CN113225211B - Fine-grained service function chain extension method - Google Patents
Fine-grained service function chain extension method Download PDFInfo
- Publication number
- CN113225211B CN113225211B CN202110462420.1A CN202110462420A CN113225211B CN 113225211 B CN113225211 B CN 113225211B CN 202110462420 A CN202110462420 A CN 202110462420A CN 113225211 B CN113225211 B CN 113225211B
- Authority
- CN
- China
- Prior art keywords
- expansion
- physical link
- link
- hop count
- extension
- 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
- 238000000034 method Methods 0.000 title claims abstract description 80
- 230000008859 change Effects 0.000 claims description 8
- 238000012937 correction Methods 0.000 abstract description 2
- 238000002474 experimental method Methods 0.000 description 6
- 230000007480 spreading Effects 0.000 description 4
- 238000004808 supercritical fluid chromatography Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 235000008694 Humulus lupulus Nutrition 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 230000003247 decreasing effect Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- HEFNNWSXXWATRW-UHFFFAOYSA-N Ibuprofen Chemical compound CC(C)CC1=CC=C(C(C)C(O)=O)C=C1 HEFNNWSXXWATRW-UHFFFAOYSA-N 0.000 description 1
- 240000000278 Syzygium polyanthum Species 0.000 description 1
- AGOYDEPGAOXOCK-KCBOHYOISA-N clarithromycin Chemical compound O([C@@H]1[C@@H](C)C(=O)O[C@@H]([C@@]([C@H](O)[C@@H](C)C(=O)[C@H](C)C[C@](C)([C@H](O[C@H]2[C@@H]([C@H](C[C@@H](C)O2)N(C)C)O)[C@H]1C)OC)(C)O)CC)[C@H]1C[C@@](C)(OC)[C@@H](O)[C@H](C)O1 AGOYDEPGAOXOCK-KCBOHYOISA-N 0.000 description 1
- 238000010835 comparative analysis Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- 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
- H04L47/83—Admission control; Resource allocation based on usage prediction
-
- 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
- H04L41/0896—Bandwidth or capacity management, i.e. automatically increasing or decreasing capacities
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/50—Reducing energy consumption in communication networks in wire-line communication networks, e.g. low power modes or reduced link rate
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention relates to a fine-grained SFC (Small form factor correction) expansion method, belonging to the field of network security. Firstly, a vertical extension method is improved, and vertical extension and flow splitting are combined, so that the success rate of vertical extension is improved. And secondly, improving the horizontal extension method, providing resources for the SFC according to the requirement of the SFC for extending the resources, reducing the cost of the extended resources and improving the utilization rate of the resources. Finally, an improved vertical extension method is combined with a horizontal extension method, so that the extension power is further improved, and the extension resource overhead is reduced.
Description
Technical Field
The invention relates to a fine-grained Service Function Chain (SFC) extension method, which comprises improved vertical and horizontal extension methods and belongs to the field of network security.
Background
The document "Hui Yu, Jianhai Yang, and Carol Long. Fine-Grained Cloud Resource Provisioning for Virtual Network Function" proposes an elastic Resource supply method, namely the ElasticNFV method, for the dynamic SFC expansion problem. According to the method, the resource overhead is reduced by adopting vertical extension, and when resources such as a CPU (central processing unit) of the server do not meet the requirement of extending the resources, other VNF instances deployed on the server are migrated until enough residual resources exist. The document "Adel Nadjaran Toosi, Jungmin Son, Qinghua Chi, Rajkumar Buyya. elastic SFC: auto-scaling techniques for electronic service function in network functions simulation-based clusters" proposes an elastic SFC expansion method, namely an elastic SFC method, for the problem of dynamic SFC expansion. The method adopts horizontal extension and vertical extension, and improves the extension success rate. However, the following problems exist in the elastonfv process and the elastosfc process:
(1) the ElasticNFV method is subject to the constraints of available resources of the server and available bandwidth of the underlying link, so that SFC expansion failure is easily caused, and the expansion success rate of the method is low.
(2) When the elastic SFC method adopts vertical extension, the SFC extension is easy to fail due to the constraint of the available bandwidth of a bottom link.
(3) When horizontal expansion is adopted in the ElasticSFC method, the method belongs to coarse-grained expansion, the expansion resource expense is increased easily, and the resource utilization rate is reduced.
Disclosure of Invention
Technical problem to be solved
In order to improve the success rate of service function chain extension and further reduce the cost of extended resources, the invention provides a fine-grained SFC extension method.
Technical scheme
A fine-grained service function chain extension method is characterized by comprising the following steps:
step 1: predicting the resource demand of the g service function chain SFC;
step 2: judging whether expansion is needed or not according to the resource demand prediction result; if the resource demand change rate at the time of SFC (g) t +1 is greater than the maximum resource demand change rate satisfying the service level agreement, i.e. lambda g (t+1)>Lambda-delta, then need to be extended(ii) a If λ g (t+1)<1, releasing corresponding resources;
and step 3: for each virtual network function and corresponding virtual link, firstly, a vertical expansion method is adopted for expansion;
and 4, step 4: and if the improved vertical extension method fails, performing extension by adopting a horizontal extension method.
The further technical scheme of the invention is as follows: in the step 1, the CloudScale technology is adopted for prediction.
The further technical scheme of the invention is as follows: the vertical extension method in step 3 combines vertical extension and flow splitting, and comprises the following steps:
step 1: judging whether the available CPU, forwarding and storage resources of the server node are more than or equal to the jth virtual network function f j A resource demand increase value at a next time; if the result is negative, the vertical expansion fails; otherwise, expanding the virtual link;
and 2, step: judgment of f j-1 Whether vertical expansion or horizontal expansion is adopted; if it is a horizontal extension, choose to connect the newly deployed f j-1 Examples and f j One physical link of the example is used for providing increased bandwidth for the corresponding virtual link, and the hop count of the selected physical link is less than or equal to the hop count of the original physical link; if the virtual link is vertically extended, whether the available bandwidth of the physical link bearing the corresponding virtual link meets the requirement of the increased bandwidth resource is judged, and if the available bandwidth meets the requirement, the physical link provides the increased bandwidth; if not, connection f is selected j-1 Examples and f j An example physical link provides increased bandwidth for a corresponding virtual link while the selected physical link has a hop count that is less than or equal to the hop count of the original physical link.
The further technical scheme of the invention is as follows: the horizontal extension method in step 4 comprises the following steps:
step 1: according to jth virtual network function f j Increased resource demand selection server node deployment of new f j Examples; the selected server node is to satisfy f j Increased resource demand and load capacity constraints, while the number of hops between the new instance and the original instance is less than or equal to the hop count constraint h 0 (ii) a If the corresponding server node does not exist, the expansion fails;
step 2: judgment of f j-1 Whether vertical expansion or horizontal expansion is adopted; if vertical expansion, connection f is selected j-1 Instances and newly deployed f j One physical link of the instance is used for providing increased bandwidth for the corresponding virtual link, and the hop count of the selected physical link is less than or equal to the hop count of the original physical link; if it is a horizontal extension, choose to connect the newly deployed f j-1 Instances and newly deployed f j One physical link of the instance is used for providing increased bandwidth for the corresponding virtual link, and the hop count of the selected physical link is less than or equal to the hop count of the original physical link; if there is no corresponding physical link to provide the increased bandwidth, the expansion fails.
A computer system, comprising: one or more processors, a computer readable storage medium, for storing one or more programs, which when executed by the one or more processors, cause the one or more processors to implement the above-described method.
A computer-readable storage medium having stored thereon computer-executable instructions for performing the above-described method when executed.
A computer program comprising computer executable instructions which when executed perform the method described above.
Advantageous effects
The invention provides a fine-grained SFC (Small form-factor correction) expansion method. Firstly, a vertical extension method is improved, and vertical extension and flow splitting are combined, so that the success rate of vertical extension is improved. And secondly, improving the horizontal extension method, providing resources for the SFC according to the requirement of the SFC for extending the resources, reducing the cost of the extended resources and improving the utilization rate of the resources. And finally, an improved vertical extension method is combined with a horizontal extension method, so that the extension power is further improved, and the extension resource overhead is reduced.
Drawings
The drawings are only for purposes of illustrating particular embodiments and are not to be construed as limiting the invention, wherein like reference numerals are used to designate like parts throughout.
FIG. 1 is a schematic diagram of the SFC deployment of the present invention.
FIG. 2 is a schematic diagram illustrating the SFC expansion method of the present invention: (a) SFC; (b) vertically expanding; (c) improved vertical expansion; (d) horizontal expansion; (e) improved horizontal spreading.
Fig. 3 is a schematic diagram of an improved vertical expansion method according to the present invention: (a) SFC deployment; (b) improved vertical spreading.
Fig. 4 is a flow chart of the HSM method according to the present invention.
FIG. 5 is a graph of the power comparison results expanded in the method of the present invention: (a) | N g |＝3；(b)|N g |＝4；(c)|N g |＝5。
Fig. 6 is a graph comparing the average extended resource overhead in the method of the present invention.
FIG. 7 is a graph of the comparison of average extended resource utilization in the method of the present invention: (a) a CPU; (b) bandwidth.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and do not limit the invention. In addition, the technical features involved in the embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other.
1. Establishing SFC deployed network model
Physical network: according to the invention, a plurality of infrastructure providers are selected to provide hardware services as an application scene, and the bearing capacity of the universal server nodes may have differences. The physical network may use an empowerment undirected graph G s ＝(V s ,E s ) Is shown in which V s ＝V s,s ∪V s,f ，V s ＝{v i |i＝1,2,…,|V s |}，V s,s ＝{v s,i |i＝1,2,…,|V s,s }，V s,f ＝{v f,i |i＝1,2,…,|V s,f |}，E s ＝{e j |j＝1,2,…,|E s }。
The SFC requests: an SFC request may be granted undirected G g ＝{N g ,L g ,S g ,T g In which N is g ＝{f j |j＝1,2,…,|N g |}，L g ＝{l j |j＝1,2,…,|L g And l. Traffic flows in from one switch node, through a given sequence of virtual network functions, and out from another switch node.
Deployment of the SFC: when the SFC request arrives, the service provider instantiates the various virtual network functions of the service function chain in a defined order, as shown in fig. 1. SFC deployment requires consumption of bandwidth resources, computing resources, and forwarding resources of the underlying network, while SFC resource requirements are dynamically changing. The symbols commonly used in the present invention and their meanings are shown in table 1.
TABLE 1 common symbols and their meanings
2. SFC extension method description
The SFC extension method is mainly divided into vertical extension and horizontal extension.
(1) Vertical expansion
As shown in fig. 2(b), when the resource demand of the SFC increases, the server node bearing the VNF and the physical link bearing the corresponding virtual link respectively provide resources for the server node and the physical link according to the resource demand. When the resource requirement of the SFC is reduced, the server node and the corresponding physical link release the corresponding resource. When the resource demand of the SFC increases, the vertical extension is prone to fail due to the constraints of the available resources of the server node and the available bandwidth of the physical link.
(2) Horizontal expansion
As shown in fig. 2(d), when the resource demand of the SFC increases, a new VNF instance is deployed on other server nodes, the server nodes provide the same resource for the new instance as the original instance, and the bandwidth provided by the physical link between the newly added instance and the previous instance is the same as the bandwidth provided by the original physical link. The resources provided by the server node for the newly added instance and the bandwidth provided by the newly added physical link are often both greater than the resource requirements. When the resource requirement of the SFC is reduced, the server node and the corresponding physical link release the corresponding resource. Horizontal expansion belongs to coarse-grained expansion, which easily causes resource over-supply and has low utilization rate of expanded resources.
3. Improved vertical expansion method
As shown in fig. 2(c), the Improved Vertical Spreading (IVS) method combines vertical spreading with traffic splitting, reducing the impact of bandwidth resource constraints and increasing the spread-to-power. The method comprises the following specific steps:
step 1: judging whether the available CPU, forwarding and storage resources of the server node are more than or equal to the next moment f j The resource demand increase value of (2). If the result is negative, the vertical expansion fails; and on the other side, expanding the virtual link.
Step 2: judgment of f j-1 Vertical or horizontal expansion is used. If it is a horizontal extension, choose to connect the newly deployed f j-1 Examples and f j An example physical link provides increased bandwidth for a corresponding virtual link, while the hop count of the physical link is selected to be less than or equal to the hop count of the original physical link. If the virtual link is vertically extended, whether the available bandwidth of the physical link carrying the corresponding virtual link meets the requirement of the increased bandwidth resource is judged, and if the available bandwidth meets the requirement, the physical link provides the increased bandwidth. If not, connection f is selected j-1 Examples and f j An example physical link provides increased bandwidth for a corresponding virtual link while the selected physical link has a hop count that is less than or equal to the hop count of the original physical link. As shown in fig. 3, the physical link e 1 Does not meet the increased bandwidth demand, over the physical link e 4 Providing increased bandwidth. If there is no corresponding physical link to provide the increased bandwidth, the expansion fails.
4. Improved horizontal expansion method
As shown in fig. 2(e), the improved horizontal extension (IHS) method is a fine-grained extension method, which reduces the overhead of extended resources and improves the utilization of extended resources. The method comprises the following specific steps:
step 1: according to f j Increased resource demand selection server node deployment of new f j Examples are given. The selected server node is to satisfy f j Increased resource demand and load-bearing capacity constraints, while the hop count between the new instance and the original instance is less than or equal to the hop count constraint h 0 . If there is no corresponding server node, the extension fails.
Step 2: judgment of f j-1 Vertical or horizontal expansion is used. If vertical expansion, select connection f j-1 Instances and newly deployed f j An example physical link provides increased bandwidth for a corresponding virtual link while the selected physical link has a hop count that is less than or equal to the hop count of the original physical link. If it is a horizontal extension, choose to connect the newly deployed f j-1 Instance and newly deployed f j An example physical link provides increased bandwidth for a corresponding virtual link, while the hop count of the physical link is selected to be less than or equal to the hop count of the original physical link. If there is no corresponding physical link to provide the increased bandwidth, the expansion fails.
5. Establishing SFC extended integer linear programming model
The method adopts the CloudScale technology to predict the resource demand of the SFC, and supposing that the demand change rates of various resources are the same, the demand change rates are expressed as follows:
let λ be the maximum rate of change of resource demand to meet the service level agreement and δ be an infinitesimal quantity.
CPU, forwarding and storage resource requirements that increase or decrease at time t +1 are used separately
And
indicating increased or decreased bandwidth demand at time t +1
And (4) showing.
According to the invention, a plurality of infrastructure providers are selected to provide hardware services as an application scene, and the bearing capacities of the universal server nodes may have differences. The invention assumes that each server node can only carry several types of virtual network functions, if server node v s,i Can carry virtual network functions f j Then x (v) s,i ,f j ) 1. Otherwise, x (v) s,i ,f j )＝0。
In order to better describe the expansion problem of the SFC, the invention establishes an integer linear programming model of the SFC expansion, and an objective function and related constraint conditions are as follows:
(1) objective function
Wherein, | SFC ss (t) | represents the number of SFCs that successfully expanded at time t, | SFCs ns (t) | represents the number of SFCs that need to be expanded at time t, and η represents the expansion success rate.
(2) Constraint conditions
When lambda is g (t+1)>At the time of the lambda-delta,
constraint (4) indicates if server node v s,i For virtual network functions f j Providing increased resources, then y (v) s,i ,f j ) 1. Otherwise, y (v) s,i ,f j ) 0. Constraint (5) indicates if physical link e i For a virtual link l j Providing increased bandwidth, y (e) i ,l j ) 1. Otherwise, y (e) i ,l j )＝0。
Constraint (6) ensures that only one server node is a virtual network function f j Providing increased resources. Constraint (7) ensures that only one physical link is a virtual link/ j Providing increased bandwidth.
Constraint (8) ensuring server node v s,i There are enough CPU, forwarding and storage resources to satisfy the virtual network function f j Increased resource requirements.
Constraint (9) ensures physical link e i There is enough bandwidth to satisfy the virtual link/ j Increased bandwidth requirements.
h g,a ≤h g,p (10)
The constraint (10) ensures that the number of hops after SFC expansion does not increase.
The constraint (11) ensures that the server node carrying the new VNF instance satisfies the bearer capability constraint.
When lambda is g (t+1)<When the pressure of the mixture is 1, the pressure is lower,
restraint (12) ensuring load bearing f j Of a server node
Releasing
And
and (4) resources.
The constraint (13) ensuring the load bearing j Physical link e of i Releasing
Bandwidth.
6. HSM method design
Fig. 4 is a flow chart of the HSM method according to the present invention.
First, the resource demand of sfc (g) is predicted using CloudScale technology. Secondly, judging whether expansion is needed or not according to the resource demand prediction result. If λ g (t+1)>Lambda-delta, then expansion is required. For all virtual network functions and corresponding virtual links, first of all, an IVS method is used for expansion, e.g.If IVS fails, an IHS method is adopted for expansion. If the IHS fails, the extension fails. If λ g (t+1)<And 1, releasing the corresponding resources.
7. Performance evaluation and analysis
The invention utilizes MATLAB to carry out experimental simulation, selects a larger-scale network scene to carry out performance verification on the method provided by the invention, and carries out comparative analysis with other two methods.
(1) Experimental Environment settings
The underlying network topology and the SFC topology used in the experiment were generated by a modified Salam network topology random generation algorithm. The invention assumes that the switch nodes and the server nodes of the physical network are in the same position, the number of the switch nodes and the server nodes is 100, and the connectivity between the nodes is 0.5. The resource compliance parameters of both the server node and the switch node are [50-60 ]]Is equally distributed, the link bandwidth resource compliance parameter between the switches is [50-60 ]]The average distribution of (c). The invention assumes that each server node can carry VNF type { f } 1 ,f 2 ,f 3 ,f 4 ,f 5 Any two of them.
The invention simulates the sample data of SFC resource requirement by superposition of sine and cosine signals and discretizes the sample data. To simulate a real environment, each sample is added with a value that obeys a poisson distribution. The life cycle of an SFC follows an exponential distribution with a parameter of 1000.
The experiment lasts 10000 time units, the experiment is carried out for 10 times in order to reduce the influence of random factors, and the average value of 10 experimental results is taken as the final experimental result.
(2) Analysis of experiments
The invention sets an experiment to verify the performance of the proposed HSM method, and compares the performance with other two latest expansion methods under the same experimental conditions, and as shown in the table II, the performance of the HSM method in the aspects of expansion success rate and reasonable resource utilization is verified.
TABLE 2 comparison of methods
As shown in fig. 5(a), the HSM is extended to a power plateau of 0.95. The IVS combines vertical expansion and flow splitting, and expansion failure caused by bandwidth resource constraint is reduced. IHS provides resources according to resource requirements, reduces the cost of expanding resources and improves the success rate of expansion. The HSM combines IVS with IHS, which is extended to be most powerful. The expansion of the elastic SFC is stable at 0.88, the vertical expansion and the horizontal expansion are combined, the vertical expansion is easily failed due to the bandwidth resource constraint, the horizontal expansion resource overhead is large, and the vertical expansion is easily failed due to the resource constraint. The extension of ElasticNFV, which is stabilized at 0.78 power, employs vertical extension and is subject to failure due to resource constraints of the server node and bandwidth constraints of the link.
As can be seen from fig. 5(b) and 5(c), the expansion success rate of the HSM method is always the highest for SFCs of different VNF numbers.
As shown in fig. 6, as the number of VNFs increases, the average resource overhead of the ElasticSFC is 119, 173, and 216, respectively, and among the three methods, the resource overhead is the largest. When the available resources of the server node do not meet the resource requirements, the ElasticSFC adopts horizontal expansion to deploy a new VNF instance, the resources provided by the server node for the new instance are the same as the original instance, and the bandwidth provided by the newly added physical link is the same as the original physical link. They tend to be both larger than the resource requirements. Therefore, its average extended resource overhead is the largest. Both HSM and ElasticNFV provide resources according to resource demand, so their extended resource demand is much lower than ElasticSFC. If the available resources of the physical node do not meet the resource requirement, the ElasticNFV will migrate other VNF instances on the server node, and the migrated resources may be larger than the resource requirement. The HSM considers hop count constraints while selecting physical nodes and physical links, and the newly added hop count of the physical link may be lower than that of the original physical link. Therefore, the average resource overhead of HSM is slightly lower than ElasticNFV.
FIG. 7(a) shows average extended CPU resource utilization. HSM and ElasticNFV provide resources according to resource demand, so their average extended CPU resource utilization is always 1. If the available resources of the physical node do not meet the resource requirement, the ElasticSFC adopts horizontal extension, and the CPU provided for the new instance is the same as the original instance and is probably greater than the resource requirement. Therefore, its average expanded CPU resource utilization is less than 1, and as the number of VNFs increases, the utilization is decreasing.
Fig. 7(b) shows the average extended bandwidth resource utilization. Because the hop count of the physical link carrying the SFC is generally greater than the hop count of the virtual link, the average expanded bandwidth resource utilization rate of the three methods is less than 1. When horizontal expansion is adopted by the elastic SFC, the bandwidth provided by the newly added physical link is the same as that of the original physical link and is probably greater than the resource requirement, so that the average expanded bandwidth resource utilization rate is the lowest. The HSM and the ElasticNFV provide bandwidth according to resource demand, so the average bandwidth resource utilization rate is much higher than that of ElasticSFC. When the HSM selects a physical link, hop count constraint is considered, and the hop count of the newly added physical link may be smaller than that of the original physical link, so that the average expanded bandwidth resource utilization rate is slightly higher than that of the ElasticNFV.
From the above experiments, it can be seen that the method HSM provided by the present invention is a fine-grained extension method, and has a higher extension success rate, less average extended resource overhead, and a higher average extended resource utilization rate compared with other two extension methods.
While the invention has been described with reference to specific embodiments, it will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention.
Claims (4)
1. A fine-grained service function chain extension method is characterized by comprising the following steps:
step 1: predicting the resource demand of the g service function chain SFC;
and 2, step: judging whether expansion is needed or not according to the resource demand prediction result; if the resource demand change rate at the time of SFC (g) t +1 is greater than the maximum resource demand change rate satisfying the service level agreement, i.e. lambda g If (t +1) > lambda-delta, expansion is needed; if λ g If (t +1) < 1, releasing the corresponding resources; wherein λ is the maximum resource demand change rate that satisfies the service level agreement, δ is an infinitesimal quantity;
and step 3: for each virtual network function and corresponding virtual link, firstly, a vertical expansion method is adopted for expansion;
the vertical extension method combines vertical extension and flow splitting, and comprises the following steps:
step 3.1: judging whether the available CPU, forwarding and storage resources of the server node are more than or equal to the jth virtual network function f j A resource demand increase value at a next time; if the result is negative, the vertical expansion fails; otherwise, expanding the virtual link;
step 3.2: judgment of f j-1 Whether vertical expansion or horizontal expansion is adopted; if it is a horizontal extension, choose to connect the newly deployed f j-1 Examples and f j One physical link of the instance is used for providing increased bandwidth for the corresponding virtual link, and the hop count of the selected physical link is less than or equal to the hop count of the original physical link; if the virtual link is vertically extended, whether the available bandwidth of the physical link bearing the corresponding virtual link meets the requirement of the increased bandwidth resource is judged, and if the available bandwidth meets the requirement, the physical link provides the increased bandwidth; if not, then select connection f j-1 Examples and f j One physical link of the instance is used for providing increased bandwidth for the corresponding virtual link, and the hop count of the selected physical link is less than or equal to the hop count of the original physical link;
and 4, step 4: if the improved vertical expansion method fails, adopting a horizontal expansion method for expansion;
the horizontal expansion method comprises the following steps:
step 4.1: according to the jth virtual network function f j Increased resource demand selection server node deployment of new f j Examples; selected server node to satisfy f j Increased resource demand and load-bearing capacity constraints, while the hop count between the new instance and the original instance is less than or equal to the hop count constrainth 0 (ii) a If the corresponding server node does not exist, the expansion fails;
step 4.2: judgment of f j-1 Whether vertical expansion or horizontal expansion is adopted; if vertical expansion, connection f is selected j-1 Instances and newly deployed f j One physical link of the instance is used for providing increased bandwidth for the corresponding virtual link, and the hop count of the selected physical link is less than or equal to the hop count of the original physical link; if it is a horizontal extension, choose to connect the newly deployed f j-1 Instances and newly deployed f j One physical link of the instance is used for providing increased bandwidth for the corresponding virtual link, and the hop count of the selected physical link is less than or equal to the hop count of the original physical link; if there is no corresponding physical link to provide the increased bandwidth, the expansion fails.
2. The method of claim 1, wherein the step 1 employs a CloudScale technique for prediction.
3. A computer system, comprising: one or more processors, a computer readable storage medium, for storing one or more programs, wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method of claim 1.
4. A computer-readable storage medium having stored thereon computer-executable instructions, which when executed, perform the method of claim 1.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110462420.1A CN113225211B (en) | 2021-04-27 | 2021-04-27 | Fine-grained service function chain extension method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110462420.1A CN113225211B (en) | 2021-04-27 | 2021-04-27 | Fine-grained service function chain extension method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113225211A CN113225211A (en) | 2021-08-06 |
| CN113225211B true CN113225211B (en) | 2022-09-02 |
Family
ID=77089305
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110462420.1A Expired - Fee Related CN113225211B (en) | 2021-04-27 | 2021-04-27 | Fine-grained service function chain extension method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113225211B (en) |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2015118875A1 (en) * | 2014-02-06 | 2015-08-13 | 日本電気株式会社 | Optimal arrangement method for virtual network function, network control device, network management device, and network system |
| CN107332913A (en) * | 2017-07-04 | 2017-11-07 | 电子科技大学 | A kind of Optimization deployment method of service function chain in 5G mobile networks |
| CN107682203A (en) * | 2017-10-30 | 2018-02-09 | 北京计算机技术及应用研究所 | A kind of security function dispositions method based on service chaining |
| CN108900358A (en) * | 2018-08-01 | 2018-11-27 | 重庆邮电大学 | Virtual network function dynamic migration method based on deepness belief network resource requirement prediction |
| CN109104313A (en) * | 2018-08-20 | 2018-12-28 | 电子科技大学 | A kind of SFC dynamic deployment method with flow consciousness with energy perception |
| CN110120978A (en) * | 2019-05-17 | 2019-08-13 | 电子科技大学 | A kind of method for security protection of elasticity user's cloud computing resources |
| CN110224873A (en) * | 2019-06-24 | 2019-09-10 | 北京邮电大学 | A kind of NFV method of combination and device based on the multiplexing of VNF example |
| CN111475252A (en) * | 2020-03-06 | 2020-07-31 | 重庆邮电大学 | Virtual network function deployment optimization algorithm based on deep reinforcement learning |
| CN111580930A (en) * | 2020-05-09 | 2020-08-25 | 山东汇贸电子口岸有限公司 | Native cloud application architecture supporting method and system for domestic platform |
| CN111638959A (en) * | 2020-06-02 | 2020-09-08 | 山东汇贸电子口岸有限公司 | Elastic expansion method based on load regression prediction in cloud environment and readable storage medium |
| WO2020252390A1 (en) * | 2019-06-12 | 2020-12-17 | Arigato Machine, Inc., Dba Manifold | Predictive autoscaling and resource optimization |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8756609B2 (en) * | 2011-12-30 | 2014-06-17 | International Business Machines Corporation | Dynamically scaling multi-tier applications vertically and horizontally in a cloud environment |
| WO2015118876A1 (en) * | 2014-02-06 | 2015-08-13 | 日本電気株式会社 | Network management method and device |
| US9462084B2 (en) * | 2014-12-23 | 2016-10-04 | Intel Corporation | Parallel processing of service functions in service function chains |
| EP3398304B1 (en) * | 2015-12-30 | 2020-07-22 | Koninklijke KPN N.V. | Network service requests |
| EP3987396A1 (en) * | 2019-06-18 | 2022-04-27 | Telefonaktiebolaget LM Ericsson (publ) | Method and system for deploying a new service function chain (sfc) based on similarities with previously deployed sfcs |
| CN110545228B (en) * | 2019-07-26 | 2020-11-20 | 北京邮电大学 | Service function chain request processing method and system |
-
2021
- 2021-04-27 CN CN202110462420.1A patent/CN113225211B/en not_active Expired - Fee Related
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2015118875A1 (en) * | 2014-02-06 | 2015-08-13 | 日本電気株式会社 | Optimal arrangement method for virtual network function, network control device, network management device, and network system |
| CN107332913A (en) * | 2017-07-04 | 2017-11-07 | 电子科技大学 | A kind of Optimization deployment method of service function chain in 5G mobile networks |
| CN107682203A (en) * | 2017-10-30 | 2018-02-09 | 北京计算机技术及应用研究所 | A kind of security function dispositions method based on service chaining |
| CN108900358A (en) * | 2018-08-01 | 2018-11-27 | 重庆邮电大学 | Virtual network function dynamic migration method based on deepness belief network resource requirement prediction |
| CN109104313A (en) * | 2018-08-20 | 2018-12-28 | 电子科技大学 | A kind of SFC dynamic deployment method with flow consciousness with energy perception |
| CN110120978A (en) * | 2019-05-17 | 2019-08-13 | 电子科技大学 | A kind of method for security protection of elasticity user's cloud computing resources |
| WO2020252390A1 (en) * | 2019-06-12 | 2020-12-17 | Arigato Machine, Inc., Dba Manifold | Predictive autoscaling and resource optimization |
| CN110224873A (en) * | 2019-06-24 | 2019-09-10 | 北京邮电大学 | A kind of NFV method of combination and device based on the multiplexing of VNF example |
| CN111475252A (en) * | 2020-03-06 | 2020-07-31 | 重庆邮电大学 | Virtual network function deployment optimization algorithm based on deep reinforcement learning |
| CN111580930A (en) * | 2020-05-09 | 2020-08-25 | 山东汇贸电子口岸有限公司 | Native cloud application architecture supporting method and system for domestic platform |
| CN111638959A (en) * | 2020-06-02 | 2020-09-08 | 山东汇贸电子口岸有限公司 | Elastic expansion method based on load regression prediction in cloud environment and readable storage medium |
Non-Patent Citations (6)
| Title |
|---|
| Reliability-Aware Service Function Chain Backup Protection Method;DONG ZHAI,XIANGRU MENG, ZHENHUA YU,XIAOYANG HAN;《IEEE Access》;20210112;全文 * |
| 基于在线实例配置的服务功能链部署方法;孙士清等;《计算机工程》;20191215(第12期);全文 * |
| 翟东 ; 孟相如 ; 康巧燕 ; 胡航 ; 韩晓阳.面向时延与可靠性优化的服务功能链部署方法.《电子与信息学报》.2020, * |
| 虚拟网络功能迁移研究综述;朱晓荣等;《南京邮电大学学报(自然科学版)》;20180304(第01期);全文 * |
| 阳勇 ; 孟相如 ; 康巧燕 ; 赵文文.基于流量优化的可靠服务功能链部署方法.《系统工程与电子技术》.2021, * |
| 韩晓阳 ; 孟相如 ; 康巧燕 ; 翟东 ; 刘鹏飞.可靠性与拓扑感知的服务功能链备份保护方法.《系统工程与电子技术》.2020, * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113225211A (en) | 2021-08-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111445111B (en) | Electric power Internet of things task allocation method based on edge cooperation | |
| CN108076158B (en) | Minimum load route selection method and system based on naive Bayes classifier | |
| Cui et al. | A novel offloading scheduling method for mobile application in mobile edge computing | |
| CN110231976B (en) | Load prediction-based edge computing platform container deployment method and system | |
| CN111130904A (en) | Virtual network function migration optimization algorithm based on deep certainty strategy gradient | |
| CN109167671A (en) | A kind of adapted communication system equally loaded dispatching algorithm towards quantum key distribution business | |
| CN102981912B (en) | Method and system for resource distribution | |
| CN110519783B (en) | 5G network slice resource allocation method based on reinforcement learning | |
| Beck et al. | A distributed, parallel, and generic virtual network embedding framework | |
| CN111901170A (en) | Reliability-aware service function chain backup protection method | |
| CN108683557B (en) | Micro-service health degree evaluation method, elastic expansion method and framework | |
| CN108509280B (en) | Distributed computing cluster locality scheduling method based on push model | |
| CN111538570A (en) | VNF deployment method and device for energy conservation and QoS guarantee | |
| WO2019056771A1 (en) | Distributed storage system upgrade management method and device, and distributed storage system | |
| Zhao et al. | PLOFR: An online flow route framework for power saving and load balance in SDN | |
| CN108540405B (en) | Network resource migration method and device | |
| CN112883526B (en) | Workload distribution method under task delay and reliability constraint | |
| CN113993218A (en) | Multi-agent DRL-based cooperative unloading and resource allocation method under MEC architecture | |
| CN112073237B (en) | Large-scale target network construction method in cloud edge architecture | |
| CN113596868A (en) | 5G network slice resource management mechanism based on SDN and NFV | |
| CN114625500A (en) | Method and application for scheduling micro-service application based on topology perception in cloud environment | |
| Zhang et al. | A novel virtual network mapping algorithm for cost minimizing | |
| CN107360235B (en) | Task migration method based on reliability grading | |
| CN114466407B (en) | Network slice arrangement algorithm based on particle swarm inheritance | |
| CN113225211B (en) | Fine-grained service function chain extension method |
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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20220902 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |