CN102624597A - Two-way sequencing virtual network mapping method - Google Patents
Two-way sequencing virtual network mapping method Download PDFInfo
- Publication number
- CN102624597A CN102624597A CN2012100617356A CN201210061735A CN102624597A CN 102624597 A CN102624597 A CN 102624597A CN 2012100617356 A CN2012100617356 A CN 2012100617356A CN 201210061735 A CN201210061735 A CN 201210061735A CN 102624597 A CN102624597 A CN 102624597A
- Authority
- CN
- China
- Prior art keywords
- net
- request
- mapping
- empty
- scale
- 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.)
- Granted
Links
Images
Abstract
The invention provides a two-way sequencing virtual network mapping method. The method comprises the following steps of: initiatively judging a state of a current virtual networking mapping system, and calling a corresponding sequencing method; using a forward sequencing method when a revenue scale of a current virtual network is less than a scale of remaining resources of a bottom-layer physical network; using a reverse sequencing method when the revenue scale of the current virtual network is equal to or greater than the scale of the remaining resources of the bottom-layer physical network; and finally, calling a corresponding mapping algorithm to map. According to the two-way sequencing virtual network mapping method, the state of the remaining resources of the current physical network is taken fully into account, the probability of bottleneck occurred on the bottom-layer physical network under medium-sized condition is reduced, and the success rate of the virtual networking mapping and the total revenue quantity of the virtual network with successful mapping are improved. The method provided by the invention also can be used by combining with various virtual network mapping algorithms, and has the characteristic of strong expandability.
Description
Technical field
The network virtualization technology is one of important method that promotes the Internet architectural framework development; Its essence is on a public physical network, to run a plurality of virtual subnets through abstract, distribution, isolation mech isolation test independently; Each virtual subnet can use separate protocol architecture; And can carry out reasonable disposition to node and link circuit resource in the whole network according to the demand of user's dynamic change; Thereby strengthen network more flexible and diversity, realize the measurable and controllable property of network, the distribution of peak optimizating network resource and scheduling; Improve safety with service quality, reduce operation maintenance cost, in the hope of essence ground solve the Internet existing rigid, with patch be updated to main current situation.
The network virtualization technology can be used to the new network Research of structure basis of sharing the Physical Experiment network is provided; It can also be separated bottom physical facility provider and network service provider simultaneously; Allow the network of a plurality of operators to share same public bottom physical network architecture (link, switching node etc.); Each network all has the Internet resources share that can adjust flexibly again by other web influences therein; Heterogeneous networks operator can adopt the various network agreement, and the end-to-end service of innovation is provided, so network virtualization also gets a good chance of becoming a kind of main flow operation mode of future network.
Background technology
The virtual network mapping problems then is a requisite link in the network virtualization technology; Its major function is that user's virtual network request (Virtual Request) is reasonably mapped to the bottom physical network facility (Substrate Network) that operator provides; Mapping process not only will be realized the separation between the virtual network and be independent of each other; Thereby guarantee the service quality (QoS) of each virtual network user; Also to try one's best simultaneously and reasonably distribute the bottom physical network resource, improve resource utilization.
Because the diversity of virtual network request topology, and node and the consideration simultaneously of two groups of restrictive conditions of link make that a plurality of different virtual networks are mapped to a public bottom physical network becomes the NP-hard problem.For addressing this problem, lot of domestic and international researcher has proposed some based on the time window model and has realized the mapping method of suboptimal solution.The time window model is meant, the current all void net mapping request of statistics in each time window, and once shine upon, to shining upon successful request, corresponding renewal bottom physical network state; The lost request that loses of mapping is put into waiting list with request; Or directly refuse this request after satisfying certain condition.This process is as shown in Figure 1.
In Fig. 1; Before in the current time window, using mapping algorithm request being shone upon to virtual network; All will carry out preliminary treatment to the virtual network in the time window, the method that basic at present all algorithms use all is that the request of void net is sorted according to its income (Revenue) from big to small, and the basis of this method is: the bigger void net request of preferential mapping income; The successful probability of these request mappings is increased, thereby can promote the successful income quantity of overall map.But; This method is only applicable to the situation of empty net request scale less than bottom physical network surplus resources scale, and wherein, the scale of empty net and physics net is meant the node processing ability (CPU) of network or the size of link bandwidth (BW); And when empty net request scale equals bottom physical network surplus resources scale; Make can cause being mapped to power in this way and descend rapidly, the income that overall map is successful also descends rapidly, and this is because the bigger void net request of preferential mapping income under situation such as the scale of grade; Can cause the key component of the suitable physical network surplus resources of scale occupied; In the bottom physical network, produced node or link bottleneck thus, these bottlenecks will make follow-up physical network surplus resources used smoothly, are mapped to power decline thereby cause.
In addition; The situation that empty net request scale equals bottom physical network surplus resources scale is significant in void net mapping problems: at first; When void net request scale during greater than bottom physical network surplus resources scale; To the influence of mapped system with etc. the scale situation similar, the scale situation such as therefore can classify as to handle; Secondly, when void net request scale equals bottom physical network surplus resources scale, need new void net request sort method to promote the successful income quantity of overall map; The 3rd; When void net request scale during less than bottom physical network surplus resources scale; Along with the previous void net request of shining upon successfully and accomplishing service to constantly the taking of bottom physics net resource, bottom physics net surplus resources can reduce and reach situation about equating with empty net request scale gradually.In sum, it is a kind of situation of key that empty net request scale equals bottom physical network surplus resources scale, and what need that a kind of reasonable method promotes this moment is mapped to power and the successful income quantity of overall map.
Summary of the invention
The present invention has analyzed the situation that empty net request scale equals bottom physical network surplus resources scale; Find that cause the bottom physical network bottleneck to occur easily by the method that income sorts from big to small the request of void net this moment; Be that certain has shone upon successfully and takes in some key components that bigger void net request can occupy bottom physics net surplus resources; Possibly cause surplus resources to be isolated, thereby can not reduce the successful void net request total income of mapping for follow-up void net request service.In order to address this problem, a rational starting point should be: on the bottom physics net surplus resources of the scale of grade, increase the successful void net request total income of mapping as far as possible.
The present invention proposes to use empty net request by taking in the method for ordering (sorting by reversals) from small to large according to this starting point, is used for the situation that empty net request scale equals bottom physical network surplus resources scale.The method of this sorting by reversals makes that the less void net request of income is paid the utmost attention to, and has improved the success rate of mapping, has reduced the possibility that bottom physical network bottleneck occurs.Simultaneously, because void is netted reducing of granularity, physics net surplus resources has obtained utilizing more fully, and promptly the successful void net request total income of mapping is improved.
At last, the present invention is positive and negative two kinds of sort methods comprehensively, have designed a kind of virtual network mapping method of two-way ordering.In the method, before the empty net request of each mapping, all will judge the scale of empty net request of this moment and bottom physical network surplus resources, if empty net request scale less than bottom physics net surplus resources scale, is then called the forward sort method; If empty net request scale equals bottom physics net surplus resources scale, then call the sorting by reversals method.During the two-way ordering mapping method that uses down that the present invention proposes for the virtual network of routine mapping environment, the mapping incipient stage, empty network planning mould should be less than bottom physics net surplus resources scale, and should call the forward sort method this moment; But along with empty net constantly the taking of shining upon successfully and not accomplishing service to bottom physics net resource; Bottom physics net surplus resources scale begins to reduce the nearly empty net request scale of not disconnecting; Should call the sorting by reversals method this moment, to guarantee the success rate of shining upon and to avoid the bottom physical network bottleneck to occur.
