CN105242956B - Virtual functions service chaining deployment system and its dispositions method - Google Patents
Virtual functions service chaining deployment system and its dispositions method Download PDFInfo
- Publication number
- CN105242956B CN105242956B CN201510584507.0A CN201510584507A CN105242956B CN 105242956 B CN105242956 B CN 105242956B CN 201510584507 A CN201510584507 A CN 201510584507A CN 105242956 B CN105242956 B CN 105242956B
- Authority
- CN
- China
- Prior art keywords
- platform
- virtual functions
- service chaining
- service
- physical
- 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.)
- Active
Links
Abstract
The present invention relates to a kind of virtual functions service chaining deployment systems and its dispositions method, system to include:Virtual functions interference prediction module predicts the performance interference between virtual functions, and the dynamic adjustment for service chaining provides decision-making foundation;Service chaining mapping block can handle user service request, monitor service chaining operating status in real time and realize that service chaining maps;Virtual functions carrying platform for receiving and processing the function activation request from service chaining mapping block, feedback active information, and monitors virtual functions operating status, asks to generate respective instance by function activation.The present invention is interfered for dependence, succession, the performance of function distributing between each virtual network function unit in service chaining, in the case where being predicted based on virtual functions degree of disturbance, the execution performance that service chaining can be effectively improved meets disposition optimization target, the execution performance of service chaining can be effectively improved, meet the target of disposition optimization, substantially reduce cost.
Description
Technical field
The present invention relates to computer network field, more particularly to a kind of virtual functions service chaining deployment system and its deployment side
Method.
Background technology
With the continuous growth of internet scale and continuing to bring out for new network service, how Internet resources are made full use of
And adjustment, on-premise network function become urgent problem to be solved.Traditional changes function by increasing hardware in a network
Method it is of high cost and lack flexibility.In this regard, researcher proposes network function being separated with hardware platform so that network work(
It can realize and Internet resources are efficiently used by flexible deployment on different physical platforms.In this context, make
Virtual functions service chaining to realize one of virtual network function key technology causes the extensive concern of people.
Directed connection of the virtual functions service chaining by several virtual network function units and therebetween forms.It is virtual in link
Network function defines it by user.Sequence between virtual functional units is by the dependence between virtual functional units and user demand
It codetermines.Virtual functions service chaining needs to be mapped in physical network to realize service function.Each virtual functions are reflected
It is mapped in the related platform in physical network, is exactly specifically one virtual functions example of generation in related available platform,
This example can be carried by virtual machine.During service chaining deployment, different network function examples is to the speed of data flow
Rate can generate different influences, and there may be some dependences between network function unit.Particularly, when different virtual networks
When function example deployment is to same physical platform, performance interference can be generated between each network function example.The execution of each example
Performance is not a determining state with contacting between virtual resource, it is continuous dynamic change.It is primarily due to virtual net
The execution performance of network function example is influenced by itself workload size, if workload changes, even if point
The virtual resource configuration of dispensing example does not change, and the execution performance of example will also change.
In addition, since virtual network function example deployment is on respective physical platform, although current virtualization technology energy
Enough provide some effective performance isolation mechanism between these examples, but the monitoring management unit on physical platform is by department of physics
When resource allocation of uniting gives different virtual network function examples, these examples will fight for the physical resource of platform, lead to void
Intend the variation of resource service ability, i.e., formed and interfered with each other between example.Therefore, virtual functions service chaining is being mapped to Physical Network
When in network, it is necessary to consider the annoyance level that the example that its virtual network function unit maps out is subject in corresponding platform.
Invention content
For deficiency of the prior art, the present invention provides a kind of virtual functions service chaining deployment system and its deployment side
Method.
According to designing scheme provided by the present invention, a kind of virtual functions service chaining deployment system, comprising:
Virtual functions interference prediction module distributes virtual resource, to virtual functions and virtual resource demand for load application
Between relationship analyzed, predict virtual functions between performance interference, with service chaining mapping block carry out information exchange;
Users service needs are converted to the service module function of formalization, according to service function by service chaining mapping block
Schedule dependence and user demand between module are ranked up service module function, and selection target physical platform, need to
The service module function information and active information wanted are sent to target physical platform;
Virtual functions carrying platform, comprising physical platform and platform control system, platform control system is used to receive and locate
The function activation request from service chaining mapping block, feedback active information are managed, and monitors virtual functions operating status, platform control
System processed asks to generate respective instance by function activation.
