CN111245701B - Link priority virtual network mapping method based on maximum weighted matching - Google Patents
Link priority virtual network mapping method based on maximum weighted matching Download PDFInfo
- Publication number
- CN111245701B CN111245701B CN202010067331.2A CN202010067331A CN111245701B CN 111245701 B CN111245701 B CN 111245701B CN 202010067331 A CN202010067331 A CN 202010067331A CN 111245701 B CN111245701 B CN 111245701B
- Authority
- CN
- China
- Prior art keywords
- link
- virtual
- physical
- mapping
- links
- 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
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L12/00—Data switching networks
- H04L12/28—Data switching networks characterised by path configuration, e.g. LAN [Local Area Networks] or WAN [Wide Area Networks]
- H04L12/46—Interconnection of networks
- H04L12/4641—Virtual LANs, VLANs, e.g. virtual private networks [VPN]
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L12/00—Data switching networks
- H04L12/28—Data switching networks characterised by path configuration, e.g. LAN [Local Area Networks] or WAN [Wide Area Networks]
- H04L12/46—Interconnection of networks
- H04L12/4641—Virtual LANs, VLANs, e.g. virtual private networks [VPN]
- H04L12/4675—Dynamic sharing of VLAN information amongst network nodes
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L45/00—Routing or path finding of packets in data switching networks
- H04L45/12—Shortest path evaluation
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L45/00—Routing or path finding of packets in data switching networks
- H04L45/12—Shortest path evaluation
- H04L45/123—Evaluation of link metrics
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L45/00—Routing or path finding of packets in data switching networks
- H04L45/12—Shortest path evaluation
- H04L45/124—Shortest path evaluation using a combination of metrics
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L45/00—Routing or path finding of packets in data switching networks
- H04L45/12—Shortest path evaluation
- H04L45/125—Shortest path evaluation based on throughput or bandwidth
Abstract
The invention discloses a link priority virtual network mapping method based on maximum weighted matching, relates to the technical field of computer networks, and particularly relates to virtual network mapping. On the basis of a link priority mapping method, the random link mapping is changed into a mapping mode which takes link distance minimization as a target, a link comprehensive bandwidth measurement index is newly defined, the bandwidth of a link and the bandwidth of an adjacent link are comprehensively considered, then the first virtual link in maximum weighted matching is mapped to the physical link with the maximum comprehensive bandwidth measurement index, and the subsequent mapping success probability is improved. Through the scheme, the method and the device can effectively reduce the average number of the physical links of the virtual links in the virtual network mapping result and improve the acceptance rate of the virtual network.
Description
Technical Field
The invention belongs to the technical field of computer networks, and particularly relates to a link priority mapping method based on maximum weighted matching.
Background
The network virtualization technology can create a plurality of logically mutually independent virtual networks on a bottom physical network, the virtual network mapping problem is an important research content in the field of network virtualization, and the efficient virtual network mapping algorithm can improve the utilization rate of network resources and provide a high-quality virtual network mapping result.
The virtual network mapping problem is essentially to study how to reasonably allocate resources of a physical network, but the resource allocation problem has many new characteristics, such as that a requested resource and a resource to be allocated both have network structures, and the constraint condition for allocating resources is more, so that the resource allocation problem is very challenging. How to design a virtual network mapping algorithm to efficiently and reasonably map a virtual network is a key technology in the field of network virtualization.
The current virtual network mapping algorithm is divided into an exact solution algorithm and a non-exact solution algorithm. The general idea of the accurate solution algorithm is based on the optimization theory, the virtual network mapping problem is modeled and classified into a mathematical programming problem, and the optimal solution of the mathematical programming problem is obtained through the optimization theory. The non-exact solution generally gives a better feasible solution in an acceptable time by a heuristic way, utilizing the characteristics of the problem to be solved and a specific solving way.
Different algorithms also perform different processing on the condition of the mapping failure of the virtual network, one type is to directly reject the virtual network request with the mapping failure, and each virtual network request arrives and is immediately processed to ensure the real-time performance required by an application scene. And the other type designs a processing model with a time window, sorts virtual network requests arriving in the same time window from large to small according to the possible benefits and tries mapping in sequence. And (4) putting the virtual network request which fails to be mapped back to the waiting queue, taking out the virtual network request in the waiting queue in the next time window and processing the virtual network request together with the newly arrived virtual network request, wherein the request which is not mapped is rejected if the specified time is exceeded. Although the processing can improve the income of the operator, the virtual network request needs to be processed in a centralized way after the time window is finished, so that the real-time property of the virtual network request applied by the user cannot be met.
Disclosure of Invention
The technical problem to be solved by the invention is to provide a link priority virtual network mapping method based on maximum weighted matching.
In order to achieve the purpose, the invention adopts the following technical scheme:
a link priority virtual network mapping method based on maximum weighted matching comprises the following steps:
the method comprises the following steps: calculating a maximum weighted match for a given network topology;
step two: sorting all the virtual links in the maximum weighted matching in a descending order according to the bandwidth requirement, mapping the first virtual link to be mapped to the physical link with the maximum link comprehensive bandwidth metric index value, and sequentially selecting the physical link by the rest virtual links by taking the minimum link distance as a target, namely selecting the physical link with the minimum average distance with the mapped physical link;
step three: the rest unmapped virtual nodes are sorted in descending order according to the size of the resource value and then are mapped to the physical node which enables the whole link resource cost to be minimum in sequence;
step four: the remaining unmapped virtual links are mapped using the KSP mapping algorithm.
Wherein, the calculation formula of the link comprehensive bandwidth measurement index value in the second step is as follows:
wherein cb (l)i) Indicates the current physical link liA composite bandwidth metric index value of (a); n (l)i) Is represented byiAdjacent links of, i.e. with liLinks with common nodes; the weight gamma belongs to (0,1), the relative weight between the current physical link and the adjacent link is adjusted, when gamma is 0, the formula is degenerated into the link bandwidth, and only the bandwidth value of the link is used as the index of the link importance; the larger the value of gamma is,the greater the bandwidth value impact of the contiguous link,indicating a contiguous link ljAt the current physical link liThe proportion of all adjacent links; nbw (l)i) And nbw (l)j) Respectively representing the current physical link liAnd a contiguous link ljThe link bandwidth of (c).
Wherein, the link distance calculation formula in the second step is as follows:
where dis (l)a,b,lc,d) Represents a physical link la,bWith physical links lc,dThe distance of (d); sp (node1, node2) represents the length of the shortest path between node1 to node2, and a, b and c, d are two nodes of two physical links, respectively.
Wherein, the link resource overhead calculation formula of the physical node in the third step is:
whereinFor a virtual node that has not yet been mapped, collecting all unmapped virtual nodes;is a mapped virtual link that belongs to the largest weighted match,representing virtual linksThe bandwidth requirements of the link of (a),anda virtual link exists between them;representing physical nodesTo the physical nodeThe number of physical links included in the shortest path of (c);for all and in the networkA set of connected virtual links; for physical nodes that are not mapped in the network request,is composed ofThe physical node mapped to.
Wherein, the step four is specifically as follows:
calculating the first K shortest paths between two physical nodes mapped by two virtual nodes of a virtual link to be mapped, arranging the shortest paths according to the hop count of the paths in an ascending order, and sequentially checking whether the residual bandwidth resources of all the physical links on the shortest paths meet the bandwidth requirements of the virtual link to be mapped; if yes, mapping the virtual link to be mapped to the first shortest path meeting the condition; if the K shortest paths are checked and the conditions are not met, the virtual link mapping fails; wherein K is a set value.
Compared with the prior art, the invention has the following technical effects:
the invention provides a link comprehensive bandwidth measurement index, which comprehensively considers the bandwidth of a link and the bandwidth of an adjacent link and improves the mapping success rate of a subsequent link; and the link distance is proposed, so that the physical links used for mapping are gathered together as much as possible, and the average number of the physical links of the virtual links is reduced.
Drawings
FIG. 1 is a schematic flow diagram of a specific embodiment;
Detailed Description
The invention is further described below with reference to the accompanying drawings:
referring to fig. 1, the method for mapping a link-first virtual network based on maximum weighted matching includes the following steps:
the method comprises the following steps: calculating a maximum weighted match for a given network topology;
step two: all virtual links in the maximum weighted matching are mapped according to the principle that one virtual link is mapped to one physical link. According to the bandwidth requirement of the virtual links, carrying out descending sorting and sequential mapping, mapping the first virtual link to be mapped to the physical link with the maximum link comprehensive bandwidth metric index value, and selecting the physical link by the rest virtual links by taking the minimum link distance as a target, namely selecting the physical link with the minimum average link distance to the physical link which is mapped and used;
the calculation formula of the link comprehensive bandwidth metric index value is as follows:
wherein cb (l)i) Indicates the current physical link liA composite bandwidth metric index value of (a); n (l)i) Is represented byiAdjacent links of, i.e. with liLinks with common nodes; the weight gamma belongs to (0,1), the relative weight between the current physical link and the adjacent link is adjusted, when gamma is 0, the formula is degenerated into the link bandwidth, and only the bandwidth value of the link is used as the index of the link importance; the larger gamma, the greater the bandwidth value impact of the adjacent link,indicating a contiguous link ljAt the current physical link liThe proportion of all adjacent links; nbw (l)i) And nbw (l)j) Respectively representing the current physical link liAnd a contiguous link ljThe link bandwidth of (c).
The link distance calculation formula is as follows:
where dis (l)a,b,lc,d) Represents a physical link la,bWith physical links lc,dThe distance of (d); sp (node1, node2) represents the length of the shortest path between node1 to node2, and a, b and c, d are two nodes of two physical links, respectively.
The specific process is in Step 1.
Step 1
Step three: mapping the remaining unmapped virtual nodes. And sequencing the rest unmapped nodes in a descending order according to the size of the resource value of the virtual nodes, and then mapping in sequence, namely mapping the virtual nodes with larger resource values in advance and mapping in sequence to the physical nodes which enable the whole link resource cost to be minimum. The resource value calculation formula of the virtual node is as follows:
wherein CPU (n)V)、BW(lV) Respectively representing virtual nodes nVCPU resource requirement and virtual link lVBandwidth resource requirements of; neib (n)V) Representation and virtual node nVConnected virtual links.
In order to minimize the resource overhead, the resource overhead of all physical nodes satisfying the resource constraint condition needs to be calculated and sorted. If the virtual node to be mappedMapping to physical nodesIn the above, the calculation formula of the link resource overhead consumed by the virtual node mapping scheme is as follows:
wherein the content of the first and second substances,for a virtual node that has not yet been mapped, for all unmapped virtualA node set;is a mapped virtual link that belongs to the largest weighted match,representing virtual linksThe bandwidth requirements of the link of (a),anda virtual link exists between them;representing physical nodesTo the physical nodeThe number of physical links included in the shortest path of (c);for all and in the networkA set of connected virtual links; for physical nodes that are not mapped in the network request,is composed ofThe physical node mapped to.
The specific process of mapping the remaining unmapped virtual nodes is shown as step 2.
Step 2
Step four: mapping the remaining unmapped virtual links. The virtual node mapping scheme is determined after all virtual nodes are mapped, and the mapping of the remaining unmapped virtual links can be completed only by using a KSP mapping algorithm. The method specifically comprises the following steps: calculating the first K shortest paths between two physical nodes mapped by two virtual nodes of a virtual link to be mapped, arranging the shortest paths according to the hop count of the paths in an ascending order, and sequentially checking whether the residual bandwidth resources of all the physical links on the shortest paths meet the bandwidth requirements of the virtual link to be mapped; if yes, mapping the virtual link to be mapped to the first shortest path meeting the condition; if the K shortest paths are checked and the conditions are not met, the virtual link mapping fails; wherein K is a set value.
The specific mapping process is shown as step 3.
Step 3
Although specific embodiments of, and examples for, the invention are disclosed in the accompanying drawings for illustrative purposes and to aid in the understanding of the contents of the invention and the manner in which the same may be practiced, those skilled in the art will understand that: various substitutions, changes and modifications are possible without departing from the spirit and scope of the present invention and the appended claims. The present invention should not be limited to the disclosure of the embodiments and drawings described in the specification, and the scope of the present invention is defined by the scope of the claims.
Claims (3)
1. A link priority virtual network mapping method based on maximum weighted matching is characterized by comprising the following steps:
the method comprises the following steps: calculating a maximum weighted match for a given network topology;
step two: sorting all the virtual links in the maximum weighted matching in a descending order according to the bandwidth requirement, mapping the first virtual link to be mapped to the physical link with the maximum link comprehensive bandwidth metric index value, and sequentially selecting the physical link by the rest virtual links by taking the minimum link distance as a target, namely selecting the physical link with the minimum average distance with the mapped physical link;
step three: the rest unmapped virtual nodes are sorted in descending order according to the size of the resource value and then are mapped to the physical node which enables the whole link resource cost to be minimum in sequence;
step four: mapping the rest unmapped virtual links by using a KSP mapping algorithm;
wherein, the calculation formula of the link comprehensive bandwidth measurement index value in the second step is as follows:
wherein cb (l)i) Indicates the current physical link liA composite bandwidth metric index value of (a); n (l)i) Is represented byiAdjacent links of, i.e. with liLinks with common nodes; the weight value gamma belongs to (0,1), the relative weight between the current physical link and the adjacent link is adjusted, and when gamma is 0, the formulaThe sub-link is degraded into link bandwidth, and only the bandwidth value of the link is used as the index of link importance; the larger gamma, the greater the bandwidth value impact of the adjacent link,indicating a contiguous link ljAt the current physical link liThe proportion of all adjacent links; nbw (l)i) And nbw (l)j) Respectively representing the current physical link liAnd a contiguous link ljThe link bandwidth of (a);
the link distance calculation formula in the second step is as follows:
where dis (l)a,b,lc,d) Represents a physical link la,bWith physical links lc,dThe distance of (d); sp (node1, node2) represents the length of the shortest path between node1 to node2, and a, b and c, d are two nodes of two physical links, respectively.
2. The method for mapping a link-first virtual network based on maximum weighted matching according to claim 1, wherein the link resource overhead calculation formula of the physical node in step three is as follows:
whereinFor a virtual node that has not yet been mapped, collecting all unmapped virtual nodes;is a mapped virtual link that belongs to the largest weighted match,representing virtual linksThe bandwidth requirements of the link of (a),anda virtual link exists between them;representing physical nodesTo the physical nodeThe number of physical links included in the shortest path of (c);for all and in the networkA set of connected virtual links; for physical nodes that are not mapped in the network request,is composed ofThe physical node mapped to.
3. The method for mapping a link-first virtual network based on maximum weighted matching according to claim 1, wherein the step four is specifically:
calculating the first K shortest paths between two physical nodes mapped by two virtual nodes of a virtual link to be mapped, arranging the shortest paths according to the hop count of the paths in an ascending order, and sequentially checking whether the residual bandwidth resources of all the physical links on the shortest paths meet the bandwidth requirements of the virtual link to be mapped; if yes, mapping the virtual link to be mapped to the first shortest path meeting the condition; if the K shortest paths are checked and the conditions are not met, the virtual link mapping fails; wherein K is a set value.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010067331.2A CN111245701B (en) | 2020-01-20 | 2020-01-20 | Link priority virtual network mapping method based on maximum weighted matching |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010067331.2A CN111245701B (en) | 2020-01-20 | 2020-01-20 | Link priority virtual network mapping method based on maximum weighted matching |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111245701A CN111245701A (en) | 2020-06-05 |