The definition that the present invention relates to:
1) income (Revenue)
Revenue is meant that empty net shine upon the profit that successfully obtains, and defines according to shining upon the wide and CPU of successful empty guipure:
Revenue＝α
R∑BW
R+β
R∑CPU
R (1)
Wherein, BW
RBe that the empty guipure that shines upon successfully is wide, CPU
RBe the successful void net node cpu resource of mapping, α
RAnd β
RBe the weight coefficient that is used to regulate bandwidth and CPU, also be appreciated that the unit price that empty net service Time Bandwidth and cpu resource are provided for operator, subscript R refers to income.
The present invention; The one, the void net mapping method by the income sorting by reversals has been proposed; This method can reduce effectively in the bottom physical network surplus resources and the probability of bottleneck occurs, equals the being mapped to problem that power and mapping total income quantity fall sharply under the bottom physical network surplus resources scale situation thereby solved empty net request scale.The 2nd, two kinds of sort methods of comprehensive Direct/Reverse have proposed a kind of virtual network mapping method of two-way ordering, and this method can be judged the scale of current Internet resources, selects to use ordering forward or backwards, to adapt to various network conditions.
(1) the void net mapping method of sorting by reversals:
As stated; The existing empty method that mapping algorithm generally uses empty net request to sort from big to small by its income of netting; But this method is only applicable to the situation of empty network planning mould less than physics net surplus resources scale; And under actual conditions, the situation that empty network planning mould equals physics net surplus resources scale just more is worthy of consideration.Therefore, the present invention is directed to the situation that empty network planning mould equals physics net surplus resources scale, propose the void request of netting is taken in the method for ordering (sorting by reversals) from small to large according to it, call corresponding empty net mapping algorithm again.Like this, take in less void net request and will preferentially obtain mapping, because income scale is less, it is higher therefore to be mapped to power, and it is lower to form the probability of bottom physics net bottleneck, follow-up empty net request be mapped to the also corresponding raising of power.The advantage of above-mentioned sorting by reversals method can be represented with Fig. 2.
In Fig. 2; Traditional forward sort algorithm can preferential mapping be taken in maximum void net request a-b-c-d; Thereby in bottom physics net, form bottleneck node A, B and D, can have influence on the use of follow-up void net request, thereby cause follow-up empty net request mapping failure node C and E.And the sorting by reversals method begins mapping from taking in minimum void net request, owing to avoided the appearance of bottleneck, has therefore successfully shone upon virtual network e-f, and g-h, and i-j are mapped to power and the successful void net total income of mapping thereby promoted.In addition, this method is as the pre-treatment step of void net mapping algorithm, can use with the combination of existing empty net mapping algorithm, and the situation that empty network planning mould equals physics net surplus resources scale is played good optimization function.
(2) the virtual network mapping method of two-way ordering:
In order to tackle more general virtual network mapping scene; The present invention proposes a kind of virtual network mapping method of two-way ordering; This method is subdivided into empty net income scale with the virtual network mapping and nets the situation that income scale equals bottom physics net surplus resources scale less than the situation and the void of bottom physics net surplus resources scale; In addition; Empty net income scale is relatively more rare in practical application greater than the situation of bottom physics net surplus resources scale, and its influence to mapped system such as is similar at the scale situation, therefore also scale situation such as it classifies as is handled in the present invention.
In general virtual network mapping scene; System mode can void net income scale less than and equal constantly conversion between the situation of bottom physics net surplus resources scale, the virtual network mapping method of two-way ordering will be judged current system mode according to following expression formula before each empty net shines upon:
Wherein, The node and the link of all virtual networks of also shining upon in
and
expression current time window, the node and the link surplus resources of bottom physics network before the next empty net mapping of
and
expression is carried out.γ
ScaleBe the parameter that is used to scale situation scopes such as regulating, generally get the real number between the 0.8-1.2.If following formula be true, then system such as is at the scale situation, and the void net mapping method of two-way ordering will be selected the minimum request of income in the empty net request of residue, re-uses corresponding empty net mapping algorithm and carries out void and net and shine upon; If following formula is false; Then system is in situation on a small scale; The income of promptly empty net request is less than physics net surplus resources scale, and the void net mapping method of two-way ordering will be selected the maximum request of income in the empty net request of residue, re-uses corresponding empty net mapping algorithm and carries out the mapping of void net.
After having used the virtual network mapping method of two-way ordering; The situation that scales such as empty net request income and bottom physics net node surplus resources are checked and write off scale has obtained classification and thinning processing; The scale situation layer physical network of going to the bottom such as effectively avoided to occur the problem of bottleneck easily, the success rate that has promoted empty net mapping is taken in quantity with the successful void net of overall map.
Description of drawings
Virtual network mapping flow process under Fig. 1 time window pattern
The advantage of sorting by reversals method under the scale situation such as Fig. 2
The void net mapping method concrete steps of the two-way ordering of Fig. 3
Execution mode
Concrete operations flow process of the present invention is according to the time window mapped mode, in a time window, at first adds up all void net requests to be mapped, and selects one by one according to two-way ordering rule, and shines upon, and idiographic flow is as shown in Figure 3:
A. discharge the bottom physics net resource that the void net request left in the previous time window takies, the void net request of leaving comprises the request of the service of completion and by the initiatively request of refusal; Empty net request comprises the node request of empty net and empty network chain road request two parts;
B. add up the void net request that arrives in this time window, the void net request of arrival comprises newly arrived request and the request of requeuing, and remembers that the void net request set of this arrival is R
Ct
C. judge the state of current mapped system according to formula (2): if formula (2) be true, then system mode such as is at a scale, therefore selects the void net request of current income minimum; If formula (2) is false, then system mode is on a small scale, therefore selects the maximum void net request of current income.Calling mapping algorithm at last shines upon.
D. if current void net request is shone upon successfully among the step C, success is shone upon on promptly empty net node and empty network chain road simultaneously, then upgrades the state of bottom physical network; If mapping failure, then should the request of void net deliver to waiting list and wait for next time window, or should void net request accumulative total shine upon the frequency of failure greater than the threshold values DELAY that is provided with in advance after, directly refusal should be asked.Upgrade R
CtState.
E. repeat step C to D, until R
CtIn the empty net request of current time window number reduce to 0.
This void net mapping flow process has guaranteed that empty net request can handle in real time, and the mechanism of permitting the entrance of empty net request can control through regulating parameter (as postpone, the empty net request of refusal).
Claims (4)
1. the virtual network mapping method of a two-way ordering, carry out the virtual network mapping steps and comprise in a time window:
A. discharge the bottom physics net resource that the void net request left in the previous time window takies, the void net request of leaving comprises the request of the service of completion and by the initiatively request of refusal; Empty net request comprises the node request of empty net and empty network chain road request two parts;
B. add up the void net request that arrives in this time window, the void net request of arrival comprises newly arrived request and the request of requeuing, and the void net request set of said arrival is R
Ct
C. judge the state of current mapped system according to formula (1): if formula (1) be true, then system mode such as is at a scale, therefore selects the void net request of current income minimum, and calls mapping algorithm and shine upon; If formula (1) be false, then system mode be on a small scale, therefore selects the current void net request of taking in maximum, and calls mapping algorithm and shine upon.
D. if current void net request is shone upon successfully among the step C, success is shone upon on promptly empty net node and empty network chain road simultaneously, then upgrades the state of bottom physical network; If mapping failure, then should the request of void net deliver to waiting list and wait for next time window, or should void net request accumulative total shine upon the frequency of failure greater than the threshold values DELAY that is provided with in advance after, directly refusal should be asked.Upgrade R
CtState.
E. repeat step C to D, until R
CtIn the empty net request of current time window number reduce to 0.
Above-mentioned formula (1) does
2. the method for claim 1; Wherein, The node and the link of all virtual networks of also shining upon in
and
expression current time window; Before the next empty net mapping of
and
expression is carried out, the node of bottom physical network and link surplus resources.γ
ScaleBe the parameter that is used to scale situation scopes such as regulating, generally get the real number between the 0.8-1.2.If following formula be true, then system such as is at the scale situation, and the void net mapping method of two-way ordering will select to take in the empty net request of residue the request of minimum; If following formula is false; Then system is in situation on a small scale; The income of promptly empty net request is less than physics net surplus resources scale, and the void net mapping method of two-way ordering will be selected the maximum request of income in the empty net request of residue, and this mapping method will use the net mapping algorithm to carry out the mapping of void net at last.
3. the method for claim 1, wherein
Income is meant that empty net shines upon the profit that successfully obtains, and defines according to the empty guipure wide (BW) and the CPU that shine upon successfully:
Revenue＝α
R∑BW
R+β
R∑CPU
R
Wherein, BW
RBe that the empty guipure that shines upon successfully is wide, CPU
RBe the successful void net node cpu resource of mapping, α
RAnd β
RBe the weight coefficient that is used to regulate bandwidth and CPU, subscript R refers to Revenue (income).
4. method as claimed in claim 2, the void net mapping algorithm that said mapping method uses are to accomplish the mapping algorithm of single empty net mapping.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210061735.6A CN102624597B (en) | 2012-03-09 | 2012-03-09 | Two-way sequencing virtual network mapping method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210061735.6A CN102624597B (en) | 2012-03-09 | 2012-03-09 | Two-way sequencing virtual network mapping method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102624597A true CN102624597A (en) | 2012-08-01 |
| CN102624597B CN102624597B (en) | 2014-12-17 |
Family
ID=46564288
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210061735.6A Active CN102624597B (en) | 2012-03-09 | 2012-03-09 | Two-way sequencing virtual network mapping method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102624597B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103763174A (en) * | 2014-01-08 | 2014-04-30 | 浙江工商大学 | Virtual network mapping method based on function block |
| CN106301924A (en) * | 2016-08-18 | 2017-01-04 | 北京邮电大学 | A kind of mapping method of virtual network and device |
| CN107360031A (en) * | 2017-07-18 | 2017-11-17 | 哈尔滨工业大学 | It is a kind of based on optimization overhead gains than mapping method of virtual network |
| CN108809699A (en) * | 2018-05-22 | 2018-11-13 | 哈尔滨工业大学 | A method of realizing that large-scale virtual network node repeats to map |
| CN110958144A (en) * | 2019-11-29 | 2020-04-03 | 腾讯科技（深圳）有限公司 | Method and device for acquiring network |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2000051298A1 (en) * | 1999-02-26 | 2000-08-31 | Redstone Communications, Inc. | Network router search engine using compressed tree forwarding table |
| CN1520550A (en) * | 2001-04-20 | 2004-08-11 | �������չɷ�����˾ | Virtual networking system and method in processing system |
| CN1664791A (en) * | 2004-03-05 | 2005-09-07 | 中国科学院计算技术研究所 | Virtual storing model and method thereof |
| CN102075402A (en) * | 2011-02-12 | 2011-05-25 | 华为技术有限公司 | Virtual network mapping processing method and system |
| CN102075429A (en) * | 2011-01-21 | 2011-05-25 | 北京邮电大学 | Virtual network mapping method based on principle of proximity |
-
2012
- 2012-03-09 CN CN201210061735.6A patent/CN102624597B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2000051298A1 (en) * | 1999-02-26 | 2000-08-31 | Redstone Communications, Inc. | Network router search engine using compressed tree forwarding table |
| CN1520550A (en) * | 2001-04-20 | 2004-08-11 | �������չɷ�����˾ | Virtual networking system and method in processing system |
| CN1664791A (en) * | 2004-03-05 | 2005-09-07 | 中国科学院计算技术研究所 | Virtual storing model and method thereof |
