CN103825963B - Virtual Service moving method - Google Patents
Virtual Service moving method Download PDFInfo
- Publication number
- CN103825963B CN103825963B CN201410101765.4A CN201410101765A CN103825963B CN 103825963 B CN103825963 B CN 103825963B CN 201410101765 A CN201410101765 A CN 201410101765A CN 103825963 B CN103825963 B CN 103825963B
- Authority
- CN
- China
- Prior art keywords
- service
- virtual
- migration
- matrix
- cost
- 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.)
- Expired - Fee Related
Links
Abstract
The present invention relates to a kind of Virtual Service moving method, including：According to service type and user's request selection migration evaluating, monitor monitors the dummy node in network, when new request reaches or user's request changes, obtains status information of the dummy node on evaluating；The services migrating cost of each dummy node is calculated according to the status information；The dummy node for obtaining Virtual Service migration Least-cost from dummy node by the migration cost computational methods is used as service node；The service node is selected to migrate the Virtual Service.Virtual Service moving method provided by the invention, influence of the various factors to migration can be effectively integrated, migration is judged and performed, network resource management is realized using services migrating and improves user service Quality of experience.
Description
Technical Field
The invention relates to the field of mobile internet, in particular to a virtual service migration method.
Background
With the increasing development of technology, the mobile internet has become one of the main trends of the development of the internet. According to statistics, by 3 months in 2013, the number of fixed internet broadband users in our country is 1.81 hundred million users, while the number of mobile internet users reaches 8.17 hundred million users. With the enhancement of network mobility requirements and the change of user behaviors, the continuous enrichment of information interaction types and the increasing increase of data traffic, the guarantee and the improvement of the service experience quality of users become new challenges to be faced in the internet field. The development of virtualization technology provides the possibility of solving the problem of mobility requirement. The virtualization aims to realize smooth movement of virtual services under the condition of not considering the attributes of a bottom-layer physical network, realize on-demand allocation of network resources and improve the experience quality of users. Fig. 1 is a schematic diagram of network virtualization in the prior art. As shown in fig. 1, the virtualization technology supports multiple Virtual Networks (VN) on a common underlying physical Network (SN) through abstraction, separation, and isolation mechanisms, each Virtual Network may use a protocol system independent of each other, and reasonably configures node resources and link resources in the entire Network according to dynamically changing user requirements, so as to greatly exert the advantage of resource sharing, improve the utilization rate of Network resources to the maximum extent, and obtain the maximum benefit.
Fig. 2 is a schematic diagram of the prior art Flowvisor implementing virtualization. As shown in fig. 2, the FlowVisor effectively implements network virtualization by dividing a flow table space to generate independent network segments, and divides a physical network into a plurality of network segments. The network flows on each network fragment are isolated from each other, and the bandwidth, the use of a CPU, the configuration of a flow table and the like are managed. The user can carry out the experimental research of various flow models, protocol innovation and the like which are not interfered with each other on each segment. At present, flowVisor is deployed in some large campuses such as Stanford university in the United states, and the FlowVisor is also used for managing virtualization on the famous future network experimental bed GENI and Internet2 projects.
Fig. 3 is a schematic diagram of a network virtualization layered service providing model in the prior art. As shown in fig. 3, in a virtualization environment, a Service Provider (SP) describes required resources (network resources, computing resources, storage resources, etc.) to an underlying Infrastructure Provider (InP) in a certain form according to the needs of a User (User). The infrastructure provider deploys and manages the underlying physical resources, and selects corresponding resources from the virtual resource pool to complete the creation of the virtual network. The service provider leases network resources to the infrastructure provider to provide the required services to the user.
Due to the addition of some new users, the removal of some old users, the change of the positions of some users in the network, the change of the number of users, the user behavior and the user preference in the network, or the change of some underlying networks, the virtual service needs to be adjusted and migrated according to the change. How to adjust the scale and resource distribution of the virtual network in time according to the changes, ensure the Quality of network Service (QoS) and the Quality of user Experience (QoE), obtain reliable and stable network Service with minimum delay, and is one of the challenges in implementing virtual Service. Virtualization in the present invention mainly refers to virtualization of a server/host, and provides sharable and reusable software and hardware resources and information of virtualization to a computer and other devices as needed.
Fig. 4 is a schematic diagram of user migration in the prior art. As shown in fig. 4, service migration requires consideration of a balance of various costs. When the virtual node closer to the user acts as a service provider, the delay of the service may be smaller, and the quality of service and the quality of experience are higher. However, the migration at the same time may also bring other overhead, which may have negative effects, such as pressure on the network from a large amount of data transmission during the migration, and even may cause service interruption. The service migration problem is how to reasonably adjust the position of the network service, so that the network resource is more effectively saved, the service response time and cost are reduced, and the user experience is improved.
In the prior art, currently, in a virtualization environment, research and application for implementing network Resource management and reducing energy consumption by using service migration are still more preliminary, such as research made by J Grassler, S Schmid, et al in "at 32nd IEEE Conference on Computer Communications (INFOCOM Demo), furin, italy, april2013. The service migration problem in the virtualization environment is mainly divided into two application scenarios, namely a single-domain application scenario and a multi-domain application scenario.
In a single domain environment, the difference between nodes in terms of the type, quality and the like of resources is small, and the migration cost is low. But when the nodes in the domain can not meet the requirements of the user, the nodes in other domains need to be migrated to provide services. Not only are there differences between nodes in multiple domains, but additional roaming costs are incurred across domains.
The following references to M Bienkowski, A Feldmann et al In "In Proc. ACM SIGCMM VISA,2010." comprehensive analysis fVirtual service balance migration Algorithm (MIG) proposed by or service migration in vnets and Cross-Domain balance Algorithm (MIX) proposed by D Arora, M Bienkowski et al in "Proceedings of the5th International Conference on Principles, systems and Applications of IP Telecommunications, 2011" on line protocols for intra and inter provider service migration in virtual networks k ) A brief introduction is made.
(1) Virtual service balance migration algorithm (MIG)
And quantifying each parameter of the migration cost and the migration profit by a virtual service balance migration algorithm (MIG), and judging the migration time by a dynamic comparison method. The basic idea of the MIG algorithm is to reach a migration Cost when a migration occurs mig And profit Cost acc A balance between selecting a viable, better service provider.
When the location of the user changes, the delay from the virtual server side to the client side will increase, which will affect the quality of service for some services. By migration, the optimization of service delay can be realized, namely, the service delay is the migration benefit Cost acc A part of (a). In addition, whether migration can be implemented is also related to the available load of the server. If the potential node cannot meet the user's needs, the migration cannot proceed. When migration is performed, under the same condition, a node with a large available load of the server should be selected for migration. Thus at time t, for request sequence R t Profit Cost generated by migration acc Can be expressed as
It is assumed herein that the available load of all servers can meet the user's demand, for Cost acc Is simplified to obtain
Due to the influence of the bandwidth on the migration path and the size of the service itself, care needs to be taken whether to perform the service migration. The size(s) of the service itself and the bandwidth w (p) of the migration path together determine the time required for migration. Cost of service s to be migrated in this document mig Is shown as
In the virtual service balance migration algorithm, only the service migration problem in one infrastructure providing domain is considered, so the Cost of service migration mig Can be simplified into
Cost mig (u,v)＝max e size(s)/w(e) （4）
The virtual service balance migration algorithm divides time into a plurality of time slots, assuming that the initial provider is node v. When a request arrives, a time slot starts, and a Cost generated due to a change of the request is calculated acc (v) In that respect If another virtual network node, such as node u, is used as the service provider, i.e. service migration occurs, a migration Cost is generated mig (v, u). Let β = max u {Cost mig (u, v) }. If Cost is satisfied acc （v）>, beta, migration occurs from satisfying the inequality Cost acc （u）&The solution set of beta randomly selects a node as the service provider of the request. If no such node u exists, no migration is required and the slot ends. When the next request arrives, a new slot starts, and the Cost is recalculated acc （v）。
(2) Cross-domain balancing algorithm (MIX) k ）
Cross-domain balancing algorithm (MIX) k ) The method is an improvement and optimization of a virtual service balance migration algorithm, and considers the condition that a service providing node is positioned in a plurality of virtual networks. The latency of the request is Cost acc (v) Migration cost β = max u {Cost mig (u, v) }. Assuming the additional cost incurred across a domainIs pi (wherein pi is more than or equal to beta) 2 ) Then the cost of roaming across k realms is k x pi.
Assuming that the original provider is node v, when the sequence of service requests arrives, the migration within a domain is considered first. Calculating a revenue Cost generated by the request acc (v) And the migration cost β = max u {Cost mig (u, v) } comparison. If Cost is satisfied acc （v）>, beta, then satisfy the inequality Cost acc （u）&And (4) randomly selecting one node as a migration destination node in the solution set of the beta. If no such node u exists in the domain, service migration in a cross-domain case is considered. If the profit Cost acc (v) Migration is done at an additional cost over cross-domain generation.
In summary, the migration method of the prior art has the following problems: the MIG migration algorithm only simply considers two influence factors of service delay and link bandwidth, and the factors influencing the selection of the migration nodes are many. The service delay is simply quantified as the number of hops between the service request access node and the service provider. The quantification of the two factors is too simple and rigid, which is not favorable for the dynamic adjustment of the migration opportunity. Moreover, the factors determining migration are influenced by interaction, and the mutual relation among the factors cannot be reflected by simply comparing the sizes. Although MIX k Roaming cost caused by cross-domain is added in the algorithm, but the problem of simplicity in quantization and correlation characterization still exists.
Disclosure of Invention
The invention aims to solve the problems and provides a virtual service migration method based on fairness, fairness and dynamic QoS calculation models.
In order to achieve the above object, the present invention provides a virtual service migration method, where the method includes:
selecting a migration evaluation parameter according to the service type and the user requirement, monitoring a virtual node in the network by a monitor, and obtaining the state information of the virtual node about the evaluation parameter when a new request arrives or the user request changes;
calculating the service migration cost of each virtual node according to the state information;
acquiring a virtual node with the minimum virtual service migration cost from the virtual nodes as a service node by calculating the service migration cost of each virtual node;
and selecting the service node to migrate the virtual service.
Preferably, the state information includes a delay of the service, an available load of the server, a bandwidth on the migration path, a size of the service itself, a cost of service interruption and restoration, a service provider credit, and an execution price.
Preferably, the calculating the service migration cost of each virtual node according to the state information specifically includes:
and establishing and generating a QoS-based calculation model according to the state information.
Preferably, the establishing and generating a QoS-based calculation model according to the state information specifically includes:
obtaining a matrix Q according to the state information:
wherein m and n are integers, q n,m For elements in the matrix Q, use C (v) i ) Representing a virtual node v i Each row in the matrix Q represents various pieces of state information of the virtual node, and each column in the matrix Q represents one piece of state information that affects the migration cost.
Preferably, the establishing and generating a QoS-based calculation model according to the state information further includes:
normalizing the matrix Q, normalizing the state information of different dimensions into dimensionless standardized parameters, and forming a uniform measurement standard;
and grouping the standardized parameters, wherein each group comprises a plurality of standardized parameters, and operating according to the group to obtain the migration cost information of each grouped virtual node.
Preferably, the normalizing the matrix Q to normalize the state information of different dimensions into dimensionless normalized parameters, and forming a uniform metric specifically includes:
the first matrix is represented by N = { N = { (N) } 1 ,n 2 ,...,n m Denotes wherein n is j J is not less than 0 or 1,1 and not more than m;
second matrix C = { C = 1 ,c 2 ,...,c m Denotes, c is j Is a constant, j is more than or equal to 1 and less than or equal to m;
each element in the matrix Q is normalized by the following equation:
wherein, the first and the second end of the pipe are connected with each other,obtaining a matrix Q' as an average value of j-th cost standards in the matrix Q:
wherein q is i,j Being an element in the matrix Q, Q n,m 'is an element in the matrix Q'.
Preferably, the method further comprises: the migration of the virtual node is not performed when no new request arrives or no change occurs in the user request transmission.
The invention has the following beneficial effects:
1. the cost of service migration is calculated by adopting a method based on a QoS calculation model, so that the problem that dynamic adjustment of migration opportunity is not facilitated due to too simple and rigid quantization of influence factors is avoided;
2. the influence of various factors on the migration cost is effectively integrated, custom input parameters are allowed to be added, and dynamic adjustment can be performed according to the virtual network environment and the requirements of users;
3. influence parameters related to the properties of the virtual nodes are considered, the credit and the price of the virtual nodes are increased, and the service quality of the virtual service nodes is evaluated more comprehensively and practically;
4. and the node with the minimum migration cost is selected for migration, so that the cost caused by migration is minimized, the service experience quality of a user is improved, and green, energy-saving and efficient virtual resource migration and scheduling are realized.
Drawings
FIG. 1 is a diagram illustrating network virtualization in the prior art according to the present invention;
FIG. 2 is a schematic diagram of a Flowvisor in the prior art according to the present invention;
FIG. 3 is a diagram illustrating a network virtualization layered service providing model in the prior art according to the present invention;
FIG. 4 is a diagram illustrating user migration in the prior art;
FIG. 5 is a flowchart illustrating a virtual service migration method according to an embodiment of the present invention;
FIG. 6 is a diagram illustrating a local monitor monitoring each virtual node in a network in accordance with an embodiment of the present invention;
fig. 7 is a flowchart of calculating a service migration cost of each virtual service node in an embodiment of the present invention.
Detailed Description
The technical solution of the present invention is further described in detail by the accompanying drawings and embodiments.
FIG. 5 is a flowchart illustrating a virtual service migration method according to an embodiment of the present invention.
As shown in fig. 5, first, in step 501, migration evaluation parameters are selected according to the service type and the user requirement. The monitor monitors the virtual nodes in the network and obtains the state information of the virtual nodes about the evaluation parameters when a new request arrives or a user request changes.
Specifically, the cost of a virtual node/virtual server is affected by a combination of factors. To simplify the problem, in one embodiment of the present invention, only the case where there is only one virtual network on the physical network, and in the virtual network, there is only one virtual node/server.
Table 1 gives several major factors that influence the migration cost.
TABLE 1
| Influencing parameter | Meaning of parameters |
| C delay | Time delay of service |
| C aload | Available load of server |
| C bandwidth | Bandwidth on migration paths |
| C size | Size of service itself |
| C interrupt | Cost of service interruption and resumption |
| C reputation | Service provider credit |
| C price | Price of execution |
Wherein, in order to select the virtual node with better service quality as the service provider, the invention adds 2 attributes related to the self property of the service provider, namely C reputation And C price 。
C reputation The credit is a main evaluation index of the credibility of the virtual node for the service provider. It depends on the end user's historical service experience. Different end users may have different ratings for the same service provider. The credit of a virtual node is defined as the average of the feedback evaluations of a plurality of end-users, i.e.Where n is the total number of times a node is evaluated, R i Feedback value, R, for end-user to node credit i Is of [0,5 ]]Is an integer of (1).
C price In order to implement the price, the user needs to pay the required fee when the virtual node provides the service. In the same case, the requester is more inclined to select a less expensive node to provide service.
Fig. 6 is a schematic diagram of a local monitor monitoring each virtual node in a network according to an embodiment of the present invention.
As shown in fig. 6, the monitor monitors each virtual node in the network and collects status information on the virtual node. The state information includes the state information shown in table 1, such as delay time, link bandwidth, and node available load.
Specifically, in an embodiment of the present invention, a set of all virtual service providers is defined as V = { V = { (V) } 1 ,v 2 ,...,v n Denotes at t k Time of day, request delta k And (4) arrival. Previous stage of virtual service provider usage s k-1 And (4) showing. The object of the present embodiment is to determine at t k Time of day request delta k When it arrives, whether the virtual service provider needs to be migrated to a new virtual node, and to which node. When migration is needed, the node with the minimum migration cost is selected for migration. Is composed of C (v) i ) Is expressed as node v i The migration cost of (2). Using m criteria to evaluate the cost of a node, the following matrix Q can be obtained:
the matrix Q is a matrix of n rows and m columns, n and m being integers. Wherein the ith row in the matrix Q represents a virtual service node v i Each column represents a factor affecting the cost.
As shown in fig. 5, in the next step 502, a service migration cost of each virtual node is calculated based on the state information. The calculation method comprises the following specific steps:
fig. 7 is a flowchart of calculating a service cost of each virtual service node according to an embodiment of the present invention.
As shown in fig. 7, first, in step 701, the matrix Q is normalized, and the state information of different dimensions is normalized into dimensionless normalized parameters, so as to form a uniform metric.
Specifically, the purpose of normalizing the matrix Q is: (1) Allows for a unit independent, standard migration cost measurement method; (2) Providing a unified index for evaluating the migration cost for each virtual service provider; and (3) setting a threshold value.
First, two matrices are defined. First matrixN={n 1 ,n 2 ,...,n m J is more than or equal to 1 and less than or equal to m, wherein n j =0 or 1. If following q ij Increase, increase the cost of migration, let n j =1 (e.g. parameter C) size The larger the migration cost). On the contrary n j =0 (e.g. migration is more inclined towards C aload Larger nodes). The second matrix C = { C = 1 ,c 2 ,...,c m }，c j Is a constant set to the maximum value of each cost evaluation index normalization. Each element in Q is normalized by the formula (6) (7).
In the above-mentioned formula, the compound of formula,is the average of the jth cost criteria in the matrix Q. The new matrix Q' is obtained by operating Q according to the above formula, as shown in formula (8):
in the next step 702, the standardized parameters are grouped, each group includes a plurality of standardized parameters, and the operation is performed according to the group, so as to obtain the migration cost information of each grouped virtual node.
Specifically, the cost parameters of the virtual nodes are grouped, and each group may include multiple parameters and operate according to the group. In an embodiment of the present invention, the access Cost can be divided into acc And a migration Cost mig Cost of server pri Three parts, such as bandwidth, size of service itself, cost of service interruption and recovery all belong toMigration Cost mig Service delay and available load, etc. are part of the Cost of access mig The price and credit of the server belong to the server Cost pri . In this embodiment, a matrix D is introduced, and the matrix D is used to define the relationship between the cost index and the cost group.
Wherein, each row in the matrix D represents a cost index factor, each column represents a cost group, and l is the total group number. In matrix D, if the ith cost index belongs to the jth packet in Q', D i,j =1, otherwise d i,j =0。
The matrix G is cost information of each virtual service node after grouping.
Wherein, each row in G represents a network service provider, and each column represents a value of one cost packet.
The matrix G can be calculated by the following formula:
G=Q、*D （11）
the matrix G is normalized by first defining two new matrices: matrix T and matrix F. Matrix T = { T = { (T) 1 ,t 2 ,...,t l Where constant t j Indicating the normalized threshold for each group. G is normalized according to equation (12) to yield the result G'.
As shown in fig. 7, in the final step 703, migration costs of all virtual nodes are comprehensively calculated according to packet weights. Definition matrix F = { F 1 ,f 2 ,...,f l In which f j The weight of the jth group in the overall evaluation, which represents the cost evaluation, can be used to represent the user's preference for the jth group evaluation criteria. Providing node s for virtual service i The cost calculation of (c) can be obtained by equation (14):
in the following step 503, the virtual node with the minimum virtual service migration cost is obtained from the virtual nodes as the service node by the migration cost calculation method.
In an embodiment of the present invention, a virtual network with 6 nodes is preferred, and the node set is V = { V = { V } 1 ,v 2 ,...,v 6 }. Initial service node S 0 Is a node v 1 At t 1 Time of day, request sequence delta 1 And (4) arriving. Preferably 5 migration cost evaluation parameters: time delay C of service delay Server available load C aload Migration path bandwidth C bandwidth Price C price And credit C reputation . Obtaining a matrix Q of evaluation parameters of each node through a local monitor:
a threshold value C = (5,5,5,5), and N = (1,0,0,1,0) is obtained from 5 evaluation indices. By the above equations (6) and (7), the normalized matrix Q' is calculated:
in the embodiment, 5 evaluation indexes are classified into 3 types, namely access cost Costacc, migration cost Costmig and server cost Costpri. The matrix D is then:
the matrix G is calculated by equation (11) as:
in the examples, a threshold matrix T = (3, 3) is defined, and G' is obtained by normalization by equation (12):
the weights of the 3-class evaluation criteria in the total migration evaluation were defined to be 0.4, 0.2, respectively. The migration costs of the 6 service nodes calculated by the above equation (14) are 1.1941, 1.0616, 1.2203, 1.0025, 0.6944 and 0.8271, respectively.
Specifically, the migration costs of the 6 service nodes obtained from the above calculation are 1.1941, 1.0616, 1.2203, 1.0025, 0.6944 and 0.8271 respectively, where 0.6944 is the smallest in the migration cost value, and the virtual node v corresponding to 0.694 is selected 5 Providing a node for a service.
Returning to fig. 5, in the final step 504, the service node is selected to migrate the virtual service, i.e. from the service node at the previous time to the virtual node with the smallest migration cost.
Specifically, among the 6 service nodes, the service node v from the previous time is 1 Migration to v 5 I.e. the virtual service node corresponding to the minimum migration cost of 0.6944. In summary, the present invention provides a method and system based on a public, fair and dynamicThe QoS calculation model provides a virtual service migration method. Wherein the QoS reconciles the needs of the service requester with the needs of the service provider based on available network resources. QoS includes the likelihood that a service will respond to a request at a given time, how well the service will perform its tasks, how fast the service will run, and the reliability and security of the service. Thus, the QoS parameters that affect the service are throughput, delay time, execution time, reliability, cost, security, credit, etc. The unit of various parameters is different, the numerical value is greatly different, indexes have no comparability, and the result of directly comparing the sizes is inaccurate. Normalization processing and comprehensive calculation of the parameter information are required, thereby allowing the service requester to select a service with higher quality of service among a plurality of services satisfying the requirements.
The virtual service migration method provided by the invention applies the QoS calculation idea to the service migration cost calculation, not only considers two influence parameters of service delay and link bandwidth, but also considers various parameters influencing the service migration cost, such as available load, price and the like of a server, in the process of selecting a target migration node, comprehensively calculates the parameters, and selects the node with the minimum migration cost as a service provider of a request sequence. The method can effectively integrate the influence of various factors on the migration, judge and execute the migration, realize network resource management by using service migration and improve the quality of user service experience.
Those of skill would further appreciate that the various illustrative components and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative components and steps have been described above generally in terms of their functionality in order to clearly illustrate this interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied in hardware, a software module executed by a processor, or a combination of the two. A software module may reside in Random Access Memory (RAM), memory, read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
The above-mentioned embodiments are intended to illustrate the objects, technical solutions and advantages of the present invention in further detail, and it should be understood that the above-mentioned embodiments are merely exemplary embodiments of the present invention, and are not intended to limit the scope of the present invention, and any modifications, equivalent substitutions, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (5)
1. A virtual service migration method, the method comprising:
selecting migration evaluation parameters according to service types and user requirements, monitoring virtual nodes in a network by a monitor, and obtaining state information of the virtual nodes about the migration evaluation parameters when a new request arrives or a user request changes;
calculating the service migration cost of each virtual node according to the state information;
calculating the service migration cost of each virtual node, and acquiring the virtual node with the minimum service migration cost from the virtual nodes as a service node;
selecting the service node to migrate the virtual service;
the state information comprises service time delay, available load of a server, bandwidth on a migration path, size of the service, service interruption and recovery cost, service provider credit and execution price;
the calculating the service migration cost of each virtual node according to the state information specifically includes:
and establishing a QoS-based calculation model according to the state information.
2. The virtual service migration method according to claim 1, wherein the establishing a QoS-based calculation model according to the state information specifically includes:
obtaining a matrix Q according to the state information:
wherein m and n are integers, m is the number of kinds of state information, n is the number of virtual nodes, q is the number of the virtual nodes i,j Is an element in the matrix Q, i is an integer not greater than n, j is an integer not greater than m, using C (v) i ) Representing a virtual node v i The ith row in the matrix Q represents a virtual node v i Each column in the matrix Q represents a type of state information that affects the service migration cost.
3. The virtual service migration method according to claim 2, wherein the establishing a QoS-based calculation model according to the state information further specifically includes:
normalizing the matrix Q, normalizing the state information of different dimensions into dimensionless normalized parameters, and forming a uniform measurement standard;
and grouping the standardized parameters, wherein each group comprises a plurality of standardized parameters, and operating according to the group to obtain service migration cost information of each grouped virtual node.
4. The virtual service migration method according to claim 3, wherein the normalizing the matrix Q normalizes the state information of different dimensions into dimensionless normalized parameters, and forming a uniform metric specifically includes:
the first matrix is represented by N = { N = { (N) } 1 ,n 2 ,...,n m Denotes whereinM is the number of the types of the state information, j is more than or equal to 1 and less than or equal to m, if the number is following q i,j Increasing, the service migration cost becomes larger, then n j =1, otherwise n j ＝0；
Second matrix C = { C = 1 ,c 2 ,...,c m Denotes, c is j Is a constant which is set as the maximum value of normalization of each state information, m is the number of the types of the state information, and j is more than or equal to 1 and less than or equal to m;
each element in the matrix Q is normalized by the following equation:
wherein the content of the first and second substances,obtaining a matrix Q' for the average value of j-th state information in the matrix Q:
wherein q is i,j Being elements of the matrix Q, Q i,j 'is an element in the matrix Q'.
5. The virtual service migration method of claim 1, wherein the method further comprises: the virtual service is not migrated when no new requests arrive or user request transmissions do not change.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410101765.4A CN103825963B (en) | 2014-03-18 | 2014-03-18 | Virtual Service moving method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410101765.4A CN103825963B (en) | 2014-03-18 | 2014-03-18 | Virtual Service moving method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103825963A CN103825963A (en) | 2014-05-28 |
| CN103825963B true CN103825963B (en) | 2017-12-22 |
Family
ID=50760787
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410101765.4A Expired - Fee Related CN103825963B (en) | 2014-03-18 | 2014-03-18 | Virtual Service moving method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103825963B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104539551B (en) * | 2014-12-22 | 2017-11-17 | 清华大学 | Routing switch platform Virtual Service moving method |
| CN104537682B (en) * | 2015-01-26 | 2018-09-07 | 四川众亿得科技有限责任公司 | A kind of segmentation of medical image and dispatching method |
| CN105743985A (en) * | 2016-03-24 | 2016-07-06 | 国家计算机网络与信息安全管理中心 | Virtual service migration method based on fuzzy logic |
| CN111045822B (en) * | 2019-12-07 | 2023-12-29 | 深圳先进技术研究院 | Service migration method, system and terminal equipment in mobile cloud computing |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102790793A (en) * | 2012-05-08 | 2012-11-21 | 北京邮电大学 | Decision method and control module facing to cloud computing virtual machine migration |
| CN103064744A (en) * | 2012-12-27 | 2013-04-24 | 北京仿真中心 | Resource optimizing method applied to multi-layer web application based on SLA (Service Level Agreement) |
| CN103561077A (en) * | 2013-10-29 | 2014-02-05 | 李飞 | Cloud storage task scheduling method on condition of multiple QoS constraints |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP5835846B2 (en) * | 2012-08-29 | 2015-12-24 | 株式会社日立製作所 | Network system and virtual node migration method |
-
2014
- 2014-03-18 CN CN201410101765.4A patent/CN103825963B/en not_active Expired - Fee Related
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102790793A (en) * | 2012-05-08 | 2012-11-21 | 北京邮电大学 | Decision method and control module facing to cloud computing virtual machine migration |
| CN103064744A (en) * | 2012-12-27 | 2013-04-24 | 北京仿真中心 | Resource optimizing method applied to multi-layer web application based on SLA (Service Level Agreement) |
| CN103561077A (en) * | 2013-10-29 | 2014-02-05 | 李飞 | Cloud storage task scheduling method on condition of multiple QoS constraints |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103825963A (en) | 2014-05-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Pei et al. | Resource aware routing for service function chains in SDN and NFV-enabled network | |
| US7953843B2 (en) | System and method for evaluating a heterogeneous cluster for supporting expected workload in compliance with at least one service parameter | |
| US9740534B2 (en) | System for controlling resources, control pattern generation apparatus, control apparatus, method for controlling resources and program | |
| EP3329639B1 (en) | Network function virtualization | |
| CN107846371B (en) | QoE resource allocation method for multimedia service | |
| Shang et al. | Service-aware adaptive link load balancing mechanism for Software-Defined Networking | |
| Hemmati et al. | QoE-aware bandwidth allocation for video traffic using sigmoidal programming | |
| CN103825963B (en) | Virtual Service moving method | |
| Kim et al. | An energy-aware service function chaining and reconfiguration algorithm in NFV | |
| Tajiki et al. | CECT: computationally efficient congestion-avoidance and traffic engineering in software-defined cloud data centers | |
| D’Oro et al. | Auction-based resource allocation in OpenFlow multi-tenant networks | |
| Wang et al. | Multi-leader multi-follower Stackelberg game based dynamic resource allocation for mobile cloud computing environment | |
| JP5506889B2 (en) | Communication traffic prediction device, communication traffic prediction method, and program | |
| Dezhabad et al. | Learning-based dynamic scalable load-balanced firewall as a service in network function-virtualized cloud computing environments | |
| Abreu et al. | A rank scheduling mechanism for fog environments | |
| Gouareb et al. | Delay sensitive virtual network function placement and routing | |
| Li et al. | Service home identification of multiple-source IoT applications in edge computing | |
| Sun et al. | Efficient VNF placement for Poisson arrived traffic | |
| Zhang et al. | Leveraging QoE heterogenity for large-scale livecaset scheduling | |
| Ye et al. | Delay-based network utility maximization modelling for congestion control in named data networking | |
| Yi et al. | A multi-criteria decision approach for minimizing the influence of VNF migration | |
| Lu et al. | Cost-efficient resource provisioning in delay-sensitive cooperative fog computing | |
| Shuai et al. | A cost-based distributed algorithm for load balancing in content delivery network | |
| Kamboj et al. | A policy based framework for quality of service management in software defined networks | |
| Chakravarthy et al. | Software-defined network assisted packet scheduling method for load balancing in mobile user concentrated cloud |
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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20171222 Termination date: 20200318 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |