CN110190988A - A kind of service deployment method and device - Google Patents

A kind of service deployment method and device Download PDF

Info

Publication number
CN110190988A
CN110190988A CN201910411785.4A CN201910411785A CN110190988A CN 110190988 A CN110190988 A CN 110190988A CN 201910411785 A CN201910411785 A CN 201910411785A CN 110190988 A CN110190988 A CN 110190988A
Authority
CN
China
Prior art keywords
business
disposed
deployment
network
target
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
Application number
CN201910411785.4A
Other languages
Chinese (zh)
Other versions
CN110190988B (en
Inventor
郑毅
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
China United Network Communications Group Co Ltd
Original Assignee
China United Network Communications Group Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by China United Network Communications Group Co Ltd filed Critical China United Network Communications Group Co Ltd
Priority to CN201910411785.4A priority Critical patent/CN110190988B/en
Publication of CN110190988A publication Critical patent/CN110190988A/en
Application granted granted Critical
Publication of CN110190988B publication Critical patent/CN110190988B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • 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
    • 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
    • H04L41/14—Network analysis or design
    • H04L41/145—Network analysis or design involving simulating, designing, planning or modelling of a network
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L47/00—Traffic control in data switching networks
    • H04L47/70—Admission control; Resource allocation
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L47/00—Traffic control in data switching networks
    • H04L47/70—Admission control; Resource allocation
    • H04L47/80—Actions related to the user profile or the type of traffic
    • H04L47/805—QOS or priority aware

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Data Exchanges In Wide-Area Networks (AREA)
  • Telephonic Communication Services (AREA)

Abstract

The embodiment of the present invention provides a kind of service deployment method and apparatus, is related to the communications field, can guarantee that quality guarantees resource utilization again in the business of deployment.This method comprises: obtain the business to be disposed in current deployment cycle business KPI data and required virtual machine quantity, network environment parameters, the virtual machine quantity that DC can be disposed and its related link circuits first network KPI data；The corresponding second network KPI data of business to be disposed is obtained according to mapping function is preset；The priority of business to be disposed is determined according to the second network KPI data；According to the sequence of priority from high to low, according to the second network KPI data, wait the business of disposing needed for virtual machine quantity, the virtual machine quantity for the data center DC that can be disposed and first network KPI data, sequentially generate each target deployment scheme for waiting for deployment business；The target deployment scheme of business to be disposed is sent to network controller and cloud system, is disposed so that it treats deployment business.

Description

A kind of service deployment method and device
Technical field
The present invention relates to the communications field more particularly to a kind of service deployment method and devices.
Background technique
With Internet of Things, the development of cloud computing, user proposes higher and higher demand to quality of service.Current techniques side In case, in order to meet the quality requirement of customer service usually there are two types of method: one is by from network perspective, using SDN The scheme of (Network Defined Software, software defined network) flow scheduling, it is shorter by being selected for Business Stream Path simultaneously configures QoS (Quality of Service, service quality) priority to improve quality of service.But the pole of this scheme Limit effect is still limited by transmission range.I.e. time delay can not be less than straight from DC (Data Center, data center) to user side Time delay needed for linear distance optical transport.Another method is by service deployment in the fringe node close to user.But due to edge Number of nodes is huge, and the number of users that each node is serviced is little.So small-sized DC would generally be selected to be disposed.And these are saved Point is often limited by power supply or space, and scalability is extremely limited, is less likely for all business to be all deployed in simultaneously all Fringe node.In addition, the scheme of all fringe nodes of dilatation inherently expends a large amount of construction costs.
In existing solution, the place that mainly there are following several respects to be left to be desired: 1) customer service experience simultaneously by The influence of network state and deployed position.But the prior art usually only considers to change network means or deployed position to solve to ask Topic, without organically combining the two, does not account for the economic benefit of deployment scheme yet.2) there are multi-services to be deployed in edge Adjusted Option when node, when not accounting for beyond office's room capacity.3) when ensureing user quality, network index is mostly used greatly Such as bandwidth mode, without the production practical to business such as the virtual condition (such as whether congestion, network physical condition) of consideration network Raw influence, i.e., identical network KPI (Key Performance Indicator, KPI Key Performance Indicator) (bandwidth, time delay) exist (time, concurrent user number, place) etc. may provide different business KPI under different external condition.So on the whole, Existing service deployment scheme in the case where guaranteeing quality of service for that cannot reach the peak use rate of resource.
Summary of the invention
The embodiment of the present invention provides a kind of service deployment method, while for guaranteeing quality of service in the business of deployment Improve network resource utilization.
In order to achieve the above objectives, the embodiment of the present invention adopts the following technical scheme that
In a first aspect, providing a kind of service deployment method, comprising:
It obtains at least one in current deployment cycle and waits for the business KPI Key Performance Indicator KPI data of deployment business, to portion The virtual machine quantity for the data center DC that virtual machine quantity, network environment parameters needed for administration's business, business to be disposed can dispose And the first network KPI data of the associated link of DC；
According to business KPI data and network environment parameters, business to be disposed corresponding the is obtained according to mapping function is preset Two network KPI datas；
The priority of business to be disposed is determined according to the corresponding second network KPI data of business to be disposed；
According to the sequence of priority from high to low, according to the corresponding second network KPI data of business to be disposed, industry to be disposed The virtual machine quantity of data center DC that virtual machine quantity needed for business, business to be disposed can dispose and the associated link of DC First network KPI data sequentially generates each target deployment scheme for waiting for deployment business；Target deployment scheme includes target portion Affix one's name to DC and target deployment link；
The target deployment scheme of business to be disposed is sent to network controller and cloud system, so that network controller and cloud System is treated deployment business according to the target deployment scheme of business to be disposed and is disposed.
Service deployment method provided by the above embodiment, the first industry by acquiring business to be disposed in current deployment cycle Business KPI data, the data center that can be disposed wait virtual machine quantity, network environment parameters needed for the business of disposing, business to be disposed The first network KPI data of the associated link of virtual machine quantity and DC of DC, then according to the business KPI number of business to be disposed According to the corresponding network KPI parameter for obtaining business to be disposed according to default mapping function with external environment data, then according to each The corresponding network KPI parameter of business to be disposed carries out the division of priority to it, so that it is determined that the elder generation disposed in the business of deployment It, then then can be according to the network KPI that respectively business to be disposed needs afterwards sequentially to guarantee the quality of service of each business to be disposed The network KPI parameter of the virtual machine quantity and DC related link circuits of data and virtual machine quantity and its DC that can be disposed, according to excellent The sequence of first grade from high to low is each corresponding target deployment scheme of service generation to be disposed；Finally send target deployment To network controller and cloud system, so that network controller and cloud system treat deployment business carry out portion according to target deployment scheme Administration.Because combining network environment parameters, business KPI data and default mapping letter during generating target deployment scheme After number obtains network KPI parameter, the thought cooperateed with cloud net, not only only from network facet (network KPI) or office Fang Ziyuan The single factor of aspect (the virtual machine quantity of DC) considers, but the two is combined to codetermine deployment scheme, in addition because in advance The priority of each business to be disposed is determined, and first determines that the high rear determination of priority is excellent when determining deployment scheme First grade is low, is also achieved that and utmostly guarantees rationally effectively to be assigned with while each quality requirement of business to be disposed Internet resources improve resource utilization.
Second aspect provides a kind of service deployment device, comprising: obtain module, mapping block, Priority Determination module, Processing module and sending module；
Module is obtained, the business KPI Key Performance Indicator of deployment business is waited for for obtaining at least one in current deployment cycle KPI data, the data center DC that can be disposed wait virtual machine quantity, network environment parameters needed for the business of disposing, business to be disposed Virtual machine quantity and the associated link of DC first network KPI data；
Mapping block, business KPI data and network environment parameters for being obtained according to module is obtained, according to default mapping Function obtains the corresponding second network KPI data of business to be disposed；
Priority Determination module, the corresponding network KPI data of business to be disposed for being obtained according to mapping block determine The priority of business to be disposed；
Processing module, the sequence of priority from high to low for being determined according to Priority Determination module, according to mapping mould Block obtain the corresponding second network KPI data of business to be disposed, obtain module obtain wait virtual machine needed for the business of disposing What quantity, the virtual machine quantity for obtaining the data center DC that the business to be disposed that module obtains can dispose and acquisition module obtained The first network KPI data of the associated link of DC sequentially generates each target deployment scheme for waiting for deployment business；Target deployment Scheme includes target deployment DC and target deployment link；
The target deployment scheme of sending module, the business to be disposed for generating processing module is sent to network controller And cloud system, so that network controller and cloud system treat deployment business carry out portion according to the target deployment scheme of business to be disposed Administration.
The third aspect provides a kind of service deployment device, including memory, processor, bus and communication interface；Memory For storing computer executed instructions, processor is connect with memory by bus；When the operation of service deployment device, processor The computer executed instructions of memory storage are executed, so that service deployment device executes the business department's management side provided such as first aspect Method.
Fourth aspect provides a kind of computer storage medium, including computer executed instructions, when computer executed instructions exist When being run on computer, so that computer executes the service deployment method provided such as first aspect.
5th aspect, provides a kind of service deployment system, the service deployment device provided including second aspect.
Service deployment method and device provided in an embodiment of the present invention, this method comprises: obtaining in current deployment cycle At least one waits for the business KPI Key Performance Indicator KPI data of deployment business, wait virtual machine quantity, network rings needed for the business of disposing The virtual machine quantity for the data center DC that border parameter, business to be disposed can dispose and the first network KPI of the associated link of DC Data；According to business KPI data and network environment parameters, corresponding second net of business to be disposed is obtained according to mapping function is preset Network KPI data；The priority of business to be disposed is determined according to the corresponding second network KPI data of business to be disposed；According to preferential Grade sequence from high to low, according to the corresponding second network KPI data of business to be disposed, wait the business of disposing needed for virtual machine number The virtual machine quantity for the data center DC that amount, business to be disposed can dispose and the first network KPI data of the associated link of DC, Sequentially generate each target deployment scheme for waiting for deployment business；Target deployment scheme includes target deployment DC and target deployment chain Road；The target deployment scheme of business to be disposed is sent to network controller and cloud system, so that network controller and cloud system Deployment business is treated according to the target deployment scheme of business to be disposed to be disposed.Business department's management side provided in an embodiment of the present invention Method, first by acquiring the business KPI data of business to be disposed in current deployment cycle, wait virtual machine number needed for the business of disposing The of the virtual machine quantity of the data center DC that amount, network environment parameters, business to be disposed can dispose and the associated link of DC Then one network KPI data is obtained according to the business KPI data of business to be disposed and external environment data according to mapping function is preset The corresponding network KPI parameter of business to be disposed is taken, then it is carried out according to the respectively corresponding network KPI parameter of business to be disposed The division of priority, so that it is determined that the sequencing disposed in the business of deployment is to guarantee the business matter of each business to be disposed Amount, then then can be according to the network KPI data and virtual machine quantity and its DC that can be disposed that respectively business to be disposed needs The network KPI parameter of virtual machine quantity and DC related link circuits is each business to be disposed according to the sequence of priority from high to low Generate corresponding target deployment scheme；Target deployment is finally sent to network controller and cloud system, so that network-control Device and cloud system are treated deployment business according to target deployment scheme and are disposed.Because in the process for generating target deployment scheme In, after combining network environment parameters, business KPI data and default mapping function to obtain network KPI parameter, cooperateed with cloud net Thought, not only only (the virtual machine quantity of DC) single factor is examined in terms of network facet (network KPI) or office's room resource Consider, but the two is combined to codetermine deployment scheme, in addition because having been carried out really to the priority of each business to be disposed in advance It is fixed, and first determine that the high rear determining priority of priority is low when determining deployment scheme, it is also achieved that and utmostly guarantees Internet resources are rationally effectively each assigned with while the quality requirement of business to be disposed, are improved resource utilization.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this Some embodiments of invention for those of ordinary skill in the art without creative efforts, can be with It obtains other drawings based on these drawings.
Fig. 1 is a kind of flow diagram of service deployment method provided in an embodiment of the present invention；
Fig. 2 be another embodiment of the present invention provides a kind of service deployment method flow diagram；
Fig. 3 is a kind of service deployment example schematic provided in an embodiment of the present invention；
Fig. 4 is a kind of structural schematic diagram of service deployment device provided in an embodiment of the present invention；
Fig. 5 is a kind of structural schematic diagram of service deployment system provided in an embodiment of the present invention；
Fig. 6 is the structural schematic diagram of another service deployment device provided in an embodiment of the present invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other Embodiment shall fall within the protection scope of the present invention.
It should be noted that in the embodiment of the present invention, " illustrative " or " such as " etc. words make example, example for indicating Card or explanation.Be described as in the embodiment of the present invention " illustrative " or " such as " any embodiment or design scheme do not answer It is interpreted than other embodiments or design scheme more preferably or more advantage.Specifically, " illustrative " or " example are used Such as " word is intended to that related notion is presented in specific ways.
It should also be noted that, in the embodiment of the present invention, " (English: of) ", " corresponding (English: Corresponding, relevant) " it sometimes can be mixed with " corresponding (English: corresponding) ", it should be pointed out that It is that, when not emphasizing its difference, meaning to be expressed is consistent.
For the ease of clearly describing the technical solution of the embodiment of the present invention, in an embodiment of the present invention, use " the One ", the printed words such as " second " distinguish function and the essentially identical identical entry of effect or similar item, and those skilled in the art can To understand that the printed words such as " first ", " second " are not to be defined to quantity and execution order.
Existing service deployment scheme, when designing deployment scheme, usually only by considering to change network configuration or only By considering that deployed position determines final deployment scheme, the two is not organically combined, do not account for yet network environment because Influence of the element to quality of service, so under normal circumstances, can only guarantee quality of service to a certain extent in deployment, for net The utilization rate of network resource is lower.
In view of the above-mentioned problems, the embodiment of the present invention provides a kind of service deployment method shown in referring to Fig.1, comprising:
101, obtain at least one in current deployment cycle wait for deployment business business KPI Key Performance Indicator KPI data, Virtual machine wait the data center DC that virtual machine quantity, network environment parameters needed for the business of disposing, business to be disposed can dispose The first network KPI data of quantity and the associated link of DC.
Specifically, the service deployment scheme is for an area (such as Beijing) or region (such as Haidian District), In practice generally can from from operation system obtain for area or for the business KPI data for needing the business of being disposed in region with And for area or for the network environment parameters in region, the void for the DC that each business to be disposed can dispose is obtained from cloud system Quasi- machine quantity, obtains the first network KPI data of the associated link of each DC from monitoring network quality system.
Illustratively, when the business of disposing is web-browsing service, the business KPI parameter that business KPI data includes is extremely It is few are as follows: domain name system DNS parses the time, the transmission control protocol TCP link setup time, redirects time, peak download rate and head Shield the time；
When business to be disposed is OTT (Over The Top, internet television) video traffic, business KPI data includes Business KPI parameter at least are as follows: dns resolution time, mean 0100 calorie immediately between, fragment is averaged speed of download and Caton rate.
Illustratively, the network KPI parameter that first network KPI data includes is at least are as follows: time delay, packet loss, bandwidth and shake.
102, according to business KPI data and network environment parameters, it is corresponding that business to be disposed is obtained according to default mapping function The second network KPI data.
Specifically, default mapping function is using artificial intelligence to the previous business KPI data for having disposed business, history Network environment parameters and disposed network KPI data that the network KPI data of business is obtained using the method for machine learning and The mapping function of business KPI data and network environment data；The specific formula of the mapping function specifically obtained such as following formula:
(s1,s2,s3,...sx)=F (n1,n2,n3,...ny；e1,e2,e3,...ez)；
Wherein, s1, s2, s3... sxFor the value of different business KPI parameters, n1, n2, n3... nxFor different network KPI Parameter, e1, e2, e3... exFor different network environment parameters (such as time, voice and packet data concurrent service number etc.), F is mapping function；
Under conditions of historical data abundance, above-mentioned mapping function will be more acurrate, in practice in order to be reflected faster It penetrates as a result, mapping function generally described above can be converted into the i.e. any group of business KPI parameter and any group of network rings that mapping table uses The corresponding one group of determining network KPI parameter of border parameter.
103, the priority of business to be disposed is determined according to the corresponding second network KPI data of business to be disposed.
Specifically, because every kind of business quality requirement when it is different, experience be exactly corresponding network KPI in data It is different when data, so needing to determine each business to be disposed to quality of service according to network KPI data in deployment Desirability, that is, priority, the priority the high then higher to the desirability of quality of service, because the higher deployment of quality requirement It is required that it is also higher, it just can guarantee quality of service so needing to dispose in advance in the case where Internet resources abundance, so rear It then needs to pay the utmost attention to dispose this kind of quality requirement high business when continuous deployment scheme determines.
Optionally, referring to shown in Fig. 2,103 steps are specifically included:
1031, the target instruction target word of the corresponding user terminal of the business to be disposed of acquisition first.
Wherein, target instruction target word is at least used for the priority of specified business to be disposed, and the first business to be disposed is at least one To any business to be disposed in deployment business.
1032, the priority of the first business to be disposed is determined according to target instruction target word.
Specifically, considering when the priority for the business of disposing, because its quality of service mainly will meet user to industry The demand of business, so should be with priority that user specifies for the first standard, other factors are as the second standard；It is mentioned here The priority that the priority that user specifies can be the business that user needs it is specified, can be user itself in operator Locating grade (such as consumption grade) in client, is also possible to user all with identical wait dispose the grade in user (such as member vip grade).
1033, the priority of the second business to be disposed is determined according to the corresponding network KPI data of the second business to be disposed.
Wherein, the second business to be disposed be at least one wait in deployment business in addition to first wait the business of disposing wait dispose Any of business.
Specifically, determining the excellent of a part of deployment business i.e. first business to be disposed in the priority specified according to user After first grade, remaining second business to be disposed then needs to determine priority according to its corresponding network KPI data；It is exemplary , when the network KPI parameter for including in the second network KPI data be time delay and bandwidth when, delay requirement height (small) second to The priority of deployment business is high, and in the identical situation of time delay, bandwidth demand is smaller, and priority is higher.
104, the sequence according to priority from high to low, according to the corresponding second network KPI data of business to be disposed, to portion The virtual machine quantity and the associated chain of DC for the data center DC that virtual machine quantity, business to be disposed needed for administration's business can dispose The first network KPI data on road sequentially generates each target deployment scheme for waiting for deployment business；Target deployment scheme includes mesh Mark deployment DC and target deployment link.
Optionally, referring to shown in Fig. 2,104 steps are specifically included:
1041, the sequence according to priority from high to low, according to the corresponding second network KPI data of business to be disposed, to The virtual machine quantity and DC for the data center DC that virtual machine quantity, business to be disposed needed for deployment business can dispose are associated The first network KPI data of link successively determines that each waits for the first deployment scheme of deployment business；First deployment scheme includes First deployment DC and the first deployment link.
1042, the resource supply and demand ratio in the first deployment scheme of business to be disposed is calculated；Resource supply and demand ratio includes the first confession Need to than with the second supply and demand ratio.
Wherein, the first supply and demand ratio is the first network KPI parameter in the corresponding second network KPI data of business to be disposed Value, with wait the business of disposing it is corresponding first deployment link first network KPI data in first network KPI parameter when current The ratio of the value at quarter；First network KPI parameter is the resources-type network KPI parameter that any one can be consumed by business to be disposed.
Second supply and demand ratio is wait virtual machine quantity needed for the business of disposing, and first deployment DC corresponding with business to be disposed exists The ratio of the virtual machine quantity at current time.
1043, by the product of all first supply and demand ratios in the first deployment scheme of business to be disposed, with business to be disposed The first deployment scheme in the second supply and demand ratio product be determined as business to be disposed the first deployment scheme total supply and demand ratio.
1044, when determining that at least one waits in deployment business in the presence of can not determine the third industry to be disposed of the first deployment scheme When business, according to the sequence of priority from low to high, be sequentially adjusted at least one wait in deployment business except third wait for deployment business with The target deployment scheme of the 4th outer business to be disposed, waiting for deployment business until third, there are until the first deployment scheme.
Wherein, the 4th target deployment scheme after disposing business reorganization is not that total supply and demand ratio of business to be disposed is the smallest First deployment scheme.
1045, the smallest first deployment scheme of total supply and demand ratio of business to be disposed is determined as to the target portion of business to be disposed Management side case.
Specifically, then illustrating that remaining resource is more because supply and demand ratio is smaller, more utilizing the portion to subsequent business to be disposed Administration, is equivalent to and improves resource utilization.
Illustratively, it in order to better illustrate above-mentioned 104 step, is illustrated below with specific example:
Referring to shown in Fig. 3, by taking network KPI includes time delay and bandwidth as an example, smiling face refers to that user terminal, DC1 and DC2 are in figure Two can be used to dispose user terminal demand business to be disposed data center, E1, E2, C1 and C2 be specific data transmit Link；
From monitoring network quality system it is available to each link time delay and available bandwidth it is as shown in the table:
Link name This Duan Shiyan Bandwidth
E1 1ms 10M
E2 3ms 20M
C1 5ms 20M
C2 8ms 50M
Table 1
The virtual machine quantity of DC1 is 100, and the virtual machine quantity of DC2 is 1000；The business to be disposed of user terminal has Four, wherein A4 business assigned priority is 4 grades, the priority of four business to be disposed, required virtual machine quantity and respective KPI parameter request in second network KPI data is as follows:
Business Name Delay requirement Bandwidth demand Virtual machine demand Priority
A1 2ms 1M 20 1
A2 4ms 4M 40 2
A3 9ms 8M 30 3
A4 5ms 10M 30 4
Table 2
Wherein, 1 grade of highest priority, 4 grades minimum；
In setting above three when the target deployment scheme of deployment business, need first, in accordance with priority from high to low Sequence successively determines the first deployment scheme that three deployment schemes may be implemented:
(1) for business A1, the link for being able to satisfy time delay, bandwidth and virtual machine quantity demand has E1；
When selecting E1, bandwidth demand and supply ratio are as follows: 1M/10M, the demand and supply ratio of virtual machine are as follows: 20/100；So making With link E1 by A1 be deployed in DC1 deployment scheme aggregate demand/supply than (i.e. above-mentioned total supply and demand ratio) are as follows: K1=(1/ 10)*(20/100)；
Because only that one kind can deployment scheme i.e. the first deployment scheme, so selection scheme K1.Business A1 is deployed in DC1, Selection link E1 is transmitted.
Resources left situation after the completion of A1 deployment becomes:
Project Bandwidth or virtual machine surplus
E1 9M
E2 20M
C1 20M
C2 50M
DC1 80
DC2 1000
Table 3
(2) for business A2, the chain of time delay, bandwidth and virtual machine quantity demand is able to satisfy according to table 1, table 2 and table 3 There are E1 and E2 in road；
When selecting E1, bandwidth demand and supply ratio are as follows: 4M/9M, the demand and supply ratio of virtual machine are as follows: 40/80；So using A1 is deployed in aggregate demand/supply ratio of the deployment scheme of DC1 by link E1 are as follows: K1=(4/9) * (40/80)；
When selecting E2, bandwidth demand and supply ratio are as follows: 4M/20M, the demand and supply ratio of virtual machine are as follows: 40/80；So making A1 is deployed in aggregate demand/supply ratio of the deployment scheme on DC1 with link E2 are as follows: K2=(4/20) * (40/80)；
Wherein, because of K2 < K1, selection scheme K2.Business A2 is deployed in DC1, and link E2 is selected to be transmitted.
Resources left situation after the completion of A2 deployment becomes:
Table 4
(3) for business A3, according to table 1, table 2 and table 4, determine that the link for being able to satisfy demand has: E1, E2, C1+E1, C1+ E2；
When selecting E1, bandwidth demand and supply ratio are as follows: 8M/9M；The demand and supply ratio of virtual machine are as follows: 30/40；So using A3 is deployed in aggregate demand/supply ratio of the deployment scheme on DC1 by link E1 are as follows: K1=(8/9) * (30/40)；
When selecting E2, bandwidth demand and supply ratio are as follows: 8M/16M；The demand and supply ratio of virtual machine are as follows: 30/40；So making A3 is deployed in aggregate demand/supply ratio of the deployment scheme on DC1 with link E2 are as follows: K2=(8/16) * (30/40)；
When selecting C1+E1, bandwidth demand and supply ratio are as follows: E1 8M/9M；C1 is 8M/16M；Since in service deployment, one The supply and demand ratio of a whole set of link should be subject to the supply and demand ratio of the maximum link of supply and demand ratio, therefore, the bandwidth of entire C1+E1 link Demand is 8M/9M than the calculating according to E1；The demand and supply ratio of virtual machine are as follows: 30/1000；So will using link C1+E1 A3 is deployed in aggregate demand/supply ratio of the deployment scheme on DC2 are as follows: K3=(8/9) * (30/1000)；
When selecting C1+E2, bandwidth demand and supply ratio are as follows: E2 8M/16M；C1 is 8M/20M；Therefore, the band of entire link Wide demand is 8M/16M than the calculating according to E2；The demand and supply ratio of virtual machine are as follows: 30/1000；So using link C1+ A3 is deployed in aggregate demand/supply ratio of the deployment scheme on DC2 by E2 are as follows: K4=(8/16) * (30/1000)；
The supply and demand ratio of above-mentioned four kinds of schemes is compared, aggregate demand/supply ratio the smallest K4 of value is selected.That is: business A3 deployment In DC2, link C1+E2 is selected to be transmitted.
Then resources left situation becomes after the completion of A3 deployment:
Table 5
(4) for business A4, according to table 1, table 2 and table 4, determine that the link for being able to satisfy delay requirement has: E1 and E2, it can The DC of deployment is DC1, but E1 and E2 current remaining bandwidth is insufficient, so needing the successively deployment to A3, A2 and A1 at this time Scheme is adjusted that have until A4 can be until deployment scheme, in general, can be by target deployment project setting first in adjustment Total supply and demand ratio is merely greater than the first deployment scheme of previously determined target deployment scheme；According to above-mentioned calculating process, it can be deduced that It needs for the deployment scheme of A3 to be adjusted to the corresponding scheme of K3, i.e., A3 is deployed on DC2 using link C1+E1, A4 is just at this time There is the first deployment scheme that can be disposed, i.e., A4 be deployed on DC1 using link E2 because A4 only have this first Deployment scheme, so its final target deployment scheme is the program.
Then resources left situation becomes after A3 adjustment and after the completion of A4 deployment:
Project Bandwidth or virtual machine surplus
E1 1M
E2 6M
C1 15M
C2 50M
DC1 10vm
DC2 970vm
Table 6
Deployment business (i.e. the 4th industry to be disposed is waited for it should be noted that can also exist howsoever adjust other in practice Business) target deployment scheme can not all make A4 (i.e. above-mentioned third waits for deployment business) there are the first deployment schemes, if such as It when the virtual machine quantity of A4 demand is 50, just cannot dispose forever, then need to abandon at this time to dispose A4.
105, the target deployment scheme of business to be disposed is sent to network controller and cloud system, so that network controller Deployment business is treated according to the target deployment scheme of business to be disposed with cloud system to be disposed.