| CN102075429A (en) * | 2011-01-21 | 2011-05-25 | 北京邮电大学 | Virtual network mapping method based on principle of proximity |
| CN102075402A (en) * | 2011-02-12 | 2011-05-25 | 华为技术有限公司 | Virtual network mapping processing method and system |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103763174A (en) * | 2014-01-08 | 2014-04-30 | 浙江工商大学 | Virtual network mapping method based on function block |
| CN103763174B (en) * | 2014-01-08 | 2017-02-22 | 浙江工商大学 | Virtual network mapping method based on function block |
| CN106301924A (en) * | 2016-08-18 | 2017-01-04 | 北京邮电大学 | A kind of mapping method of virtual network and device |
| CN107360031A (en) * | 2017-07-18 | 2017-11-17 | 哈尔滨工业大学 | It is a kind of based on optimization overhead gains than mapping method of virtual network |
| CN107360031B (en) * | 2017-07-18 | 2020-04-14 | 哈尔滨工业大学 | Virtual network mapping method based on optimized overhead-to-revenue ratio |
| CN108809699A (en) * | 2018-05-22 | 2018-11-13 | 哈尔滨工业大学 | A method of realizing that large-scale virtual network node repeats to map |
| CN108809699B (en) * | 2018-05-22 | 2021-04-09 | 哈尔滨工业大学 | Method for realizing large-scale virtual network node repeated mapping |
| CN110958144A (en) * | 2019-11-29 | 2020-04-03 | 腾讯科技（深圳）有限公司 | Method and device for acquiring network |
| CN110958144B (en) * | 2019-11-29 | 2021-06-22 | 腾讯科技（深圳）有限公司 | Method and device for acquiring network |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102624597B (en) | 2014-12-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102075429B (en) | Virtual network mapping method based on principle of proximity | |
| CN106330576A (en) | Automatic scaling and migration scheduling method, system and device for containerization micro-service | |
| CN102624597B (en) | Two-way sequencing virtual network mapping method | |
| CN103559219B (en) | Distributed network crawler capturing method for scheduling task, dispatching terminal equipment and crawl node | |
| CN103617062B (en) | The render farm Dynamic Deployment System of a kind of flexibility and method | |
| CN104951372A (en) | Method for dynamic allocation of Map/Reduce data processing platform memory resources based on prediction | |
| CN106445675B (en) | B2B platform distributed application scheduling and resource allocation method | |
| CN102546232B (en) | Multi-topology mapping method of virtual network | |
| CN105554102A (en) | Elastic expansion method based on container cluster and application system thereof | |
| CN106572019A (en) | Network energy-saving flow scheduling method based on mixing of time delay guaranteeing and SDN | |
| CN104270421B (en) | A kind of multi-tenant cloud platform method for scheduling task for supporting Bandwidth guaranteed | |
| CN105446810B (en) | More farm cloud rendering task dissemination systems based on cost price and method | |
| CN112492003B (en) | Cloud network convergence service processing method and device based on service orchestrator | |
| CN103888371B (en) | A kind of method and apparatus of virtual network mapping | |
| CN105721354B (en) | Network-on-chip interconnected method and device | |
| CN107276664B (en) | Mixing void net mapping method based on the load of thresholding formula | |
| CN113641417B (en) | Vehicle security task unloading method based on branch-and-bound method | |
| CN111127154A (en) | Order processing method, device, server and nonvolatile storage medium | |
| WO2020134133A1 (en) | Resource allocation method, substation, and computer-readable storage medium | |
| CN107124303A (en) | The service chaining optimization method of low transmission time delay | |
| CN107147734A (en) | A kind of network traffics thread-level dynamic load balancing method and system based on two level forwarding | |
| CN109951311A (en) | Method, apparatus, equipment and the storage medium of network slice instantiation | |
| CN106028453B (en) | Wireless dummy network resource cross-layer scheduling mapping method based on queueing theory | |
| CN102082732A (en) | Virtual network energy saving method based on virtual router on the move (VROOM) | |
| CN106775961A (en) | A kind of method of cross-system data and signal transmission |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |