CN106161640A - A kind of virtual machine two-stage optimizing management and running platform based on cloud computing - Google Patents
A kind of virtual machine two-stage optimizing management and running platform based on cloud computing Download PDFInfo
- Publication number
- CN106161640A CN106161640A CN201610583226.8A CN201610583226A CN106161640A CN 106161640 A CN106161640 A CN 106161640A CN 201610583226 A CN201610583226 A CN 201610583226A CN 106161640 A CN106161640 A CN 106161640A
- Authority
- CN
- China
- Prior art keywords
- module
- virtual machine
- level
- cloud computing
- resource
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/104—Peer-to-peer [P2P] networks
- H04L67/1074—Peer-to-peer [P2P] networks for supporting data block transmission mechanisms
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/1001—Protocols in which an application is distributed across nodes in the network for accessing one among a plurality of replicated servers
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention proposes a kind of virtual machine two-stage optimizing management and running platform based on cloud computing, and this platform includes cloud computing platform door, schedule level one module, secondary scheduling module, and schedule level one optimizes module, and second-level dispatching optimizes module, physical source distributing module.The present invention introduces schedule level one on the basis of the two-level scheduler model of traditional cloud computing and optimizes module and second-level dispatching optimization module, two-level scheduler optimizes module and uses different bionic intelligence algorithms to be optimized the scheduling of resource distribution of schedule level one module and secondary scheduling module, static and dynamic globally optimal solution is provided for cloud virtual machine load balancing, obtain optimum scheduling scheme, effectively reduce the resource overhead of virtual machine (vm) migration, improve the utilization ratio of cloud computing resources, improve the service quality of user simultaneously.
Description
Technical field
The present invention relates to the technical field of cloud computing, particularly relate to the scheduling of a kind of virtual machine two-stage optimizing based on cloud computing
Management platform.
Background technology
Along with computer and the development of Internet technology, people are increasing to the demand of data, to data message
Disposal ability require more and more higher, the process of data also from traditional unit process cluster process, and cluster process number
Relate to the utilization rate problem of server according to processing mode, the most efficiently utilize cluster server to become Ge great supplier urgently
The problem solved, virtual machine thus arises at the historic moment.And cloud computing is a kind of computation schema based on the Internet, need to carry by user
For the resource of the most easily extension, its advantage with motility, convenience and economy.This based on virtual machine and cloud computing
Coordination service pattern under, the research of load-balancing technique causes the attention of lot of domestic and foreign enterprises and mechanism, and this technology is not
But improve resource utilization, improve the service quality of user simultaneously, while it is true, it is still faced with in the urgent need to address
Scheduling virtual machine is inefficient and load balancing imperfection problem.
Summary of the invention
For the problems referred to above, the present invention proposes a kind of virtual machine two-stage optimizing management and running platform based on cloud computing,
This platform includes cloud computing platform door, schedule level one module, secondary scheduling module, and schedule level one optimizes module, second-level dispatching
Optimize module, physical source distributing module.
Described cloud computing platform door front end is connected with the client of user, and rear end is connected with described schedule level one module,
Described schedule level one module side optimizes module with described schedule level one and is connected, and rear end is connected with described secondary scheduling module, institute
Stating secondary scheduling module side to be connected with described second-level dispatching optimization module, rear end is connected with described physical source distributing module.
Described schedule level one optimizes module and uses ant colony algorithm to realize, and described second-level dispatching optimizes module and uses ant group algorithm
Realize.
Described cloud computing platform door provides client, described user to submit high in the clouds task, described one-level to for all users
Scheduler module and described secondary scheduling module complete scheduling and the distribution of resource, finally by corresponding described physical source distributing mould
Block distribution physical resource gives described user, and the result that the task that returns completes.
Described schedule level one module includes that resource description module and schedule virtual resources module, described resource description module connect
Receive the task of the described user of described cloud computing platform door, it is judged that the type of task and scale, and simultaneously by the type of task
It is sent to described schedule level one with size values and optimizes module and described schedule virtual resources module, described schedule virtual resources mould
The described informix that tuber optimizes module and the offer of described resource description module according to described schedule level one carries out scheduling of resource
Prediction.
Described secondary scheduling module includes physical machine scheduler module and virtual machine planning module, described physical machine scheduler module
Receive the result of the scheduling of resource prediction of described resource description module, combined with virtual machine resource and the use feelings of physical machine resource
Condition, formulates the placement of resource and migration strategy, and described strategy is sent to described second-level dispatching optimizes module to carry out strategy excellent
Change processes；Described virtual machine planning module is set up and described physical machine scheduler module and the strategy of described second-level dispatching optimization module
The mapping relations of information, the virtual machine planner of described virtual machine planning module calls described physical resource according to mapping result and divides
Join the physical resource in module, and return result to described user.
Described schedule level one optimizes module and uses ant colony algorithm to realize, and the step that realizes of described ant colony algorithm is:
S1, initiation parameter, produce initial position；
S2, quality evaluation, and judge whether to meet end condition；
If meeting, then perform S4；Otherwise, S3 is performed；
S3, task carries out investigations as investigation honeybee, and by the activity of following, gathers in the crops food source, obtains the virtual machine of prediction, and returns
Return S2；
S4, exports optimal solution, and this optimal solution is returned as arithmetic result.
Described second-level dispatching optimizes module and uses ant group algorithm to realize, and the step that realizes of described ant group algorithm is:
S1, initializes ant colony pheromone, and described pheromone is the disposal ability of each virtual machine；
S2, ant colony search solve, specifically, when a Formica fusca complete its path reach a virtual machine time, update the letter on this path
Breath element, the pheromone on described path is the disposal ability of virtual machine；
S3, it may be judged whether meeting overall situation update condition, if meeting, then performing S4；Otherwise, S2 is performed；
S4, using the result of S3 as policy optimization result, and returns to described virtual machine planning mould by described policy optimization result
Block.
The present invention introduces schedule level one on the basis of the two-level scheduler model of traditional cloud computing and optimizes module and two grades
Optimizing scheduling module, two-level scheduler optimizes module and uses different bionic intelligence algorithms to schedule level one module and second-level dispatching mould
The scheduling of resource distribution of block is optimized, and provides static and dynamic globally optimal solution for cloud virtual machine load balancing, it is thus achieved that
Optimum scheduling scheme, effectively reduces the resource overhead of virtual machine (vm) migration, improves the utilization ratio of cloud computing resources, carry simultaneously
The high service quality of user.
Accompanying drawing explanation
Fig. 1 is the structure chart of the virtual machine two-stage optimizing management and running platform based on cloud computing in the embodiment of the present invention.
Detailed description of the invention
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme of the embodiment of the present invention is carried out clear, complete
Ground describes, it is clear that described embodiment is only a part of embodiment of the present invention rather than whole embodiments.Based on
Embodiment in the present invention, those skilled in the art obtained on the premise of not making creative work all other
Embodiment, broadly falls into protection scope of the present invention.
Fig. 1 is the structure chart of the virtual machine two-stage optimizing management and running platform based on cloud computing in the embodiment of the present invention.
Below in conjunction with Fig. 1, embodiments of the present invention are done concrete description.As it is shown in figure 1, should virtual machine two-stage based on cloud computing
Optimized Operation management platform includes cloud computing platform door, schedule level one module, secondary scheduling module, and schedule level one optimizes mould
Block, second-level dispatching optimizes module, physical source distributing module.
Cloud computing platform door has provided the user unified certification and control of authority, and different users enjoys different clothes
Business, as general user provides publicly-owned cloud service, advanced level user provides privately owned cloud and publicly-owned cloud service；Meanwhile, cloud computing platform door
Family also provides for manager and logs in interface, it is simple to manager provides the maintenance of platform to manage with upgrading etc. at non-serving end.Cloud meter
Calculate platform portal and have the function of front end services management concurrently, for monitoring the life cycle of service, service procedure and service state, clothes
The security monitoring of business.Cloud computing platform door front end is connected with the client of user, and rear end is connected with schedule level one module, client
End is service offering layer, for providing the user interface of the several operation systems such as compatible linux and windows, this user circle
Face provides the user the application interface icon of multiple high in the clouds application, improves interaction effect.Schedule level one module side is adjusted with one-level
Degree optimizes module and connects, and rear end is connected with secondary scheduling module, and secondary scheduling module side optimizes module with second-level dispatching and is connected,
Rear end is connected with physical source distributing module.Cloud computing platform door provides client, user to submit to high in the clouds to appoint for all users
Business, schedule level one module and secondary scheduling module complete scheduling and the distribution of resource, finally by corresponding physical source distributing mould
Block distribution physical resource gives described user, and the result that the task that returns completes.Schedule level one optimizes module and uses ant colony algorithm real
Existing, second-level dispatching optimizes module and uses ant group algorithm to realize.
Schedule level one module includes resource description module and schedule virtual resources module, and resource description module receives cloud computing
The task of the user of platform portal, it is judged that the type of task and scale, and the type of task is sent to size values simultaneously
Schedule level one optimizes module and schedule virtual resources module, and the Main Function of schedule virtual resources module is for appointing that user submits to
Business provides corresponding resources of virtual machine, it is established that the effective mapping relations between resource and task, especially has multiple money
During source node, can jointly share substantial amounts of concurrent access request, and thus reduce the time that request responds, minimizing task completes
Time, to reach effective use of resources of virtual machine.This schedule level one optimizes migration and the load balancing that module is virtual machine
Distribution for subsequent physical resource is made that the preparation of early stage, is first committed step of two-stage optimizing.Virtual resource
Scheduler module carries out the prediction of scheduling of resource according to the informix that schedule level one optimization module and resource description module provide.One
Level scheduler module completes some miscellaneous functions simultaneously, such as distribution and the examination & approval of resource bid, the recovery of waste resource, generates resource
Utilize form etc..
Secondary scheduling module includes physical machine scheduler module and virtual machine planning module, physical resource scheduler module main
Function is in virtual resource reasonable Arrangement to physical machine resource, to reach the optimal allocation of physical machine resource.Physical machine is dispatched
Module receives the result of the scheduling of resource prediction of resource description module, combined with virtual machine resource and the use feelings of physical machine resource
Condition, formulates the placement of resource and migration strategy, and states strategy and be sent to second-level dispatching and optimize module and carry out policy optimization process；Empty
Plan machine planning module sets up the mapping relations of the policy information optimizing module with physical machine scheduler module and second-level dispatching, virtual machine
The virtual machine planner of planning module calls the physical resource in physical source distributing module according to mapping result, and returns result
To described user.Secondary scheduling module also completes the function of driven management, and such as network-driven, storage drives, and calculates driving etc., real
Show the driven management of physical machine resource.
Schedule level one optimizes module and uses ant colony algorithm to realize, and the step that realizes of ant colony algorithm is:
S1, initiation parameter, produce initial position；
S2, quality evaluation, and judge whether to meet end condition；
If meeting, then perform S4；Otherwise, S3 is performed；
S3, task carries out investigations as investigation honeybee, and by the activity of following, gathers in the crops food source, obtains the virtual machine of prediction, and returns
Return S2；
S4, exports optimal solution, and this optimal solution is returned as arithmetic result.
Second-level dispatching optimizes module and uses ant group algorithm to realize, and the step that realizes of ant group algorithm is:
S1, initializes ant colony pheromone, and described pheromone is the disposal ability of each virtual machine；
S2, ant colony search solve, specifically, when a Formica fusca complete its path reach a virtual machine time, update the letter on this path
Breath element, the pheromone on described path is the disposal ability of virtual machine；
S3, it may be judged whether meeting overall situation update condition, if meeting, then performing S4；Otherwise, S2 is performed；
S4, using the result of S3 as policy optimization result, and returns to described virtual machine planning module by policy optimization result.
The present invention introduces schedule level one on the basis of the two-level scheduler model of traditional cloud computing and optimizes module and two grades
Optimizing scheduling module, two-level scheduler optimizes module and uses different bionic intelligence algorithms to schedule level one module and second-level dispatching mould
The scheduling of resource distribution of block is optimized, and provides static and dynamic globally optimal solution for cloud virtual machine load balancing, it is thus achieved that
Optimum scheduling scheme, effectively reduces the resource overhead of virtual machine (vm) migration, improves the utilization ratio of cloud computing resources, carry simultaneously
The high service quality of user.
The above, the only detailed description of the invention of the present invention, but protection scope of the present invention is not limited thereto, and any
Those familiar with the art in the technical scope that the invention discloses, the change that can readily occur in or replacement, all answer
Contain within protection scope of the present invention.Therefore, protection scope of the present invention should be as the criterion with scope of the claims.
Claims (6)
1. a virtual machine two-stage optimizing management and running platform based on cloud computing, it is characterised in that include cloud computing platform door
Family, schedule level one module, secondary scheduling module, schedule level one optimizes module, and second-level dispatching optimizes module, physical source distributing mould
Block；
Described cloud computing platform door front end is connected with the client of user, and rear end is connected with described schedule level one module, described
Schedule level one module side optimizes module with described schedule level one and is connected, and rear end is connected with described secondary scheduling module, and described two
Level scheduler module side optimizes module with described second-level dispatching and is connected, and rear end is connected with described physical source distributing module；
Described schedule level one optimizes module and uses ant colony algorithm to realize, and described second-level dispatching optimizes module and uses ant group algorithm real
Existing.
A kind of virtual machine two-stage optimizing management and running platform based on cloud computing, it is characterised in that
Described cloud computing platform door provides client, described user to submit high in the clouds task, described schedule level one module to for all users
With scheduling and the distribution that described secondary scheduling module completes resource, finally by corresponding described physical source distributing module assignment thing
Reason resource gives described user, and the result that the task that returns completes.
A kind of virtual machine two-stage optimizing management and running platform based on cloud computing, it is characterised in that
Described schedule level one module includes resource description module and schedule virtual resources module, and described resource description module receives described cloud
Calculate the task of the described user of platform portal, it is judged that the type of task and scale, and the type of task is believed with scale simultaneously
Breath is sent to described schedule level one and optimizes module and described schedule virtual resources module, and described schedule virtual resources module is according to institute
The described informix stating schedule level one optimization module and the offer of described resource description module carries out the prediction of scheduling of resource.
A kind of virtual machine two-stage optimizing management and running platform based on cloud computing, it is characterised in that
Described secondary scheduling module includes physical machine scheduler module and virtual machine planning module, and described physical machine scheduler module receives described
The result of the scheduling of resource prediction of resource description module, combined with virtual machine resource and the service condition of physical machine resource, formulate money
The placement in source and migration strategy, and described strategy is sent to described second-level dispatching optimize module carry out policy optimization process；Institute
State reflecting of the virtual machine planning module foundation policy information with described physical machine scheduler module and described second-level dispatching optimization module
Penetrating relation, the virtual machine planner of described virtual machine planning module calls in described physical source distributing module according to mapping result
Physical resource, and return result to described user.
A kind of virtual machine two-stage optimizing management and running platform based on cloud computing, it is characterised in that
The step that realizes of described ant colony algorithm is: S1, initiation parameter, produces initial position；S2, quality evaluation, and judge whether full
Foot end condition, if meeting, then performs S4, otherwise, performs S3；S3, task carries out investigations as investigation honeybee, and by following work
Dynamic, gather in the crops food source, obtain the virtual machine of prediction, and return S2；S4, exports optimal solution, and this optimal solution is tied as algorithm
Fruit returns.
A kind of virtual machine two-stage optimizing management and running platform based on cloud computing, it is characterised in that
The step that realizes of described ant group algorithm is: S1, initializes ant colony pheromone, and described pheromone is the disposal ability of each virtual machine；
S2, ant colony search solve, specifically, when a Formica fusca complete its path reach a virtual machine time, update the letter on this path
Breath element, the pheromone on described path is the disposal ability of virtual machine；S3, it may be judged whether meet overall situation update condition, if meeting,
Then perform S4, otherwise, perform S2；S4, using the result of S3 as policy optimization result, and returns to described policy optimization result
Described virtual machine planning module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610583226.8A CN106161640A (en) | 2016-07-24 | 2016-07-24 | A kind of virtual machine two-stage optimizing management and running platform based on cloud computing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610583226.8A CN106161640A (en) | 2016-07-24 | 2016-07-24 | A kind of virtual machine two-stage optimizing management and running platform based on cloud computing |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106161640A true CN106161640A (en) | 2016-11-23 |
Family
ID=58060479
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610583226.8A Pending CN106161640A (en) | 2016-07-24 | 2016-07-24 | A kind of virtual machine two-stage optimizing management and running platform based on cloud computing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106161640A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107656877A (en) * | 2017-09-15 | 2018-02-02 | 联想(北京)有限公司 | Information processing method and its equipment |
| CN109788046A (en) * | 2018-12-29 | 2019-05-21 | 河海大学 | A kind of more tactful edge calculations resource regulating methods based on improvement ant colony algorithm |
| CN111124652A (en) * | 2019-12-31 | 2020-05-08 | 联想(北京)有限公司 | Resource pre-scheduling method, equipment and storage medium |
| CN113138838A (en) * | 2021-05-07 | 2021-07-20 | 桂林电子科技大学 | Virtual machine placement method based on artificial bee colony algorithm |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101727763A (en) * | 2009-12-11 | 2010-06-09 | 中国人民解放军空军军训器材研究所 | Method for integrated scheduling and real-time scheduling of training system |
| CN105375507A (en) * | 2015-07-10 | 2016-03-02 | 华北电力大学（保定） | Power two-stage interactive optimization scheduling system of virtual power plant in haze environment |
-
2016
- 2016-07-24 CN CN201610583226.8A patent/CN106161640A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101727763A (en) * | 2009-12-11 | 2010-06-09 | 中国人民解放军空军军训器材研究所 | Method for integrated scheduling and real-time scheduling of training system |
| CN105375507A (en) * | 2015-07-10 | 2016-03-02 | 华北电力大学（保定） | Power two-stage interactive optimization scheduling system of virtual power plant in haze environment |
Non-Patent Citations (1)
| Title |
|---|
| HIEN NGUYEN VAN ET AL: "SLA-aware Virtual Resource Management for Cloud Infrastructures", 《IEEE NINTH INTERNATIONAL CONFERENCE ON COMPUTER AND INFORMATION TECHNOLOGY》 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107656877A (en) * | 2017-09-15 | 2018-02-02 | 联想(北京)有限公司 | Information processing method and its equipment |
| CN107656877B (en) * | 2017-09-15 | 2021-06-15 | 联想(北京)有限公司 | Information processing method and apparatus thereof |
| CN109788046A (en) * | 2018-12-29 | 2019-05-21 | 河海大学 | A kind of more tactful edge calculations resource regulating methods based on improvement ant colony algorithm |
| CN109788046B (en) * | 2018-12-29 | 2020-06-16 | 河海大学 | Multi-strategy edge computing resource scheduling method based on improved bee colony algorithm |
| CN111124652A (en) * | 2019-12-31 | 2020-05-08 | 联想(北京)有限公司 | Resource pre-scheduling method, equipment and storage medium |
| CN113138838A (en) * | 2021-05-07 | 2021-07-20 | 桂林电子科技大学 | Virtual machine placement method based on artificial bee colony algorithm |
| CN113138838B (en) * | 2021-05-07 | 2024-03-29 | 桂林电子科技大学 | Virtual machine placement method based on artificial bee colony algorithm |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN100570569C (en) | Operation cross-domain control method under the grid computing environment | |
| CN104461740B (en) | A kind of cross-domain PC cluster resource polymerization and the method for distribution | |
| Shu et al. | A novel energy-efficient resource allocation algorithm based on immune clonal optimization for green cloud computing | |
| Liu et al. | Resource preprocessing and optimal task scheduling in cloud computing environments | |
| CN106095591A (en) | A kind of virtual machine two-stage optimizing management and running platform based on cloud computing | |
| CN106161640A (en) | A kind of virtual machine two-stage optimizing management and running platform based on cloud computing | |
| Liu et al. | A survey on virtual machine scheduling in cloud computing | |
| CN106027318A (en) | Cloud computing-based two-level optimal scheduling management platform for virtual machine | |
| CN103475538A (en) | Multi-interface-based self-adaptive cloud service test method | |
| Zhao et al. | SLA-based profit optimization for resource management of big data analytics-as-a-service platforms in cloud computing environments | |
| Zhou et al. | Strategy optimization of resource scheduling based on cluster rendering | |
| Mazidi et al. | An autonomic decision tree‐based and deadline‐constraint resource provisioning in cloud applications | |
| CN111242801A (en) | Power system regulation and control cloud power grid operation analysis platform | |
| CN103268261A (en) | Hierarchical computing resource management method suitable for large-scale high-performance computer | |
| CN117493020A (en) | Method for realizing computing resource scheduling of data grid | |
| Zheng et al. | A cloud resource prediction and migration method for container scheduling | |
| Wang et al. | Gmpr: a two-phase heuristic algorithm for virtual machine placement in large-scale cloud data centers | |
| CN108536518A (en) | Method and system, reference platform, service terminal and the memory of task scheduling | |
| CN104869154A (en) | Distributed resource scheduling method for balancing resource credibility and user satisfaction | |
| El-Zoghdy | A load balancing policy for heterogeneous computational grids | |
| CN103023986A (en) | System and method for providing relational database management system (RDBMS) services for multiple users | |
| Ma | Resource management framework for virtual data center embedding based on software defined networking | |
| Lin et al. | Virtualized resource scheduling in cloud computing environments: An review | |
| El-Zoghdy | A CAPACITY-BASED LOAD BALANCING AND JOBMIGRATION ALGORITHM FOR HETEROGENEOUS COMPUTATIONAL GRIDS | |
| CN109544040B (en) | Service flow dynamic reconstruction method based on mode |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20161123 |
|
| WD01 | Invention patent application deemed withdrawn after publication |