CN111245701B true CN111245701B (en) | 2021-08-31 |
Family
ID=70878011
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010067331.2A Active CN111245701B (en) | 2020-01-20 | 2020-01-20 | Link priority virtual network mapping method based on maximum weighted matching |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111245701B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111884854B (en) * | 2020-07-29 | 2022-09-02 | 中国人民解放军空军工程大学 | Virtual network traffic migration method based on multi-mode hybrid prediction |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108667657A (en) * | 2018-04-28 | 2018-10-16 | 西安交通大学 | A kind of mapping method of virtual network based on local feature information towards SDN |
CN110224918A (en) * | 2019-05-17 | 2019-09-10 | 西安交通大学 | A kind of cross-domain SDN mapping method of virtual network |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104320324B (en) * | 2014-11-18 | 2017-12-12 | 中国科学技术大学 | A kind of mapping method of virtual network based on link interference |
CN107277832A (en) * | 2017-06-12 | 2017-10-20 | 重庆邮电大学 | A kind of mapping method of wireless dummy network |
CN107770096B (en) * | 2017-12-11 | 2021-07-30 | 国网河南省电力公司信息通信公司 | SDN/NFV network dynamic resource allocation method based on load balancing |
-
2020
- 2020-01-20 CN CN202010067331.2A patent/CN111245701B/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108667657A (en) * | 2018-04-28 | 2018-10-16 | 西安交通大学 | A kind of mapping method of virtual network based on local feature information towards SDN |
CN110224918A (en) * | 2019-05-17 | 2019-09-10 | 西安交通大学 | A kind of cross-domain SDN mapping method of virtual network |
Non-Patent Citations (4)
Title |
---|
VirtualRack: Bandwidth-Aware Virtual Network Allocation for Multi-Tenant Datacenters;Tianlin Huang;《IEEE ICC》;20140614;全文 * |
基于二分图最优匹配的虚拟网络映射算法;韩晓阳!;《系统工程与电子技术》;20191231;全文 * |
基于多维属性的跨域虚拟网络映射算法;张治中;《电子科技大学学报》;20190331;全文 * |
基于链路带宽检测的虚拟网络映射算法;陈星;《计算机与网络》;20160126;全文 * |
Also Published As
Publication number | Publication date |
---|---|
CN111245701A (en) | 2020-06-05 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108260169B (en) | QoS guarantee-based dynamic service function chain deployment method | |
CN109150627B (en) | Virtual network mapping construction method based on dynamic resource demand and topology perception | |
CN108566659B (en) | 5G network slice online mapping method based on reliability | |
CN108965014B (en) | QoS-aware service chain backup method and system | |
CN112738820A (en) | Dynamic deployment method and device of service function chain and computer equipment | |
CN107454019B (en) | Dynamic bandwidth allocation method, device, equipment and storage medium for software defined network | |
CN108684046B (en) | Random learning-based access network service function chain deployment method | |
WO2019072162A1 (en) | Virtual network mapping method, device and storage medium | |
CN107196806B (en) | Topological proximity matching virtual network mapping method based on sub-graph radiation | |
Liu | Intelligent routing based on deep reinforcement learning in software-defined data-center networks | |
CN112486690A (en) | Edge computing resource allocation method suitable for industrial Internet of things | |
CN112291791B (en) | Power communication mesh bandwidth resource allocation method based on 5G slice | |
WO2020177255A1 (en) | Resource allocation method and device for wireless access network | |
CN107124303A (en) | The service chaining optimization method of low transmission time delay | |
Wang et al. | Adaptive placement and routing for service function chains with service deadlines | |
Hsu et al. | Virtual network mapping algorithm in the cloud infrastructure | |
CN111092827B (en) | Power communication network resource allocation method and device | |
CN111245701B (en) | Link priority virtual network mapping method based on maximum weighted matching | |
CN110048966B (en) | Coflow scheduling method for minimizing system overhead based on deadline | |
CN110191155B (en) | Parallel job scheduling method, system and storage medium for fat tree interconnection network | |
CN112423041B (en) | Video stream processing method and system based on QoS constraint under distributed computing platform | |
CN111756655B (en) | Virtual network resource migration method based on resource reservation | |
CN111935748B (en) | Virtual network resource allocation method with high reliability and load balance | |
WO2024036909A1 (en) | Fair load unloading and migration method for edge service network | |
Zhang | Reliable virtual network mapping algorithm with network characteristics and associations |
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 |