CN111756655B - Virtual network resource migration method based on resource reservation - Google Patents
Virtual network resource migration method based on resource reservation Download PDFInfo
- Publication number
- CN111756655B CN111756655B CN202010505459.2A CN202010505459A CN111756655B CN 111756655 B CN111756655 B CN 111756655B CN 202010505459 A CN202010505459 A CN 202010505459A CN 111756655 B CN111756655 B CN 111756655B
- Authority
- CN
- China
- Prior art keywords
- virtual
- network
- migration
- link
- node
- 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
- 238000013508 migration Methods 0.000 title claims abstract description 146
- 230000005012 migration Effects 0.000 title claims abstract description 144
- 238000000034 method Methods 0.000 title claims abstract description 30
- 238000013468 resource allocation Methods 0.000 claims abstract description 15
- 238000013210 evaluation model Methods 0.000 claims abstract description 9
- 238000013507 mapping Methods 0.000 claims description 46
- 230000000694 effects Effects 0.000 abstract description 3
- 238000004458 analytical method Methods 0.000 description 12
- 238000005516 engineering process Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 4
- 238000004891 communication Methods 0.000 description 4
- 238000002474 experimental method Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000011160 research Methods 0.000 description 4
- 239000000758 substrate Substances 0.000 description 3
- 238000009827 uniform distribution Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000005265 energy consumption Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 238000001228 spectrum Methods 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012552 review Methods 0.000 description 1
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
- H04L47/72—Admission control; Resource allocation using reservation actions during connection setup
-
- 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
- H04L45/22—Alternate routing
-
- 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
- H04L45/58—Association of routers
- H04L45/586—Association of routers of virtual routers
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/14—Session management
- H04L67/148—Migration or transfer of sessions
Abstract
The invention provides a virtual network resource migration method based on resource reservation under 5G network slicing, which comprises the following steps: step S11, constructing a network model and a migration model in a network slicing environment; step S12, an important link resource searching model and a migration urgency evaluating model are constructed; step S13, constructing a virtual network resource migration algorithm based on resource reservation under the network slice; step S14, searching an important virtual link in a network slicing environment according to the virtual network resource migration algorithm and combining the important link resource searching model, and reserving resources for the important virtual link; and step S15, determining virtual nodes and virtual links to be migrated according to the virtual network resource migration algorithm and in combination with the migration urgency evaluation model, and performing migration operation on the virtual nodes and virtual links. The method has better application effect and performance, and better solves the problem of low success rate of virtual network resource allocation.
Description
Technical Field
The invention relates to the technical field of resource management in a network slicing environment, in particular to a virtual network resource migration method based on resource reservation.
Background
With the rapid development and application of 5G technology, the network resources are increasingly demanded by various industries. To meet the demands of network resources by increasing the utilization of network resources, network slicing technology is becoming a key solution.
In a network slicing environment, a conventional base network is divided into an underlay network and a virtual network. The bottom network provides network resources for the virtual network, and the virtual network applies resources from the bottom network, and loads various services after constructing the virtual network to provide services for users. Virtual network resource mapping has become a key research content for efficient use of underlying network resources.
In the prior art, methods such as migration technology, intelligent algorithm, optimization theory and the like are mainly adopted to solve the problems of low resource utilization rate, low mapping success rate and the like in resource allocation. For example, the existing literature [ Soto P, botero J f.gredy dispersed path-ranking virtual optical network embedding onto EON-based substrate networks [ C ] In:2017IEEE Colombian Conference on Communications and Computing (lcom) & lt/EN & gt: IEEE,2017:1-6 ] aims to solve the problem of low utilization of underlying network resources In an optical network, and adopts a path migration technology to migrate underlying link resources with high utilization, thereby improving the mapping success rate and underlying network resource utilization of a virtual network. Another prior document [ Chordhury S R, ahmed R, shahriar N, et al ReViNE Reallocation of Virtual Network Embedding to eliminate substrate bottlenecks [ C ]. In: integrated Network and Service management: portugal: IEEE,2017 ] improves the utilization of underlying network resources by designing heuristic remapping algorithms. There is also a document [ Zhang Y, zhu Y, yan F, et al energy-efficient radio resource allocation in software-defined wireless sensor networks [ J ]. IET Communications,2017,12 (3): 349-358 ] aimed at minimizing energy consumption problems, which proposes a resource allocation mechanism in a dynamic environment, and effectively reduces energy consumption overhead of underlying network resources. In addition, the patent document [ M.S.Parwez, D.B.Rawat.Resource Allocation in Adaptive Virtualized Wireless Networks with Mobile Edge Computing [ C ] 2018IEEE International Conference on Communications (ICC), kansas City,2018:1-7 ] aims at solving the problem of wireless virtual network resource mapping, and performs joint solution on resources such as calculation, storage, frequency spectrum and the like based on model Carlo theory, so that the resource utilization efficiency and the frequency spectrum resource utilization rate are better improved.
From the existing research analysis, the network slicing technology is a key technology for improving the utilization rate of network resources, whether a front-end network or a core network. In the research of the virtual network resource allocation problem, firstly, resource allocation is carried out through an optimization algorithm, and secondly, resource adjustment is carried out on the used bottom network resource through reconfiguration and migration technology, so that the utilization rate of the network resource is further improved. However, when the resources are migrated, load balancing is mainly considered in the existing research, and reservation of important resources is not considered, so that the utilization rate of a part of important bottom network resources is too high, and the mapping success rate of the virtual network is affected.
Disclosure of Invention
The invention aims to solve the technical problem that the virtual network resource migration method based on resource reservation has good application effect and performance and solves the problem of low success rate of virtual network resource allocation.
In order to solve the above technical problems, in one aspect of the present invention, a virtual network resource migration method based on resource reservation is provided, which includes the following steps:
step S11, constructing a network model and a migration model in a network slicing environment;
step S12, an important link resource searching model and a migration urgency evaluating model are constructed;
step S13, constructing a virtual network resource migration algorithm based on resource reservation under the network slice;
step S14, searching an important virtual link in a network slicing environment according to the virtual network resource migration algorithm and combining the important link resource searching model, and reserving resources for the important virtual link;
and step S15, determining virtual nodes and virtual links to be migrated according to the virtual network resource migration algorithm and in combination with the migration urgency evaluation model, and performing migration operation on the virtual nodes and virtual links.
Wherein, the step S11 includes:
a network model is built, a traditional network is divided into a bottom layer network and a virtual network in a network slicing environment, wherein the bottom layer network comprises bottom layer nodes and bottom layer links, CPU resources and bandwidth resources are respectively provided for the virtual network, and the network model is used for quickly building the virtual network; the virtual network comprises a virtual node and a virtual link, and CPU resources of the virtual node and bandwidth resources of the virtual link are applied to the bottom network; the method comprises the steps that a bottom layer network adopts a virtual network mapping algorithm to realize resource allocation for a virtual network, wherein the virtual network mapping algorithm comprises node mapping and link mapping algorithms;
and constructing a migration model, and constructing a virtual node migration formula, a virtual link migration formula and constraint conditions corresponding to each formula.
The virtual node migration formula and constraint conditions are as follows:
wherein ,MN :N S →N S Representing a virtual node migration, wherein,is a virtual node; fn is the mapping relation between the virtual node and the bottom layer node; />In order to migrate the underlying node prior to the migration,/>the node is a bottom layer node after migration; n (N) S Is a bottom layer node set; s.t. constraint condition +.>For virtual network node->CPU resource requirements of (2); /> and />And respectively refers to CPU resources of the bottom nodes before and after migration.
The virtual link migration formula and constraint conditions are as follows:
wherein ,ME :P S →P S Representing virtual link migration, meaning that the virtual link is migrated from the old underlying pathMigration to New bottom Path->Applying; s.t. is a constraint, bw (e V ) Bandwidth resources for virtual network links, +.>The table shows two before and after migrationBandwidth resources of the underlying path.
Wherein, in step S12, further comprises:
constructing an important link resource lookup model, validating for computation to compute nodes in an underlying networkAnd node->Link bandwidth resource demand between +.>The following formula (3):
wherein ,the larger the value, the larger the demand for that link; />The result of (2) represents the centrality of the current node in the network; />Representing the degree of the node, N s Representing the number of nodes of the underlying network; />Representing node->And node->Is a common neighbor of (2); />Representation and node->A set of connected nodes;
constructing a migration urgency evaluation model, and determining migration urgency of an underlying link for calculating needed migration resourcesFormula (4) of (2):
wherein ,representing the amount of node resources carried; />Representing the amount of the link resources of the bearer, wherein the larger the amount of the link resources is, the larger the migration overhead is; alpha and beta are fixed coefficients.
The virtual network resource migration algorithm based on resource reservation under the construction network slice comprises the following steps: and constructing important link resource searching and important link resource migration.
The step S14 specifically includes:
calculating the bandwidth resource demand of each virtual link by using a formula (3), and arranging in a descending order;
selecting a preset number of virtual links arranged in the front, calculating the shortest paths of node pairs in the virtual links, and marking the shortest paths;
and carrying out resource reservation on the preset virtual links with more shortest paths.
The step S15 specifically includes:
calculating urgency of virtual link resource migration by using the formula (4), and arranging in a descending order;
migrating the link resources one by one specifically includes:
when determining that the resource migration needs to be carried out on the virtual nodes, searching the bottom nodes meeting the CPU resource requirements for the virtual nodes in a bottom network again, and mapping;
setting a bottom link corresponding to a virtual link to be migrated at present as unavailable, and allocating bottom link resources for the virtual link of the virtual node after migration and the virtual link of the virtual node connected before migration by using a shortest path algorithm.
Compared with the prior art, the invention has the following beneficial effects:
the invention provides a virtual network resource migration method based on resource reservation, which is characterized in that a virtual network resource migration algorithm based on resource reservation under network slicing is provided by designing a migration urgency calculation method of a bottom link, and important virtual links under the network slicing environment are searched and resource reservation is carried out on the important virtual links; and meanwhile, according to the migration urgency evaluation model, determining virtual nodes and virtual links to be migrated, and performing migration operation on the virtual nodes and the virtual links. From three index analysis of the virtual network mapping success rate, the average utilization rate of the bottom network link and the average utilization rate of the bottom network node, the migration algorithm provided by the invention better improves the virtual network mapping success rate and the resource utilization rate. When the embodiment of the invention is used for migrating the resources, the virtual network on the key urgent resources can be migrated, so that the needed resources are provided for new virtual network requests.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions of the prior art, the drawings which are required in the description of the embodiments or the prior art will be briefly described, it being obvious that the drawings in the description below are only some embodiments of the invention, and that it is within the scope of the invention to one skilled in the art to obtain other drawings from these drawings without inventive faculty.
FIG. 1 is a schematic diagram illustrating a main flow of an embodiment of a virtual network resource migration method based on resource reservation according to the present invention;
fig. 2 is a schematic diagram of analysis of mapping success rate of virtual network according to the present invention;
FIG. 3 is a schematic diagram illustrating an analysis of average utilization of an underlying network link in accordance with the present invention;
fig. 4 is a schematic diagram illustrating average utilization analysis of an underlying network node according to the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings, for the purpose of making the objects, technical solutions and advantages of the present invention more apparent.
In the scheme of the invention, in order to solve the problem of low success rate of virtual network resource allocation in a network slicing environment, the invention provides a virtual network resource migration method based on resource reservation.
As shown in fig. 1, a main flow diagram of an embodiment of a virtual network resource migration method based on resource reservation according to the present invention is provided, in this embodiment, the method includes the following steps:
step S11, constructing a network model and a migration model in a network slicing environment;
constructing a network model and a migration model in a network slice environment comprises constructing a network model and constructing a migration model.
Specifically, in a network slicing environment, a legacy network is partitioned into an underlay network G S ＝(N S ,E S ) And virtual network G V ＝(N V ,E V ). Underlying network G S ＝(N S ,E S ) Includes an underlying nodeAnd the bottom link->Providing CPU resources for virtual networks respectively>And bandwidth resource->For fast construction of virtual networks. Virtual network G V ＝(N V ,E V ) Comprising virtual node->And virtual Link->Applying for CPU resources of a virtual node by issuing a virtual network request to an underlying network>Bandwidth resource->The bottom network is implemented using a virtual network mapping algorithm in order to allocate resources to the virtual network. The virtual network mapping algorithm generally comprises two processes of node mapping and link mapping. Node mapping usage +.>Representation means the bottom node->Is virtual node->Allocation meets its CPU constraints->CPU resource->Link mapping usage +.>Representation means the bottom link->For virtual link->Allocation meets its bandwidth constraint->Bandwidth resource-> wherein ,/>Composed of underlying links, representing virtual linksThe set of underlying links through which an end-to-end connection between the underlying nodes to which the two endpoints map.
After the bottom layer network and the virtual network run for a period of time, in order to improve the resource utilization rate and maintain the stable running of the network, the virtual network already carried on the bottom layer network needs to be migrated. In general, virtual network migration includes two processes, virtual node migration and virtual link migration. The resource migration concept of the virtual network is described as follows.
Constructing a virtual node migration formula and corresponding constraint conditions, wherein the virtual node migration formula and the constraint conditions are as follows:
wherein ,MN :N S →N S Representing virtual node migration, referred to as virtual linksFrom the underlying path to the new underlying path. />Is a virtual node; fn is the mapping relation between the virtual node and the bottom layer node; />For the bottom node before migration, +.>The node is a bottom layer node after migration; n (N) S Is a bottom layer node set; s.t. constraint condition +.>For virtual network node->CPU resource requirements of (2); /> and />And respectively refers to CPU resources of the bottom nodes before and after migration. The constraint indicates that the bandwidth resources of both the underlying paths before and after the migration must meet the bandwidth resource requirements of the virtual network link.
Constructing a virtual link migration formula and corresponding constraint conditions, wherein the virtual link migration formula and the constraint conditions are as follows:
wherein ,ME :P S →P S Representing virtual link migration, meaning that the virtual link is migrated from the old underlying pathMigration to New bottom Path->Applying; s.t. is a constraint, bw (e V ) Bandwidth resources for virtual network links, +.>The tables represent bandwidth resources of the two underlying paths before and after the migration, respectively.
Step S12, an important link resource searching model and a migration urgency evaluating model are constructed;
the method comprises the steps of constructing an important link resource searching model and a migration urgency evaluating model, wherein the migration urgency evaluating model and the important link resource searching model comprise two parts.
In order to improve the utilization rate of network resources through virtual network migration, the invention adopts the thought that the utilization rate of the network resources of the bottom layer is improved by reducing the times of virtual network mapping failure.
In general, reasons for virtual network mapping failure include: the method comprises the steps of not meeting the CPU resource requirement of the virtual node, and not meeting the bandwidth resource requirement of the virtual link. Therefore, the main reasons for the failure of virtual network mapping are the shortage of the resources of the underlying node CPU and the shortage of the bandwidth resources of the underlying link. If the frequently used bottom node resources and bottom link resources can be found, the allocated resources on the bottom node resources and the bottom link resources can be migrated or the resources can be expanded, so that the resource utilization rate can be improved.
Analysis of virtual network resource allocation studies shows that frequently used underlying nodes and underlying links are related to the location in the network where they are located.
More specifically, in this step, an important link resource lookup model is built, validated for calculation to calculate nodes in the underlying networkAnd node->Link bandwidth resource demand between +.>The following formula (3):
wherein ,the larger the value, the larger the demand for that link; />The result of (2) represents the centrality of the current node in the network; />Representing the degree of the node, N s Representing the number of nodes of the underlying network; />Representing node->And node->Is a common neighbor of (2); />Representation and node->A set of connected nodes;
it will be appreciated that the present invention is based on the link prediction technique [7-8 ]]To measure the demand for a link for a future period of time. The formula fully (3) considers the centrality of the nodes and the common neighbor characteristics among the nodes to measure the nodesAnd node->Link demand between. The larger the value, the greater the demand for the link.
For ease of description, important underlying link usageAnd (3) representing. Two nodes of the link use +.> Representation, which respectively represent links->Left node of->And right node->As can be seen from an analysis of the working process of the virtual network mapping, the virtual resources carried on the important underlying links include node type, link type and node link type. The node type refers to that virtual node resources are borne on an end node of an underlying link. The link type refers to the bearing virtual link resources on the underlying link. Node link type refers to a bottom linkThe end nodes and the links of the network node bear resources of the virtual node and the virtual link respectively.
On a node-type map, there are two cases: (1) The left (or right) node of the link carries the virtual node; (2) The left node and the right node of the link bear virtual nodes at the same time. Neither case uses link resources and therefore migration is not considered. On the link-type mapping, there are two cases: (1) The link belongs to the left (or right) end link of the bottom layer path of the virtual link mapping; (2) The links belong to intermediate links of the underlying path of the virtual link map. Both cases require migration. Namely: the current underlying link is set to unavailable and the shortest path is again found for the virtual link carried thereon. On the node link type map, there are two cases: (1) The left (or right) node of the link carries a virtual node, and the current link carries a virtual link; (2) The left node and the right node of the link bear virtual nodes at the same time, and the current link bears virtual links. In case (1), firstly, the loaded virtual nodes are migrated, then the current bottom layer link is set to be unavailable, and the shortest path is searched for the virtual links loaded on the current bottom layer link again. In case (2), the current resource allocation belongs to the optimal resource, the migration cost is large, and the case does not migrate.
The migration thought analysis shows that the resource migration is an NP difficult problem. In order to solve the problem, the greedy migration algorithm thought provided by the invention is as follows: calculating migration urgency of an underlying link of a resource to be migrated, and performing migration one by one according to the urgency from low to high. The reason that migration is carried out from low to high is to ensure that the most urgent underlying link is migrated last, so that occupation of other resources after migration can be effectively reduced.
Specifically, a migration urgency evaluation model is built, and migration urgency of an underlying link for calculating the needed migration resources is determinedFormula (4) of (2):
wherein ,representing the amount of node resources carried; />Representing the amount of link resources carried, α and β are fixed coefficients. From equation (4), the larger the amount of resources carried, the larger the migration overhead and the lower the urgency of migration.
Step S13, constructing a virtual network resource migration algorithm based on resource reservation under the network slice;
the invention provides a virtual network resource migration algorithm (Virtual network resource migration algorithm based on resource reservation, hereinafter referred to as VNRMoRR) based on resource reservation under network slicing. The algorithm comprises two steps of important link resource searching and important link resource migration, and the detailed description of the steps is given below in step S14 and step S15. Through the algorithm, the underlying network G is input S ＝(N S ,E S ) Virtual network G V ＝(N V ,E V ) Can output the migrated bottom network G' S ＝(N S ,E S )。
Step S14, searching an important virtual link in a network slicing environment according to the virtual network resource migration algorithm and combining the important link resource searching model, and reserving resources for the important virtual link; the method specifically comprises the following steps:
calculating the bandwidth resource demand of each virtual link by using a formula (3), and arranging in a descending order;
selecting a preset number of virtual links arranged in the front, calculating the shortest paths of node pairs in the virtual links, and marking the shortest paths;
and carrying out resource reservation on the preset virtual links with more shortest paths.
And step S15, determining virtual nodes and virtual links to be migrated according to the virtual network resource migration algorithm and in combination with the migration urgency evaluation model, and performing migration operation on the virtual nodes and virtual links. The method specifically comprises the following steps:
calculating urgency of virtual link resource migration by using the formula (4), and arranging in a descending order;
migrating the link resources one by one specifically includes:
when determining that the resource migration needs to be carried out on the virtual nodes, searching the bottom nodes meeting the CPU resource requirements for the virtual nodes in a bottom network again, and mapping;
setting a bottom link corresponding to a virtual link to be migrated at present as unavailable, and allocating bottom link resources for the virtual link of the virtual node after migration and the virtual link of the virtual node connected before migration by using a shortest path algorithm.
Through the steps S11 to S15, the virtual network resource migration method based on resource reservation can be implemented.
In order to further explain the effects that the present invention can have, the following description will be made with reference to fig. 2 to 4.
In a specific example, the present invention uses the GT-ITM [ ZEGURA E W, CALVERT K L, BHATTACHARJEE S. How to model an Internet work [ C ]// IEEE Information, C1996:594-602 ] tool to create a network environment. The network environment includes an underlying network and a virtual network. In the topology aspect of the bottom layer network, the number of bottom layer nodes of the bottom layer network is 100, and the bottom layer links are formed by connecting the bottom layer nodes with each other with the probability of 0.5. The CPU resources of the underlying nodes and the bandwidth resources of the underlying links obey a uniform distribution of [20, 50 ]. In the topology aspect of the virtual network, the number of the virtual nodes obeys the uniform distribution of [2,8], and the virtual links are formed by connecting the virtual nodes with each other with the probability of 0.5. The CPU resources and bandwidth resources requested by the virtual network obey a uniform distribution of [1,8 ]. In simulating virtual network requests, the arrival of each virtual network request is subject to a poisson distribution of 1.5 time unit intervals. The lifecycle of each virtual network request is 20 time units. The experiments were run for 6000 time units in total.
In the aspect of algorithm performance comparison, the algorithm VNRMORR is compared with the existing virtual network resource migration algorithm (Virtual network resource Migration algorithm for reducing utilization, VNRMORU) for reducing the utilization rate, and particularly three dimensions of virtual network mapping success rate, average utilization rate of a bottom network link and average utilization rate of a bottom network node are compared. The algorithm VNRMoRU evaluates how urgent the migration is in terms of resource utilization. In terms of evaluation index, the virtual network mapping success rate refers to the ratio of the number of virtual network requests that are successfully mapped to the total number of virtual network requests. The average utilization of the underlying network links refers to the ratio of the amount of underlying link bandwidth allocated to the virtual network to the total amount of underlying link bandwidth. The average utilization of the bottom network node refers to the ratio of the number of bottom node CPUs allocated to the virtual network to the total number of bottom node CPUs.
To evaluate the impact of virtual network resource migration on the performance of the mapping algorithm, a virtual network mapping algorithm [ YU M, YI Y, REXFORD J, CHIANG M, "Rethinking virtual network embedding: substrate support for path splitting and migration," ACM SIGCOMM Computer Communication Review,2008:38 (2), 17-29). The algorithm execution process is as follows: generating 100 virtual network requests and performing resource allocation, and then executing a migration algorithm; and generating 100 virtual network requests and carrying out resource allocation, and then counting three indexes of virtual network mapping success rate, average utilization rate of a bottom network link and average utilization rate of a bottom network node. The algorithm was performed 5 times in total and the experimental results are shown in fig. 2 to 4.
As can be seen from fig. 2, in 5 experiments, the virtual network mapping success rate values of the two algorithms are relatively stable. Both algorithms are described to achieve an improvement in virtual network mapping success rate. From the performance analysis of the two algorithms, the virtual network mapping success rate of the algorithm VNNMORR is about 6.5% higher than that of the algorithm VNNMORU.
As can be seen from fig. 3, in 5 experiments, the average utilization of the underlying network links of both algorithms is relatively stable. Both algorithms are described to achieve an increase in average utilization of the underlying network links. From the performance analysis of the two algorithms, the average utilization rate of the network links of the bottom layer of the algorithm VNRMORR is about 8.2 percent higher than that of the network links of the bottom layer of the algorithm VNRMORU.
As can be seen from fig. 4, in 5 experiments, the average utilization values of the bottom network nodes of the two algorithms are relatively stable. Both algorithms are described to achieve an increase in average utilization of the underlying network nodes. From the performance analysis of the two algorithms, the average utilization rate of the bottom network node of the algorithm VNRMORR is about 11.5% higher than that of the bottom network node of the algorithm VNRMORU.
By analyzing three indexes of the virtual network mapping success rate, the average utilization rate of the bottom network link and the average utilization rate of the bottom network node of fig. 2 to fig. 4, the migration algorithm provided by the invention better improves the virtual network mapping success rate and the resource utilization rate. The method and the device illustrate that the migration algorithm can migrate the virtual network on the key urgent resource when migrating the resource, thereby providing the needed resource for the new virtual network request.
Compared with the prior art, the invention has the following beneficial effects:
the invention provides a virtual network resource migration method based on resource reservation, which is characterized in that a virtual network resource migration algorithm based on resource reservation under network slicing is provided by designing a migration urgency calculation method of a bottom link, and important virtual links under the network slicing environment are searched and resource reservation is carried out on the important virtual links; and meanwhile, according to the migration urgency evaluation model, determining virtual nodes and virtual links to be migrated, and performing migration operation on the virtual nodes and the virtual links. From three index analysis of the virtual network mapping success rate, the average utilization rate of the bottom network link and the average utilization rate of the bottom network node, the migration algorithm provided by the invention better improves the virtual network mapping success rate and the resource utilization rate. When the embodiment of the invention is used for migrating the resources, the virtual network on the key urgent resources can be migrated, so that the needed resources are provided for new virtual network requests.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, alternatives, and improvements that fall within the spirit and scope of the invention.
Claims (3)
1. The virtual network resource migration method based on resource reservation is characterized by comprising the following steps:
step S11, constructing a network model and a migration model in a network slicing environment;
step S12, an important link resource searching model and a migration urgency evaluating model are constructed;
step S13, constructing a virtual network resource migration algorithm based on resource reservation under the network slice;
step S14, searching an important virtual link in a network slicing environment according to the virtual network resource migration algorithm and combining the important link resource searching model, and reserving resources for the important virtual link;
step S15, determining virtual nodes and virtual links to be migrated according to the virtual network resource migration algorithm and in combination with the migration urgency evaluation model, and performing migration operation on the virtual nodes and virtual links;
wherein, the step S11 includes:
a network model is built, a traditional network is divided into a bottom layer network and a virtual network in a network slicing environment, wherein the bottom layer network comprises bottom layer nodes and bottom layer links, CPU resources and bandwidth resources are respectively provided for the virtual network, and the network model is used for quickly building the virtual network; the virtual network comprises a virtual node and a virtual link, and CPU resources of the virtual node and bandwidth resources of the virtual link are applied to the bottom network; the method comprises the steps that a bottom layer network adopts a virtual network mapping algorithm to realize resource allocation for a virtual network, wherein the virtual network mapping algorithm comprises node mapping and link mapping algorithms;
constructing a migration model, and constructing a virtual node migration formula, a virtual link migration formula and constraint conditions corresponding to each formula;
the virtual node migration formula and constraint conditions are as follows:
(1)
S.t. ,/>
wherein ,representing virtual node migration, ++>Is a virtual node; f (F) N () The mapping relation between the virtual node and the bottom layer node is adopted; />For the bottom node before migration, +.>The node is a bottom layer node after migration; />Is a bottom layer node set; s.t. constraint condition +.>For virtual network node->CPU resource requirements of (2); /> and />CPU resources of the bottom nodes before and after migration are respectively indicated;
the virtual link migration formula and constraint conditions are as follows:
(2)
S.t.
wherein ,representing virtual link migration, meaning that the virtual link is +_from the old underlying path>Migration to New bottom Path->Applying; s.t. constraint condition +.>Bandwidth resources for virtual network links, +.>、/>Bandwidth resources of two bottom paths before and after migration are respectively represented;
wherein, in step S12, further comprises:
constructing an important link resource lookup model, validating for computation to compute nodes in an underlying networkAnd node->Link bandwidth resource demand between +.>The following formula (3):
（3）
wherein ,the larger the value, the larger the demand for that link; />The result of (2) represents the centrality of the current node in the network; />Representing the degree of a node>Representing the number of nodes of the underlying network; />Representing node->And node->Is a common neighbor of (2); />Representation and node->A set of connected nodes;
constructing migration urgency evaluation model for determinationMigration urgency for computing underlying links that require migrating resourcesFormula (4) of (2):
(4)
wherein ,representing the amount of node resources carried; />Representing the amount of the link resources of the bearer, wherein the larger the amount of the link resources is, the larger the migration overhead is; alpha and beta are fixed coefficients.
2. The method according to claim 1, wherein constructing a virtual network resource migration algorithm based on resource reservation under a network slice comprises: and constructing two steps of important link resource searching and important link resource migration.
3. The method according to claim 2, wherein the step S15 specifically includes:
calculating urgency of virtual link resource migration by using the formula (4), and arranging in a descending order;
migrating the link resources one by one specifically includes:
when determining that the resource migration needs to be carried out on the virtual nodes, searching the bottom nodes meeting the CPU resource requirements for the virtual nodes in a bottom network again, and mapping;
setting a bottom link corresponding to a virtual link to be migrated at present as unavailable, and allocating bottom link resources for the virtual link of the virtual node after migration and the virtual link of the virtual node connected before migration by using a shortest path algorithm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010505459.2A CN111756655B (en) | 2020-06-05 | 2020-06-05 | Virtual network resource migration method based on resource reservation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010505459.2A CN111756655B (en) | 2020-06-05 | 2020-06-05 | Virtual network resource migration method based on resource reservation |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111756655A CN111756655A (en) | 2020-10-09 |
| CN111756655B true CN111756655B (en) | 2023-09-15 |
Family
ID=72674576
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010505459.2A Active CN111756655B (en) | 2020-06-05 | 2020-06-05 | Virtual network resource migration method based on resource reservation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111756655B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112291791B (en) * | 2020-10-31 | 2022-11-08 | 国网河南省电力公司经济技术研究院 | Power communication mesh bandwidth resource allocation method based on 5G slice |
| CN114598665A (en) * | 2022-01-19 | 2022-06-07 | 锐捷网络股份有限公司 | Resource scheduling method and device, computer readable storage medium and electronic equipment |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107147530A (en) * | 2017-05-24 | 2017-09-08 | 西安交通大学 | A kind of virtual network method for reconfiguration based on resource conservation |
| CN108989126A (en) * | 2018-08-13 | 2018-12-11 | 北京邮电大学 | A kind of mapping method of virtual network |
| CN109495300A (en) * | 2018-11-07 | 2019-03-19 | 西安交通大学 | A kind of reliable SDN virtual network mapping algorithm |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8990397B2 (en) * | 2009-07-31 | 2015-03-24 | Ntt Docomo, Inc. | Resource allocation protocol for a virtualized infrastructure with reliability guarantees |
| US10432552B2 (en) * | 2015-10-12 | 2019-10-01 | Fujitsu Limited | Just-enough-time provisioning of service function chain resources |
-
2020
- 2020-06-05 CN CN202010505459.2A patent/CN111756655B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107147530A (en) * | 2017-05-24 | 2017-09-08 | 西安交通大学 | A kind of virtual network method for reconfiguration based on resource conservation |
| CN108989126A (en) * | 2018-08-13 | 2018-12-11 | 北京邮电大学 | A kind of mapping method of virtual network |
| CN109495300A (en) * | 2018-11-07 | 2019-03-19 | 西安交通大学 | A kind of reliable SDN virtual network mapping algorithm |
Non-Patent Citations (2)
| Title |
|---|
| 基于资源整合的节能虚拟网络重配置算法;吕新亮等;《计算机应用》;20160410;第36卷(第04期);第894-904页 * |
| 网络功能虚拟化的资源分配机制研究;宋雪;《中国优秀硕士学位论文全文数据库》;20180815(第08期);第7-15页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111756655A (en) | 2020-10-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10810045B2 (en) | Method and apparatus for allocating central processing unit (CPU) resources in a default resource pool | |
| CN102932422B (en) | Cloud environment task scheduling method based on improved ant colony algorithm | |
| CN111756655B (en) | Virtual network resource migration method based on resource reservation | |
| CN111182037B (en) | Mapping method and device of virtual network | |
| Bessis et al. | Using a novel message-exchanging optimization (MEO) model to reduce energy consumption in distributed systems | |
| CN113163498B (en) | Virtual network resource allocation method and device based on genetic algorithm under 5G network slice | |
| Qu et al. | Study QoS optimization and energy saving techniques in cloud, fog, edge, and IoT | |
| Zhang et al. | A novel virtual network mapping algorithm for cost minimizing | |
| CN111611076B (en) | Fair distribution method for mobile edge computing shared resources under task deployment constraint | |
| CN107070965B (en) | Multi-workflow resource supply method under virtualized container resource | |
| CN111698703B (en) | Network reliability optimization method based on service priority and load balancing | |
| WO2024022142A1 (en) | Resource use method and apparatus | |
| Mao et al. | Optimal scheduling algorithm of MapReduce tasks based on QoS in the hybrid cloud | |
| CN116954905A (en) | Task scheduling and migration method for large Flink data | |
| CN110308965B (en) | Rule-based heuristic virtual machine distribution method and system for cloud data center | |
| Thiam et al. | An energy-efficient VM migrations optimization in cloud data centers | |
| CN109818788B (en) | Secondary-mode optimization-based calculation resource allocation method in edge cache C-RAN | |
| CN113079053B (en) | Virtual resource reconfiguration method and system based on particle swarm theory under network slice | |
| Yakubu et al. | Priority based delay time scheduling for quality of service in cloud computing networks | |
| CN106227600B (en) | A kind of multidimensional virtual resource allocation method based on Energy-aware | |
| Jeong et al. | An energy-efficient service scheduling algorithm in federated edge cloud | |
| WO2020244300A1 (en) | Method and apparatus for reducing power consumption of virtual machine cluster | |
| Patel et al. | An efficient load balancing mechanism with cost estimation on GridSim | |
| CN109831337B (en) | Grouping mapping method for adjacent nodes in wireless network virtualization | |
| CN115269110A (en) | Resource allocation method and device for cloud computing platform, electronic equipment and storage medium |
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 |