CN102984249A - Distributed resource allocation method in horizontal dynamic cloud alliance - Google Patents
Distributed resource allocation method in horizontal dynamic cloud alliance Download PDFInfo
- Publication number
- CN102984249A CN102984249A CN2012104828676A CN201210482867A CN102984249A CN 102984249 A CN102984249 A CN 102984249A CN 2012104828676 A CN2012104828676 A CN 2012104828676A CN 201210482867 A CN201210482867 A CN 201210482867A CN 102984249 A CN102984249 A CN 102984249A
- Authority
- CN
- China
- Prior art keywords
- cloud provider
- resource
- local
- cooperation
- price
- 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
Images
Landscapes
- Information Transfer Between Computers (AREA)
Abstract
The invention discloses a distributed resource allocation method in a horizontal dynamic cloud alliance. The method includes that a local cloud provider sets an initialized tentative resource price according to demands of the local cloud provider for resources and sends the information of the initialized tentative resource price to various cooperative cloud providers, the cooperative cloud providers enter into a competing iterative stage, the cooperative cloud providers calculate the quantity of resources which can be provided by each cooperative cloud provider and send the information of the quantity of resources to the local cloud provider according to the resource price information sent by the local cloud provider and conditions of each cooperative cloud provider, the local cloud provider calculates the total quantity of resources supplied by the cooperative cloud providers according to a received feedback message and judges whether the calculated total quantity of supplied resources is equal to the quantity of resources required by the local cloud provider or not, if the calculated total quantity of supplied resources is equal to the quantity of resources required by the local cloud provider, the competing iterative stage is stepped out, and if the calculated total quantity of supplied resources is not equal to the quantity of resources required by the local cloud provider, the local cloud provider adjusts the resource price according to a certain rule.
Description
Technical field
The present invention relates to the cloud computing field, special, the present invention is the distributed resource collocation method for the game that cooperates in cloud computing alliance.
Background technology
The cloud computing of rising is representing a kind of technical foundation that has prospect, and it has advantageous advantage in management and service side's mask of disposing based on Web, it so that some web services providers can from the present situation of self computational resource deficiency, free.The development of cloud computing is so that resource can be leased according to the operation demand by enterprise from virtual resource pool.The charge mode that this kind asked for as required is to weighing as standard service time of resource take reality.So, enterprise can be very significantly improved aspect the retractility of the investment of information technoloy equipment and service, the autgmentability and improve.
Although cloud computing has a lot of advantageous advantages for the service compute aspect in future, still there are some defectives in present itself:
1) the certain flexible autgmentability of single cloud provider's shortage
Although cloud of today provides the autgmentability that claim the commercial city can provide unlimited, even if also can face so problem but reality is maximum cloud provider: when unconfined growths of user, cloud provider also can exist and expands phenomenon limited, resource shortage.In the long run, along with the scale of cloud provider service item and the growth of userbase, the scalability problem that they face will be more and more serious.
2) lack interoperability between a plurality of cloud provider
The interoperability between the Yun Yuyun is not considered in present cloud computing in design, thereby causes being difficult to form a business cooperation partnership between the cloud provider.Simultaneously, the shortage of interoperability provides market so that middle-size and small-size cloud equipment supplier is difficult to enter cloud service.This will strangle market competition, and the consumer is confined in some fixing cloud service provider.
Along with each large enterprises disposes self cloud platform one after another, above-mentioned defective will greatly restrict each cloud provider in the service supply capacity of particular time.
In horizontal dynamic cloud alliance, different cloud providers dynamically cooperate, thus the economic interests that the maximization resources of virtual machine is created in the situation of meeting consumers' demand.In this dynamic cooperative, distributed resource policy is extremely important, also is more complicated simultaneously.Horizontal dynamic cloud alliance set up aspect alliance and the Dynamic Pricing all different from vertical supply chain union model.Therefore, a kind of new distributed resource allocation algorithm of necessary research solves this complicated problem.
Summary of the invention
The present invention is intended to can't provide in the peak traffic phase for existing cloud provider the problem of enough resources of virtual machine, proposed a kind ofly based on game theoretic cloud provider cooperation resource allocation methods, the method can effectively solve the resource provisioning problem of cloud provider in the peak traffic phase.
To achieve these goals, solve corresponding technical problem, the invention provides a kind of cooperation game Resource Allocation Formula based on price:
Step 1: local cloud provider, arranges the exploratory resource price of initialization and sends it to each cooperation cloud provider for resource requirement according to self;
Step 2: each cloud provider that cooperates enters the game iteration phase, and they are according to the resource price of local cloud provider issue and the situation of self, calculates the stock number that self can supply and sends it to local cloud provider;
Step 3: local cloud provider calculates the resource provisioning total amount of cooperation cloud provider according to the feedback information that receives, and judges the whether magnitude relationship of the stock number required with it of the resource provisioning total amount that calculates;
Step 4: if the required stock number of the resource provisioning total amount of calculating in the step 3 and local cloud provider equate, then jump out the game iteration phase;
Step 5: if the resource provisioning total amount of calculating in the step 3 is greater than the required stock number of local cloud provider, then local cloud provider will reduce resource price according to certain rule, and with the price upgraded to the issue of cooperation cloud provider, continue the repeated game iteration from step 2;
Step 6: if the resource provisioning total amount of calculating in the step 3 is less than the required stock number of local cloud provider, then resource price will improve according to certain rule in local cloud provider, and with the price upgraded to the issue of cooperation cloud provider, continue the repeated game iteration from step 2.
In step 2, cooperation cloud provider carries out can setting a threshold value in the process that the resource provisioning amount calculates, and when the resource provisioning amount that calculates during greater than threshold value, it is set to threshold value; When its value less than zero the time, the cloud provider that should cooperate removes tabulating from cooperating.
As can be seen from the above technical solutions, technical scheme of the present invention can solve the resource provisioning not enough problem of local cloud provider in the peak traffic phase well, by setting up horizontal dynamic cloud alliance with other similar cloud providers, can take full advantage of the idling-resource of the cloud provider that respectively cooperates, for whole cloud alliance creates more effectiveness.
Description of drawings
Fig. 1 is the system architecture diagram that comprises local cloud provider, cooperation cloud provider and user in the embodiment of the invention;
Fig. 2 is the flow chart that cooperation cloud provider carries out the game cooperation in the embodiment of the invention;
Embodiment
Clearer for what technical scheme advantage of the present invention was described, below in conjunction with accompanying drawing the specific embodiment of the present invention is described in further detail, obvious described embodiment is part embodiment of the present invention, rather than whole embodiment.According to embodiments of the invention, those of ordinary skill in the art can realize every other embodiment of the present invention on without the basis of creative work, all belong to protection scope of the present invention.
See accompanying drawing 1, the dynamic need that the system architecture of cloud of the present invention alliance resource allocation strategy is based on cloud provider is set up.
The entity that the present invention relates generally to has two parts: local cloud provider, cooperation cloud provider.
1, local cloud provider: as the promoter of horizontal dynamic cloud alliance, when local cloud provider predicted in the own resource deficiency in the peak traffic phase, it will initiate resource request to each cloud provider that cooperates, and the resource provisioning total amount of being responsible for the announcement resource price and gathering cooperation cloud provider, in whole resource distribution game process, it takes on a guide's role.
2, cooperation cloud provider: as the respondent of horizontal dynamic cloud alliance, the stock number that self can supply is calculated according to the resource price of announcing by cooperation cloud provider when receiving the resource request of local cloud provider, and it is fed back to local cloud provider.Cooperation cloud provider supplies with slack resources by cooperation and can obtain extra interests.The cooperation cloud provider here, when its also because face the peak traffic phase during two inadequate resources, it also can be used as local cloud provider and initiates to set up horizontal dynamic cloud alliance.
Fig. 2 is a horizontal dynamic cloud of embodiment of the invention alliance cooperation game resource distribution flow chart, specifically comprises:
Step 201: local cloud provider arranges the exploratory resource price of initialization and sends it to each cooperation cloud provider.
Local cloud provider in this step because and the stock number that can supply of the cloud provider of not knowing to cooperate, just set first an initial resource price and issue resource request information to the cooperation cloud provider of adding cloud federation protocol.
Step 202: each cloud provider that cooperates enters the game cooperation stage, according to resource price and s own situation, calculates the resource provisioning amount and numerical value is fed back to local cloud provider.
The resource provisioning amount of cloud provider of herein cooperating must satisfy greater than zero and less than its resource provisioning upper limit, if do not satisfy this condition then with this cooperation cloud provider deletion from tabulation.
Step 203: local cloud provider calculates cooperation resource provisioning total amount according to feedback information.
Step 204: local cloud provider's judgement cooperation resource provisioning total amount and resources requirement Relations Among.
Step 205: if cooperation resource provisioning total amount is not equal to resources requirement, then local cloud provider adjusts with certain principle resource price, and again to the issue of cooperation cloud provider, repeated game process.
Step 206: if cooperation resource provisioning total amount equals resources requirement, then calculate respectively respectively the cooperate effectiveness of cloud provider and the overall utility of cloud alliance.
Claims (6)
1. the distributed resource collocation method in the horizontal dynamic cloud alliance is characterized in that may further comprise the steps:
Step 1: local cloud provider, arranges the exploratory resource price of initialization and sends it to each cooperation cloud provider for resource requirement according to self;
Step 2: each cloud provider that cooperates enters the game iteration phase, and they are according to the resource price of local cloud provider issue and the situation of self, calculates the stock number that self can supply and sends it to local cloud provider;
Step 3: local cloud provider calculates the resource provisioning total amount of cooperation cloud provider according to the feedback information that receives, and judges the whether magnitude relationship of the stock number required with it of the resource provisioning total amount that calculates;
Step 4: if the required stock number of the resource provisioning total amount of calculating in the step 3 and local cloud provider equate, then jump out the game iteration phase;
Step 5: if the resource provisioning total amount of calculating in the step 3 is greater than the required stock number of local cloud provider, then local cloud provider will reduce resource price according to certain rule, and with the price upgraded to the issue of cooperation cloud provider, continue the repeated game iteration from step 2;
Step 6: if the resource provisioning total amount of calculating in the step 3 is less than the required stock number of local cloud provider, then resource price will improve according to certain rule in local cloud provider, and with the price upgraded to the issue of cooperation cloud provider, continue the repeated game iteration from step 2.
2. resource allocation method in the cloud according to claim 1 alliance is characterized in that:
In the described step 1, the local cloud provider in this step represents the initiator of horizontal dynamic cloud alliance, when it predicts own resource and can't satisfy professional ability, just initiates resource request to each cooperation cloud provider.
3. resource allocation method in the cloud according to claim 1 alliance is characterized in that:
In the described step 2, cooperation cloud provider need to cause certain cost when resource provision is provided, therefore when resource price higher, cooperation cloud provider is ready to provide more resource; Resource price is lower, otherwise then.
In the described step 2, the own resource supply that cooperation cloud provider calculates must be satisfied greater than zero and less than its threshold limit value.
4. resource allocation method in the cloud according to claim 1 alliance is characterized in that:
In the described step 3, feedback of each cooperation cloud provider is that distributed earth sends it back local cloud provider.
5. resource allocation method in the cloud according to claim 1 alliance is characterized in that:
In the described step 5, if the resource provisioning total amount of cooperation cloud provider greater than the actual demand amount of local cloud provider, resource price will be turned down at original basis of price.
6. resource allocation method in the cloud according to claim 1 alliance is characterized in that:
In the described step 6, if the resource provisioning total amount of cooperation cloud provider less than in the actual demand amount of local cloud provider, resource price will be heightened at original basis of price.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2012104828676A CN102984249A (en) | 2012-11-22 | 2012-11-22 | Distributed resource allocation method in horizontal dynamic cloud alliance |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2012104828676A CN102984249A (en) | 2012-11-22 | 2012-11-22 | Distributed resource allocation method in horizontal dynamic cloud alliance |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN102984249A true CN102984249A (en) | 2013-03-20 |
Family
ID=47857983
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2012104828676A Pending CN102984249A (en) | 2012-11-22 | 2012-11-22 | Distributed resource allocation method in horizontal dynamic cloud alliance |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102984249A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103701917A (en) * | 2013-12-31 | 2014-04-02 | 遵义天义利威机电有限责任公司 | OCF game-based context awareness incentive mechanism of smart phone |
| CN105204947A (en) * | 2015-10-15 | 2015-12-30 | 云南大学 | Hybrid cloud computing resource management system based on commercial bank model |
| CN106055425A (en) * | 2016-05-20 | 2016-10-26 | 长春理工大学 | Method for cloud disaster recovery data backup based on game theory |
| CN112465554A (en) * | 2020-12-03 | 2021-03-09 | 广东工业大学 | Block chain-based computing resource pricing method |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101170434A (en) * | 2007-09-20 | 2008-04-30 | 武汉理工大学 | Grid resource allocation method based on decomposition policy |
| CN102076025A (en) * | 2011-01-04 | 2011-05-25 | 南京邮电大学 | Stackeberg game-based cognitive network resource allocation method |
| CN102567077A (en) * | 2011-12-15 | 2012-07-11 | 杭州电子科技大学 | Virtualized resource distribution method based on game theory |
| CN102710746A (en) * | 2012-04-30 | 2012-10-03 | 电子科技大学 | Sequential-game-based virtual machine bidding distribution method |
-
2012
- 2012-11-22 CN CN2012104828676A patent/CN102984249A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101170434A (en) * | 2007-09-20 | 2008-04-30 | 武汉理工大学 | Grid resource allocation method based on decomposition policy |
| CN102076025A (en) * | 2011-01-04 | 2011-05-25 | 南京邮电大学 | Stackeberg game-based cognitive network resource allocation method |
| CN102567077A (en) * | 2011-12-15 | 2012-07-11 | 杭州电子科技大学 | Virtualized resource distribution method based on game theory |
| CN102710746A (en) * | 2012-04-30 | 2012-10-03 | 电子科技大学 | Sequential-game-based virtual machine bidding distribution method |
Non-Patent Citations (1)
| Title |
|---|
| 李志洁等: "一种基于序贯博弈的网格资源分配策略", 《软件学报》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103701917A (en) * | 2013-12-31 | 2014-04-02 | 遵义天义利威机电有限责任公司 | OCF game-based context awareness incentive mechanism of smart phone |
| CN105204947A (en) * | 2015-10-15 | 2015-12-30 | 云南大学 | Hybrid cloud computing resource management system based on commercial bank model |
| CN106055425A (en) * | 2016-05-20 | 2016-10-26 | 长春理工大学 | Method for cloud disaster recovery data backup based on game theory |
| CN106055425B (en) * | 2016-05-20 | 2018-09-18 | 长春理工大学 | Cloud disaster tolerance data back up method based on game theory |
| CN112465554A (en) * | 2020-12-03 | 2021-03-09 | 广东工业大学 | Block chain-based computing resource pricing method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wang et al. | Efficient multi-tasks scheduling algorithm in mobile cloud computing with time constraints | |
| CN103248659B (en) | A kind of cloud computing resource scheduling method and system | |
| CN101938416B (en) | Cloud computing resource scheduling method based on dynamic reconfiguration virtual resources | |
| Gao et al. | Hybrid data pricing for network-assisted user-provided connectivity | |
| US8515792B2 (en) | Method and system for chargeback allocation in information technology systems | |
| WO2019205791A1 (en) | Method and device for adjusting data plan for a plurlaity of user identifications | |
| US20150081374A1 (en) | Client-selectable power source options for network-accessible service units | |
| CN104009939B (en) | A kind of service resource allocation method and system | |
| Niu et al. | Cost-effective cloud HPC resource provisioning by building semi-elastic virtual clusters | |
| CN108170530B (en) | Hadoop load balancing task scheduling method based on mixed element heuristic algorithm | |
| CN103561055B (en) | Web application automatic elastic extended method under conversation-based cloud computing environment | |
| CN102262567A (en) | Virtual machine scheduling decision system, platform and method | |
| CN102711139B (en) | A kind of data flow statistic method and terminal | |
| CN107566133A (en) | A kind of resource billing method, device and platform | |
| KR20120105212A (en) | Cloud center controlling apparatus and cloud center selecting method of the same | |
| CN102984249A (en) | Distributed resource allocation method in horizontal dynamic cloud alliance | |
| JP2012517639A (en) | Method and system for calculating charges online based on user service volume | |
| Wang et al. | Monetizing edge service in mobile internet ecosystem | |
| CN102521662A (en) | Consumption charging method in cloud computing environment | |
| CN103336722A (en) | Virtual machine CPU source monitoring and dynamic distributing method | |
| CN104574051A (en) | Charging method and device | |
| Blackburn et al. | Last call for the buffet: economics of cellular networks | |
| CN106095581A (en) | A kind of network storage virtualization dispatching method under the conditions of privately owned cloud | |
| CN109684077A (en) | Resource dynamic allocation and feedback method and device for spark streaming | |
| CN105592160B (en) | Resource allocation method towards service consumer under a kind of cloud computing environment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| DD01 | Delivery of document by public notice |
Addressee: Beijing University of Posts and Telecommunications Document name: Notification of Publication of the Application for Invention |
|
| DD01 | Delivery of document by public notice |
Addressee: Beijing University of Posts and Telecommunications Document name: Notification of Patent Invention Entering into Substantive Examination Stage |
|
| C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20130320 |