehensively consider physical machine energy consumption and each dimension resource behaviour in service further provides energy resource state index (PAR);The service condition that physical machine respectively ties up resource is substantially envisaged on the basis of Energy-aware, improves resource utilization;According to the index proposed, to optimize to virtual machine (vm) migration and virtual machine placement process, reduce the wasting of resources of data center, it improves resource utilization, energy consumption is reduced simultaneously, the dynamic resource allocation management being more suitable in cloud computing, and provide better service quality.
Description
Technical Field
The invention belongs to the field of cloud computing virtual resource allocation, and particularly relates to a multi-dimensional virtual resource allocation method based on energy perception.
Background
With the rapid development of cloud computing, the scale of a data center is continuously increased, and the problem of energy consumption of the data center becomes a considerable problem. Currently, virtualization technology has become an integral part of resource allocation schemes. The virtualization technology realizes that a plurality of users share one hardware device by virtualizing computer hardware and abstracting software and hardware resources into a plurality of virtual resources, allows a computer system to allocate resources and dynamically migrate a workload according to user demands, greatly improves the utilization rate of physical resources, and saves the cost of a data center to a certain extent. Therefore, research on resource management of the cloud computing data center, particularly management of virtualized resources, has great practical significance for effectively reducing energy consumption of the data center and constructing a green data center.
In a cloud data center, application requests of users are various, and requirements for various resource types are also greatly different (for example, the size of a CPU, a memory, the size of a disk, bandwidth and the like). The existing energy-saving allocation mode does not consider the heterogeneity of the workload, and lacks of research on effective allocation of multidimensional resources of a single physical machine, so that a resource waste phenomenon is caused, namely one resource is used up, and other resources are left in large quantity. These problems directly affect the efficient and intensive utilization of cloud data center resources, resulting in a great deal of waste and loss of cloud resources. An efficient resource allocation mechanism can take full advantage of the resources owned to serve more customers, thereby reducing the cost overhead (computing, network, storage, and infrastructure cooling, excess energy provisioning) of purchasing, operating, and maintaining equipment. Therefore, how to balance the load among the physical machines through a proper resource scheduling algorithm to improve the resource utilization rate and the overall performance of the cloud data center is a key problem in the field of cloud computing at present.
Disclosure of Invention
The invention provides a multidimensional virtual resource allocation method based on energy perception, and aims to solve the problems that in the prior art, energy consumption and performance are balanced, and physical machine resources cannot be fully utilized due to the diversity of user requests in a cloud data center.
The technical scheme adopted by the invention is as follows:
a multidimensional virtual resource allocation method based on energy perception comprises the following steps:
step 1: constructing a D-dimensional resource state model of the physical machine, and setting a physical machine resource overload threshold;
the D-dimensional resource state model comprises the utilization rate of various resources of each physical machine, the physical machine resource state saturation distance and the no-load distance;
step 2: judging whether the physical machine is overloaded or not, if so, entering a step 3, and otherwise, repeating the step 2;
and step 3: putting the virtual machine with the minimum resource utilization rate on the overloaded physical machine into a virtual machine migration list;
and 4, step 4: sequentially obtaining the size of resources required by the virtual machine to be migrated from the virtual machine migration list, traversing all the physical machines, selecting the physical machine which meets the resources required by the virtual machine to be migrated, taking the physical machine with the minimum physical machine comprehensive measurement index PAR selected as the target physical machine of the current virtual machine to be migrated, completing virtual machine migration, and returning to the step 2;
the physical machine comprehensive measurement index PAR is obtained by calculation according to the following formula:
wherein,representing physical machines PMjReceiving resource state saturation distance, PM, after virtual machine VM migrationjThe _ Power represents the energy consumption increased by the physical machine after the virtual machine is placed on the physical machine; a and b are respectively a resource state saturation weight and an energy consumption weight, which are positive numbers, and a + b is 1;
PMj_Power=Pfixed+(Pfull-Pfixed)*(ΔRUCPU)
wherein, Delta RUCPURepresenting the variable quantity of the CPU resource utilization rate after the virtual machine is placed;
the resource state saturation distance of the jth physical machine is
Resource state no-load distance of jth physical machine
Wherein,representing physical machines PMjThe amount of usage of the above d-th class of resources,representing physical machines PMjThe total capacity of the above class d resources,representing physical machines PMjResidual capacity of resource of last d-th class, 0<j≤M,0<D is less than or equal to D, M represents the number of physical machines, and D represents the number of resource classes on the physical machines;
Vdrepresenting the d-th type resource capacity required by the virtual machine;
Pfixedrepresents the energy consumption, P, required by a physical machine to maintain normal operationfullRepresenting the energy consumption, RU, required by a physical machine when it is operating at full capacityCPUIndicating the utilization of the CPU.
If the migration of the virtual machine is completed, searching a physical machine with the lowest overall resource utilization rate, migrating all the virtual machines on the physical machine according to the target physical machine selection method in the step 4, if the physical machine is overloaded after the migration, cancelling the migration of the virtual machine, and otherwise, setting the physical machine to be in a sleep mode;
total resource utilization of jth physical machine is RUj:RUj(PMj_RU1,PMj_RU2,...,PMj_RUd);
The lowest utilization rate of the overall resources of the physical machine is calculated and obtained according to the minimum idle distance of the resource state of the physical machine.
The virtual machine with the minimum resource utilization rate in the step 3 means that the total resource utilization rate of the virtual machine on the overloaded physical machine is minimum, and the total resource utilization rate of the virtual machine on the physical machine is minimumCalculated according to the following formula:
wherein,indicating the total capacity of the class d resource on the physical machine in which the overload occurred. Each physical machine comprises D different types of resources, when any one-dimensional resource is used up, the fact that a new virtual machine cannot be placed at the physical machine means that a new physical machine must be started to runAnd (4) a virtual machine. In a cloud data center, the energy consumption of a physical machine is mainly derived from a CPU, a memory, a disk storage, and a network interface. While the CPU consumes most of the energy compared to other system resources, and the physical machine in the idle state consumes 70% of the physical machine in the full load state.
Advantageous effects
The invention provides a multidimensional virtual resource allocation method based on energy perception, which introduces a physical machine distance index by establishing a D-dimensional resource state model; the energy resource state index (PAR) is further provided by comprehensively considering the physical energy consumption and the use condition of each dimension of resource; the use condition of each dimension resource of the physical machine is fully considered on the basis of energy perception, and the resource utilization rate is improved; according to the provided indexes, the virtual machine migration and virtual machine placement processes are optimized, resource waste of a data center is reduced, the resource utilization rate is improved, energy consumption is reduced, the method is more suitable for dynamic resource allocation management in cloud computing, and better service quality is provided.
Drawings
FIG. 1 is a flow chart of the algorithm of the present invention;
fig. 2 is a D-dimensional resource state diagram of the present invention (D-2);
FIG. 3 is a schematic diagram of the physical machine distance indicator of the present invention;
FIG. 4 is a schematic diagram illustrating a comparison of total energy consumption of data center physical machines obtained by applying the method and other algorithms of the present invention;
FIG. 5 is a diagram illustrating comparison of SLA breach rates during system operation obtained by applying the method and other algorithms of the present invention;
fig. 6 is a schematic diagram showing comparison of migration times when the method of the present invention is applied to virtual machine migration with other algorithms.
Detailed Description
The invention will be further described with reference to the following figures and examples.
A multidimensional virtual resource allocation method based on energy perception, as shown in fig. 1, specifically includes the following steps:
step 1: constructing a D-dimensional resource state model of the physical machine, and setting a physical machine resource overload threshold;
the D-dimensional resource state model comprises the utilization rate of various resources of each physical machine, the physical machine resource state saturation distance and the no-load distance;
in the D-dimensional resource state model, the resource state of each physical machine corresponds to a point in the model, namely: point RUj(PMj_RU1,PMj_RU2,...,PMj_RUd) Representing physical machines PMjThe state of (1). Hereinafter, D ═ 2(CPU, memory) will be specifically described. As shown in fig. 2, each coordinate axis represents a one-dimensional resource (the vertical axis is CPU, and the horizontal axis is memory), and the readings of the coordinate axes represent the resource utilization rate of the physical machine.
The solid point represents the resource usage state of the current physical machine, namely: RU (RU)j. Point S (1, 1) is a saturation point, indicating that all resources are used up; point O (0, 0) represents the physical machine in an idle state.
Physical machine resource state saturation distance:the index represents the physical machine PM in the resource state modeljDistance from the saturation point (shown in dashed lines in fig. 3). WhereinRepresenting the remaining capacity of the d-dimensional resource of the physical machine.
Physical machine resource state idle distance:the index represents the physical machine PM in the resource state modeljDistance from the origin (shown in solid lines in fig. 3).
Step 2: judging whether the physical machine is overloaded or not, if so, entering a step 3, and otherwise, repeating the step 2;
and step 3: when the physical machine is found to be overloaded (the CPU resource utilization rate exceeds a threshold value), the virtual machine manager calls a virtual machine selection algorithm, the virtual machine with the minimum overall resource utilization rate on the physical machine is placed into a virtual machine migration list, and the next step is carried out;
and 4, step 4: and when the virtual machine migration list is not empty, the virtual machine manager calls a virtual machine placement algorithm.
Firstly, a virtual machine manager traverses the whole physical machine list, judges whether the physical machine has enough resources to run the virtual machine to be migrated, and calculates the PAR index of the physical machine if the physical machine has enough resources to run the virtual machine to be migrated; if not, continuing to judge the next physical machine. After searching all the physical machines, selecting the physical machine with the minimum PAR, and placing the virtual machine in the virtual machine migration list on the physical machine;
and 5: the virtual machine manager searches a physical machine with the minimum overall resource utilization rate, tries to allocate all the virtual machines on the physical machine to other physical machines, and enables the physical machine to be in a sleep mode if allocation is successful; if the physical machine is overloaded in the distribution process, canceling the distribution and allowing the physical machine to continue to operate;
step 6: returning to the step 2, the virtual machine manager continues to monitor the load condition of the physical machine.
The experimental environment is as follows:
the present invention uses cloudsim3.0 to implement and evaluate the proposed resource allocation strategy. A data center is constructed in a simulation mode and comprises 800 heterogeneous physical machines, namely HP ProLiant ML110G4servers and HP ProLiant ML110G5servers, and specific parameter configurations are shown in Table 1.
Table 1: physical machine type
The types of virtual machines, corresponding to the instance types of Amazon EC2, are all single cores. Respectively as follows: high-CPUmedium instance (2500MIPS,0.85GB), extra large instance (2000MIPS,3.75GB), small instance (1000MIPS,1.7GB), and micro instance (500MIPS,613 MB). In document [1], a real dataset was collected from the CoMon project from Planet Lab, and in this simulation, 6 were randomly selected, as shown in Table 2:
table 2: data set parameters (CPU utilization)
Data set | Number of virtual machines | Mean(%) | St.dev.(%) | Quartile 1(%) | Median(%) | Quartile 3(%) |
1 | 1052 | 12.31 | 17.09 | 2 | 6 | 15 |
2 | 898 | 12.44 | 16.83 | 2 | 5 | 13 |
3 | 1061 | 10.70 | 15.57 | 2 | 4 | 13 |
4 | 1054 | 11.54 | 15.15 | 2 | 6 | 16 |
5 | 1078 | 10.56 | 14.14 | 2 | 6 | 14 |
6 | 1463 | 12.39 | 16.55 | 2 | 6 | 17 |
The above are data sets used in experiments, all of which are the settings in reference [1 ];
the experimental evaluation indexes are three: energy consumption (KWh); SLA breach rate (%); number of virtual machine migrations.
The first indicator is the total energy consumption of the data center. The second is the rate of SLA (service level agreement) violations, which indicates the frequency of SLA violations during system operation. In this experiment, it is considered that the MIPS required when the system cannot allocate the VM is the SLA breach. The third indicator is the number of virtual machine migrations.
The algorithm for comparison is PABFD-MMT proposed in the document [1], PABFD is a virtual machine placement algorithm, MMT is a virtual machine migration algorithm, and the algorithm proposed by the invention is MRBEA.
In the experiment, the threshold was set to 0.9.
The following are graphs of experimental results corresponding to three indices:
fig. 4 shows the total energy consumption of the physical machines of the data center, and it can be seen that the algorithm proposed by the present invention has less energy consumption. This also illustrates that when resource allocation is performed, only the energy consumption of a single physical machine is considered, and the energy consumption of the whole data center cannot be minimized. The use condition and the energy consumption condition of various resources of the physical machine are required to be integrated to select the most appropriate distribution scheme.
FIG. 5 shows the SLA breach rate during system operation. The algorithm provided by the invention effectively reduces the SLA violation rate, greatly reduces the cost paid by the cloud provider due to SLA violation, and provides higher performance guarantee for the user.
Fig. 6 compares the number of migration times of the algorithm. The MRBEA provided by the invention completes cloud tasks with fewer migration times. Migration is a cost, the corresponding cost is higher, and the more migration times, the more SLA violations occur. The MRBEA algorithm comprehensively considers the utilization rate of resources of all dimensions of the virtual machine and the physical machine on the basis of energy conservation, thereby reducing unnecessary migration and improving the efficiency of resource allocation.
Reference documents:
[1]Beloglazov A,Buyya R.Optimal online deterministic algorithms andadaptive heuristics for energy and performance efficient dynamicconsolidation of virtual machines in Cloud data centers[J].Concurrency&Computation Practice&Experience,2012,24(13):1397–1420。
Claims (3)
1. A multidimensional virtual resource allocation method based on energy perception is characterized by comprising the following steps:
step 1: constructing a D-dimensional resource state model of the physical machine, and setting a physical machine resource overload threshold;
the D-dimensional resource state model comprises the utilization rate of various resources of each physical machine, the physical machine resource state saturation distance and the no-load distance;
step 2: judging whether the physical machine is overloaded or not, if so, entering a step 3, and otherwise, repeating the step 2;
and step 3: putting the virtual machine with the minimum resource utilization rate on the overloaded physical machine into a virtual machine migration list;
and 4, step 4: sequentially obtaining the size of resources required by the virtual machine to be migrated from the virtual machine migration list, traversing all the physical machines, selecting the physical machine which meets the resources required by the virtual machine to be migrated, taking the physical machine with the minimum physical machine comprehensive measurement index PAR selected as the target physical machine of the current virtual machine to be migrated, completing virtual machine migration, and returning to the step 2;
the physical machine comprehensive measurement index PAR is obtained by calculation according to the following formula:
wherein,representing physical machines PMjReceiving the resource state saturation distance after the virtual machine VM is migrated,
PMjthe _ Power represents the energy consumption increased by the physical machine after the virtual machine is placed on the physical machine; a and b are respectively a resource state saturation weight and an energy consumption weight, which are positive numbers, and a + b is 1;
PMj_Power=Pfixed+(Pfull-Pfixed)*(ΔRUCPU)
wherein, Delta RUCPURepresenting the variable quantity of the CPU resource utilization rate after the virtual machine is placed;
the resource state saturation distance of the jth physical machine is
Resource state no-load distance of jth physical machine
Wherein,representing physical machines PMjThe amount of usage of the above d-th class of resources,representing physical machines PMjThe total capacity of the above class d resources,representing physical machines PMjResidual capacity of resource of last d-th class, 0<j≤M,0<D is less than or equal to D, M represents the number of physical machines, and D represents the number of resource classes on the physical machines;
Vdrepresenting the d-th type resource capacity required by the virtual machine;
Pfixedrepresents the energy consumption, P, required by a physical machine to maintain normal operationfullRepresenting the energy consumption, RU, required by a physical machine when it is operating at full capacityCPUIndicating the utilization of the CPU.
2. The method according to claim 1, wherein if the migration of the virtual machine is completed, a physical machine with the lowest overall resource utilization rate is searched, all the virtual machines on the physical machine are migrated according to the target physical machine selection method in step 4, if the physical machine is overloaded after the migration, the virtual machine migration is cancelled, otherwise, the physical machine is set to a sleep mode;
total resource utilization of jth physical machine is RUj:RUj(PMj_RU1,PMj_RU2,...,PMj_RUd);
The lowest utilization rate of the overall resources of the physical machine is calculated and obtained according to the minimum idle distance of the resource state of the physical machine.
3. The method according to claim 1 or 2, wherein the virtual machine with the least resource utilization in step 3 means that the total resource utilization of the virtual machine on the physical machine in which the overload occurs is the least, and the total resource utilization of the virtual machine on the physical machine is the leastCalculated according to the following formula:
wherein,indicating the total capacity of the class d resource on the physical machine in which the overload occurred.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610592975.7A CN106227600B (en) | 2016-07-25 | 2016-07-25 | A kind of multidimensional virtual resource allocation method based on Energy-aware |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610592975.7A CN106227600B (en) | 2016-07-25 | 2016-07-25 | A kind of multidimensional virtual resource allocation method based on Energy-aware |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106227600A CN106227600A (en) | 2016-12-14 |
CN106227600B true CN106227600B (en) | 2019-05-17 |
Family
ID=57534099
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610592975.7A Active CN106227600B (en) | 2016-07-25 | 2016-07-25 | A kind of multidimensional virtual resource allocation method based on Energy-aware |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106227600B (en) |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109144664B (en) * | 2018-07-26 | 2021-09-14 | 西安电子科技大学 | Dynamic migration method of virtual machine based on user service quality demand difference |
CN109656796B (en) * | 2018-12-14 | 2022-05-10 | 武汉斗鱼鱼乐网络科技有限公司 | Task selection method and device |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102508714A (en) * | 2011-11-03 | 2012-06-20 | 南京邮电大学 | Green-computer-based virtual machine scheduling method for cloud computing |
CN102546379A (en) * | 2010-12-27 | 2012-07-04 | 中国移动通信集团公司 | Virtualized resource scheduling method and system |
CN103778020A (en) * | 2014-02-08 | 2014-05-07 | 中国联合网络通信集团有限公司 | Virtual machine placing method and device |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8949431B2 (en) * | 2011-08-24 | 2015-02-03 | Radware, Ltd. | Method for live migration of virtual machines |
-
2016
- 2016-07-25 CN CN201610592975.7A patent/CN106227600B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102546379A (en) * | 2010-12-27 | 2012-07-04 | 中国移动通信集团公司 | Virtualized resource scheduling method and system |
CN102508714A (en) * | 2011-11-03 | 2012-06-20 | 南京邮电大学 | Green-computer-based virtual machine scheduling method for cloud computing |
CN103778020A (en) * | 2014-02-08 | 2014-05-07 | 中国联合网络通信集团有限公司 | Virtual machine placing method and device |
Non-Patent Citations (1)
Title |
---|
基于利用率和负载均衡的云资源调度算法研究;张海洲;《中国优秀硕士学位论文全文数据库 信息科技辑》;20140315(第3期);第27-32页 |
Also Published As
Publication number | Publication date |
---|---|
CN106227600A (en) | 2016-12-14 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108182105B (en) | Local dynamic migration method and control system based on Docker container technology | |
Mi et al. | Online self-reconfiguration with performance guarantee for energy-efficient large-scale cloud computing data centers | |
US9218213B2 (en) | Dynamic placement of heterogeneous workloads | |
CN102236582B (en) | Method for balanced distribution of virtualized cluster load in a plurality of physical machines | |
Li | An adaptive overload threshold selection process using Markov decision processes of virtual machine in cloud data center | |
Wang et al. | A prediction based energy conserving resources allocation scheme for cloud computing | |
Cao et al. | Energy efficient allocation of virtual machines in cloud computing environments based on demand forecast | |
Guo et al. | A container scheduling strategy based on neighborhood division in micro service | |
CN109976879B (en) | Cloud computing virtual machine placement method based on resource usage curve complementation | |
Song et al. | Server consolidation energy-saving algorithm based on resource reservation and resource allocation strategy | |
Kaaouache et al. | An energy-efficient VM placement method for cloud data centers using a hybrid genetic algorithm | |
CN106227600B (en) | A kind of multidimensional virtual resource allocation method based on Energy-aware | |
CN114741160A (en) | Dynamic virtual machine integration method and system based on balanced energy consumption and service quality | |
Ajayi et al. | Multi-Class load balancing scheme for QoS and energy conservation in cloud computing | |
Ma et al. | SE-PSO: resource scheduling strategy for multimedia cloud platform based on security enhanced virtual migration | |
Jayasena et al. | Multi-objective energy efficient resource allocation using virus colony search (VCS) algorithm | |
Gao et al. | Energy-aware load balancing in heterogeneous cloud data centers | |
Wang et al. | Effects of correlation-based VM allocation criteria to cloud data centers | |
CN110069319A (en) | A kind of multiple target dispatching method of virtual machine and system towards cloudlet resource management | |
Singhi et al. | A load balancing approach for increasing the resource utilization by minimizing the number of active servers | |
CN115269110A (en) | Resource allocation method and device for cloud computing platform, electronic equipment and storage medium | |
Wei et al. | Towards multi-resource physical machine provisioning for IaaS clouds | |
Karthikeyan et al. | Novel heuristics energy efficiency approach for cloud Data Center | |
Zhang et al. | Speeding up vm startup by cooperative vm image caching | |
Li et al. | SLA‐Aware and Energy‐Efficient VM Consolidation in Cloud Data Centers Using Host State 3rd‐Order Markov Chain Model |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | 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 |