Above-mentioned, the physical platform is single server or the data center to gather server composition.
A kind of virtual functions service chaining dispositions method, specifically comprises the following steps:
Step 1. service chaining mapping block receives user service request, and issues virtual functions after service request is formalized
Interference prediction module;
Step 2. virtual functions interference prediction module obtains the physical in compass of competency by virtual functions carrying platform
The application of function carrying data of platform, predict, and prediction result is anti-performance interference suffered after new function example deployment
It is fed to service chaining mapping block;
Step 3. service chaining mapping block assesses service chaining overall interference, selects optimal deployment scheme;
Optimal deployment scheme is mapped to corresponding virtual functions carrying platform by step 4. service chaining mapping block, and is activated
Function example;
Step 5. virtual functions carrying platform monitors physical platform function operation data in real time, and service chaining mapping block is real-time
Link channel operation data is monitored, if occurring overloading according to the judgement of the testing result of data packetloss rate or interfering excessive situation, is returned
Return step 2.
Above-mentioned virtual functions service chaining dispositions method, the step 2 specifically include following content:
After step 2.1. virtual functions interference predictions module receives user's request, the operation information of physical platform is collected, is known
Other resource redundancy platform, and it is sent to service chaining mapping block;
Step 2.2. service chainings mapping block removes the physical platform of connectivity of link difference according to resource redundancy platform, and
Feed back to virtual functions interference prediction module;
Step 2.3. virtual functions interference prediction modules examine or check physical platform work(according to cpu busy percentage and I/O bandwidth resources
Applicable performance degree of disturbance, establishes degree of disturbance prediction model;
Step 2.4. optimizes degree of disturbance prediction model, is solved using linear regression method, and will solve result of calculation and send
To service chaining mapping block.
Preferably, the step 2.4 specifically includes following content:
Step 2.4.1. is based on degree of disturbance prediction model, defines the degree of disturbance attribute of each physical platform, and demarcate one
Virtual functions carry out degree of disturbance traversal to all physical platforms, elect N number of physics for virtual functions degree of disturbance minimum
Platform, wherein, platform quantitative value N is determined by optimization complexity;
Step 2.4.2. chooses a physical platform from N number of physical platform at random, virtual by what is demarcated in previous step
Function distributing is to the physical platform, and using the physical platform as the starting point of service chaining;
Step 2.4.3. continues to demarcate remaining virtual functions, by walking to removing preamble according to degree of disturbance prediction model
All physical platforms outside physical platform disposed in rapid carry out degree of disturbance traversal, calculate wherein each physical platform and interfere
The difference of the interference value of virtual functions demarcated in value and step 2.4.1 chooses M platform minimum in difference, platform quantity
Value M is determined according to optimization complexity;
Step 2.4.4. chooses a physical platform from M physical platform at random, virtual by what is demarcated in step 2.4.3
On function distributing to the physical platform, remaining virtual functions are disposed successively according to step 2.4.3, and it is complicated to record decision optimization
The platform quantitative value of property;
Step 2.4.5. is according to the corresponding platform quantitative value of service chaining sequential search, the platform quantity corresponding to virtual functions
Value is equal to 1, then is examined in the platform quantitative value of subsequent virtual functions in sequence, until all platform quantitative values are whole
When being 1, the selection of its functional link is terminated, when the corresponding platform quantitative value of virtual functions is more than 1, is then subtracted 1, and simultaneously from original
It is deleted in corresponding physical platform and corresponding has used physical platform, and jump in step 2.4.3 and re-execute the virtual functions
Deployment;
Step 2.4.6. performs step 2.4.1 ~ 2.4.5 to remaining service chaining, and the degree of disturbance for calculating every service chaining is equal
Value, the degree of disturbance mean value of more each service chaining select the link of mean value minimum as optimal deployment scheme.
Above-mentioned virtual functions service chaining dispositions method, the step 5 also include:
Step 5.1. checks whether each virtual functions requirement is mapped to corresponding object in users service needs
Platform if the total resources needed for virtual functions requirement are less than or equal to the available resource of the physical platform, carries out
Next step, otherwise, switching platform examination object examines or check new physical platform;
Step 5.2. activates function example, and active information is back to service chaining mapping block;
Step 5.3. service chaining mapping blocks compile each virtual functions deployment scenario of service chaining, in each virtual work(
Non-overloaded channel can be selected to create link between deployment platform;
Step 5.4. service chainings mapping block activates entire service chaining and monitors the performance operating condition of each virtual functions
And message transmission rate.
Above-mentioned virtual functions service chaining dispositions method, the service request formalization content in step 1 is by user service
Demand is divided into several execution modules, set of all execution module types as formalization, in task resolution demand process, from
Corresponding execution module is called in set.
Beneficial effects of the present invention:
1. the present invention predicts the performance interference between virtual functions, is service chaining by virtual functions interference prediction module
Dynamic adjustment provide decision-making foundation;Service chaining mapping block can handle user service request, real time monitoring service chaining operation
State simultaneously realizes that service chaining maps;The present invention can effectively improve service chaining in the case of based on virtual functions interference prediction
Execution performance, meet the target of disposition optimization, substantially reduce cost.
2. the present invention designs function combination and service chaining selection method based on degree of disturbance using simulated annealing thought, consider
Dependence, succession, the interference of the performance of function distributing in service chaining between each virtual network function unit, substantially reduce example
In the annoyance level of corresponding platform, the flexibility of service chaining deployment.
Description of the drawings:
Fig. 1 is the virtual functions service chaining deployment system schematic diagram of the present invention;
Fig. 2 is the virtual functions service chaining dispositions method flow diagram of the present invention;
The performance interference that Fig. 3 is the present invention carries out prediction flow diagram;
Fig. 4 is the optimization degree of disturbance prediction model of the present invention and solves flow diagram;
The service chaining that Fig. 5 is the present invention maps flow diagram.
Specific embodiment:
The present invention is described in further detail with technical solution below in conjunction with the accompanying drawings, and it is detailed to pass through preferred embodiment
Describe bright embodiments of the present invention in detail, but embodiments of the present invention are not limited to this.
Embodiment one, a kind of shown in Figure 1, virtual functions service chaining deployment system, comprising:
Virtual functions interference prediction module distributes virtual resource, to virtual functions and virtual resource demand for load application
Between relationship analyzed, predict virtual functions between performance interference, with service chaining mapping block carry out information exchange;
Users service needs are converted to the service module function of formalization, according to service function by service chaining mapping block
Schedule dependence and user demand between module are ranked up service module function, and selection target physical platform, need to
The service module function information and active information wanted are sent to target physical platform;
Virtual functions carrying platform, comprising physical platform and platform control system, platform control system is used to receive and locate
The function activation request from service chaining mapping block, feedback active information are managed, and monitors virtual functions operating status, platform control
System processed asks to generate respective instance by function activation.
Preferably, the physical platform is single server or the data center to gather server composition.
Embodiment two, shown in Figure 2, a kind of virtual functions service chaining dispositions method specifically comprises the following steps:
Step 1. service chaining mapping block receives user service request, and issues virtual functions after service request is formalized
Interference prediction module, wherein user service include type, duration and the QoS demand of service;
Step 2. virtual functions interference prediction module obtains the physical in compass of competency by virtual functions carrying platform
The application of function carrying data of platform, predict, and prediction result is anti-performance interference suffered after new function example deployment
It is fed to service chaining mapping block;
Step 3. service chaining mapping block assesses service chaining overall interference, selects optimal deployment scheme;
Optimal deployment scheme is mapped to corresponding virtual functions carrying platform by step 4. service chaining mapping block, and is activated
Function example;
Step 5. virtual functions carrying platform monitors physical platform function operation data in real time, and service chaining mapping block is real-time
Link channel operation data is monitored, if occurring overloading according to the judgement of the testing result of data packetloss rate or interfering excessive situation, is returned
Return step 2.
Embodiment three, it is shown in Figure 3, it is essentially identical with embodiment two, the difference lies in:
The step 2 specifically includes following content:
After step 2.1. virtual functions interference predictions module receives user's request, the operation information of physical platform is collected, is known
Other resource redundancy platform, and it is sent to service chaining mapping block;
Step 2.2. service chainings mapping block removes the physical platform of connectivity of link difference, knows according to resource redundancy platform
Do not go out the platform of resource redundancy, and result is fed back into virtual functions interference prediction module;
Step 2.3. virtual functions interference prediction modules examine or check physical platform work(according to cpu busy percentage and I/O bandwidth resources
Applicable performance degree of disturbance, establishes degree of disturbance prediction model;
Step 2.4. optimizes degree of disturbance prediction model, is solved using linear regression method, and will solve result of calculation and send
To service chaining mapping block.
Example IV, it is shown in Figure 4, it is essentially identical with embodiment two, the difference lies in:The step 2.4 is specific
Include following content:
Step 2.4.1. is based on degree of disturbance prediction model, defines the degree of disturbance attribute of each physical platform, and demarcate one
Virtual functions carry out degree of disturbance traversal to all physical platforms, elect N number of physics for virtual functions degree of disturbance minimum
Platform, wherein, platform quantitative value N is determined by optimization complexity;
Step 2.4.2. chooses a physical platform from N number of physical platform at random, virtual by what is demarcated in previous step
Function distributing is to the physical platform, and using the physical platform as the starting point of service chaining;
Step 2.4.3. continues to demarcate remaining virtual functions, by walking to removing preamble according to degree of disturbance prediction model
All physical platforms outside physical platform disposed in rapid carry out degree of disturbance traversal, calculate wherein each physical platform and interfere
The difference of the interference value of virtual functions demarcated in value and step 2.4.1 chooses M platform minimum in difference, platform quantity
Value M is determined according to optimization complexity;
Step 2.4.4. chooses a physical platform from M physical platform at random, virtual by what is demarcated in step 2.4.3
On function distributing to the physical platform, remaining virtual functions are disposed successively according to step 2.4.3, and it is complicated to record decision optimization
The platform quantitative value of property;
Step 2.4.5. is according to the corresponding platform quantitative value of service chaining sequential search, the platform quantity corresponding to virtual functions
Value is equal to 1, then is examined in the platform quantitative value of subsequent virtual functions in sequence, until all platform quantitative values are whole
When being 1, the selection of its functional link is terminated, when the corresponding platform quantitative value of virtual functions is more than 1, is then subtracted 1, and simultaneously from original
It is deleted in corresponding physical platform and corresponding has used physical platform, and jump in step 2.4.3 and re-execute the virtual functions
Deployment;
Step 2.4.6. performs step 2.4.1 ~ 2.4.5 to remaining service chaining, and the degree of disturbance for calculating every service chaining is equal
Value, the degree of disturbance mean value of more each service chaining, degree of disturbance mean value computation Consideration include the degree of disturbance of each platform in link
With the weights of importance of platform, more each link interference degree mean value selects the link of mean value minimum as optimal deployment scheme.
Embodiment five, it is shown in Figure 5, it is essentially identical with embodiment two, the difference lies in:The step 5 also includes:
Step 5.1. checks whether each virtual functions requirement is mapped to corresponding object in users service needs
Platform if the total resources needed for virtual functions requirement are less than or equal to the available resource of the physical platform, carries out
Next step, otherwise, switching platform examination object examines or check new physical platform;
Step 5.2. activates function example, and active information is back to service chaining mapping block;
Step 5.3. service chaining mapping blocks compile each virtual functions deployment scenario of service chaining, in each virtual work(
Non-overloaded channel can be selected to create link between deployment platform;
Step 5.4. service chainings mapping block activates entire service chaining and monitors the performance operating condition of each virtual functions
And message transmission rate.
Above-mentioned virtual functions service chaining dispositions method, the service request formalization content in step 1 is by user service
Demand is divided into several execution modules, set of all execution module types as formalization, in task resolution demand process, from
Corresponding execution module is called in set.
The invention is not limited in above-mentioned specific embodiment, those skilled in the art can also make a variety of variations accordingly,
It is but any all to cover within the scope of the claims with equivalent or similar variation of the invention.
Claims (7)
1. a kind of virtual functions service chaining deployment system, it is characterised in that:Comprising:
Virtual functions interference prediction module distributes virtual resource, between virtual functions and virtual resource demand for load application
Relationship is analyzed, and predicts the performance interference between virtual functions, information exchange is carried out with service chaining mapping block;
Users service needs are converted to the service module function of formalization, according to service module function by service chaining mapping block
Between schedule dependence and user demand service module function is ranked up, and selection target physical platform, it would be desirable to
Service module function information and active information are sent to target physical platform;
Virtual functions carrying platform, comprising physical platform and platform control system, platform control system comes for receiving and processing
Function activation request, feedback active information from service chaining mapping block, and virtual functions operating status is monitored, platform courses system
System asks to generate respective instance by function activation.
2. virtual functions service chaining deployment system according to claim 1, it is characterised in that:The physical platform is single
Server or the data center to gather server composition.
3. a kind of virtual functions service chaining dispositions method, specifically comprises the following steps:
Step 1. service chaining mapping block receives user service request, and issues virtual functions after service request is formalized and do
Disturb prediction module;
Step 2. virtual functions interference prediction module obtains the physical platform in compass of competency by virtual functions carrying platform
Application of function carries data, and performance interference suffered after new function example deployment is predicted, and prediction result is fed back to
Service chaining mapping block;
Step 3. service chaining mapping block assesses service chaining overall interference, selects optimal deployment scheme;
Optimal deployment scheme is mapped to corresponding virtual functions carrying platform by step 4. service chaining mapping block, and activates work(
It can example;
Step 5. completes service chaining mapping, virtual functions carrying platform real time monitoring physical platform function operation data, service chaining
Mapping block monitors link channel operation data in real time, if occurring overloading or interfere according to the judgement of the testing result of data packetloss rate
Excessive situation, return to step 2.
4. virtual functions service chaining dispositions method according to claim 3, it is characterised in that:The step 2 specifically includes
Following content:
After step 2.1. virtual functions interference predictions module receives user's request, the operation information of physical platform, identification money are collected
Source redundancy platform, and it is sent to service chaining mapping block;
Step 2.2. service chainings mapping block removes the physical platform of connectivity of link difference, and feed back according to resource redundancy platform
To virtual functions interference prediction module;
Step 2.3. virtual functions interference prediction modules should according to cpu busy percentage and I/O bandwidth resources examination physical platform function
Performance degree of disturbance establishes degree of disturbance prediction model;
Step 2.4. optimizes degree of disturbance prediction model, is solved using linear regression method, and is sent to clothes by result of calculation is solved
Business chain mapping block.
5. virtual functions service chaining dispositions method according to claim 4, it is characterised in that:The step 2.4 is specifically wrapped
Containing following content:
Step 2.4.1. is based on degree of disturbance prediction model, defines the degree of disturbance attribute of each physical platform, and demarcates one virtually
Function carries out degree of disturbance traversal to all physical platforms, elects N number of physical for virtual functions degree of disturbance minimum
Platform, wherein, platform quantitative value N is determined by optimization complexity;
Step 2.4.2. chooses a physical platform, the virtual functions that will be demarcated in previous step from N number of physical platform at random
The physical platform is deployed to, and using the physical platform as the starting point of service chaining;
Step 2.4.3. continues to demarcate remaining virtual functions, by removing in previous step according to degree of disturbance prediction model
All physical platforms outside the physical platform disposed carry out degree of disturbance traversal, calculate wherein each physical platform interference value with
The difference of the interference value for the virtual functions demarcated in step 2.4.1 chooses M platform minimum in difference, platform quantitative value M roots
It is determined according to optimization complexity;
Step 2.4.4. chooses a physical platform, the virtual functions that will be demarcated in step 2.4.3 from M physical platform at random
It is deployed on the physical platform, remaining virtual functions is disposed successively according to step 2.4.3, and record and determine optimization complexity
Platform quantitative value;
Step 2.4.5. is according to the corresponding platform quantitative value of service chaining sequential search, platform quantitative value corresponding to virtual functions etc.
In 1, then it is examined in the platform quantitative value of subsequent virtual functions in sequence, until all platform quantitative values all 1
When, the selection of its functional link is terminated, when the corresponding platform quantitative value of virtual functions is more than 1, is then subtracted 1, and simultaneously from former right
It answers to delete in physical platform and corresponding has used physical platform, and jump in step 2.4.3 and re-execute the virtual functions portion
Administration;
Step 2.4.6. performs step 2.4.1 ~ 2.4.5 to remaining service chaining, calculates the degree of disturbance mean value of every service chaining, than
The degree of disturbance mean value of more each service chaining selects the link of mean value minimum as optimal deployment scheme.
6. according to the virtual functions service chaining dispositions method described in claim 3, it is characterised in that:The step 5 also includes:
Step 5.1. checks whether each virtual functions requirement is mapped to corresponding physical in users service needs
Platform if the total resources needed for virtual functions requirement are less than or equal to the available resource of the physical platform, carries out next
Step, otherwise, switching platform examination object examines or check new physical platform;
Step 5.2. activates function example, and active information is back to service chaining mapping block;
Step 5.3. service chaining mapping blocks compile each virtual functions deployment scenario of service chaining, in each virtual functions
Non-overloaded channel is selected to create link between deployment platform;
Step 5.4. service chainings mapping block activate entire service chaining and monitor each virtual functions performance operating condition and
Message transmission rate.
7. virtual functions service chaining dispositions method according to claim 3, it is characterised in that:Service request in step 1
Formalization content is that users service needs are divided into several execution modules, all execution module types as the set formalized,
In task resolution demand process, corresponding execution module is called from set.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510584507.0A CN105242956B (en) | 2015-09-15 | 2015-09-15 | Virtual functions service chaining deployment system and its dispositions method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510584507.0A CN105242956B (en) | 2015-09-15 | 2015-09-15 | Virtual functions service chaining deployment system and its dispositions method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN105242956A CN105242956A (en) | 2016-01-13 |
CN105242956B true CN105242956B (en) | 2018-06-12 |
Family
ID=55040612
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510584507.0A Active CN105242956B (en) | 2015-09-15 | 2015-09-15 | Virtual functions service chaining deployment system and its dispositions method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105242956B (en) |
Families Citing this family (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107483222B (en) * | 2016-06-08 | 2021-08-27 | 中兴通讯股份有限公司 | Virtual network function management method based on micro-service and network management system |
CN106452842B (en) * | 2016-09-14 | 2019-09-24 | 上海海事大学 | Network system based on network function virtualization intermediary system architecture |
CN107526636B (en) * | 2016-10-26 | 2020-11-03 | 腾讯科技(深圳)有限公司 | Resource identification method and device |
US10187263B2 (en) | 2016-11-14 | 2019-01-22 | Futurewei Technologies, Inc. | Integrating physical and virtual network functions in a service-chained network environment |
CN108400998B (en) * | 2017-02-07 | 2020-03-20 | 华为技术有限公司 | VNF deployment method and system |
CN107231412A (en) * | 2017-05-22 | 2017-10-03 | 浙江工商大学 | A kind of service path building method mapped based on virtual net |
CN107483286B (en) * | 2017-08-14 | 2021-01-26 | 电子科技大学 | Method for merging and deploying service function chain based on cloud-fog environment |
CN107395501B (en) * | 2017-08-29 | 2020-04-14 | 电子科技大学 | Cross-domain deployment method of network service function chain |
CN109428817B (en) * | 2017-08-31 | 2021-06-22 | 华为技术有限公司 | Service chain processing method, related network element and system |
CN107579852A (en) * | 2017-09-15 | 2018-01-12 | 郑州云海信息技术有限公司 | Virtual network performance isolation system and method based on historical models in Cloud Server |
CN107749801B (en) * | 2017-09-28 | 2019-09-06 | 西南交通大学 | A kind of virtual network function laying method based on population Incremental Learning Algorithm |
CN109639447B (en) * | 2017-10-09 | 2021-11-12 | 中兴通讯股份有限公司 | Method and device for mapping network function virtualization service chain under ring networking |