Service deployment method provided in an embodiment of the present invention, this method comprises: obtaining at least one in current deployment cycle The business KPI Key Performance Indicator KPI data of a business to be disposed is joined wait virtual machine quantity needed for the business of disposing, network environment The virtual machine quantity for the data center DC that number, business to be disposed can dispose and the first network KPI data of the associated link of DC； According to business KPI data and network environment parameters, the corresponding second network KPI of business to be disposed is obtained according to mapping function is preset Data；The priority of business to be disposed is determined according to the corresponding second network KPI data of business to be disposed；According to priority by height To low sequence, according to the corresponding second network KPI data of business to be disposed, wait the business of disposing needed for virtual machine quantity, to The virtual machine quantity for the data center DC that deployment business can dispose and the first network KPI data of the associated link of DC, successively Generate each target deployment scheme for waiting for deployment business；Target deployment scheme includes target deployment DC and target deployment link； The target deployment scheme of business to be disposed is sent to network controller and cloud system so that network controller and cloud system according to The target deployment scheme of business to be disposed is treated deployment business and is disposed.Service deployment method provided in an embodiment of the present invention, First by acquire the business KPI data of business to be disposed in current deployment cycle, wait virtual machine quantity needed for the business of disposing, The virtual machine quantity for the data center DC that network environment parameters, business to be disposed can dispose and the first net of the associated link of DC Network KPI data, then according to the business KPI data of business to be disposed and external environment data according to preset mapping function obtain to Then the corresponding network KPI parameter of deployment business carries out it preferentially according to the respectively corresponding network KPI parameter of business to be disposed The division of grade, so that it is determined that the sequencing disposed in the business of deployment to be to guarantee the quality of service of each business to be disposed, so It afterwards then can be according to the virtual machine of respectively the network KPI data that business to be disposed needs and virtual machine quantity and its DC that can be disposed The network KPI parameter of quantity and DC related link circuits is that each service generation to be disposed is each according to the sequence of priority from high to low Self-corresponding target deployment scheme；Target deployment is finally sent to network controller and cloud system, so that network controller and cloud System is treated deployment business according to target deployment scheme and is disposed.Because being tied during generating target deployment scheme After conjunction network environment parameters, business KPI data and default mapping function obtain network KPI parameter, the thought cooperateed with cloud net, The factor consideration that not only only (the virtual machine quantity of DC) is single in terms of network facet (network KPI) or office's room resource, but Deployment scheme is codetermined in conjunction with the two, in addition because being determined in advance to the priority of each business to be disposed, and It determines and first determines that the high rear determining priority of priority is low when deployment scheme, be also achieved that and utmostly guarantee each to portion Internet resources are rationally effectively assigned with while the quality requirement of administration's business, are improved resource utilization.
Referring to shown in Fig. 4, the embodiment of the present invention also provides a kind of service deployment device 01, comprising: obtains module 41, mapping Module 42, Priority Determination module 43, processing module 44 and sending module 45；
Module 41 is obtained, waits for that the business Key Performance of deployment business refers to for obtaining at least one in current deployment cycle The data center marking KPI data, being disposed wait virtual machine quantity, network environment parameters needed for the business of disposing, business to be disposed The first network KPI data of the associated link of virtual machine quantity and DC of DC；
Mapping block 42, business KPI data and network environment parameters for being obtained according to module 41 is obtained, according to default Mapping function obtains the corresponding second network KPI data of business to be disposed；
Priority Determination module 43, the corresponding network KPI data of business to be disposed for being obtained according to mapping block 42 Determine the priority of business to be disposed；
Processing module 44, the priority sequence from high to low for being determined according to Priority Determination module 43, according to reflecting Penetrate module 42 acquisition the corresponding second network KPI data of business to be disposed, obtain module 41 obtain wait needed for the business of disposing Virtual machine quantity, obtain the virtual machine quantity and acquisition of data center DC that the business to be disposed that module 41 obtains can dispose The first network KPI data for the associated link of DC that module 41 obtains, sequentially generates each target deployment for waiting for deployment business Scheme；Target deployment scheme includes target deployment DC and target deployment link；
The target deployment scheme of sending module 45, the business to be disposed for generating processing module 44 is sent to network control Device and cloud system processed, so that network controller 03 and cloud system 06 treat deployment industry according to the target deployment scheme of business to be disposed Business is disposed.
Illustratively, referring to Figure 5, the embodiment of the present invention also provides a kind of service deployment system 00, including above-mentioned Service deployment device, wherein the KPI data of business to be disposed and network environment data are sent to AI analysis system by operation system 02 The acquisition module 41 of system 05 and service deployment device 01；Network controller 03 obtains each DC by monitoring network quality system 04 Between link first network KPI data, and send it to the acquisition module of AI analysis system 05 and service deployment device 01 41；The virtual machine quantity of each DC is sent to the acquisition module of service deployment device 01 by cloud system 06；Wherein AI analysis system After 05 can obtain mapping function according to a large amount of business KPI data, network environment data and first network KPI data, send It is used to the mapping block of service deployment device 01；Network controller 03 and cloud system 06 are respectively used to treat deployment business most Determining deployment link and deployment DC are configured eventually.
Optionally, the target instruction target word that module 41 is also used to obtain the corresponding user terminal of the first business to be disposed is obtained；Mesh Priority of the mark instruction at least for specified business to be disposed；First business to be disposed is that at least one waits for appointing in deployment business One business to be disposed；
Priority Determination module 43 is specifically used for:
The priority of the first business to be disposed is determined according to the target instruction target word for obtaining the acquisition of module 41；
The corresponding network KPI data of the second business to be disposed obtained according to mapping block 42 determines the second business to be disposed Priority；Second business to be disposed is that at least one waits for the business to be disposed in deployment business in addition to first wait the business of disposing Any of.
Illustratively, processing module 44 is specifically used for: from high to low according to the determining priority of Priority Determination module 43 Sequence, according to mapping block 42 obtain the corresponding second network KPI data of business to be disposed, obtain module 41 obtain to Virtual machine quantity needed for deployment business, the virtual machine for obtaining the data center DC that the business to be disposed that module 41 obtains can dispose Quantity and the first network KPI data for obtaining the associated link of DC that module 41 obtains, successively determine each industry to be disposed First deployment scheme of business；First deployment scheme includes the first deployment DC and the first deployment link；
Calculate the resource supply and demand ratio in the first deployment scheme of business to be disposed；Resource supply and demand ratio include the first supply and demand ratio and Second supply and demand ratio；
First supply and demand ratio is the value of the first network KPI parameter in the corresponding second network KPI data of business to be disposed, with Business corresponding first to be disposed disposes the first network KPI parameter in the first network KPI data of link at current time The ratio of value；First network KPI parameter is the resources-type network KPI parameter that any one can be consumed by business to be disposed；
Second supply and demand ratio is wait virtual machine quantity needed for the business of disposing, and first deployment DC corresponding with business to be disposed exists The ratio of the virtual machine quantity at current time；
By the product of all first supply and demand ratios in the first deployment scheme of business to be disposed, with business to be disposed first The product of the second supply and demand ratio in deployment scheme is determined as total supply and demand ratio of the first deployment scheme of business to be disposed；
The smallest first deployment scheme of total supply and demand ratio of business to be disposed is determined as to the target portion management side of business to be disposed Case.
Optionally, service deployment device 01 further includes judgment module 46 and adjustment module 47；
When judgment module 46 determines that at least one waits for that there are processing modules 44 can not determine the first deployment side in deployment business For the third of case when deployment business, adjustment module 47 is sequentially adjusted in processing module for the sequence according to priority from low to high 44 at least one determined wait for the target deployment scheme of the 4th business to be disposed in deployment business, until processing module 44 can be Until first business to be disposed determines the first deployment scheme；
4th business to be disposed waits for any wait dispose in addition to third waits for deployment business in deployment business at least one Business；It include third industry to be disposed in the DC for the target deployment link association that the target deployment scheme of 4th business to be disposed includes Any of the DC disposed of business；
The 4th target deployment scheme after disposing business reorganization is not that total supply and demand ratio of business to be disposed is the smallest by first Deployment scheme.
Service deployment device provided in an embodiment of the present invention works as front for obtaining because the device includes: acquisition module At least one in administration's period waits for the business KPI Key Performance Indicator KPI data of deployment business, wait virtual machine needed for the business of disposing The virtual machine quantity of the data center DC that quantity, network environment parameters, business to be disposed can dispose and the associated link of DC First network KPI data；Mapping block, business KPI data and network environment parameters for being obtained according to module is obtained, foundation Default mapping function obtains the corresponding second network KPI data of business to be disposed；Priority Determination module, for according to mapping mould The corresponding network KPI data of the business to be disposed that block obtains determines the priority of business to be disposed；Processing module, for according to excellent The sequence of the priority that first grade determining module determines from high to low, the business to be disposed corresponding second obtained according to mapping block Network KPI data obtains the business to be disposed obtained wait virtual machine quantity needed for the business of disposing, acquisition module that module obtains The virtual machine quantity for the data center DC that can be disposed and the first network KPI number for obtaining the associated link of DC that module obtains According to sequentially generating each target deployment scheme for waiting for deployment business；Target deployment scheme includes target deployment DC and target portion Affix one's name to link；The target deployment scheme of sending module, the business to be disposed for generating processing module is sent to network controller And cloud system, so that network controller and cloud system treat deployment business carry out portion according to the target deployment scheme of business to be disposed Administration.So service deployment device provided in an embodiment of the present invention is when treating deployment business and being disposed, it first can be by adopting Collect the business KPI data of business to be disposed current deployment cycle Nei, join wait virtual machine quantity needed for the business of disposing, network environment The virtual machine quantity for the data center DC that number, business to be disposed can dispose and the first network KPI data of the associated link of DC, Then business to be disposed is obtained according to mapping function is preset according to the business KPI data of business to be disposed and external environment data Then corresponding network KPI parameter carries out the division of priority according to the respectively corresponding network KPI parameter of business to be disposed to it, So that it is determined that the sequencing disposed in the business of deployment to be to guarantee the quality of service of each business to be disposed, it then then can root It is closed according to the network KPI data and virtual machine quantity and the virtual machine quantity and DC of its DC that can be disposed that respectively business to be disposed needs The network KPI parameter for joining link is each corresponding mesh of service generation to be disposed according to the sequence of priority from high to low Mark deployment scheme；Target deployment is finally sent to network controller and cloud system, so that network controller and cloud system are according to mesh Mark deployment scheme is treated deployment business and is disposed.Because combining network environment during generating target deployment scheme After parameter, business KPI data and default mapping function obtain network KPI parameter, with cloud net cooperate with thought, not only only from (the virtual machine quantity of DC) single factor considers in terms of network facet (network KPI) or office's room resource, but combines the two altogether With deployment scheme is determined, in addition because being determined in advance to the priority of each business to be disposed, and in determining section management side First determine that the high rear determining priority of priority is low, is also achieved that the matter for utmostly guaranteeing each business to be disposed when case Internet resources are rationally effectively assigned with while amount demand, are improved resource utilization.
Referring to shown in Fig. 6, the embodiment of the present invention also provides another service deployment device, including memory 61, processor 62, bus 63 and communication interface 64；Memory 61 passes through always for storing computer executed instructions, processor 62 and memory 61 Line 63 connects；When the operation of service deployment device, processor 62 executes the computer executed instructions that memory 61 stores, so that industry Business deployment device executes such as service deployment method provided by the above embodiment.
In concrete implementation, as one embodiment, processor 62 (62-1 and 62-2) may include one or more CPU, such as CPU0 and CPU1 shown in Fig. 6.And as one embodiment, service deployment device may include multiple processors 62, such as processor 62-1 and processor 62-2 shown in Fig. 6.Each of these processors 62 CPU can be one Single core processor (Single-CPU) is also possible to a multi-core processor (Multi-CPU).Here processor 62 can refer to One or more equipment, circuit, and/or the processing core for handling data (such as computer program instructions).
Memory 61 can be read-only memory 61 (Read-Only Memory, ROM) or can store static information and refer to The other kinds of static storage device enabled, random access memory (Random Access Memory, RAM) or can store The other kinds of dynamic memory of information and instruction, is also possible to Electrically Erasable Programmable Read-Only Memory (Electrically Erasable Programmable Read-Only Memory, EEPROM), CD-ROM (Compact Disc Read-Only Memory, CD-ROM) or other optical disc storages, optical disc storage (including compression optical disc, laser disc, light Dish, Digital Versatile Disc, Blu-ray Disc etc.), magnetic disk storage medium or other magnetic storage apparatus or can be used in carry or Store have instruction or data structure form desired program code and can by any other medium of computer access, but It is without being limited thereto.Memory 61, which can be, to be individually present, and is connected by communication bus 63 with processor 62.Memory 61 can also be with It is integrated with processor 62.
In concrete implementation, memory 61, for storing the data in the application and executing the software program of the application Corresponding computer executed instructions.Processor 62 can by running or executing the software program being stored in memory 61, with And call the data being stored in memory 61, the various functions of service deployment device.
Communication interface 64 is used for and other equipment or communication, such as control using the device of any transceiver one kind System processed, wireless access network (Radio Access Network, RAN), WLAN (Wireless Local Area Networks, WLAN) etc..Communication interface 64 may include that receiving unit realizes that receive capabilities and transmission unit realize transmission Function.
It is total to can be industry standard architecture (Industry Standard Architecture, ISA) for bus 63 Line, external equipment interconnection (Peripheral Component Interconnect, PCI) bus or extension Industry Standard Architecture Structure (Extended Industry Standard Architecture, EISA) bus etc..The bus 63 can be divided into address Bus, data/address bus, control bus etc..Only to be indicated with a thick line in Fig. 6, it is not intended that only one convenient for indicating Bus or a type of bus.
The embodiment of the present invention also provides a kind of computer storage medium, and computer storage medium includes that computer execution refers to It enables, when computer executed instructions are run on computers, so that computer executes such as service deployment provided by the above embodiment Method.
The embodiment of the present invention also provides a kind of computer program, which can be loaded directly into memory, and Containing software code, which is loaded into via computer and can be realized business department provided by the above embodiment after executing Arranging method.
Those skilled in the art are it will be appreciated that in said one or multiple examples, function described in the invention It can be realized with hardware, software, firmware or their any combination.It when implemented in software, can be by these functions Storage in computer-readable medium or as on computer-readable medium one or more instructions or code transmitted. Computer-readable medium includes computer storage media and communication media, and wherein communication media includes convenient for from a place to another Any medium of one place transmission computer program.Storage medium can be general or specialized computer can access it is any Usable medium.
Through the above description of the embodiments, it is apparent to those skilled in the art that, for description It is convenienct and succinct, only the example of the division of the above functional modules, in practical application, can according to need and will be upper It states function distribution to be completed by different functional modules, i.e., the internal structure of device is divided into different functional modules, to complete All or part of function described above.
In several embodiments provided herein, it should be understood that disclosed device and method can pass through it Its mode is realized.For example, the apparatus embodiments described above are merely exemplary, for example, the module or unit It divides, only a kind of logical function partition, there may be another division manner in actual implementation.Such as multiple units or components It may be combined or can be integrated into another device, or some features can be ignored or not executed.Another point, it is shown or The mutual coupling, direct-coupling or communication connection discussed can be through some interfaces, the indirect coupling of device or unit It closes or communicates to connect, can be electrical property, mechanical or other forms.Unit can be or can also as illustrated by the separation member Not to be physically separated, component shown as a unit can be a physical unit or multiple physical units, it can It is in one place, or may be distributed over multiple and different places.Can select according to the actual needs part therein or Person's whole unit achieves the purpose of the solution of this embodiment.
It, can also be in addition, the functional units in various embodiments of the present invention may be integrated into one processing unit It is that each unit physically exists alone, can also be integrated in one unit with two or more units.Above-mentioned integrated list Member both can take the form of hardware realization, can also realize in the form of software functional units.If integrated unit with The form of SFU software functional unit is realized and when sold or used as an independent product, can store and storage Jie can be read at one In matter.Based on this understanding, the portion that the technical solution of the embodiment of the present application substantially in other words contributes to the prior art Divide or all or part of the technical solution can be embodied in the form of software products, which is stored in one In storage medium, including some instructions are used so that an equipment (can be single-chip microcontroller, chip etc.) or processor (processor) it performs all or part of the steps of the method described in the various embodiments of the present invention.And storage medium above-mentioned includes: The various media that can store program code such as USB flash disk, mobile hard disk, ROM, RAM, magnetic or disk.
The above description is merely a specific embodiment, but scope of protection of the present invention is not limited thereto, any In the technical scope disclosed by the present invention, any changes or substitutions that can be easily thought of by those familiar with the art, all answers It is included within the scope of the present invention.Therefore, protection scope of the present invention should be subject to the protection scope in claims.

Claims (13)

1. a kind of service deployment method characterized by comprising
Obtain the business KPI Key Performance Indicator KPI data, described to portion that at least one in current deployment cycle waits for deployment business The virtual machine for the data center DC that virtual machine quantity, network environment parameters needed for administration's business, the business to be disposed can dispose The first network KPI data of quantity and the associated link of the DC；
According to the business KPI data and the network environment parameters, the business to be disposed is obtained according to mapping function is preset Corresponding second network KPI data；
The priority of the business to be disposed is determined according to the corresponding second network KPI data of the business to be disposed；
According to the sequence of priority from high to low, according to the corresponding second network KPI data of the business to be disposed, described to portion The virtual machine quantity for the data center DC that virtual machine quantity needed for administration's business, the business to be disposed can dispose and the DC The first network KPI data of associated link sequentially generates the target deployment scheme of each business to be disposed；The mesh Marking deployment scheme includes target deployment DC and target deployment link；
The target deployment scheme of the business to be disposed is sent to network controller and cloud system, so that the network controller The business to be disposed is disposed according to the target deployment scheme of the business to be disposed with the cloud system.
2. service deployment method according to claim 1, which is characterized in that the business to be disposed according to is corresponding Second network KPI data determines that the priority of the business to be disposed includes:
The target instruction target word of the corresponding user terminal of the business to be disposed of acquisition first；The target instruction target word be at least used for it is specified described to The priority of deployment business；First business to be disposed be it is described at least one wait for any industry to be disposed in deployment business Business；
The priority of the described first business to be disposed is determined according to the target instruction target word；
The priority of the described second business to be disposed is determined according to the corresponding second network KPI data of the second business to be disposed；Institute State the second business to be disposed be it is described at least one wait for the industry to be disposed in deployment business in addition to described first wait the business of disposing Any of business.
3. service deployment method according to claim 2, which is characterized in that described according to priority from high to low suitable Sequence, according to the corresponding second network KPI data of the business to be disposed, it is described wait the business of disposing needed for virtual machine quantity, institute State the virtual machine quantity for the data center DC that business to be disposed can dispose and the first network KPI number of the associated link of the DC According to the target deployment scheme for sequentially generating each business to be disposed includes:
According to the sequence of priority from high to low, according to the corresponding second network KPI data of the business to be disposed, described to portion The virtual machine quantity for the data center DC that virtual machine quantity needed for administration's business, the business to be disposed can dispose and the DC The first network KPI data of associated link successively determines the first deployment scheme of each business to be disposed；Described One deployment scheme includes the first deployment DC and the first deployment link；
Calculate the resource supply and demand ratio in the first deployment scheme of the business to be disposed；The resource supply and demand ratio includes the first supply and demand Than with the second supply and demand ratio；
First supply and demand ratio is the first network KPI parameter in the corresponding second network KPI data of the business to be disposed Value disposes the first network KPI parameter in the first network KPI data of link with the business corresponding first to be disposed In the ratio of the value at current time；The first network KPI parameter is the resource that any one can be consumed by the business to be disposed Class network KPI parameter；
Second supply and demand ratio is described wait virtual machine quantity needed for the business of disposing, with the business corresponding first to be disposed DC is disposed in the ratio of the virtual machine quantity at current time；
By the product of all first supply and demand ratios in the first deployment scheme of the business to be disposed, with the industry to be disposed The product of second supply and demand ratio in first deployment scheme of business is determined as the first deployment scheme of the business to be disposed Total supply and demand ratio；
The smallest first deployment scheme of total supply and demand ratio of the business to be disposed is determined as to the target portion of the business to be disposed Management side case.
4. service deployment method according to claim 3, which is characterized in that further include: when determine it is described at least one wait for In deployment business in the presence of can not determine the third of the first deployment scheme when deployment business,
According to the sequence of priority from low to high, be sequentially adjusted in it is described at least one wait for the 4th business to be disposed in deployment business Target deployment scheme, waiting for deployment business until the third, there are until the first deployment scheme；
4th business to be disposed be it is described at least one wait for appointing in addition to the third waits for deployment business in deployment business One business to be disposed；Include in the DC for the target deployment link association that the target deployment scheme of 4th business to be disposed includes The third waits for any of the DC disposed of deployment business；
The described 4th target deployment scheme after disposing business reorganization is not that total supply and demand ratio of the business to be disposed is the smallest First deployment scheme.
5. service deployment method according to claim 1, which is characterized in that when the business to be disposed is web page browsing industry When business, the business KPI parameter that the business KPI data includes is at least are as follows: domain name system DNS parses time, transmission control protocol The TCP link setup time redirects time, peak download rate and initial screen time；
When the business KPI ginseng that when business of disposing is internet television OTT video traffic, the business KPI data includes Number is at least are as follows: dns resolution time, mean 0100 calorie immediately between, fragment is averaged speed of download and Caton rate.
6. service deployment method according to claim 4, which is characterized in that the net that the first network KPI data includes Network KPI parameter is at least are as follows: time delay, packet loss, bandwidth and shake；
The network KPI parameter that the second network KPI data includes is at least are as follows: time delay, packet loss, bandwidth and shake.
7. a kind of service deployment device characterized by comprising obtain module, mapping block, Priority Determination module, processing Module and sending module；
The acquisition module waits for the business KPI data, described of deployment business for obtaining at least one in current deployment cycle Void wait the data center DC that virtual machine quantity, network environment parameters needed for the business of disposing, the business to be disposed can dispose The first network KPI data of quasi- machine quantity and the associated link of the DC；
The mapping block, the business KPI data and the network environment parameters for being obtained according to the acquisition module, The corresponding second network KPI data of the business to be disposed is obtained according to mapping function is preset；
The Priority Determination module, for the corresponding network KPI of business to be disposed according to mapping block acquisition Data determine the priority of the business to be disposed；
The processing module, the sequence of priority from high to low for being determined according to the Priority Determination module, according to institute State described in the corresponding second network KPI data of the business to be disposed of mapping block acquisition, acquisitions module acquisition to The data center DC's that virtual machine quantity needed for deployment business, the business to be disposed for obtaining module acquisition can dispose Virtual machine quantity and the first network KPI data for obtaining the associated link of the DC that module obtains, sequentially generate every The target deployment scheme of business to be disposed described in one；The target deployment scheme includes target deployment DC and target deployment chain Road；
The sending module, the target deployment scheme for business to be disposed described in generating the processing module are sent to net Network controller and cloud system, so that the target portion management side of the network controller and the cloud system business to be disposed according to Case disposes the business to be disposed.
8. service deployment device according to claim 7, which is characterized in that
The target instruction target word for obtaining module and being also used to obtain the corresponding user terminal of the first business to be disposed；The target instruction target word Priority at least for the specified business to be disposed；First business to be disposed be it is described at least one wait for deployment business In any business to be disposed；
The Priority Determination module is specifically used for:
The priority of the described first business to be disposed is determined according to the target instruction target word that the acquisition module obtains；
The corresponding network KPI data of the second business to be disposed obtained according to the mapping block determines the described second industry to be disposed The priority of business；Second business to be disposed be it is described at least one wait in deployment business except the described first business to be disposed with Any of outer business to be disposed.
9. service deployment device according to claim 8, which is characterized in that the processing module is specifically used for:
According to the sequence of the determining priority of the Priority Determination module from high to low, the institute obtained according to the mapping block It states described in the corresponding second network KPI data of business to be disposed, acquisition module acquisition wait virtual needed for the business of disposing Machine quantity, the virtual machine quantity of data center DC that the business to be disposed that module obtains can dispose and described of obtaining The first network KPI data for obtaining the associated link of the DC that module obtains successively determines each described business to be disposed The first deployment scheme；First deployment scheme includes the first deployment DC and the first deployment link；
Calculate the resource supply and demand ratio in the first deployment scheme of the business to be disposed；The resource supply and demand ratio includes the first supply and demand Than with the second supply and demand ratio；
First supply and demand ratio is the first network KPI parameter in the corresponding second network KPI data of the business to be disposed Value disposes the first network KPI parameter in the first network KPI data of link with the business corresponding first to be disposed In the ratio of the value at current time；The first network KPI parameter is the resource that any one can be consumed by the business to be disposed Class network KPI parameter；
Second supply and demand ratio is described wait virtual machine quantity needed for the business of disposing, with the business corresponding first to be disposed DC is disposed in the ratio of the virtual machine quantity at current time；
By the product of all first supply and demand ratios in the first deployment scheme of the business to be disposed, with the industry to be disposed The product of second supply and demand ratio in first deployment scheme of business is determined as the first deployment scheme of the business to be disposed Total supply and demand ratio；
The smallest first deployment scheme of total supply and demand ratio of the business to be disposed is determined as to the target portion of the business to be disposed Management side case.
10. service deployment device according to claim 9, which is characterized in that further include judgment module and adjustment module；
At least one waits for that there are processing modules can not determine the first deployment side in deployment business described in determining when the judgment module For the third of case when deployment business, the adjustment module is sequentially adjusted in the place for the sequence according to priority from low to high Reason module determine it is described at least one wait for the target deployment scheme of the 4th business to be disposed in deployment business, until the processing Until module can determine the first deployment scheme for the described first business to be disposed；
4th business to be disposed be it is described at least one wait for appointing in addition to the third waits for deployment business in deployment business One business to be disposed；Include in the DC for the target deployment link association that the target deployment scheme of 4th business to be disposed includes The third waits for any of the DC disposed of deployment business；
The described 4th target deployment scheme after disposing business reorganization is not that total supply and demand ratio of the business to be disposed is the smallest First deployment scheme.
11. a kind of service deployment device, which is characterized in that including memory, processor, bus and communication interface；The storage For storing computer executed instructions, the processor is connect with the memory by the bus device；When the business department When affixing one's name to device operation, the processor executes the computer executed instructions of the memory storage, so that the business department It affixes one's name to device and executes service deployment method as claimed in any one of claims 1 to 6.
12. a kind of computer storage medium, which is characterized in that the computer storage medium includes computer executed instructions, when When the computer executed instructions are run on computers, so that the computer is executed as described in claim any one of 1-6 Service deployment method.
13. a kind of service deployment system, which is characterized in that including the described in any item service deployment devices of claim 7-10.
CN201910411785.4A 2019-05-16 2019-05-16 Service deployment method and device Active CN110190988B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910411785.4A CN110190988B (en) 2019-05-16 2019-05-16 Service deployment method and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910411785.4A CN110190988B (en) 2019-05-16 2019-05-16 Service deployment method and device

Publications (2)

Publication Number Publication Date
CN110190988A true CN110190988A (en) 2019-08-30
CN110190988B CN110190988B (en) 2022-04-22

Family

ID=67716616

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910411785.4A Active CN110190988B (en) 2019-05-16 2019-05-16 Service deployment method and device

Country Status (1)

Country Link
CN (1) CN110190988B (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113839864A (en) * 2020-06-23 2021-12-24 中兴通讯股份有限公司 Network deployment method, device, system and storage medium of autonomous domain system AS
CN117478612A (en) * 2023-12-27 2024-01-30 成都新希望金融信息有限公司 Flow distribution method and device and electronic equipment

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105357691A (en) * 2015-09-28 2016-02-24 中国普天信息产业北京通信规划设计院 LTE (Long Term Evolution) wireless network user sensitive monitoring method and system
US20160269319A1 (en) * 2015-03-13 2016-09-15 Microsoft Technology Licensing, Llc Intelligent Placement within a Data Center
CN106302574A (en) * 2015-05-15 2017-01-04 华为技术有限公司 A kind of service availability management method, device and network function virtualization architecture thereof
US20180082355A1 (en) * 2016-01-16 2018-03-22 International Business Machines Corporation Tracking business performance impact of optimized sourcing algorithms
CN109150567A (en) * 2017-06-19 2019-01-04 中兴通讯股份有限公司 Monitoring method, equipment and the readable storage medium storing program for executing of virtual network function module
US20190042297A1 (en) * 2018-09-13 2019-02-07 Intel Corporation Technologies for deploying virtual machines in a virtual network function infrastructure

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20160269319A1 (en) * 2015-03-13 2016-09-15 Microsoft Technology Licensing, Llc Intelligent Placement within a Data Center
CN106302574A (en) * 2015-05-15 2017-01-04 华为技术有限公司 A kind of service availability management method, device and network function virtualization architecture thereof
CN105357691A (en) * 2015-09-28 2016-02-24 中国普天信息产业北京通信规划设计院 LTE (Long Term Evolution) wireless network user sensitive monitoring method and system
US20180082355A1 (en) * 2016-01-16 2018-03-22 International Business Machines Corporation Tracking business performance impact of optimized sourcing algorithms
CN109150567A (en) * 2017-06-19 2019-01-04 中兴通讯股份有限公司 Monitoring method, equipment and the readable storage medium storing program for executing of virtual network function module
US20190042297A1 (en) * 2018-09-13 2019-02-07 Intel Corporation Technologies for deploying virtual machines in a virtual network function infrastructure

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113839864A (en) * 2020-06-23 2021-12-24 中兴通讯股份有限公司 Network deployment method, device, system and storage medium of autonomous domain system AS
CN117478612A (en) * 2023-12-27 2024-01-30 成都新希望金融信息有限公司 Flow distribution method and device and electronic equipment
CN117478612B (en) * 2023-12-27 2024-03-15 成都新希望金融信息有限公司 Flow distribution method and device and electronic equipment

Also Published As

Publication number Publication date
CN110190988B (en) 2022-04-22

Similar Documents

Publication Publication Date Title
CN112187545B (en) Network slice deployment method and device
CN105103506B (en) For the method and system for the non-homogeneous bandwidth request allocation bandwidth in system for cloud computing
US10412021B2 (en) Optimizing placement of virtual machines
CN109417719B (en) Network resource management method, device and system
CN110896355B (en) Network slice selection method and device
WO2020258920A1 (en) Network slice resource management method and apparatus
US10198297B1 (en) Provisioning virtual resource on a server based on label associated with virtual resource and servers
CN107566194B (en) Method for realizing cross-domain virtual network mapping
Botero et al. Greener networking in a network virtualization environment
CN109560952B (en) Network slice management method and equipment
Li et al. Maximizing user service satisfaction for delay-sensitive IoT applications in edge computing
CN109218047A (en) Network sliced sheet processing method and device, communication system and storage medium
CN110308995A (en) A kind of edge cloud computing service system edges cloud node deployment device
CN107463582A (en) The method and device of distributed deployment Hadoop clusters
CN104521198A (en) System and method for virtual ethernet interface binding
CN111182037B (en) Mapping method and device of virtual network
CN110708708B (en) Wireless resource optimization method and device
CN110166507A (en) More resource regulating methods and device
WO2020177255A1 (en) Resource allocation method and device for wireless access network
WO2020036156A1 (en) Communication control device, communication control system, communication control method, and communication control program
CN110190988A (en) A kind of service deployment method and device
CN109002364A (en) Optimization method, electronic device and the readable storage medium storing program for executing of interprocess communication
CN113495776A (en) VNF instantiation method and device
CN107872533B (en) Information-pushing method, device, server and storage medium
CN109041255A (en) A kind of cut-in method and UE

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
GR01 Patent grant
GR01 Patent grant