CN114650249A - Algorithm model and path determination method, electronic device, SDN controller and medium - Google Patents
Algorithm model and path determination method, electronic device, SDN controller and medium Download PDFInfo
- Publication number
- CN114650249A CN114650249A CN202011400354.7A CN202011400354A CN114650249A CN 114650249 A CN114650249 A CN 114650249A CN 202011400354 A CN202011400354 A CN 202011400354A CN 114650249 A CN114650249 A CN 114650249A
- Authority
- CN
- China
- Prior art keywords
- service
- services
- deployed
- path
- network
- 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.)
- Pending
Links
- 238000004422 calculation algorithm Methods 0.000 title claims abstract description 112
- 238000000034 method Methods 0.000 title claims abstract description 85
- 239000013598 vector Substances 0.000 claims abstract description 63
- 238000012549 training Methods 0.000 claims abstract description 45
- 238000005457 optimization Methods 0.000 claims abstract description 37
- 238000013135 deep learning Methods 0.000 claims abstract description 12
- 238000012545 processing Methods 0.000 claims description 52
- 230000006870 function Effects 0.000 claims description 30
- 238000013528 artificial neural network Methods 0.000 claims description 19
- 238000011156 evaluation Methods 0.000 claims description 18
- 238000004364 calculation method Methods 0.000 claims description 17
- 230000014759 maintenance of location Effects 0.000 claims description 13
- 230000002068 genetic effect Effects 0.000 claims description 10
- 210000000349 chromosome Anatomy 0.000 claims description 6
- 238000002922 simulated annealing Methods 0.000 claims description 4
- 230000000903 blocking effect Effects 0.000 claims description 3
- 238000004590 computer program Methods 0.000 claims description 3
- 230000008685 targeting Effects 0.000 claims description 2
- 238000010586 diagram Methods 0.000 description 6
- 230000003993 interaction Effects 0.000 description 6
- 230000004913 activation Effects 0.000 description 5
- 238000013500 data storage Methods 0.000 description 4
- 238000013459 approach Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000002360 explosive Substances 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000013138 pruning Methods 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 230000007723 transport mechanism Effects 0.000 description 1
Images
Classifications
-
- 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
- H04L45/14—Routing performance; Theoretical aspects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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
- H04L41/0803—Configuration setting
-
- 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
- H04L41/0893—Assignment of logical groups to network elements
-
- 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
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/12—Discovery or management of network topologies
-
- 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
- H04L41/14—Network analysis or design
-
- 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
- H04L41/14—Network analysis or design
- H04L41/145—Network analysis or design involving simulating, designing, planning or modelling of a network
-
- 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
- H04L41/16—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks using machine learning or artificial intelligence
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Signal Processing (AREA)
- Computer Networks & Wireless Communication (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Biophysics (AREA)
- Mathematical Physics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Biomedical Technology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Databases & Information Systems (AREA)
- Medical Informatics (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The present disclosure provides a method for determining a routing algorithm model, including: acquiring a training sample, wherein an input vector in the training sample comprises network resource information before a plurality of services are deployed and service demand information of the services, and an output vector of the training sample comprises service path information of a service path through which the services are deployed, wherein the service path through which the services are deployed meets a preset network optimization target; and performing deep learning by using the training samples to obtain a routing algorithm model, wherein the routing algorithm model can output information of a plurality of preselected links by using service demand information of the service to be deployed and network resource information of a current network as input vectors, and the preselected links are used for deploying the service to be deployed. The disclosure also provides a method for determining a service target path, an electronic device, an SDN controller, and a computer-readable storage medium.
Description
Technical Field
The present invention relates to the field of Software Defined Networking (SDN), and in particular, to a method for determining a routing algorithm model, a method for determining a service target path, an SDN controller, an electronic device, and a computer-readable storage medium.
Background
In recent years, with the continuous abundance of network access methods and the continuous decrease of network use cost, the traffic of network transmission is increasing year by year. In the face of explosive data growth trends, network operators generally increase the capacity of networks by upgrading switches/routers and scaling up the networks. However, this approach increases the capital expenditure for the operator while increasing network capacity. In addition, the large-scale network resulting from this approach also presents greater challenges to the management and control of the network.
In view of this, SDN technology is in force. The SDN network includes a control plane including SDN controllers and a data plane including network nodes such as hosts, switches, and the like.
The SDN controller can acquire network global resource information (such as the topology of the whole network, link bandwidth, traffic and the like), and an effective means is provided for solving the problem of route optimization of the whole network facing traffic engineering.
For example, the SDN controller may calculate, according to a service requirement of a service to be deployed and global information resources, a service path of the service to be deployed by using a specific algorithm, and issue the calculated service path to a data plane, where the service is deployed by a corresponding host.
Improving the utilization rate of network resources, meeting the dynamic requirements of services, and the like are all optimization conditions which need to be considered when the services are deployed, and the service deployment is no exception on the basis of an SND (service discovery and discovery) network. However, the current algorithm for deploying the service path cannot well satisfy the above optimization condition.
Therefore, how to optimize the deployment of the service on the basis of the SDN network becomes a technical problem to be solved in the field.
Disclosure of Invention
The present disclosure provides a method of determining a routing algorithm model, a method of determining a traffic target path, an SDN controller, an electronic device, and a computer-readable storage medium.
As an aspect of the present disclosure, there is provided a method for determining a routing algorithm model, including:
acquiring a training sample, wherein an input vector in the training sample comprises network resource information before a plurality of services are deployed and service demand information of the services, and an output vector of the training sample comprises service path information of a service path through which the services are deployed, wherein the service path through which the services are deployed meets a preset network optimization target;
and performing deep learning by using the training samples to obtain a routing algorithm model, wherein the routing algorithm model can output information of a plurality of preselected links by using service demand information of the service to be deployed and network resource information of a current network as input vectors, and the preselected links are used for deploying the service to be deployed.
Optionally, before the training sample is obtained, the determining method further includes:
and respectively generating service path information of service paths for deploying the services according to the service requirements of the services and the preset network optimization target.
Optionally, in the step of generating the service path information of the service path according to the service requirements of the plurality of services to be deployed and the predetermined network optimization target, a heuristic algorithm is used to generate the service path information of the service path to deploy the plurality of services according to the service requirements of the plurality of services to be deployed and the predetermined network optimization target.
Optionally, the heuristic algorithm includes a genetic algorithm, and the step of generating service path information of the service paths for deploying the services according to the service demands of the services to be deployed and the predetermined network optimization goal includes:
taking the initial deployment sequence of the plurality of services as a chromosome of the genetic algorithm, and changing the initial deployment sequence through continuous variation and intersection of the chromosome until the genetic algorithm converges to obtain a target deployment sequence;
utilizing Dijkstra algorithm to perform deployment calculation on each service in the plurality of services to obtain initial path information of each service in the plurality of services;
and deploying the plurality of services according to the target deployment sequence and the initial path information of each service, and acquiring the service path information of the service path through which the plurality of services are deployed.
Optionally, the heuristic algorithm includes a simulated annealing algorithm, and the step of generating service path information of the service paths for deploying the plurality of services according to the service requirements of the plurality of services to be deployed and the predetermined network optimization target includes:
performing initial deployment on the plurality of services according to an initial deployment sequence by using a Dijkstra algorithm, wherein an initial weight of the Dijkstra algorithm is related to the preset network optimization target;
calculating an evaluation function according to the preset network optimization target;
randomly removing the services which are subjected to the initial deployment and have a preset proportion from the network;
redeploying the removed service by utilizing a Dijkstra algorithm;
calculating an evaluation function according to the secondary weight of the Dijkstra algorithm used during redeployment;
judging whether the evaluation function obtained by the calculation is superior to the last evaluation function;
if the judgment result is yes, deploying the removed service according to a service path calculated by a Dijkstra algorithm corresponding to the evaluation function obtained by the calculation;
if not, re-deploying the removed service by using a Dijkstra algorithm with a new weight until the evaluation function is converged;
and taking the service path finally deployed with the plurality of services as the service path information of the service path deployed with the plurality of services.
Optionally, the step of performing deep learning by using the training samples to obtain a routing algorithm model includes:
inputting the training samples into a neural network;
training the neural network by using the training sample so that the trained neural network can output an initial output vector according to an input vector, and aiming at each service corresponding to the input vector, elements in the initial output vector are respectively the retention rate of each link in the network topology;
and processing the trained neural network to obtain the routing algorithm model, wherein the routing algorithm model can represent links with retention rates larger than or equal to a preset threshold value in the initial output vector by 1, represent links with retention rates smaller than the preset threshold value in the initial output vector by 0, and output a final vector representing information of a plurality of links deploying the service to be deployed, wherein the links represented by 1 are the preselected links.
Optionally, the optimization objective comprises at least one of the following objectives:
the method has the advantages of balanced load of the whole network, lowest occupied bandwidth of the whole network, lowest time delay of the whole network and lowest blocking rate of the whole network.
As a second aspect of the present disclosure, there is provided a method for determining a traffic target path, including:
inputting a service requirement of at least one service to be deployed and a current network resource into a routing algorithm model as input vectors, and obtaining a plurality of preselected links for each service to be deployed, wherein the routing algorithm model is obtained by the determination method provided by the first aspect of the disclosure;
and selecting a path meeting a preset condition from a plurality of pre-selected links obtained by calculation for each service to be deployed as a service target path of the service to be deployed.
Optionally, the predetermined condition is that the route is shortest.
As a third aspect of the present disclosure, there is provided an electronic apparatus including:
one or more first processing modules;
a first storage module having stored thereon a first executable program, the one or more first processing modules implementing the determination method according to the first aspect of the disclosure when the first executable program is executed by the one or more first processing modules.
As a fourth aspect of the present disclosure, there is provided an SDN controller comprising:
one or more second processing modules;
a second storage module having stored thereon a second executable program, the one or more second processing modules implementing the traffic targeting path determination method according to the second aspect of the present disclosure when the second executable program is executed by the one or more second processing modules.
As a fourth aspect of the present disclosure, there is provided a service deployment method, including:
sending the service requirement of the service to be deployed and the current network resource to the SDN controller;
receiving a service target path sent by the SDN controller;
and deploying the service according to the received service target path.
As a fifth aspect of the present disclosure, there is provided an electronic apparatus including:
one or more third processing modules;
a third storage module having stored thereon a third executable program, the one or more third processing modules implementing the service deployment method according to the fourth aspect of the disclosure when the third executable program is executed by the one or more third processing modules.
As a sixth aspect of the present disclosure, there is provided a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements at least one of the following methods:
the determination method according to the first aspect of the present disclosure;
a method for determining a service target path according to a second aspect of the present disclosure;
the service deployment method according to the fourth aspect of the present disclosure.
The routing algorithm model determined by the determination method provided by the first aspect of the present disclosure needs to be used with the service target path determination method provided by the second aspect of the present disclosure. That is, after obtaining information of a plurality of preselected links for deploying the service to be deployed (which is equivalent to pruning a network topology) through the routing algorithm model, a new network composed of the preselected links needs to be calculated, and a service path meeting a predetermined condition is obtained.
The method for determining the routing algorithm model is equivalent to determining the routing algorithm model through deep learning, and network resources before service deployment and a network optimization target are considered during deep learning, so that the utilization rate of the network resources can be improved when service deployment is performed by using a preselected link obtained by calculation of the routing algorithm model. In the present disclosure, the routing model algorithm is not directly used to determine the service path, but the information of a plurality of preselected links is subsequently calculated, so that the final path information meets the predetermined conditions related to the real-time routing requirement of the service.
Drawings
Figure 1 is a diagram of an SDN network architecture;
FIG. 2 is a flow chart of one embodiment of a determination method provided by the first aspect of the present disclosure;
FIG. 3 is a flow chart of another embodiment of a determination method provided by the first aspect of the present disclosure;
FIG. 4 is a flow chart of one embodiment of step S100;
FIG. 5 is a flow chart of another embodiment of step S100;
FIG. 6 is a schematic diagram of encoding an input vector, an output vector;
FIG. 7 is a flow diagram of one embodiment of step S120;
fig. 8 is a flowchart of an embodiment of a method for determining a service target path according to a second aspect of the disclosure;
FIG. 9 is a flow chart of an embodiment of a service deployment method provided in a fourth aspect of the present disclosure;
fig. 10 is an architecture diagram of an embodiment of an SDN network system provided by the present disclosure.
Detailed Description
In order to make those skilled in the art better understand the technical solution of the present disclosure, a method for determining a routing algorithm model, a method for determining a traffic path, an SDN controller, an electronic device, and a computer-readable storage medium provided in the present disclosure are described in detail below with reference to the accompanying drawings.
Example embodiments will be described more fully hereinafter with reference to the accompanying drawings, but which may be embodied in different forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.
Embodiments of the present disclosure and features of embodiments may be combined with each other without conflict.
As used herein, the term "and/or" includes any and all combinations of one or more of the associated listed items.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the disclosure. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and/or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the relevant art and the present disclosure, and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
Shown in fig. 1 is an SDN network architecture diagram, as shown in the figure, an SDN network includes a control plane including an SDN controller and a data plane including a plurality of hosts and a plurality of switches.
In order to deploy services, a host sends service demand information (including a service source node and a service target node) of the services to be deployed to an SDN controller, the SDN controller calculates service path information for the services to be deployed, the service path information is sent to the corresponding host, and finally the host deploys the services according to the received service path information.
As a first aspect of the present disclosure, there is provided a method for determining a routing algorithm model, as shown in fig. 2, the method for determining a routing algorithm model includes:
in step S110, a training sample is obtained, where an input vector in the training sample includes network resource information before deploying a plurality of services and service demand information of the plurality of services, and an output vector of the training sample includes service path information of a service path through which the plurality of services are deployed, where the service path through which the plurality of services are deployed satisfies a predetermined network optimization target;
in step S120, deep learning is performed by using the training samples to obtain a routing algorithm model, where the routing algorithm model can output information of a plurality of preselected links by using service demand information of a service to be deployed and network resource information of a current network as input vectors, and the preselected links are used for deploying the service to be deployed.
It is noted that a traffic path comprises a plurality of links arranged in a predetermined order, said links being connected between two nodes in the network. And outputting the information of the plurality of preselected links which is not the service path information of the service by using the routing algorithm model obtained by the determination method, and further sequencing the preselected links to obtain the service path.
The routing algorithm model determined by the determination method provided by the present disclosure needs to be used in cooperation with the service target path determination method provided by the second aspect of the present disclosure. That is, after obtaining a plurality of preselected links for deploying the service to be deployed through the routing algorithm model, the information of the preselected links needs to be calculated to obtain a service path meeting a predetermined condition.
The service in the traffic engineering has dynamic attribute, and the method for determining the routing algorithm model provided by the disclosure can be oriented to the traffic engineering. The determining method is equivalent to determining a routing algorithm model through deep learning, and network resources before service deployment and a network optimization target are considered during deep learning, so that the utilization rate of the network resources can be improved when service deployment is performed by using a preselected link obtained by calculation of the routing algorithm model. In the present disclosure, the routing model algorithm is not directly used to determine the service path, but the information of a plurality of preselected links is subsequently calculated, so that the final path information meets the predetermined conditions related to the real-time routing requirement of the service.
It should be noted that the routing algorithm model determined by the present disclosure may be stored in an SDN controller, and after the SDN controller receives a service requirement of a service to be deployed, which is sent by a host in a data plane, the service requirement of the service to be deployed and current network resources are input into the routing algorithm model as data vectors to obtain information of multiple links, and then the information of the multiple links is calculated, and a service target path is finally obtained, and the host may deploy the service according to the service target path.
In the present disclosure, the network optimization objective is not particularly limited. Optionally, the network optimization target may be any one of full network load balancing, minimum full network bandwidth occupation, minimum full network delay, and minimum full network blocking rate.
When the network optimization objectives are different, the traffic paths deploying the same service may also be different.
It should be noted that, in the present disclosure, the device for executing the determining method is not particularly limited, for example, the determining method may be executed by a separate electronic device, or may be executed by an SDN controller, but no matter what device executes the determining method, a routing algorithm model obtained by the determining method needs to be sent to the SDN controller.
As described above, the training samples include not only the network resource information before the service is deployed, but also the service path information of the service path through which the plurality of services are deployed.
In the present disclosure, how to obtain the service path information is not particularly limited. As an alternative implementation, as shown in fig. 3, before step S110, the determining method further includes:
in step S100, service paths for deploying the services are respectively generated according to the service requirements of the services and the predetermined network optimization goal, and corresponding service path information is obtained.
After the service path of each service is determined, the training sample can be obtained by combining network resource information before deploying a plurality of services, service demand information of the services and network optimization target information when deploying the services.
In this disclosure, the specific implementation manner of step S100 is not particularly limited, for example, a heuristic algorithm may be used to generate service paths for deploying a plurality of services according to a plurality of services to be deployed and network optimization targets corresponding to the plurality of services to be deployed, respectively.
The heuristic algorithm is a network resource optimization algorithm based on the global service, and can improve the utilization rate of network resources.
Optionally, the heuristic algorithm is a genetic algorithm. Describing how to determine the traffic path using a genetic algorithm, as shown in fig. 4, step S100 may include:
in step S101a, taking the initial deployment sequence of the plurality of services as a chromosome of the genetic algorithm, and changing the initial deployment sequence through continuous variation and intersection of chromosomes until the genetic algorithm converges to obtain a target deployment sequence;
in step S102a, performing deployment calculation on each of the services by using dijkstra algorithm, to obtain initial path information of each of the services;
in step S103a, the multiple services are deployed according to the target deployment sequence and the initial path information of each service, and service path information that passes after the multiple services are deployed is obtained.
Of course, the disclosure is not limited thereto, and the heuristic algorithm may also be a simulated annealing algorithm. Describing how to determine the traffic path by using the simulated annealing algorithm, as shown in fig. 5, step S100 may include:
in step S101b, initially deploying the services according to an initial deployment sequence by using a dijkstra algorithm, wherein an initial weight of the dijkstra algorithm is related to the predetermined network optimization objective;
in step S102b, calculating an evaluation function according to the predetermined network optimization objective;
in step S103b, randomly removing a predetermined proportion of the services that have undergone the initial deployment from the network;
in step S104b, redeploying the removed service by using dijkstra algorithm;
in step S105b, an evaluation function is calculated according to the secondary weight of the dijkstra algorithm used in redeployment;
in step S106b, it is determined whether the evaluation function obtained by this calculation is better than the evaluation function used last time;
if yes, in step S107b, deploying the removed service according to the service path calculated by the dijkstra algorithm corresponding to the evaluation function obtained by the calculation;
if not, redeploying the removed service by using a dijkstra algorithm with a new weight value until the evaluation function is converged, and executing step S107 b;
in step S108b, the traffic path on which the plurality of services are finally deployed is taken as the traffic path information of the traffic path on which the plurality of services are deployed.
In the present disclosure, the data storage form in the training sample is not particularly limited.
As an alternative embodiment, the data in the training samples may be stored using a vectorial approach. As described above, in the training sample, the input vector includes network resource information before deploying a plurality of services and service demand information of the plurality of services. Network resource information before deployment of multiple services (which may include the remaining bandwidth of each link in the network before deployment of multiple services) may be represented by x, and may be represented by a one-dimensional vector of dimension E. The service demand information is represented by y (the service demand information may include a source node of a service, a destination node of the service, and a service bandwidth), and the service demand information may be represented by a vector with a dimension of (2V +1), where V represents the number of nodes in a network, and may represent the source node and the destination node of the service according to a one-hot code, and the position where the node is located is encoded to be 1, and the rest positions are encoded to be 0. The output may be represented by z.
The traffic path obtained for each traffic using the predetermined algorithm may represent the output z in the coding scheme shown in fig. 6. The output z is represented by a one-dimensional vector with dimension E, the value of the link through which the service is deployed is 1 (which may be referred to as a preselected link), and the values of the remaining links are 0 (which may be referred to as an excluded link).
In the embodiment shown in fig. 6, there are n links in the network, the n links are numbered according to the addresses of the n links, the bandwidth of the first link is B1, the bandwidth of the second link is B2, … …, and the bandwidth of the nth link is Bn. The bandwidth requirement of the service is B.
The inputs and outputs in the training samples may be stored in the vectorial manner described above.
In the present disclosure, the specific step of step S120 is not particularly limited as long as the routing algorithm model can be obtained through step S120. As an alternative embodiment, as shown in fig. 7, step S120 may include:
in step S121, taking network resources before deploying a plurality of services in the training sample and service requirements of the plurality of services as input vectors, and taking a plurality of service paths in which the plurality of services are deployed as output vectors, and inputting the output vectors into a neural network;
in step S122, the training sample is used to train the neural network, so as to obtain an initial output vector that can be output by the trained neural network according to the input vector, and for each service corresponding to the input vector, elements in the initial output vector are retention rates of each link in the network topology respectively;
in step S123, the trained neural network is processed to obtain the routing algorithm model, where the routing algorithm model is capable of representing links with retention rates greater than or equal to a predetermined threshold in the initial output vector as 1, representing links with retention rates less than the predetermined threshold in the initial output vector as 0, and outputting a final vector, where a link represented by 1 in the final vector is the preselected link.
As an alternative embodiment, step S122 may include: inputting an input vector x, an input vector y and an output vector z in a training sample into a neural network, and finally obtaining an output result z' of the neural network through a layer of fully-connected layer after the input vector x, the input vector y and the output vector z are transmitted forward and pass through a plurality of residual network structures consisting of fully-connected layers and batch regularization layers, wherein an activation function in the residual network structure in the neural network can be a Relu activation function, and an activation function of the last layer of fully-connected layer is a sigmoid activation function. Since the sigmoid activation function will map the input value to a value between 0 and 1, z' is a one-dimensional vector with elements between 0 and 1, the size of each element in the vector representing the probability of link selection (i.e., the retention rate above).
And solving a loss function value according to the output result z' and the corresponding output vector z result, wherein the loss function can be a two-class cross entropy loss function, and the loss function calculation mode is as follows:
suppose that the actual output bit z ═ z1，z2，……，zi，……，zn-1，zn]The output of the neural network is z' ═ zt 1，zt 2，……，zt i，……zt n-1，zt n]Loss function
And carrying out inverse gradient propagation according to the loss function, optimizing the weight value of each layer in the neural network, and stopping training until the loss value is reduced to a certain threshold value, so as to obtain the trained neural network.
In the present disclosure, step S123 is not particularly limited. Optionally, threshold discretization is performed on the output result of the trained neural network, a threshold is set according to a network link retention rate (the link retention rate is a ratio of a value of an output vector 1 in the training sample to the total number), if the link retention rate is set as the threshold, a value of an element smaller than the threshold is set as 1, a value of an element greater than or equal to the threshold is set as 1, a group of one-dimensional vectors composed of 0 and 1 can be obtained, a link corresponding to the value of 1 in the network topology is set as a preselected link according to a position of the vector, and a link corresponding to the value of 0 in the network topology is set as an excluded link.
In a second aspect of the disclosure, calculations are performed only on the preselected links to determine the final traffic path.
As a second aspect of the present disclosure, there is provided a traffic target path determining method, as shown in fig. 8, the traffic target path determining method including:
in step S210, the service requirements of the services to be deployed and the current network resources are input into a routing algorithm model as input vectors, and a plurality of preselected links are obtained for each service to be deployed, where the routing algorithm model is obtained by the determination method provided in the first aspect of the present disclosure;
in step S220, for each service to be deployed, a path meeting a predetermined condition is selected from a plurality of pre-selected links calculated for the service to be deployed as a service target path of the service to be deployed.
In the method for determining the service target path provided by the present disclosure, a routing computation model is first used to prune the network topology, a new network is formed by using the links (preselected links) meeting the conditions, then at least one part of the preselected links is ranked according to the current network condition, and the ranked acquired path is used as the service target path.
The method for determining the routing algorithm model is equivalent to determining the routing algorithm model through deep learning, and network resources before service deployment and a network optimization target are considered during deep learning, so that the utilization rate of the network resources can be improved when service deployment is performed by using link information obtained by calculation of the routing algorithm model. In the present disclosure, the routing model algorithm is not directly used to determine the service path, but a plurality of link information are subsequently calculated, so that the final path information satisfies the predetermined condition.
The service in the traffic engineering has dynamic attributes, and as described above, the routing algorithm model provided by the present disclosure, in combination with the service target path determination method, can also meet the real-time routing requirements of dynamic services, so that the service path determination method provided by the present disclosure is particularly suitable for traffic engineering-oriented services.
In the present disclosure, the predetermined condition is not particularly limited, and may be determined according to a specific service type. Optionally, the predetermined condition is that the route is shortest. Accordingly, in step S220, the traffic path with the shortest route may be determined by a greedy algorithm.
Specifically, after the training of the training sample and the obtaining of the routing algorithm model are completed by using the determination method provided in the first aspect of the present disclosure, when a new service or a batch of services comes, firstly, the bandwidth of each link in the network and the service requirement information (i.e., the source node, the destination node, and the required bandwidth of each service) of each service at that time are determined, an input vector including the above information is encoded, and then, the encoded input vector is input into the routing algorithm model. Through the routing algorithm model, a final vector of information of a plurality of links deploying the service to be deployed can be finally obtained.
Through the calculation in step S220, a service target path of the service to be deployed may be obtained.
As can be seen from the above description, the service deployment method is divided into offline training (which may be performed by an SDN controller) and online decision (which may be performed by the SDN controller). In the off-line training part, a training set is generated through a heuristic algorithm, and off-line training of the routing algorithm model is completed. In the online decision-making part, the real-time optimization of the traffic route is realized by a greedy algorithm.
As a third aspect of the present disclosure, there is provided an electronic apparatus including:
one or more first processing modules;
a first storage module having stored thereon a first executable program, the one or more first processing modules implementing the determination method provided by the first aspect of the present disclosure when the first executable program is executed by the one or more first processing modules.
Optionally, the electronic device may further include one or more first I/O interfaces, connected between the processor and the memory, configured to implement information interaction between the first processing module and the first storage module.
The first processing module is a device with data processing capability, and includes but is not limited to a Central Processing Unit (CPU) and the like; the first memory module is a device with data storage capability including, but not limited to, random access memory (RAM, more specifically SDRAM, DDR, etc.), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), FLASH memory (FLASH); the first I/O interface (read/write interface) is connected between the first processing module and the first storage module, and can implement information interaction between the first processing module and the first storage module, which includes but is not limited to a data Bus (Bus) and the like.
In some embodiments, the first processing module, the first memory module, and the first I/O interface are interconnected via a bus to further connect with other components of the electronic device.
As a fourth aspect of the present disclosure, there is provided an SDN controller comprising:
one or more second processing modules;
a second storage module having a second executable program stored thereon, the one or more second processing modules implementing the business target path determination method provided by the second aspect of the present disclosure when the second executable program is executed by the one or more second processing modules.
After the routing algorithm model is determined by using the determination method provided by the present disclosure, the routing algorithm model is stored in the SDN controller, and the second executable program is called by the second processing module of the SDN controller, so that a service target path can be calculated for a service to be deployed.
Optionally, the SDN controller may further include one or more second I/O interfaces connected between the processor and the memory, and configured to implement information interaction between the second processing module and the second storage module.
The second processing module is a device with data processing capability, and includes but is not limited to a Central Processing Unit (CPU) and the like; the second memory module is a device with data storage capability, including but not limited to random access memory (RAM, more specifically SDRAM, DDR, etc.), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), FLASH memory (FLASH); the second I/O interface (read/write interface) is connected between the second processing module and the second storage module, and can implement information interaction between the second processing module and the second storage module, which includes but is not limited to a data Bus (Bus) and the like.
In some embodiments, the second processing module, the second storage module, and the second I/O interface are interconnected via a bus to further interface with other components of the SDN controller.
As a fourth aspect of the present disclosure, there is provided a service deployment method, as shown in fig. 9, the service deployment method including:
in step S310, service requirement information of a service to be deployed and current network resource information are sent to an SDN controller provided in the third aspect of the present disclosure;
in step S320, receiving a service target path sent by the SDN controller;
in step S330, the service is deployed according to the received service target path.
The service deployment method provided by the present disclosure may be performed by a host of a data plane.
As a fifth aspect of the present disclosure, there is provided an electronic apparatus including:
one or more third processing modules;
a third storage module having a third executable program stored thereon, wherein when the third executable program is executed by the one or more third processing modules, the one or more third processing modules implement the service deployment method provided by the fourth aspect of the present disclosure.
Optionally, the electronic device may further include one or more third I/O interfaces, connected between the processor and the memory, configured to implement information interaction between the third processing module and the third storage module.
The third processing module is a device with data processing capability, and includes but is not limited to a Central Processing Unit (CPU) and the like; the third memory module is a device with data storage capability, which includes but is not limited to random access memory (RAM, more specifically SDRAM, DDR, etc.), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), FLASH memory (FLASH); the third I/O interface (read/write interface) is connected between the third processing module and the third storage module, and can implement information interaction between the third processing module and the third storage module, which includes but is not limited to a data Bus (Bus) and the like.
In some embodiments, the third processing module, the third storage module and the third I/O interface are interconnected via a bus to further connect with other components of the electronic device.
As a sixth aspect of the present disclosure, there is provided a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements at least one of the following methods:
a determination method according to the first aspect of the present disclosure;
a service target path determining method according to a second aspect of the present disclosure;
a service deployment method according to a fourth aspect of the present disclosure.
The principles and intended effects of the various aspects have been described in detail above and will not be repeated here.
Shown in fig. 10 is an architecture diagram of an SDN network system provided by the present disclosure. As shown, the control plane of the SDN network system is arranged with an SDN controller 910, which includes an information acquisition module 911, a storage module 912, a decision module 913, and a routing module 914.
The information acquisition module 911 is configured to acquire network resource information and service requirement information. The network resource information comprises network link residual bandwidth, link load, link delay and the like, and the service demand information comprises a service source node, a service target node, service required bandwidth and the like.
The storage module 912 is used for storing the information collected by the information collection module 911.
The decision module 913 is configured to deploy the path for the service through a heuristic algorithm according to the network optimization objective.
The routing module 914 is configured to receive the routing decision of the decision module and route the traffic of the data plane.
In addition, the decision module 913 is further configured to perform training according to the historical routing data in the storage module 912, and route the traffic that needs to be routed in the storage module 912 after the training is completed.
The data plane of the SDN network includes a plurality of hosts 920 and a plurality of switches 930.
It will be understood by those of ordinary skill in the art that all or some of the steps of the methods, systems, functional modules/units in the devices disclosed above may be implemented as software, firmware, hardware, and suitable combinations thereof. In a hardware implementation, the division between functional modules/units mentioned in the above description does not necessarily correspond to the division of physical components; for example, one physical component may have multiple functions, or one function or step may be performed by several physical components in cooperation. Some or all of the physical components may be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application specific integrated circuit. Such software may be distributed on computer readable storage media, which may include computer storage media (or non-transitory media) and communication media (or transitory media). The term computer storage media includes volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data, as is well known to those of ordinary skill in the art. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, Digital Versatile Disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to store the desired information and which can be accessed by a computer. In addition, communication media typically embodies computer readable instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transport mechanism and includes any information delivery media as known to those skilled in the art.
Example embodiments have been disclosed herein, and although specific terms are employed, they are used and should be interpreted in a generic and descriptive sense only and not for purposes of limitation. In some instances, features, characteristics and/or elements described in connection with a particular embodiment may be used alone or in combination with features, characteristics and/or elements described in connection with other embodiments, unless expressly stated otherwise, as would be apparent to one skilled in the art. Accordingly, 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 scope of the disclosure as set forth in the appended claims.
Claims (14)
1. A method of determining a routing algorithm model, comprising:
acquiring a training sample, wherein an input vector in the training sample comprises network resource information before a plurality of services are deployed and service demand information of the services, and an output vector of the training sample comprises service path information of a service path through which the services are deployed, wherein the service path through which the services are deployed meets a preset network optimization target;
and performing deep learning by using the training samples to obtain a routing algorithm model, wherein the routing algorithm model can output information of a plurality of preselected links by using service demand information of the service to be deployed and network resource information of a current network as input vectors, and the preselected links are used for deploying the service to be deployed.
2. The determination method of claim 1, wherein prior to obtaining the training samples, the determination method further comprises:
and respectively generating service paths for deploying the plurality of services according to the service requirements of the plurality of services and the preset network optimization target, and acquiring corresponding service path information.
3. The determination method according to claim 2, wherein in the step of generating the service path information of the service path according to the service requirements of the plurality of services to be deployed and the predetermined network optimization goal, the service path information of the service path in which the plurality of services are deployed is generated according to the service requirements of the plurality of services to be deployed and the predetermined network optimization goal by using a heuristic algorithm.
4. The determination method according to claim 3, wherein the heuristic algorithm comprises a genetic algorithm, and the step of generating traffic path information of traffic paths in which the plurality of services are deployed according to the traffic demands of the plurality of services to be deployed and the predetermined network optimization objective respectively comprises:
taking the initial deployment sequence of the plurality of services as a chromosome of the genetic algorithm, and changing the initial deployment sequence through continuous variation and intersection of the chromosome until the genetic algorithm converges to obtain a target deployment sequence;
utilizing Dijkstra algorithm to perform deployment calculation on each service in the plurality of services to obtain initial path information of each service in the plurality of services;
and deploying the plurality of services according to the target deployment sequence and the initial path information of each service, and acquiring the service path information of the service path through which the plurality of services are deployed.
5. The determination method according to claim 3, wherein the heuristic algorithm comprises a simulated annealing algorithm, and the step of generating the service path information of the service paths for deploying the plurality of services according to the service requirements of the plurality of services to be deployed and the predetermined network optimization objective respectively comprises:
performing initial deployment on the plurality of services according to an initial deployment sequence by using a Dijkstra algorithm, wherein an initial weight of the Dijkstra algorithm is related to the preset network optimization target;
calculating an evaluation function according to the preset network optimization target;
randomly removing the services which are subjected to the initial deployment and have a preset proportion from the network;
redeploying the removed service by utilizing a Dijkstra algorithm;
calculating an evaluation function according to the secondary weight of the Dijkstra algorithm used during redeployment;
judging whether the evaluation function obtained by the calculation is superior to the last evaluation function;
if the judgment result is yes, deploying the removed service according to a service path calculated by a Dijkstra algorithm corresponding to the evaluation function obtained by the calculation;
if not, re-deploying the removed service by using a Dijkstra algorithm with a new weight until the evaluation function is converged;
and taking the service path finally deployed with the plurality of services as the service path information of the service path deployed with the plurality of services.
6. The determination method according to any one of claims 1 to 5, wherein the step of performing deep learning using the training samples includes:
inputting the training samples into a neural network;
training the neural network by using the training sample so that the trained neural network can output an initial output vector according to an input vector, and aiming at each service corresponding to the input vector, elements in the initial output vector are respectively the retention rate of each link in the network topology;
and processing the trained neural network to obtain the routing algorithm model, wherein the routing algorithm model can represent links with the retention rate being greater than or equal to a preset threshold value in the initial output vector by 1, represent links with the retention rate being less than the preset threshold value in the initial output vector by 0 and output a final vector, and the links represented by 1 in the final vector are the preselected links.
7. The determination method according to any one of claims 1 to 5, wherein the optimization objective comprises at least one of the following objectives:
the method has the advantages of balanced load of the whole network, lowest bandwidth occupation of the whole network, lowest time delay of the whole network and lowest blocking rate of the whole network.
8. A method for determining a service target path comprises the following steps:
inputting a service requirement of at least one service to be deployed and a current network resource into a routing algorithm model as input vectors, and obtaining a plurality of preselected links for each service to be deployed, wherein the routing algorithm model is obtained by the determination method according to any one of claims 1 to 7;
and selecting a path meeting a preset condition from a plurality of pre-selected links obtained by calculation for each service to be deployed as a service target path of the service to be deployed.
9. The traffic destination path determining method according to claim 8, wherein the predetermined condition is that a route is shortest.
10. An electronic device, the electronic device comprising:
one or more first processing modules;
a first storage module having stored thereon a first executable program which, when executed by the one or more first processing modules, the one or more first processing modules implement the determination method of any one of claims 1 to 7.
11. An SDN controller, the SDN controller comprising:
one or more second processing modules;
a second storage module having stored thereon a second executable program, the one or more second processing modules implementing the traffic targeting path determination method according to claim 8 or 9 when the second executable program is executed by the one or more second processing modules.
12. A service deployment method comprises the following steps:
sending service requirements of a service to be deployed and current network resources to the SDN controller of claim 11;
receiving a service target path sent by the SDN controller;
and deploying the service according to the received service target path.
13. An electronic device, the electronic device comprising:
one or more third processing modules;
a third storage module having stored thereon a third executable program, the one or more third processing modules implementing the service deployment method of claim 12 when the third executable program is executed by the one or more third processing modules.
14. A computer-readable storage medium, on which a computer program is stored which, when executed by a processor, implements at least one of the following methods:
the determination method according to any one of claims 1 to 7;
the traffic target path determining method according to claim 8 or 9;
the service deployment method of claim 12.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011400354.7A CN114650249A (en) | 2020-12-02 | 2020-12-02 | Algorithm model and path determination method, electronic device, SDN controller and medium |
| PCT/CN2021/134270 WO2022116957A1 (en) | 2020-12-02 | 2021-11-30 | Algorithm model determining method, path determining method, electronic device, sdn controller, and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011400354.7A CN114650249A (en) | 2020-12-02 | 2020-12-02 | Algorithm model and path determination method, electronic device, SDN controller and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114650249A true CN114650249A (en) | 2022-06-21 |
Family
ID=81852943
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011400354.7A Pending CN114650249A (en) | 2020-12-02 | 2020-12-02 | Algorithm model and path determination method, electronic device, SDN controller and medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN114650249A (en) |
| WO (1) | WO2022116957A1 (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115905624A (en) * | 2022-10-18 | 2023-04-04 | 支付宝(杭州)信息技术有限公司 | Method, device and equipment for determining user behavior state |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115225561B (en) * | 2022-08-15 | 2022-12-06 | 南京邮电大学 | Route optimization method and system based on graph structure characteristics |
| CN116132403A (en) * | 2022-11-29 | 2023-05-16 | 浪潮通信技术有限公司 | Route distribution method and device of computing power network, electronic equipment and storage medium |
| CN115834466B (en) * | 2022-12-01 | 2024-04-16 | 中国联合网络通信集团有限公司 | Method, device, equipment, system and storage medium for analyzing path of computing power network |
| CN116156592B (en) * | 2022-12-27 | 2023-08-22 | 深圳市宇通联发科技有限公司 | Low-delay wireless transmission method, device, communication management equipment and storage medium |
| CN115866626B (en) * | 2023-02-23 | 2023-05-12 | 安徽思高智能科技有限公司 | Service deployment method based on NSGA-II and simulated annealing in edge environment |
| CN116805926B (en) * | 2023-08-21 | 2023-11-17 | 上海飞旗网络技术股份有限公司 | Network service type identification model training method and network service type identification method |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107016065A (en) * | 2017-03-16 | 2017-08-04 | 陕西科技大学 | It is customizable to rely on semantic effective origin filter method |
| CN108494601A (en) * | 2018-04-04 | 2018-09-04 | 西安电子科技大学 | Stratification determines the multiple constraint dual path method for routing in network |
| CN108667734A (en) * | 2018-05-18 | 2018-10-16 | 南京邮电大学 | It is a kind of that the through street with LSTM neural networks is learnt by decision making algorithm based on Q |
| CN110493131A (en) * | 2019-09-24 | 2019-11-22 | 大连大学 | A kind of design method of Information Network routing policy under SDN framework |
| CN110891021A (en) * | 2018-09-11 | 2020-03-17 | 中兴通讯股份有限公司 | Path calculation method and device and computer readable storage medium |
| CN111106999A (en) * | 2019-12-27 | 2020-05-05 | 国网江苏省电力公司信息通信分公司 | IP-optical network communication service joint distribution method and device |
| WO2020181761A1 (en) * | 2019-03-11 | 2020-09-17 | 江苏君英天达人工智能研究院有限公司 | Sdn enhanced path allocation device and method employing bin-packing technique |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108076158B (en) * | 2018-01-08 | 2020-07-03 | 苏州大学 | Minimum load route selection method and system based on naive Bayes classifier |
| US11050656B2 (en) * | 2018-05-10 | 2021-06-29 | Dell Products L.P. | System and method to learn and prescribe network path for SDN |
| US10666547B2 (en) * | 2018-10-25 | 2020-05-26 | Ca, Inc. | Efficient machine learning for network optimization |
| CN110505154B (en) * | 2019-07-26 | 2022-06-07 | 北京工业大学 | Switch migration method based on improved Dijkstra algorithm |
-
2020
- 2020-12-02 CN CN202011400354.7A patent/CN114650249A/en active Pending
-
2021
- 2021-11-30 WO PCT/CN2021/134270 patent/WO2022116957A1/en active Application Filing
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107016065A (en) * | 2017-03-16 | 2017-08-04 | 陕西科技大学 | It is customizable to rely on semantic effective origin filter method |
| CN108494601A (en) * | 2018-04-04 | 2018-09-04 | 西安电子科技大学 | Stratification determines the multiple constraint dual path method for routing in network |
| CN108667734A (en) * | 2018-05-18 | 2018-10-16 | 南京邮电大学 | It is a kind of that the through street with LSTM neural networks is learnt by decision making algorithm based on Q |
| CN110891021A (en) * | 2018-09-11 | 2020-03-17 | 中兴通讯股份有限公司 | Path calculation method and device and computer readable storage medium |
| WO2020181761A1 (en) * | 2019-03-11 | 2020-09-17 | 江苏君英天达人工智能研究院有限公司 | Sdn enhanced path allocation device and method employing bin-packing technique |
| CN110493131A (en) * | 2019-09-24 | 2019-11-22 | 大连大学 | A kind of design method of Information Network routing policy under SDN framework |
| CN111106999A (en) * | 2019-12-27 | 2020-05-05 | 国网江苏省电力公司信息通信分公司 | IP-optical network communication service joint distribution method and device |
Non-Patent Citations (2)
| Title |
|---|
| 房秋生;洪佩琳;: "SDN网络中基于业务资源偏好的批路由策略", 中国科学院大学学报, no. 04, 15 July 2016 (2016-07-15) * |
| 李雄飞;张海龙;刘兆军;王仁彪;: "用启发式算法求解最短路径问题", 吉林大学学报(工学版), no. 01, 15 January 2011 (2011-01-15) * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115905624A (en) * | 2022-10-18 | 2023-04-04 | 支付宝(杭州)信息技术有限公司 | Method, device and equipment for determining user behavior state |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2022116957A1 (en) | 2022-06-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114650249A (en) | Algorithm model and path determination method, electronic device, SDN controller and medium | |
| CN109818865B (en) | SDN enhanced path boxing device and method | |
| CN110661715B (en) | Service path optimization method, device, equipment and readable storage medium | |
| CN105897584B (en) | Paths planning method and controller | |
| CN110601973B (en) | Route planning method, system, server and storage medium | |
| EP3720065A1 (en) | System and methods for improved network routing | |
| CN107317697B (en) | Route configuration method of OSPF (open shortest Path first) and SDN (software defined network) hybrid network | |
| CN111612528A (en) | Method, device and equipment for determining user classification model and storage medium | |
| Wang et al. | A reinforcement learning approach for online service tree placement in edge computing | |
| CN111416774A (en) | Network congestion control method and device, computer equipment and storage medium | |
| Bhanja et al. | An evolutionary programming algorithm for survivable routing and wavelength assignment in transparent optical networks | |
| CN116390164A (en) | Low orbit satellite network trusted load balancing routing method, system, equipment and medium | |
| CN111800352A (en) | Service function chain deployment method and storage medium based on load balancing | |
| CN114422453B (en) | Method, device and storage medium for online planning of time-sensitive stream | |
| CN113472671A (en) | Method and device for determining multicast route and computer readable storage medium | |
| CN113365229B (en) | Network time delay optimization method of multi-union chain consensus algorithm | |
| KR101878213B1 (en) | Method, apparatus and computer program for summaring of a weighted graph | |
| JP6389811B2 (en) | Physical resource allocation device, physical resource allocation method, and program | |
| JP6944156B2 (en) | Orchestrator equipment, programs, information processing systems, and control methods | |
| CN115633083A (en) | Power communication network service arrangement method, device and storage medium | |
| Khedkar | A deep learning method for effective channel allotment for SDN based IoT | |
| Perepelkin et al. | Intelligent Adaptive Routing Algorithm in Software Defined Networks with Quality of Service | |
| JP7428831B2 (en) | OTN network resource optimization method and apparatus, computing device and storage medium | |
| CN115484520B (en) | Frequency spectrum distribution network obtaining method and frequency spectrum distribution method of elastic optical network | |
| CN114928568B (en) | Routing path selection method, device and computer readable 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 |