CN108897600A - A kind of virtual machine placement method under cloud computing environment - Google Patents
A kind of virtual machine placement method under cloud computing environment Download PDFInfo
- Publication number
- CN108897600A CN108897600A CN201810614926.8A CN201810614926A CN108897600A CN 108897600 A CN108897600 A CN 108897600A CN 201810614926 A CN201810614926 A CN 201810614926A CN 108897600 A CN108897600 A CN 108897600A
- Authority
- CN
- China
- Prior art keywords
- function
- virtual machine
- subordinating degree
- energy consumption
- fitness
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/44—Arrangements for executing specific programs
- G06F9/455—Emulation; Interpretation; Software simulation, e.g. virtualisation or emulation of application or operating system execution engines
- G06F9/45533—Hypervisors; Virtual machine monitors
- G06F9/45558—Hypervisor-specific management and integration aspects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/08—Configuration management of networks or network elements
- H04L41/0803—Configuration setting
- H04L41/0823—Configuration setting characterised by the purposes of a change of settings, e.g. optimising configuration for enhancing reliability
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/08—Configuration management of networks or network elements
- H04L41/0803—Configuration setting
- H04L41/0823—Configuration setting characterised by the purposes of a change of settings, e.g. optimising configuration for enhancing reliability
- H04L41/0833—Configuration setting characterised by the purposes of a change of settings, e.g. optimising configuration for enhancing reliability for reduction of network energy consumption
-
- 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
-
- 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
- G06F2009/45595—Network integration; Enabling network access in virtual machine instances
-
- 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)
- Physics & Mathematics (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Biology (AREA)
- Artificial Intelligence (AREA)
- Genetics & Genomics (AREA)
- Physiology (AREA)
- Biomedical Technology (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention provides the virtual machine placement method under a kind of cloud computing environment, the problem of solving virtual machine under cloud environment using genetic algorithm, when searching for the incidence relation of virtual machine and physical machine, guiding search direction, avoids basic genetic algorithmic from falling into local optimum with having Objective；It is scanned for using heuritic approach based on genetic algorithm to reduce physical resource energy consumption, optimization energy efficiency, and optimizes virtual machine position with adaptive algorithm to minimize maximum link utilization.The incidence relation of virtual machine VM- physical machine PM is described using membership function under cloud computing environment, when closing optimal solution using Genetic algorithm searching virtual machine association physics unit, when to the designs of two modules of membership function collection and mutation operator, the relationship that physical machine is associated with using virtual machine is limited with initialization to the building of subordinating degree function, the physical machine that virtual machine is possible to place is constrained, so that basic genetic algorithmic search be avoided to fall into local optimum and accelerate algorithm the convergence speed.
Description
Technical field
The present invention relates to the virtual machine placement methods under field of cloud calculation more particularly to a kind of cloud computing environment.
Background technique
In recent years, demand of the cloud computing to computing capability accelerates the rapid development of data center, and bring is several therewith
The huge energy consumption problem generated according to center.It is estimated according to Amazon, the energy consumption cost of data center accounts for entire data center's budget gold
The 42% of volume.Under cloud computing environment the characteristics of user task randomness, so that the task load of data center's physical server is
Dynamic change, when server is in idle condition, power reaches the 50%~60% of peak power, therefore cloud service mentions
For quotient (CSP, Cloud Service Provider) while guaranteeing service quality (QoS, Quility of Service),
How to carry out energy optimization be one it is real study a question, energy optimization is that a research of the cloud data center of virtualization is hot
Point.In addition, Internet resources are the scarce resources of data center, the performance of application is directly influenced；There is research and utilization virtual machine to put
It sets to improve the utilization rate of the network equipment, in conjunction with the optimization of routing, reduces the number of the network equipment, network energy effect is optimized with this
Rate.But whether optimize physical server energy efficiency, or the energy efficiency of the optimization network equipment, it can all bring resource
Excessive polymerization.The especially aggregation of network flow will cause link hot spot, bring network congestion problem.
Currently, placement problem one kind research about virtual machine is mainly in sides such as energy saving, fault tolerance, QoS management
Face also has focused largely on the energy consumption for reducing physical machine.Due to not accounting for the optimization of network performance, network topology and current net
The influence of network flow will directly influence the performance of application.Another kind of led to merely for the purpose of the energy consumption for reducing the network equipment
The optimization of virtual machine migration technology and network routing is crossed to reduce data center network energy consumption, to save data center's electricity
Source loss；Or by optimization virtual machine position and flow routing, dormant network equipment is closed as much as possible to save data
Central site network energy consumption.Both schemes only assume the resource requirement for meeting physical server, optimize data center network resource,
Physical server energy consumption is not optimized.
About the placement of virtual machine, the simple energy consumption for only considering physical server and as in cloud data under cloud computing environment
The optimization of one of the Internet resources of heart scarce resource will all directly affect the performance of application.Therefore, cloud service is provided
For person, virtual machine placement schemes how are designed to improve server resource utilization rate and can improve network performance be one important
Problem.
Summary of the invention
In order to overcome the deficiencies in the prior art described above, the present invention provides the virtual machine placement side under a kind of cloud computing environment
Method, method include：
Determine objective function f (t) and fitness function fitness (t)；
The process that virtual machine is placed in physical machine is carried out based on genetic algorithm；
Genetic algorithm includes：Initialization population；
Evaluation is carried out to individual according to fitness function and selects individual choice operation mode；
Crossover operation mode；
Mutation operation mode；
According to genetic algorithmic steps until the number of iterations terminates.
Preferably, step determines that objective function f (t) further includes：
Energy consumption E based on cloud data centerDC, including physical machine energy consumption Epm, network equipment energy consumption EnetAnd other energy consumptions
Eother, i.e. EDC=Epm+Enet+Eother；
Physical machine energy consumption EpmIncluding CPU energy consumption, energy consumption of memory, storage energy consumption and network interface energy consumption, network equipment energy consumption
EnetIncluding interchanger energy consumption, router energy consumption, link energy consumption；Other energy consumptions EotherIt is assisted including refrigeration air-conditioner energy consumption, illumination etc.
Equipment energy consumption；
Objective function is to minimize physical machine energy consumption, its calculation formula is：
F (t)=Epm+Enet+Eother。
Preferably, step determines that fitness function fitness (t) further includes：
According to the expression formula of objective function f, conversion is used in genetic algorithm evaluate the fitness function of membership function quality,
The expression formula of fitness function for obtaining evaluation membership function collection is：
In formula：T indicates the number of iterations；Fitness (t) indicates in each iterative process that the evaluation function of membership function is
Fitness function.
Preferably, step initialization population further includes：
A membership function relationship is constructed to indicate the virtual machine placed in physical machine.
Preferably, step carries out evaluation to individual according to fitness function and selects individual choice operation mode and further include：
Individual choice operation mode uses optimum maintaining strategy combination roulette wheel selection, according to the public affairs of fitness function
Formula calculates the fitness value size of each subordinating degree function in current population, and it is highest then to find out fitness from current population
The subordinating degree function X1 and minimum subordinating degree function Y1 of fitness, and remaining subordinating degree function in current population is denoted as
Evolution_pop retains the highest subordinating degree function X1 of fitness, and replaces the minimum subordinating degree function of fitness with it
Y1 is denoted as Y1 '.In order to which the best subordinating degree function X1 guaranteed in current population is not destroyed, degree of allowing adaptation to is strongest to be subordinate to
Degree function X1 be not involved in this evolutionary process intersection and mutation operation and be directly entered next-generation group, then again press roulette
Back-and-forth method carries out selection operation to remaining subordinating degree function evolution_pop, and the subordinating degree function being selected is handed over
Next-generation population is collectively formed with subordinating degree function X1 and Y1 ' after fork, variation；
When selecting according to roulette selection algorithm the subordinating degree function in group, subordinating degree function is selected to be carried out
Intersect the size that subordinating degree function adaptive value is proportional to the probability of mutation operation in next step.
Preferably, step crossover operation mode further includes：
Crossover operation mode uses single point crossing；By given crossover probability from individual choice operation mode selection operator quilt
Two subordinating degree functions are selected in the subordinating degree function selected at random and carry out crossing operation or recombination operation, so latter two is subordinate to
Information is exchanged at random between degree function, generates two new subordinating degree functions；By the new degree of membership of the filial generation of crossover operator generation
Function inherits the essential characteristic of godfather generation subordinating degree function thereon, therefore crossover operator embodies information exchange recombination；
According to the group generated in individual choice operation mode according to the subordinating degree function that roulette wheel selection is selected
Evolution_pop, two parents subordinating degree function P1 and P2 being therefrom randomly selected, using simple single point crossing come real
Existing crossover operation, that is, be randomly provided in the subordinating degree function coded strings chromo_cpairs being mutually paired two-by-two a certain position it
Afterwards as exchange point cpoints_chromo position, then according to given crossover probability be exchanged with each other the exchange point position it
The code segment value of latter two subordinating degree function obtains two new subordinating degree functions.
Preferably, step mutation operation mode further includes：
Candidate Set is selected with letter of guarantee number sieve and mutation operation is carried out to membership function, according to determining guarantee function constraint
The coding range of virtual machine selection physical machine, the collection of virtual machine selection physical machine is filtered out for mutation operation in mutation operation
It closes, i.e. restrict virtual machine is constrained to the transformation of corresponding element on membership function when carrying out mutation operation and selects physical machine
Relationship；According to the threshold value ψ for waiting guarantee functiontheshConstraint, the element on variable position in subordinating degree function in mutation operation
Transformation be greater than threshold value ψtheshPhysical machine.
As can be seen from the above technical solutions, the present invention has the following advantages that：
The problem of solving virtual machine under cloud environment present invention employs genetic algorithm, in the pass of search virtual machine and physical machine
When connection relationship, guiding search direction, avoids basic genetic algorithmic from falling into local optimum with having Objective；Utilize heuritic approach base
It is scanned in genetic algorithm to reduce physical resource energy consumption, optimization energy efficiency, and optimize virtual machine position with adaptive algorithm
Maximum link utilization is minimized, achievees the purpose that reducing physical server resource energy consumption, optimization network performance.In cloud meter
It calculates and describes the incidence relation of virtual machine VM- physical machine PM using membership function under environment, it is virtual using Genetic algorithm searching
When organ joins physical machine combination optimal solution, when to the designs of two modules of membership function collection and mutation operator, to subordinating degree function
Building be associated with the relationship of physical machine using virtual machine is limited with initialization, the physical machine that virtual machine is possible to placement carries out about
Beam, rather than subordinating degree function is randomly generated as basic genetic algorithmic, so that basic genetic algorithmic search be avoided to fall into part
It is optimal and accelerate algorithm the convergence speed.
Invention considers not only the energy consumption problem of physical resource, passes through the resource matched pass of " virtual machine VM- physical machine PM "
System minimizes the number of the physical server and network settings that are in active state, reduces the energy consumption of cloud data center；And
And the optimization of network performance is considered, the position by changing virtual machine changes the physical server belonging to it, changes stream
The transmitting terminal of amount and receiving end achieve the purpose that improve network performance.
Detailed description of the invention
In order to illustrate more clearly of technical solution of the present invention, attached drawing needed in description will be made below simple
Ground introduction, it should be apparent that, drawings in the following description are only some embodiments of the invention, for ordinary skill
For personnel, without creative efforts, it is also possible to obtain other drawings based on these drawings.
Fig. 1 is the virtual machine placement method flow chart under cloud computing environment.
Specific embodiment
The present invention provides the virtual machine placement method under a kind of cloud computing environment, as shown in Figure 1, method includes：
S1 determines objective function f (t) and fitness function fitness (t)；
Determine objective function f (t) and two functions of fitness function fitness (t).One function is objective function f (t)
And it is switched into fitness function fitness (t), because being the mark that fitness function is genetic algorithm evaluation solution (individual) quality
It is quasi-.Judge of the fitness function that fitness function is the evaluation criterion of membership function, therefore is designed correctly for membership function
It is most important with optimizing.Another function is to guarantee function Gs,tPhysical machine is associated with to constrain virtual machine in membership function expression formula
Relationship promote network performance so that algorithm be avoided to fall into local optimum.
S2 carries out the process that virtual machine is placed in physical machine based on genetic algorithm；
S3, genetic algorithm include：Initialization population；
S4 carries out evaluation to individual according to fitness function and selects individual choice operation mode；
S5, crossover operation mode；
S6, mutation operation mode；
S7, according to genetic algorithmic steps until the number of iterations terminates.
The foregoing description of the disclosed embodiments enables those skilled in the art to implement or use the present invention.
Various modifications to these embodiments will be readily apparent to those skilled in the art, as defined herein
General Principle can be realized in other embodiments without departing from the spirit or scope of the present invention.Therefore, of the invention
It is not intended to be limited to the embodiments shown herein, and is to fit to and the principles and novel features disclosed herein phase one
The widest scope of cause.
In the present invention, step determines that objective function f (t) further includes：
Energy consumption E based on cloud data centerDC, including physical machine energy consumption Epm, network equipment energy consumption EnetAnd other energy consumptions
Eother, i.e. EDC=Epm+Enet+Eother；
Physical machine energy consumption EpmIncluding CPU energy consumption, energy consumption of memory, storage energy consumption and network interface energy consumption, network equipment energy consumption
EnetIncluding interchanger energy consumption, router energy consumption, link energy consumption；Other energy consumptions EotherIt is assisted including refrigeration air-conditioner energy consumption, illumination etc.
Equipment energy consumption；
Objective function is to minimize physical machine energy consumption, its calculation formula is：
F (t)=Epm+Enet+Eother。
In the present invention, step determines that fitness function fitness (t) further includes：
According to the expression formula of objective function f, conversion is used in genetic algorithm evaluate the fitness function of membership function quality,
The expression formula of fitness function for obtaining evaluation membership function collection is：
In formula：T indicates the number of iterations；Fitness (t) indicates in each iterative process that the evaluation function of membership function is
Fitness function.
In the present invention, step initialization population further includes：A membership function relationship is constructed to indicate to place in physical machine
Virtual machine.Than if any 3 physical machines, a total of 5 virtual machines, then membership such as c=(2,1,3,1,1), is subordinate to
The coding of relationship is the number of physical machine, and length is the number of virtual machine, means that the virtual machine that number is 1 is placed on No. 2 physics
On machine, the virtual machine that number is 2 is placed on No. 1 physical machine, and the virtual machine that number is 3 is placed in No. 3 physical machines, the void that number is 4
Quasi- machine is placed in No. 1 physical machine, and the virtual machine that number is 5 is placed in No. 1 physical machine.Population is exactly a multi-C vector, such as
If Population Size is 20, the result of initial population is exactly 20 such memberships to indicate virtual machine in physical machine
Placement situation.
In the present invention, step carries out evaluation to individual according to fitness function and selects individual choice operation mode and further include：
Individual choice operation mode uses optimum maintaining strategy combination roulette wheel selection, according to the public affairs of fitness function
Formula calculates the fitness value size of each subordinating degree function in current population, and it is highest then to find out fitness from current population
The subordinating degree function X1 and minimum subordinating degree function Y1 of fitness, and remaining subordinating degree function in current population is denoted as
Evolution_pop (other degree of membership letters i.e. other than fitness highest and minimum two subordinating degree functions of fitness
Number), retain the highest subordinating degree function X1 of fitness, and replace the minimum subordinating degree function Y1 of fitness with it, is denoted as
Y1′.In order to which the best subordinating degree function X1 guaranteed in current population is not destroyed, the strongest subordinating degree function X1 of degree of allowing adaptation to
Be not involved in this evolutionary process intersection and mutation operation and be directly entered next-generation group, then again press roulette wheel selection pair
Remaining subordinating degree function evolution_pop carries out selection operation, after the subordinating degree function being selected is intersected, made a variation
Next-generation population is collectively formed with subordinating degree function X1 and Y1 '；
When selecting according to roulette selection algorithm the subordinating degree function in group, subordinating degree function is selected to be carried out
Intersect the size that subordinating degree function adaptive value is proportional to the probability of mutation operation in next step.It is mutually tied with optimum maintaining strategy
The average adaptive value of group can be continuously improved altogether, it is ensured that fitness highest subordinating degree function is not deteriorated i.e.
The adaptive value of best subordinating degree function will not reduce.
In the present invention, step crossover operation mode further includes：Crossover operation mode uses single point crossing；By given intersection
Probability selected at random from the subordinating degree function that individual choice operation mode selection operator is selected two subordinating degree functions into
Row crossing operation or recombination operation, so exchange information between latter two subordinating degree function at random, generate two new degree of membership letters
Number；The new subordinating degree function of the filial generation generated by crossover operator inherits the essential characteristic of godfather generation subordinating degree function thereon, because
This crossover operator embodies information exchange recombination；
According to the group generated in individual choice operation mode according to the subordinating degree function that roulette wheel selection is selected
Evolution_pop, two parents subordinating degree function P1 and P2 being therefrom randomly selected, using simple single point crossing come real
Existing crossover operation, that is, be randomly provided in the subordinating degree function coded strings chromo_cpairs being mutually paired two-by-two a certain position it
Afterwards as exchange point cpoints_chromo position, then according to given crossover probability be exchanged with each other the exchange point position it
The code segment value of latter two subordinating degree function obtains two new subordinating degree functions.
In the present invention, step mutation operation mode further includes：With letter of guarantee number sieve select Candidate Set and to membership function into
Row variation operation, according to the coding range of virtual machine selection physical machine in determining guarantee function constraint mutation operation, for change
ETTHER-OR operation filters out the set of virtual machine selection physical machine, when carrying out mutation operation to the transformation of corresponding element on membership function into
Row constraint is the relationship of restrict virtual machine selection physical machine；According to the threshold value ψ for waiting guarantee functiontheshConstraint, is making a variation
The transformation of element is greater than threshold value ψ on variable position in subordinating degree function when operationtheshPhysical machine.
It is a kind of in view of the placement problem, that is, virtual machine-physical machine mapping relations of virtual machine physically in the present invention
" NP is difficult " problem of Combinatorial Optimization is solved, and one kind that genetic algorithm can be used for solving combinatorial optimization problem efficiently inspires
Formula global search technology utilizes the exchange of population gene, continuously improves the optimizing quality of population and with faster convergence rate
Find globally optimal solution.The problem of solving virtual machine under cloud environment present invention employs the improved adaptive GA-IAGA for introducing Candidate Set,
When searching for the incidence relation of virtual machine and physical machine, guiding search direction, avoids basic genetic algorithmic from falling into having Objective
Local optimum；It is scanned for using heuritic approach based on genetic algorithm to reduce physical resource energy consumption, optimization energy efficiency, and
Maximum link utilization is minimized with optimal adaptation algorithm optimization virtual machine position, reaches and is reducing physical server resource energy
The purpose of consumption, optimization network performance.By " the incidence relation use of virtual machine VM- physical machine PM is subordinate to letter under cloud computing environment
Number is to describe, when closing optimal solution using Genetic algorithm searching virtual machine association physics unit, to membership function collection and mutation operator
It is empty to the relationship that the building of subordinating degree function is associated with physical machine using virtual machine is limited with initialization when the design of two modules
The physical machine that quasi- machine is possible to place is constrained, rather than subordinating degree function is randomly generated as basic genetic algorithmic, thus
Basic genetic algorithmic search is avoided to fall into local optimum and accelerate algorithm the convergence speed.The present invention is preliminary by improved adaptive GA-IAGA
Virtual machine-physical machine mapping relations are searched, the mapping relations of virtual machine VM- physical machine PM are found in conjunction with optimal adaptation algorithm,
Find the virtual machine VM- physical machine PM combination of global optimum.
Claims (7)
1. the virtual machine placement method under a kind of cloud computing environment, which is characterized in that method includes：
Determine objective function f (t) and fitness function fitness (t)；
The process that virtual machine is placed in physical machine is carried out based on genetic algorithm；
Genetic algorithm includes：Initialization population；
Evaluation is carried out to individual according to fitness function and selects individual choice operation mode；
Crossover operation mode；
Mutation operation mode；
According to genetic algorithmic steps until the number of iterations terminates.
2. the virtual machine placement method under cloud computing environment according to claim 1, which is characterized in that
Step determines that objective function f (t) further includes：
Energy consumption E based on cloud data centerDC, including physical machine energy consumption Epm, network equipment energy consumption EnetAnd other energy consumptions
Eother, i.e. EDC=Epm+Enet+Eother；
Physical machine energy consumption EpmIncluding CPU energy consumption, energy consumption of memory, storage energy consumption and network interface energy consumption, network equipment energy consumption EnetPacket
Include interchanger energy consumption, router energy consumption, link energy consumption；Other energy consumptions EotherIncluding ancillary equipments such as refrigeration air-conditioner energy consumption, illuminations
Energy consumption；
Objective function is to minimize physical machine energy consumption, its calculation formula is：
F (t)=Epm+Enet+Eother。
3. the virtual machine placement method under cloud computing environment according to claim 2, which is characterized in that
Step determines that fitness function fitness (t) further includes：
According to the expression formula of objective function f, conversion is obtained for evaluating the fitness function of membership function quality in genetic algorithm
The expression formula of fitness function for evaluating membership function collection is：
In formula：T indicates the number of iterations；Fitness (t) indicates in each iterative process that the evaluation function of membership function adapts to
Spend function.
4. the virtual machine placement method under cloud computing environment according to claim 1, which is characterized in that
Step initialization population further includes：
A membership function relationship is constructed to indicate the virtual machine placed in physical machine.
5. the virtual machine placement method under cloud computing environment according to claim 1, which is characterized in that
Step carries out evaluation to individual according to fitness function and selects individual choice operation mode and further include：
Individual choice operation mode uses optimum maintaining strategy combination roulette wheel selection, according to the formula meter of fitness function
The fitness value size of each subordinating degree function in current population is calculated, then finds out that fitness is highest to be subordinate to from current population
Function X1 and the minimum subordinating degree function Y1 of fitness are spent, and remaining subordinating degree function in current population is denoted as
Evolution_pop retains the highest subordinating degree function X1 of fitness, and replaces the minimum subordinating degree function of fitness with it
Y1 is denoted as Y1 '；In order to which the best subordinating degree function X1 guaranteed in current population is not destroyed, degree of allowing adaptation to is strongest to be subordinate to
Degree function X1 be not involved in this evolutionary process intersection and mutation operation and be directly entered next-generation group, then again press roulette
Back-and-forth method carries out selection operation to remaining subordinating degree function evolution_pop, and the subordinating degree function being selected is handed over
Next-generation population is collectively formed with subordinating degree function X1 and Y1 ' after fork, variation；
When selecting according to roulette selection algorithm the subordinating degree function in group, the selected progress of subordinating degree function is next
Step intersects the size that subordinating degree function adaptive value is proportional to the probability of mutation operation.
6. the virtual machine placement method under cloud computing environment according to claim 1, which is characterized in that
Step crossover operation mode further includes：
Crossover operation mode uses single point crossing；It is selected by given crossover probability from individual choice operation mode selection operator
Two subordinating degree functions are selected in subordinating degree function out at random and carry out crossing operation or recombination operation, latter two right degree of membership letter
Information is exchanged between number at random, generates two new subordinating degree functions；By the new subordinating degree function of the filial generation of crossover operator generation
The essential characteristic of godfather generation subordinating degree function thereon is inherited, therefore crossover operator embodies information exchange recombination；
According to the group generated in individual choice operation mode according to the subordinating degree function that roulette wheel selection is selected
Evolution_pop, two parents subordinating degree function P1 and P2 being therefrom randomly selected, using simple single point crossing come real
Existing crossover operation, that is, be randomly provided in the subordinating degree function coded strings chromo_cpairs being mutually paired two-by-two a certain position it
Afterwards as exchange point cpoints_chromo position, then according to given crossover probability be exchanged with each other the exchange point position it
The code segment value of latter two subordinating degree function obtains two new subordinating degree functions.
7. the virtual machine placement method under cloud computing environment according to claim 1, which is characterized in that
Step mutation operation mode further includes：
Candidate Set is selected with letter of guarantee number sieve and mutation operation is carried out to membership function, is made a variation according to determining guarantee function constraint
The coding range of virtual machine selection physical machine, the set of virtual machine selection physical machine is filtered out for mutation operation in operation, into
The pass of i.e. restrict virtual machine selection physical machine is constrained the transformation of corresponding element on membership function when row variation operates
System；According to the threshold value ψ for waiting guarantee functiontheshConstraint, in mutation operation in subordinating degree function on variable position element change
It changes and is greater than threshold value ψtheshPhysical machine.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810614926.8A CN108897600A (en) | 2018-06-14 | 2018-06-14 | A kind of virtual machine placement method under cloud computing environment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810614926.8A CN108897600A (en) | 2018-06-14 | 2018-06-14 | A kind of virtual machine placement method under cloud computing environment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108897600A true CN108897600A (en) | 2018-11-27 |
Family
ID=64344781
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810614926.8A Pending CN108897600A (en) | 2018-06-14 | 2018-06-14 | A kind of virtual machine placement method under cloud computing environment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108897600A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109697105A (en) * | 2018-12-11 | 2019-04-30 | 广东石油化工学院 | A kind of container cloud environment physical machine selection method and its system, virtual resource configuration method and moving method |
| CN110308993A (en) * | 2019-06-27 | 2019-10-08 | 大连理工大学 | A kind of cloud computing resources distribution method based on improved adaptive GA-IAGA |
| CN111324422A (en) * | 2020-02-24 | 2020-06-23 | 武汉轻工大学 | Multi-target virtual machine deployment method, device, equipment and storage medium |
| CN111338765A (en) * | 2020-03-23 | 2020-06-26 | 武汉轻工大学 | Virtual machine deployment method, device, equipment and storage medium based on cat swarm algorithm |
| CN113094149A (en) * | 2021-03-12 | 2021-07-09 | 西安交通大学 | Data center virtual machine placement method, system, medium and equipment |
| CN114528088A (en) * | 2022-04-25 | 2022-05-24 | 北京航天驭星科技有限公司 | Satellite detection task processing method and device, electronic equipment and storage medium |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103576829A (en) * | 2012-08-01 | 2014-02-12 | 复旦大学 | Hybrid genetic algorithm based dynamic cloud-computing virtual machine scheduling method |
| CN103902375A (en) * | 2014-04-11 | 2014-07-02 | 北京工业大学 | Cloud task scheduling method based on improved genetic algorithm |
| CN104811491A (en) * | 2015-04-17 | 2015-07-29 | 华南理工大学 | Cloud computing resource scheduling method based on genetic algorithm |
| CN104899100A (en) * | 2015-05-28 | 2015-09-09 | 北京邮电大学 | Resource scheduling method for cloud system |
| CN104932938A (en) * | 2015-06-16 | 2015-09-23 | 中电科软件信息服务有限公司 | Cloud resource scheduling method based on genetic algorithm |
| CN105607943A (en) * | 2015-12-18 | 2016-05-25 | 浪潮集团有限公司 | Dynamic deployment mechanism of virtual machine under cloud environment |
| CN105740051A (en) * | 2016-01-27 | 2016-07-06 | 北京工业大学 | Cloud computing resource scheduling realization method based on improved genetic algorithm |
| CN105843666A (en) * | 2015-12-01 | 2016-08-10 | 武汉科技大学 | Virtual machine placement method based on multi-objective optimization during cloud computing |
| CN107967171A (en) * | 2017-12-01 | 2018-04-27 | 电子科技大学 | Multi-workflow dispatching method based on genetic algorithm under a kind of cloud environment |
| CN108009003A (en) * | 2017-12-01 | 2018-05-08 | 湖南女子学院 | A kind of multiple target virtual machine adaptive location system of selection, distributed cloud system |
| CN108073449A (en) * | 2017-11-21 | 2018-05-25 | 山东科技大学 | A kind of virtual machine dynamic laying method |
-
2018
- 2018-06-14 CN CN201810614926.8A patent/CN108897600A/en active Pending
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103576829A (en) * | 2012-08-01 | 2014-02-12 | 复旦大学 | Hybrid genetic algorithm based dynamic cloud-computing virtual machine scheduling method |
| CN103902375A (en) * | 2014-04-11 | 2014-07-02 | 北京工业大学 | Cloud task scheduling method based on improved genetic algorithm |
| CN104811491A (en) * | 2015-04-17 | 2015-07-29 | 华南理工大学 | Cloud computing resource scheduling method based on genetic algorithm |
| CN104899100A (en) * | 2015-05-28 | 2015-09-09 | 北京邮电大学 | Resource scheduling method for cloud system |
| CN104932938A (en) * | 2015-06-16 | 2015-09-23 | 中电科软件信息服务有限公司 | Cloud resource scheduling method based on genetic algorithm |
| CN105843666A (en) * | 2015-12-01 | 2016-08-10 | 武汉科技大学 | Virtual machine placement method based on multi-objective optimization during cloud computing |
| CN105607943A (en) * | 2015-12-18 | 2016-05-25 | 浪潮集团有限公司 | Dynamic deployment mechanism of virtual machine under cloud environment |
| CN105740051A (en) * | 2016-01-27 | 2016-07-06 | 北京工业大学 | Cloud computing resource scheduling realization method based on improved genetic algorithm |
| CN108073449A (en) * | 2017-11-21 | 2018-05-25 | 山东科技大学 | A kind of virtual machine dynamic laying method |
| CN107967171A (en) * | 2017-12-01 | 2018-04-27 | 电子科技大学 | Multi-workflow dispatching method based on genetic algorithm under a kind of cloud environment |
| CN108009003A (en) * | 2017-12-01 | 2018-05-08 | 湖南女子学院 | A kind of multiple target virtual machine adaptive location system of selection, distributed cloud system |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109697105A (en) * | 2018-12-11 | 2019-04-30 | 广东石油化工学院 | A kind of container cloud environment physical machine selection method and its system, virtual resource configuration method and moving method |
| CN110308993A (en) * | 2019-06-27 | 2019-10-08 | 大连理工大学 | A kind of cloud computing resources distribution method based on improved adaptive GA-IAGA |
| CN110308993B (en) * | 2019-06-27 | 2022-12-13 | 大连理工大学 | Cloud computing resource allocation method based on improved genetic algorithm |
| CN111324422A (en) * | 2020-02-24 | 2020-06-23 | 武汉轻工大学 | Multi-target virtual machine deployment method, device, equipment and storage medium |
| CN111324422B (en) * | 2020-02-24 | 2024-04-16 | 武汉轻工大学 | Multi-target virtual machine deployment method, device, equipment and storage medium |
| CN111338765A (en) * | 2020-03-23 | 2020-06-26 | 武汉轻工大学 | Virtual machine deployment method, device, equipment and storage medium based on cat swarm algorithm |
| CN111338765B (en) * | 2020-03-23 | 2023-07-25 | 武汉轻工大学 | Virtual machine deployment method, device, equipment and storage medium based on cat swarm algorithm |
| CN113094149A (en) * | 2021-03-12 | 2021-07-09 | 西安交通大学 | Data center virtual machine placement method, system, medium and equipment |
| CN113094149B (en) * | 2021-03-12 | 2024-01-12 | 西安交通大学 | Data center virtual machine placement method, system, medium and equipment |
| CN114528088A (en) * | 2022-04-25 | 2022-05-24 | 北京航天驭星科技有限公司 | Satellite detection task processing method and device, electronic equipment and storage medium |
| CN114528088B (en) * | 2022-04-25 | 2022-07-12 | 北京航天驭星科技有限公司 | Satellite detection task processing method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108897600A (en) | A kind of virtual machine placement method under cloud computing environment | |
| CN106484512B (en) | The dispatching method of computing unit | |
| CN107579922B (en) | Network load balancing device and method | |
| CN107959633A (en) | A kind of load balance method based on price mechanism in industry real-time network | |
| CN105550033B (en) | Resource dispatching strategy method based on genetic tabu hybrid algorithm under privately owned cloud environment | |
| CN105323166B (en) | A kind of method for routing preferential based on network energy efficiency towards cloud computing | |
| CN109039942A (en) | A kind of Network Load Balance system and equalization methods based on deeply study | |
| CN106651628B (en) | Regional cooling, heating and power comprehensive energy optimal allocation method and device based on graph theory | |
| CN102904811B (en) | Towards route selection method and the system of power business | |
| CN109447264B (en) | Virtual machine placement genetic optimization method based on VHAM-R model in cloud computing environment | |
| Yang et al. | Energy-efficient data center networks planning with virtual machine placement and traffic configuration | |
| CN105071947B (en) | A kind of link optimizing method of SDN network | |
| CN108174394A (en) | A kind of Arrangement algorithm of 5G networks slice | |
| Zhang et al. | MCTE: Minimizes task completion time and execution cost to optimize scheduling performance for smart grid cloud | |
| CN104317646A (en) | Cloud data central virtual machine scheduling method based on OpenFlow frame | |
| Liu et al. | Optimal scheduling for multi-flow update in software-defined networks | |
| Neghabi et al. | Energy‐aware dynamic‐link load balancing method for a software‐defined network using a multi‐objective artificial bee colony algorithm and genetic operators | |
| WO2014040554A1 (en) | Method and apparatus for determining energy-efficient routing | |
| Yang et al. | Collective energy-efficiency approach to data center networks planning | |
| CN107749805A (en) | A kind of virtual machine deployment method and device | |
| CN102082732A (en) | Virtual network energy saving method based on virtual router on the move (VROOM) | |
| CN102291308A (en) | Method and system for implementing network dynamic load balancing | |
| Wang et al. | A green intelligent routing algorithm supporting flexible QoS for many-to-many multicast | |
| Yang et al. | Comparative analysis of routing schemes based on machine learning | |
| Mineraud et al. | Hybrid renewable energy routing for ISP networks |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181127 |