CN112671648A - SDN data transmission method, SDN, device and medium - Google Patents
SDN data transmission method, SDN, device and medium Download PDFInfo
- Publication number
- CN112671648A CN112671648A CN202011529208.4A CN202011529208A CN112671648A CN 112671648 A CN112671648 A CN 112671648A CN 202011529208 A CN202011529208 A CN 202011529208A CN 112671648 A CN112671648 A CN 112671648A
- Authority
- CN
- China
- Prior art keywords
- network
- flow table
- data set
- flow
- training
- 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
- 238000000034 method Methods 0.000 title claims abstract description 51
- 230000005540 biological transmission Effects 0.000 title claims abstract description 28
- 238000012549 training Methods 0.000 claims abstract description 80
- 238000010801 machine learning Methods 0.000 claims abstract description 62
- 238000012360 testing method Methods 0.000 claims description 22
- 238000004590 computer program Methods 0.000 claims description 12
- 238000000605 extraction Methods 0.000 claims description 5
- 238000013528 artificial neural network Methods 0.000 claims description 4
- 238000003066 decision tree Methods 0.000 claims description 4
- 238000007637 random forest analysis Methods 0.000 claims description 4
- 230000000875 corresponding effect Effects 0.000 description 12
- 238000012545 processing Methods 0.000 description 9
- 238000010586 diagram Methods 0.000 description 5
- 238000004891 communication Methods 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000005055 memory storage Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000009877 rendering Methods 0.000 description 1
Images
Landscapes
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The application discloses a SDN network data transmission method, an SDN network, equipment and a medium, wherein the method comprises the following steps: generating a routing strategy by using a management plane in the SDN network through a target routing strategy model obtained in advance based on machine learning training, and issuing the routing strategy to a control plane in the SDN network; generating a flow table based on the routing strategy through a control plane, and issuing the flow table to a data plane of a kernel state in the SDN network; and storing the flow table through a data plane, and forwarding the input network flow based on the flow table when the input network flow is received. Therefore, a more accurate flow table can be generated, the matching times of the network flow and the flow table are reduced, the network flow forwarding efficiency is improved, the generated flow tables are directly issued to the data surface of the kernel mode, switching between the kernel mode and the user mode is not required in the network flow forwarding process, and the network flow forwarding efficiency is further improved.
Description
Technical Field
The present application relates to the field of computer data transmission technologies, and in particular, to an SDN network data transmission method, an SDN network, a device, and a medium.
Background
The logically centralized control plane of an SDN (Software Defined Network) switch can support flexible scheduling of Network resources, a flexible open interface can support on-demand calling of Network capacity, a standard unified southbound interface can realize virtual transparency of Network equipment, and the SDN is helpful for changing the staticizing current situation of the Network, and can effectively provide Network support for cloud computing and more innovative services. When a network flow data packet is received, the network flow data packet needs to be sequentially matched with each flow table in the switch, but the flow table in the switch is downloaded from an initialized flow table library by related personnel, so that the problem that the matching degree of the flow table and the current SDN switch is low exists, a large amount of mismatching can exist in the process of flow table matching, the number of matching times needed is large, and the forwarding efficiency of the network flow data packet is reduced. And when the data plane of the SDN switch is not matched with the upper flow table, the core mode thread needs to be switched to the user mode thread to request the flow table, and then the core mode needs to be switched to perform subsequent data processing, so that the time consumed by forwarding the network traffic data packet is further increased, and the forwarding efficiency of the network traffic data packet is reduced.
Disclosure of Invention
In view of this, an object of the present application is to provide an SDN network data transmission method, an SDN network, a device, and a medium, which can generate a relatively accurate flow table, thereby reducing the matching times between a network traffic and the flow table, and improving network traffic forwarding efficiency, and directly issue the generated flow table to a data plane of a kernel state, without switching between the kernel state and a user state in a network traffic forwarding process, so as to further improve network traffic forwarding efficiency. The specific scheme is as follows:
in a first aspect, the present application discloses a SDN network data transmission method, including:
generating a routing strategy by a management surface in an SDN network by using a target routing strategy model obtained in advance based on machine learning training, and issuing the routing strategy to a control surface in the SDN network;
generating a flow table through the control plane based on the routing strategy, and issuing the flow table to a data plane of a kernel state in the SDN network;
and storing the flow table through the data surface, and forwarding the input network flow based on the flow table when the input network flow is received.
Optionally, before the generating, by a management plane in the SDN network, a routing policy by using a target routing policy model obtained in advance based on machine learning training, the method further includes:
and training a preset machine learning model by using a pre-acquired data set to obtain the target routing strategy model, wherein the data set comprises a training data set and a testing data set.
Optionally, the machine learning model is any one of a decision tree, a random forest, a neural network, a hidden markov model, and a self-organizing map.
Optionally, the training a preset machine learning model by using a pre-obtained data set to obtain the target routing policy model includes:
training a preset machine learning model by using a training data set in a pre-acquired data set to obtain a routing strategy model to be tested;
and testing and optimizing the routing strategy model to be tested by using the test data set in the data set to obtain the target routing strategy model.
Optionally, the training a preset machine learning model by using a training data set in a pre-acquired data set to obtain a routing strategy model to be tested, including:
performing feature extraction on a training data set in a pre-acquired data set to obtain quintuple information corresponding to each network data in the training data set;
and training a preset machine learning model by utilizing quintuple information corresponding to each network data to obtain a routing strategy model to be tested.
Optionally, the storing, by the data plane, the flow table, and forwarding, when receiving an input network traffic, the input network traffic based on the flow table includes:
storing the flow table through the data plane;
extracting quintuple information in input network flow when the input network flow is received;
matching the extracted quintuple information in the input network flow with the flow table, and forwarding the input network flow based on a matching result.
In a second aspect, the present application discloses an SDN network, comprising:
the management surface is used for generating a routing strategy by utilizing a target routing strategy model obtained in advance based on machine learning training and issuing the routing strategy to the control surface in the SDN network;
the control plane is used for generating a flow table based on the routing strategy and issuing the flow table to a data plane of a kernel state in the SDN network;
and the data surface is used for storing the flow table and forwarding the input network flow based on the flow table when the input network flow is received.
Optionally, the management plane is configured to:
and training a preset machine learning model by using a pre-acquired data set to obtain the target routing strategy model, wherein the data set comprises a training data set and a testing data set.
In a third aspect, the present application discloses an electronic device, comprising:
a memory and a processor;
wherein the memory is used for storing a computer program;
the processor is configured to execute the computer program to implement the SDN network data transmission method disclosed in the foregoing.
In a fourth aspect, the present application discloses a computer readable storage medium for storing a computer program, wherein the computer program when executed by a processor implements the SDN network data transmission method disclosed in the foregoing.
In this application, a management plane in an SDN network generates a routing policy by using a target routing policy model obtained in advance based on machine learning training, and issues the routing policy to a control plane in the SDN network; generating a flow table through the control plane based on the routing strategy, and issuing the flow table to a data plane of a kernel state in the SDN network; and storing the flow table through the data surface, and forwarding the input network flow based on the flow table when the input network flow is received. It can be seen that, in the present application, a routing policy is generated by a target router policy generation model, which is obtained based on machine learning training in advance, in a management plane of an SDN network, and then the routing policy is issued to a control plane in the SDN network, the control plane may generate a flow table based on the routing policy and issue the flow table to a data plane in a kernel state in the SDN network, and when receiving an input network traffic, the data plane may forward the input network traffic based on the flow table, so that since the routing policy model obtained based on machine learning training in advance may generate a routing policy that is more matched with a current SDN network, the flow table issued based on the routing policy may be more accurate, thereby reducing the matching times of the network traffic and the flow table, and thus reducing the matching times of the network traffic and the flow table, the network flow forwarding efficiency is improved, the generated flow tables are directly issued to the data plane of the kernel mode, switching between the kernel mode and the user mode is not needed in the network flow forwarding process, and the network flow forwarding efficiency is further improved.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, it is obvious that the drawings in the following description are only embodiments of the present application, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
Fig. 1 is a flowchart of an SDN network data transmission method disclosed in the present application;
fig. 2 is a flowchart illustrating a specific SDN network data transmission method disclosed in the present application;
FIG. 3 is a flow chart of a machine learning model training process disclosed herein;
fig. 4 is a flowchart illustrating a specific SDN network data transmission method disclosed in the present application;
figure 5 is an overall block diagram of an SDN network data transport as disclosed herein;
figure 6 is a schematic diagram of an SDN network architecture disclosed herein;
fig. 7 is a schematic structural diagram of an electronic device disclosed in the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
Referring to fig. 1, an embodiment of the present application discloses an SDN network data transmission method, including:
step S11: generating a routing strategy by a management surface in the SDN by using a target routing strategy model obtained in advance based on machine learning training, and issuing the routing strategy to a control surface in the SDN.
In practical application, a management plane in an SDN network needs to generate a routing policy by using a target routing policy model obtained in advance based on machine learning training, and issue the routing policy to a control plane in the SDN network.
That is, a management plane in a user state needs to generate a routing policy corresponding to the SDN network by using a target routing policy model obtained based on machine learning training in advance, and then issue the generated routing policy to a control plane in the SDN network, so that the control plane generates a flow table by using the routing policy.
Step S12: and generating a flow table through the control plane based on the routing strategy, and issuing the flow table to a data plane of a kernel state in the SDN network.
Correspondingly, the control plane needs to receive the routing policy issued by the management plane, and generates a flow table based on the routing policy, where the flow table is used to transmit network traffic, and after the flow table is generated, the flow table needs to be issued to a data plane located in a kernel state in the SDN network, so that the data plane stores the flow table for subsequent network traffic transmission.
Therefore, after the control plane generates the flow table, the generated flow table is directly issued to the data plane of the kernel mode, the data plane can be directly forwarded based on the flow table in the data plane after receiving the network flow, and compared with the prior art that the flow table is not hit in the data plane, the kernel mode and the user mode need not be switched back and forth, the method and the device do not need to be switched back and forth between the user mode and the kernel mode, the processing time of the network flow in the SDN network is saved, and the data transmission efficiency is improved.
Step S13: and storing the flow table through the data surface, and forwarding the input network flow based on the flow table when the input network flow is received.
Correspondingly, the data plane needs to receive the flow table issued by the control plane, store the flow table, and forward the input network traffic based on the flow table when receiving the input network traffic. Specifically, the data plane stores the flow table; when receiving input network flow, extracting quintuple information in the input network flow; matching the extracted quintuple information in the input network flow with the flow table, and forwarding the input network flow based on a matching result.
The quintuple in the quintuple information is a communication term, and generally refers to a source IP (Internet Protocol Address), a source port, a destination IP Address, a destination port, and a transport layer Protocol.
Since the target route generation model in the management plane generates the route policy for the SDN network, the control plane also generates the flow table for the SDN network, so that the generated flow table can be more accurate, thereby reducing the matching times of the input network traffic and the flow table, reducing the matching times of the network traffic and the flow table, and improving the network traffic forwarding efficiency.
In this application, a management plane in an SDN network generates a routing policy by using a target routing policy model obtained in advance based on machine learning training, and issues the routing policy to a control plane in the SDN network; generating a flow table through the control plane based on the routing strategy, and issuing the flow table to a data plane of a kernel state in the SDN network; and storing the flow table through the data surface, and forwarding the input network flow based on the flow table when the input network flow is received. It can be seen that, in the present application, a routing policy is generated by a target router policy generation model, which is obtained based on machine learning training in advance, in a management plane of an SDN network, and then the routing policy is issued to a control plane in the SDN network, the control plane may generate a flow table based on the routing policy and issue the flow table to a data plane in a kernel state in the SDN network, and when receiving an input network traffic, the data plane may forward the input network traffic based on the flow table, so that since the routing policy model obtained based on machine learning training in advance may generate a routing policy that is more matched with a current SDN network, the flow table issued based on the routing policy may be more accurate, thereby reducing the matching times of the network traffic and the flow table, and thus reducing the matching times of the network traffic and the flow table, the network flow forwarding efficiency is improved, the generated flow tables are directly issued to the data plane of the kernel mode, switching between the kernel mode and the user mode is not needed in the network flow forwarding process, and the network flow forwarding efficiency is further improved.
Referring to fig. 2, an embodiment of the present application discloses a specific SDN network data transmission method, where the method includes:
step S21: and training a preset machine learning model by using a pre-acquired data set to obtain the target routing strategy model, wherein the data set comprises a training data set and a testing data set.
In a specific implementation process, a preset machine learning model needs to be trained by using a pre-acquired data set to obtain the target routing strategy model, wherein the data set comprises a training data set and a testing data set. The machine learning model is any one of a decision tree, a random forest, a neural network, a hidden Markov model and a self-organizing map, and can be determined according to actual conditions.
Specifically, training a preset machine learning model by using a pre-acquired data set to obtain the target routing strategy model, including: training a preset machine learning model by using a training data set in a pre-acquired data set to obtain a routing strategy model to be tested; and testing and optimizing the routing strategy model to be tested by using the test data set in the data set to obtain the target routing strategy model.
That is, the preset machine learning model is trained by using the data in the training data set, and then the trained machine learning model is tested and optimized by using the data in the testing data set until the output of the machine learning model meets a preset condition, for example, the output error is smaller than a preset error, and the target route generation strategy is obtained.
The method includes the following steps that a preset machine learning model is trained by using a training data set in a pre-acquired data set, and a routing strategy model to be tested is obtained, and the method includes the following steps: performing feature extraction on a training data set in a pre-acquired data set to obtain quintuple information corresponding to each network data in the training data set; and training a preset machine learning model by utilizing quintuple information corresponding to each network data to obtain a routing strategy model to be tested.
That is, extracting quintuple information from the network data in the test data set to obtain quintuple information corresponding to each network data in the training data set, and then training a preset machine learning model by using the quintuple information corresponding to each network data to obtain a to-be-tested routing strategy model.
Referring to fig. 3, a flow chart of machine learning model training is shown. The method comprises the steps of firstly extracting quintuple information from data in a training data set, training a machine learning model by using the extracted quintuple information, extracting the quintuple information in a testing data set, and then testing and optimizing the trained machine learning model by using the extracted quintuple information to obtain a target routing strategy model.
Step S22: and generating a routing strategy by using the target routing strategy model through a management surface in the SDN network, and issuing the routing strategy to a control surface in the SDN network.
Step S23: and generating a flow table through the control plane based on the routing strategy, and issuing the flow table to a data plane of a kernel state in the SDN network.
Step S24: and storing the flow table through the data surface, and forwarding the input network flow based on the flow table when the input network flow is received.
And after the data plane receives the flow table, the flow table is stored, and when input network flow is received, the input network flow can be forwarded based on the flow table. The incoming network traffic is also a data packet.
That is, as shown in fig. 4, when a packet is obtained, the packet may be parsed to extract five-tuple information, and then the extracted five-tuple information in the packet is matched with the flow table, and corresponding actions, such as discarding, forwarding, and the like, are performed based on a matching result, and then the packet is output.
Referring to fig. 5, an overall block diagram of SDN network data transmission is shown. A machine learning module in a management surface of the SDN network utilizes data set training to obtain a target routing strategy model, a routing strategy is generated by the target routing strategy model and issued to a control surface, the control surface generates a flow table based on the routing strategy and issues the flow table to a data surface, and the data surface receives data and outputs the data based on the flow table.
Referring to fig. 6, an embodiment of the present application discloses an SDN network, including:
the management surface 11 is configured to generate a routing policy by using a target routing policy model obtained in advance based on machine learning training, and issue the routing policy to a control surface in the SDN network;
the control plane 12 is configured to generate a flow table based on the routing policy, and issue the flow table to a data plane of a kernel state in the SDN network;
the data plane 13 is configured to store the flow table, and forward the input network traffic based on the flow table when the input network traffic is received.
In this application, a management plane in an SDN network generates a routing policy by using a target routing policy model obtained in advance based on machine learning training, and issues the routing policy to a control plane in the SDN network; generating a flow table through the control plane based on the routing strategy, and issuing the flow table to a data plane of a kernel state in the SDN network; and storing the flow table through the data surface, and forwarding the input network flow based on the flow table when the input network flow is received. It can be seen that, in the present application, a routing policy is generated by a target router policy generation model, which is obtained based on machine learning training in advance, in a management plane of an SDN network, and then the routing policy is issued to a control plane in the SDN network, the control plane may generate a flow table based on the routing policy and issue the flow table to a data plane in a kernel state in the SDN network, and when receiving an input network traffic, the data plane may forward the input network traffic based on the flow table, so that since the routing policy model obtained based on machine learning training in advance may generate a routing policy that matches a current SDN network, the flow table issued based on the routing policy may be made more accurate, thereby reducing the matching times of the network traffic and the flow table, and thus reducing the matching times of the network traffic and the flow table, the network flow forwarding efficiency is improved, the generated flow tables are directly issued to the data plane of the kernel mode, switching between the kernel mode and the user mode is not needed in the network flow forwarding process, and the network flow forwarding efficiency is further improved.
In some specific implementations, the management plane 11 is configured to:
and training a preset machine learning model by using a pre-acquired data set to obtain the target routing strategy model, wherein the data set comprises a training data set and a testing data set.
In some specific implementations, the machine learning model is any one of a decision tree, a random forest, a neural network, a hidden markov model, and a self-organizing map.
In some specific implementations, the management plane 11 is configured to:
training a preset machine learning model by using a training data set in a pre-acquired data set to obtain a routing strategy model to be tested;
and testing and optimizing the routing strategy model to be tested by using the test data set in the data set to obtain the target routing strategy model.
In some specific implementations, the management plane 11 is configured to:
performing feature extraction on a training data set in a pre-acquired data set to obtain quintuple information corresponding to each network data in the training data set;
and training a preset machine learning model by utilizing quintuple information corresponding to each network data to obtain a routing strategy model to be tested.
In some specific implementations, the data plane 13 is configured to:
storing the flow table;
extracting quintuple information in input network flow when the input network flow is received;
matching the extracted quintuple information in the input network flow with the flow table, and forwarding the input network flow based on a matching result.
Referring to fig. 7, a schematic structural diagram of an electronic device 20 provided in the embodiment of the present application is shown, where the electronic device 20 may be a server, a notebook computer, a desktop computer, or the like, and may implement the SDN network data transmission method steps disclosed in the foregoing embodiment.
In general, the electronic device 20 in the present embodiment includes: a processor 21 and a memory 22.
The processor 21 may include one or more processing cores, such as a four-core processor, an eight-core processor, and so on. The processor 21 may be implemented by at least one hardware of a DSP (digital signal processing), an FPGA (field-programmable gate array), and a PLA (programmable logic array). The processor 21 may also include a main processor and a coprocessor, where the main processor is a processor for processing data in an awake state, and is also called a Central Processing Unit (CPU); a coprocessor is a low power processor for processing data in a standby state. In some embodiments, the processor 21 may be integrated with a GPU (graphics processing unit) which is responsible for rendering and drawing images to be displayed on the display screen. In some embodiments, the processor 21 may include an AI (artificial intelligence) processor for processing computing operations related to machine learning.
Memory 22 may include one or more computer-readable storage media, which may be non-transitory. Memory 22 may also include high speed random access memory, as well as non-volatile memory, such as one or more magnetic disk storage devices, flash memory storage devices. In this embodiment, the memory 22 is at least used for storing a computer program 221, wherein after being loaded and executed by the processor 21, the computer program is capable of implementing the SDN network data transmission method steps disclosed in any of the foregoing embodiments.
In some embodiments, the electronic device 20 may further include a display 23, an input/output interface 24, a communication interface 25, a sensor 26, a power supply 27, and a communication bus 28.
Those skilled in the art will appreciate that the configuration shown in FIG. 7 is not limiting of electronic device 20 and may include more or fewer components than those shown.
Further, an embodiment of the present application also discloses a computer readable storage medium for storing a computer program, wherein the computer program, when executed by a processor, implements the following steps:
generating a routing strategy by a management surface in an SDN network by using a target routing strategy model obtained in advance based on machine learning training, and issuing the routing strategy to a control surface in the SDN network; generating a flow table through the control plane based on the routing strategy, and issuing the flow table to a data plane of a kernel state in the SDN network; and storing the flow table through the data surface, and forwarding the input network flow based on the flow table when the input network flow is received.
In this application, a management plane in an SDN network generates a routing policy by using a target routing policy model obtained in advance based on machine learning training, and issues the routing policy to a control plane in the SDN network; generating a flow table through the control plane based on the routing strategy, and issuing the flow table to a data plane of a kernel state in the SDN network; and storing the flow table through the data surface, and forwarding the input network flow based on the flow table when the input network flow is received. It can be seen that, in the present application, a routing policy is generated by a target router policy generation model, which is obtained based on machine learning training in advance, in a management plane of an SDN network, and then the routing policy is issued to a control plane in the SDN network, the control plane may generate a flow table based on the routing policy and issue the flow table to a data plane in a kernel state in the SDN network, and when receiving an input network traffic, the data plane may forward the input network traffic based on the flow table, so that since the routing policy model obtained based on machine learning training in advance may generate a routing policy that is more matched with a current SDN network, the flow table issued based on the routing policy may be more accurate, thereby reducing the matching times of the network traffic and the flow table, and thus reducing the matching times of the network traffic and the flow table, the network flow forwarding efficiency is improved, the generated flow tables are directly issued to the data plane of the kernel mode, switching between the kernel mode and the user mode is not needed in the network flow forwarding process, and the network flow forwarding efficiency is further improved.
In this embodiment, when the computer subprogram stored in the computer-readable storage medium is executed by the processor, the following steps may be specifically implemented: and training a preset machine learning model by using a pre-acquired data set to obtain the target routing strategy model, wherein the data set comprises a training data set and a testing data set.
In this embodiment, when the computer subprogram stored in the computer-readable storage medium is executed by the processor, the following steps may be specifically implemented: training a preset machine learning model by using a training data set in a pre-acquired data set to obtain a routing strategy model to be tested; and testing and optimizing the routing strategy model to be tested by using the test data set in the data set to obtain the target routing strategy model.
In this embodiment, when the computer subprogram stored in the computer-readable storage medium is executed by the processor, the following steps may be specifically implemented: performing feature extraction on a training data set in a pre-acquired data set to obtain quintuple information corresponding to each network data in the training data set; and training a preset machine learning model by utilizing quintuple information corresponding to each network data to obtain a routing strategy model to be tested.
In this embodiment, when the computer subprogram stored in the computer-readable storage medium is executed by the processor, the following steps may be specifically implemented: storing the flow table through the data plane; extracting quintuple information in input network flow when the input network flow is received; matching the extracted quintuple information in the input network flow with the flow table, and forwarding the input network flow based on a matching result.
The embodiments are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same or similar parts among the embodiments are referred to each other. The device disclosed by the embodiment corresponds to the method disclosed by the embodiment, so that the description is simple, and the relevant points can be referred to the method part for description.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. A software module may reside in Random Access Memory (RAM), memory, Read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
Finally, it is further noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of other elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The SDN network data transmission method, the SDN network, the device, and the medium provided by the present application are introduced in detail above, and a specific example is applied in the present application to explain the principle and the implementation of the present application, and the description of the above embodiment is only used to help understanding the method and the core idea of the present application; meanwhile, for a person skilled in the art, according to the idea of the present application, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present application.
Claims (10)
1. An SDN network data transmission method is characterized by comprising the following steps:
generating a routing strategy by a management surface in an SDN network by using a target routing strategy model obtained in advance based on machine learning training, and issuing the routing strategy to a control surface in the SDN network;
generating a flow table through the control plane based on the routing strategy, and issuing the flow table to a data plane of a kernel state in the SDN network;
and storing the flow table through the data surface, and forwarding the input network flow based on the flow table when the input network flow is received.
2. The SDN network data transmission method of claim 1, wherein before generating the routing policy by a management plane in the SDN network using a target routing policy model obtained in advance based on machine learning training, the method further comprises:
and training a preset machine learning model by using a pre-acquired data set to obtain the target routing strategy model, wherein the data set comprises a training data set and a testing data set.
3. The SDN network data transmission method of claim 2, wherein the machine learning model is any one of a decision tree, a random forest, a neural network, a hidden markov model, and a self-organizing map.
4. The SDN network data transmission method of claim 2, wherein the training a preset machine learning model with a pre-obtained data set to obtain the target routing policy model comprises:
training a preset machine learning model by using a training data set in a pre-acquired data set to obtain a routing strategy model to be tested;
and testing and optimizing the routing strategy model to be tested by using the test data set in the data set to obtain the target routing strategy model.
5. The SDN network data transmission method of claim 4, wherein the training a preset machine learning model with a training data set in a pre-obtained data set to obtain a routing policy model to be tested, includes:
performing feature extraction on a training data set in a pre-acquired data set to obtain quintuple information corresponding to each network data in the training data set;
and training a preset machine learning model by utilizing quintuple information corresponding to each network data to obtain a routing strategy model to be tested.
6. The SDN network data transmission method of any one of claims 1 to 5, wherein the storing, by the data plane, the flow table and forwarding, when receiving incoming network traffic, the incoming network traffic based on the flow table comprises:
storing the flow table through the data plane;
extracting quintuple information in input network flow when the input network flow is received;
matching the extracted quintuple information in the input network flow with the flow table, and forwarding the input network flow based on a matching result.
7. An SDN network, comprising:
the management surface is used for generating a routing strategy by utilizing a target routing strategy model obtained in advance based on machine learning training and issuing the routing strategy to the control surface in the SDN network;
the control plane is used for generating a flow table based on the routing strategy and issuing the flow table to a data plane of a kernel state in the SDN network;
and the data surface is used for storing the flow table and forwarding the input network flow based on the flow table when the input network flow is received.
8. The SDN network of claim 7, wherein the management plane is configured to:
and training a preset machine learning model by using a pre-acquired data set to obtain the target routing strategy model, wherein the data set comprises a training data set and a testing data set.
9. An electronic device, comprising:
a memory and a processor;
wherein the memory is used for storing a computer program;
the processor is configured to execute the computer program to implement the SDN network data transmission method of any one of claims 1 to 6.
10. A computer-readable storage medium storing a computer program, wherein the computer program when executed by a processor implements the SDN network data transmission method of any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011529208.4A CN112671648A (en) | 2020-12-22 | 2020-12-22 | SDN data transmission method, SDN, device and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011529208.4A CN112671648A (en) | 2020-12-22 | 2020-12-22 | SDN data transmission method, SDN, device and medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112671648A true CN112671648A (en) | 2021-04-16 |
Family
ID=75407663
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011529208.4A Pending CN112671648A (en) | 2020-12-22 | 2020-12-22 | SDN data transmission method, SDN, device and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112671648A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113472654A (en) * | 2021-05-31 | 2021-10-01 | 济南浪潮数据技术有限公司 | Network traffic data forwarding method, device, equipment and medium |
| CN113556323A (en) * | 2021-06-24 | 2021-10-26 | 深圳市邦盛实时智能技术有限公司 | Bypass non-invasive flow acquisition system applied to enterprise internal control |
| CN115002028A (en) * | 2022-04-30 | 2022-09-02 | 济南浪潮数据技术有限公司 | Message processing method, device and medium |
| CN115086227A (en) * | 2022-07-14 | 2022-09-20 | 中国联合网络通信集团有限公司 | Method, device and equipment for determining forwarding strategy and storage medium |
| CN115174149A (en) * | 2022-06-07 | 2022-10-11 | 阿里云计算有限公司 | Data forwarding method, webpage access control method, equipment and system |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105049450A (en) * | 2015-08-24 | 2015-11-11 | 北京汉柏科技有限公司 | Cloud security system based on virtual network environment and deployment framework of cloud security system |
| CN107124365A (en) * | 2017-04-25 | 2017-09-01 | 曙光信息产业(北京)有限公司 | A kind of acquisition system of the routing policy based on machine learning |
| CN108075974A (en) * | 2016-11-14 | 2018-05-25 | 中国移动通信有限公司研究院 | A kind of flow transmission control method, device and SDN architecture systems |
| CN109831386A (en) * | 2019-03-08 | 2019-05-31 | 西安交通大学 | Optimal route selection algorithm based on machine learning under a kind of SDN |
| CN110958177A (en) * | 2019-11-07 | 2020-04-03 | 浪潮电子信息产业股份有限公司 | Network-on-chip route optimization method, device, equipment and readable storage medium |
| CN110986979A (en) * | 2019-11-27 | 2020-04-10 | 浙江工商大学 | SDN multi-path routing planning method based on reinforcement learning |
| US20200344154A1 (en) * | 2019-04-25 | 2020-10-29 | EMC IP Holding Company LLC | Method, device and computer program product for path optimization |
-
2020
- 2020-12-22 CN CN202011529208.4A patent/CN112671648A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105049450A (en) * | 2015-08-24 | 2015-11-11 | 北京汉柏科技有限公司 | Cloud security system based on virtual network environment and deployment framework of cloud security system |
| CN108075974A (en) * | 2016-11-14 | 2018-05-25 | 中国移动通信有限公司研究院 | A kind of flow transmission control method, device and SDN architecture systems |
| CN107124365A (en) * | 2017-04-25 | 2017-09-01 | 曙光信息产业(北京)有限公司 | A kind of acquisition system of the routing policy based on machine learning |
| CN109831386A (en) * | 2019-03-08 | 2019-05-31 | 西安交通大学 | Optimal route selection algorithm based on machine learning under a kind of SDN |
| US20200344154A1 (en) * | 2019-04-25 | 2020-10-29 | EMC IP Holding Company LLC | Method, device and computer program product for path optimization |
| CN110958177A (en) * | 2019-11-07 | 2020-04-03 | 浪潮电子信息产业股份有限公司 | Network-on-chip route optimization method, device, equipment and readable storage medium |
| CN110986979A (en) * | 2019-11-27 | 2020-04-10 | 浙江工商大学 | SDN multi-path routing planning method based on reinforcement learning |
Non-Patent Citations (3)
| Title |
|---|
| YANLING ZHAO ET AL.: ""A Survey of Networking Applications Applying the Software Defined Networking Concept Based on Machine Learning"", 《IEEE》 * |
| 李兆斌等: ""SDN数据安全处理机制关键模块的研究与实现"", 《计算机应用》 * |
| 陆世亮 等: ""基于内核的POF交换机设计与实现"", 《电子技术设计与应用》 * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113472654A (en) * | 2021-05-31 | 2021-10-01 | 济南浪潮数据技术有限公司 | Network traffic data forwarding method, device, equipment and medium |
| CN113556323A (en) * | 2021-06-24 | 2021-10-26 | 深圳市邦盛实时智能技术有限公司 | Bypass non-invasive flow acquisition system applied to enterprise internal control |
| CN115002028A (en) * | 2022-04-30 | 2022-09-02 | 济南浪潮数据技术有限公司 | Message processing method, device and medium |
| CN115002028B (en) * | 2022-04-30 | 2024-02-13 | 济南浪潮数据技术有限公司 | Message processing method, device and medium |
| CN115174149A (en) * | 2022-06-07 | 2022-10-11 | 阿里云计算有限公司 | Data forwarding method, webpage access control method, equipment and system |
| CN115174149B (en) * | 2022-06-07 | 2024-04-05 | 阿里云计算有限公司 | Data forwarding method, webpage access control method, equipment and system |
| CN115086227A (en) * | 2022-07-14 | 2022-09-20 | 中国联合网络通信集团有限公司 | Method, device and equipment for determining forwarding strategy and storage medium |
| CN115086227B (en) * | 2022-07-14 | 2023-10-03 | 中国联合网络通信集团有限公司 | Method, device, equipment and storage medium for determining forwarding strategy |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112671648A (en) | SDN data transmission method, SDN, device and medium | |
| US10680961B2 (en) | Using headerspace analysis to identify flow entry reachability | |
| US10630587B2 (en) | Shared memory communication in software defined networking | |
| CN107395665A (en) | A kind of block chain service handling and business common recognition method and device | |
| US9529531B2 (en) | Proxy hash table | |
| Boutros et al. | Build fast, trade fast: FPGA-based high-frequency trading using high-level synthesis | |
| CN105939284B (en) | The matching process and device of message control strategy | |
| US9075836B2 (en) | Partitioning keys for hash tables | |
| CN113411380B (en) | Processing method, logic circuit and equipment based on FPGA (field programmable gate array) programmable session table | |
| US11902119B2 (en) | System and method for serverless monitoring | |
| Gao et al. | OVS-CAB: Efficient rule-caching for Open vSwitch hardware offloading | |
| CN107682266A (en) | Matching process and device, the computer-readable recording medium of flow table item | |
| CN111405007B (en) | TCP session management method, device, storage medium and electronic equipment | |
| CN114338529B (en) | Five-tuple rule matching method and device | |
| US20220318592A1 (en) | Sampler and apparatus for executing graph neural network model | |
| EP4207702A1 (en) | Dynamic prediction of system resource requirement of network software in a live network using data driven models | |
| US10445080B2 (en) | Methods for adaptive placement of applications and devices thereof | |
| CN115002028A (en) | Message processing method, device and medium | |
| CN116306407B (en) | Verification method, device, equipment and storage medium of Network On Chip (NOC) | |
| CN112383479B (en) | Rule query method and device, computer equipment and storage medium | |
| CN113472654B (en) | Network traffic data forwarding method, device, equipment and medium | |
| CN111615124B (en) | Service detection method and device, electronic equipment and storage medium | |
| CN112783507B (en) | Data stream guiding playback method and device, electronic equipment and readable storage medium | |
| CN118118408A (en) | Data packet transmission method and device | |
| CN116980354A (en) | Data processing method, device, computer equipment and 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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210416 |
|
| RJ01 | Rejection of invention patent application after publication |