CN107682203B (en) * | 2017-10-30 | 2020-09-08 | 北京计算机技术及应用研究所 | Security function deployment method based on service chain |
CN108075990B (en) * | 2018-01-30 | 2020-09-11 | 北京邮电大学 | Resource-aware service chain backup node allocation algorithm and device |
CN111193604B (en) * | 2019-08-23 | 2021-08-17 | 腾讯科技(深圳)有限公司 | Deployment method, device, equipment and storage medium of virtual network function chain |
CN111131319A (en) * | 2019-12-30 | 2020-05-08 | 北京天融信网络安全技术有限公司 | Security capability expansion method and device, electronic equipment and storage medium |
CN113422812B (en) * | 2021-06-08 | 2022-07-29 | 北京邮电大学 | Service chain deployment method and device |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102090020A (en) * | 2008-08-26 | 2011-06-08 | 思科技术公司 | Method and apparatus for dynamically instantiating services using a service insertion architecture |
CN104137482A (en) * | 2014-04-14 | 2014-11-05 | 华为技术有限公司 | Disaster recovery data center configuration method and device under cloud computing framework |
WO2015062627A1 (en) * | 2013-10-29 | 2015-05-07 | Telefonaktiebolaget L M Ericsson (Publ) | Control of a chain of services |
CN104679595A (en) * | 2015-03-26 | 2015-06-03 | 南京大学 | Application-oriented dynamic resource allocation method for IaaS (Infrastructure As A Service) layer |
-
2015
- 2015-09-15 CN CN201510584507.0A patent/CN105242956B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102090020A (en) * | 2008-08-26 | 2011-06-08 | 思科技术公司 | Method and apparatus for dynamically instantiating services using a service insertion architecture |
WO2015062627A1 (en) * | 2013-10-29 | 2015-05-07 | Telefonaktiebolaget L M Ericsson (Publ) | Control of a chain of services |
CN104137482A (en) * | 2014-04-14 | 2014-11-05 | 华为技术有限公司 | Disaster recovery data center configuration method and device under cloud computing framework |
CN104679595A (en) * | 2015-03-26 | 2015-06-03 | 南京大学 | Application-oriented dynamic resource allocation method for IaaS (Infrastructure As A Service) layer |
Also Published As
Publication number | Publication date |
---|---|
CN105242956A (en) | 2016-01-13 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105242956B (en) | Virtual functions service chaining deployment system and its dispositions method | |
Vakili et al. | Comprehensive and systematic review of the service composition mechanisms in the cloud environments | |
Ahmad et al. | Container scheduling techniques: A survey and assessment | |
Sharma et al. | Energy-efficient resource allocation and migration in private cloud data centre | |
CN102724103B (en) | Proxy server, hierarchical network system and distributed workload management method | |
Moldovan et al. | Mela: Monitoring and analyzing elasticity of cloud services | |
Schafer et al. | Tasklets:" better than best-effort" computing | |
JP6575949B2 (en) | MTC event management method and system | |
CN113037877B (en) | Optimization method for time-space data and resource scheduling under cloud edge architecture | |
Ali et al. | A cost and energy efficient task scheduling technique to offload microservices based applications in mobile cloud computing | |
Rajabzadeh et al. | New comprehensive model based on virtual clusters and absorbing Markov chains for energy-efficient virtual machine management in cloud computing | |
Faraji‐Mehmandar et al. | A proactive fog service provisioning framework for Internet of Things applications: An autonomic approach | |
Ateya et al. | Energy efficient offloading scheme for MEC-based augmented reality system | |
KR20210041295A (en) | Virtualized resource distribution system in cloud computing environment | |
CN113242304B (en) | Edge side multi-energy data acquisition scheduling control method, device, equipment and medium | |
CN106407007A (en) | Elasticity analysis process oriented cloud resource allocation optimization method | |
CN105335376B (en) | A kind of method for stream processing, apparatus and system | |
CN113760541A (en) | Method and device for distributing edge resources | |
Vázquez et al. | A cloud scheduler assisted by a fuzzy affinity-aware engine | |
Vigliotti et al. | A green network-aware VMs placement mechanism | |
Antonescu et al. | Sla-driven predictive orchestration for distributed cloud-based mobile services | |
Faraji-Mehmandar et al. | A self-learning approach for proactive resource and service provisioning in fog environment | |
CN110430236A (en) | A kind of method and dispatching device of deployment business | |
Ghiasi et al. | Smart virtual machine placement using learning automata to reduce power consumption in cloud data centers | |
Sandhiya et al. | An Extensive Study of Scheduling the Task using Load Balance in Fog Computing |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |