CN110417576B

CN110417576B - Deployment method, device, equipment and storage medium of hybrid software custom network

Info

Publication number: CN110417576B
Application number: CN201910521265.9A
Authority: CN
Inventors: 陈闽川; 马骏; 王少军
Original assignee: Ping An Technology Shenzhen Co Ltd
Current assignee: Ping An Technology Shenzhen Co Ltd
Priority date: 2019-06-17
Filing date: 2019-06-17
Publication date: 2021-10-12
Anticipated expiration: 2039-06-17
Also published as: WO2020252895A1; CN110417576A

Abstract

The invention discloses a deployment method, a deployment device, equipment and a storage medium of a hybrid software self-defined network based on distributed deployment, which are used for enabling the deployment process to be smoother and more effective, enabling the coordination between the network control rate and the link load balance to be more reasonable and improving the network working efficiency. The method comprises the following steps: acquiring node information of a target network; judging whether the target network is a mixed Software Defined Network (SDN) or not according to the node information; if the target network is not the hybrid SDN, executing a hybrid SDN initial deployment strategy, wherein the hybrid SDN initial deployment strategy is used for calculating an initial SDN node deployment position; and establishing a virtual local network VLAN group according to the initial SDN node deployment position and a preset reinforcement learning algorithm.

Description

Deployment method, device, equipment and storage medium of hybrid software custom network

Technical Field

The invention relates to the field of distributed deployment, in particular to a deployment method, a deployment device, deployment equipment and a deployment storage medium of a hybrid software custom network.

Background

Software Defined Network (SDN), which is a novel network innovation architecture of the Emulex network, is an implementation manner of network virtualization, and its core technology OpenFlow separates a control plane and a data plane of a network device, thereby implementing flexible control of network traffic and making the network become more intelligent as a pipeline.

Due to virtualization of computing and storage resources, resources of upper-layer equipment (servers and storage) are opened, if a network architecture is still kept as it is, and a stable operation of a system is required to be ensured, corresponding configuration needs to be carried out on computing and storage resource pools, and transition of the network architecture can be achieved in an economical and practical iteration mode through SDN and traditional network hybrid networking, namely hybrid SDN, and service interruption caused by complete replacement is avoided.

Currently, in a hybrid SDN, a deployment strategy of the SDN stays on a static deployment, and only deploys for current resources, without considering that transition from a traditional network to a software-defined network is a gradual process. And the communication mode in the mixed software self-defined network is too single, and the advantage of the software self-defined network structure is not fully utilized.

Disclosure of Invention

The invention provides a deployment method, a deployment device, equipment and a storage medium of a hybrid software custom network, which are used for enabling the deployment process to be smoother and more effective, enabling the coordination between the network control rate and the link load balance to be more reasonable and improving the network working efficiency.

A first aspect of an embodiment of the present invention provides a deployment method for a hybrid software-defined network, including: acquiring node information of a target network; judging whether the target network is a mixed Software Defined Network (SDN) or not according to the node information; if the target network is not the hybrid SDN, executing a hybrid SDN initial deployment strategy, wherein the hybrid SDN initial deployment strategy is used for calculating an initial SDN node deployment position; and establishing a virtual local network VLAN group according to the initial SDN node deployment position and a preset reinforcement learning algorithm.

Optionally, in a first implementation manner of the first aspect of the embodiment of the present invention, the method further includes: and if the target network is the hybrid SDN, executing a hybrid SDN network transition deployment strategy, wherein the hybrid SDN network transition deployment strategy is used for calculating a newly added SDN node deployment position.

Optionally, in a second implementation manner of the first aspect of the embodiment of the present invention, after the executing the hybrid SDN network transition deployment policy, the method further includes: and establishing a new virtual local network VLAN group according to the deployment position of the new SDN node, wherein the new VLAN group comprises VLAN group decomposition and VLAN group combination.

Optionally, in a third implementation manner of the first aspect of the embodiment of the present invention, the establishing a VLAN group of a virtual local network according to the initial SDN node deployment location and a preset reinforcement learning algorithm includes: performing SDN node VLAN grouping according to the initial SDN node deployment position and a preset reinforcement learning algorithm to obtain a VLAN grouping set and an isolated node set at the present stage; sorting the isolated nodes in the isolated node set by taking the degree as the priority to obtain a node set in which VLAN group communication is established in the isolated nodes, traversing nodes except the node set in which the VLAN group communication is established in the isolated nodes, establishing a new VLAN group according to the number of public paths in a link path set between two nearest nodes, and adding the new VLAN group to the VLAN grouping set at the current stage to obtain a first transition VLAN grouping set; determining the link with the most VLAN groups in the first transition VLAN grouping set, and selecting the VLAN groups on any two links to be combined to obtain a second transition VLAN grouping set; and determining a VLAN group set needing to be recombined, a traditional switch node set needing to be recombined and a traditional switch set of completed recombined VLANs according to the second transition VLAN group set, then assigning values to the VLAN group set needing to be recombined and the traditional switch node set needing to be recombined, deleting the VLAN group set needing to be recombined from the VLAN group set, and finally carrying out VLAN group division on the newly added SDN switch and the rest traditional switches to obtain the recombined VLAN group set.

Optionally, in a fourth implementation manner of the first aspect of the embodiment of the present invention, the performing SDN node VLAN grouping according to the initial SDN node deployment location and a preset reinforcement learning algorithm to obtain a current-stage VLAN grouping set and an isolated node set includes: sequencing single switches vi in an SDN switch set Vs in the hybrid SDN according to degrees from large to small according to a preset reinforcement learning algorithm; setting two variables Valready and Valone, wherein the Valready represents a node set subjected to VLAN grouping, the Valone represents a node set without VLAN grouping, the Valready is initialized to an empty set, the Valone is initialized to V-Vs, and the V represents all nodes; traversing the SDN nodes with the sequenced priorities; if the Valready is an empty set, directly adding the node vi into the Valready set, and continuously traversing the next node; if the Valready only has one node, calculating the shortest path of the unique node in the Valready through the vi, establishing a new VLAN group, adding the information of the new VLAN group into the VL, and removing the node on the new VLAN group from the Valone; if at least two nodes exist in the Valready, calculating two nodes nearest to the vi in the Valready, establishing two new VLAN groups, adding the two established VLAN groups into a set VL of VLANs in a hybrid SDN network, and removing the nodes on the two new VLAN groups from the Valone; and obtaining the VL and Valone values, wherein the VL represents a current-stage VLAN group set, and the Valone represents an isolated node set.

Optionally, in a fifth implementation manner of the first aspect of the embodiment of the present invention, the method further includes: when the hybrid SDN fails, optimizing the hybrid SDN.

Optionally, in a sixth implementation manner of the first aspect of the embodiment of the present invention, when the hybrid SDN fails, optimizing the hybrid SDN includes: when the hybrid SDN fails, determining the fault type of the hybrid SDN, wherein the fault type comprises VLAN inter-group communication fault, VLAN inter-group communication fault and SDN inter-group communication fault; when the fault type is communication fault in the VLAN group, executing a fault tolerance strategy in the VLAN group, and recalculating a fault tolerance link; when the fault type is communication fault between VLAN groups, a fault tolerance strategy between VLAN groups is executed, and a fault tolerance link is recalculated; and when the fault type is communication fault between SDN groups, executing a fault tolerance strategy between the SDN groups, and recalculating the fault tolerance link.

A second aspect of an embodiment of the present invention provides a deployment apparatus for a hybrid software-defined network, including: an acquisition unit configured to acquire node information of a target network; a judging unit, configured to judge whether the target network is a hybrid software defined network SDN according to the node information; a first execution unit, configured to execute a hybrid SDN network initial deployment policy if the target network is not the hybrid SDN, where the hybrid SDN network initial deployment policy is used to calculate an initial SDN node deployment location; and the first establishing unit is used for establishing a virtual local network VLAN group according to the initial SDN node deployment position and a preset reinforcement learning algorithm.

Optionally, in a first implementation manner of the second aspect of the embodiment of the present invention, the deployment apparatus of the hybrid software-defined network further includes: a second execution unit, configured to execute a hybrid SDN network transition deployment policy if the target network is the hybrid SDN, where the hybrid SDN network transition deployment policy is used to calculate a new SDN node deployment location.

Optionally, in a second implementation manner of the second aspect of the embodiment of the present invention, the deployment apparatus of the hybrid software-defined network further includes: and the second establishing unit is used for establishing a new virtual local network VLAN group according to the deployment position of the new SDN node, wherein the new VLAN group comprises VLAN group decomposition and VLAN group combination.

Optionally, in a third implementation manner of the second aspect of the embodiment of the present invention, the first establishing unit is specifically configured to: performing SDN node VLAN grouping according to the initial SDN node deployment position and a preset reinforcement learning algorithm to obtain a VLAN grouping set and an isolated node set at the present stage; sorting the isolated nodes in the isolated node set by taking the degree as the priority to obtain a node set in which VLAN group communication is established in the isolated nodes, traversing nodes except the node set in which the VLAN group communication is established in the isolated nodes, establishing a new VLAN group according to the number of public paths in a link path set between two nearest nodes, and adding the new VLAN group to the VLAN grouping set at the current stage to obtain a first transition VLAN grouping set; determining the link with the most VLAN groups in the first transition VLAN grouping set, and selecting the VLAN groups on any two links to be combined to obtain a second transition VLAN grouping set; and determining a VLAN group set needing to be recombined, a traditional switch node set needing to be recombined and a traditional switch set of completed recombined VLANs according to the second transition VLAN group set, then assigning values to the VLAN group set needing to be recombined and the traditional switch node set needing to be recombined, deleting the VLAN group set needing to be recombined from the VLAN group set, and finally carrying out VLAN group division on the newly added SDN switch and the rest traditional switches to obtain the recombined VLAN group set.

Optionally, in a fourth implementation manner of the second aspect of the embodiment of the present invention, the first establishing unit is specifically configured to: sequencing single switches vi in an SDN switch set Vs in the hybrid SDN according to degrees from large to small according to a preset reinforcement learning algorithm; setting two variables Valready and Valone, wherein the Valready represents a node set subjected to VLAN grouping, the Valone represents a node set without VLAN grouping, the Valready is initialized to an empty set, the Valone is initialized to V-Vs, and the V represents all nodes; traversing the SDN nodes with the sequenced priorities; if the Valready is an empty set, directly adding the node vi into the Valready set, and continuously traversing the next node; if the Valready only has one node, calculating the shortest path of the unique node in the Valready through the vi, establishing a new VLAN group, adding the information of the new VLAN group into the VL, and removing the node on the new VLAN group from the Valone; if at least two nodes exist in the Valready, calculating two nodes nearest to the vi in the Valready, establishing two new VLAN groups, adding the two established VLAN groups into a set VL of VLANs in a hybrid SDN network, and removing the nodes on the two new VLAN groups from the Valone; and obtaining the VL and Valone values, wherein the VL represents a current-stage VLAN group set, and the Valone represents an isolated node set.

Optionally, in a fifth implementation manner of the second aspect of the embodiment of the present invention, the deployment apparatus of the hybrid software-defined network further includes: an optimization unit, configured to optimize the hybrid SDN when the hybrid SDN fails.

Optionally, in a sixth implementation manner of the second aspect of the embodiment of the present invention, the optimization unit is specifically configured to: when the hybrid SDN fails, determining the fault type of the hybrid SDN, wherein the fault type comprises VLAN inter-group communication fault, VLAN inter-group communication fault and SDN inter-group communication fault; when the fault type is communication fault in the VLAN group, executing a fault tolerance strategy in the VLAN group, and recalculating a fault tolerance link; when the fault type is communication fault between VLAN groups, a fault tolerance strategy between VLAN groups is executed, and a fault tolerance link is recalculated; and when the fault type is communication fault between SDN groups, executing a fault tolerance strategy between the SDN groups, and recalculating the fault tolerance link.

A third aspect of an embodiment of the present invention provides a deployment device of a hybrid software-defined network, including a memory, a processor, and a computer program that is stored in the memory and is executable on the processor, where the processor implements the deployment method of the hybrid software-defined network according to any one of the above embodiments when executing the computer program.

A fourth aspect of the embodiments of the present invention provides a computer-readable storage medium, including instructions, which, when executed on a computer, cause the computer to perform the steps of the deployment method of the hybrid software customized network described in any of the above embodiments.

In the technical scheme provided by the embodiment of the invention, node information of a target network is obtained; judging whether the target network is a mixed Software Defined Network (SDN) or not according to the node information; if the target network is not the hybrid SDN, executing a hybrid SDN initial deployment strategy, wherein the hybrid SDN initial deployment strategy is used for calculating an initial SDN node deployment position; and establishing a virtual local network VLAN group according to the initial SDN node deployment position and a preset reinforcement learning algorithm. According to the embodiment of the invention, different deployment strategies are adopted according to the actual situation of the network, so that the deployment process is smoother and more effective, and the coordination between the network control rate and the link load balance is more reasonable.

Drawings

FIG. 1 is a schematic diagram of an embodiment of a deployment method of a hybrid software-defined network according to an embodiment of the present invention;

fig. 2 is a schematic diagram of an application scenario for implementing an initial deployment policy of a hybrid SDN network according to an embodiment of the present invention;

fig. 3 is a schematic view of an application scenario of a VLAN combining and merging process in an embodiment of the present invention;

fig. 4 is a schematic diagram of another application scenario for implementing a hybrid SDN network transition deployment policy according to an embodiment of the present invention;

fig. 5 is a schematic diagram of a dynamic deployment cost variation value of a hybrid SDN network according to an embodiment of the present invention;

FIG. 6 is a schematic diagram of an embodiment of a deployment apparatus for a hybrid software-defined network in an embodiment of the present invention;

FIG. 7 is a schematic diagram of another embodiment of a deployment apparatus for a hybrid software custom network according to an embodiment of the present invention;

fig. 8 is a schematic diagram of an embodiment of a deployment device of a hybrid software custom network in the embodiment of the present invention.

Detailed Description

In order to make the technical field of the invention better understand the scheme of the invention, the embodiment of the invention will be described in conjunction with the attached drawings in the embodiment of the invention.

The terms "first," "second," "third," "fourth," and the like in the description and in the claims, as well as in the drawings, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It will be appreciated that the data so used may be interchanged under appropriate circumstances such that the embodiments described herein may be practiced otherwise than as specifically illustrated or described herein. Furthermore, the terms "comprises," "comprising," or "having," and any variations thereof, are intended to cover non-exclusive inclusions, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

Referring to fig. 1, a flowchart of a deployment method of a hybrid software-defined network according to an embodiment of the present invention specifically includes:

101. and acquiring node information of the target network.

The server obtains node information of the target network, for example, the terminal may obtain a name identifier, an address identifier, a configuration identifier of the configuration information, a path for accessing the target network node, and the like of the target network node, and may also be other node information that needs to be used, which is not limited herein.

It should be noted that the execution subject may be a server or a terminal, as long as the deployment of the hybrid software customized network can be realized, and the server is taken as an example for description in the present application.

102. And judging whether the target network is a mixed Software Defined Network (SDN) or not according to the node information.

And the server judges whether the target network is a mixed Software Defined Network (SDN) according to the node information. Specifically, the server determines whether a policy currently executed by the target network is a hybrid SDN policy according to the node information. The hybrid SDN policy is a rule that a node of a target network can execute, that is, the node of the target network manages the network according to a certain rule. The strategy is divided into two situations, wherein one situation is to upgrade a traditional network into a hybrid SDN network, namely the initial deployment strategy of the hybrid SDN network; and the other is that the hybrid SDN network carries out network upgrading by adding SDN nodes (switches), namely a hybrid SDN network transition deployment strategy. In the process of executing the initial deployment policy of the hybrid SDN network, only the problem of hardware resources needs to be considered, and in the process of executing the transitional deployment policy of the hybrid SDN network, in addition to the problem of hardware resources, the damage to an existing Virtual Local Area Network (VLAN) group and the movement of existing hardware resources (i.e., the resource migration of an SDN node (switch)) need to be considered.

103. And if the target network is not the hybrid SDN, executing a hybrid SDN initial deployment strategy, wherein the hybrid SDN initial deployment strategy is used for calculating an initial SDN node deployment position.

If the target network is not the hybrid SDN, the server executes an initial deployment strategy of the hybrid SDN, the server upgrades the target network, namely the target network is upgraded to the hybrid SDN from a traditional network, and the initial deployment strategy of the hybrid SDN is used for calculating an initial SDN node deployment position. Specifically, a plurality of target deployment nodes are selected according to an initial deployment strategy of the hybrid SDN network, switches in the target deployment nodes are replaced by SDN switches, and VLAN grouping is performed.

As shown in fig. 2, fig. 2 is a schematic diagram of a process of upgrading a legacy network into a hybrid SDN network (i.e., performing an initial deployment policy of the hybrid SDN network), where a target network includes legacy switch a, legacy switch B, legacy switch C, legacy switch D, legacy switch E, legacy switch F, legacy switch G, legacy switch H, legacy switch I, and legacy switch J; the need to replace the legacy switch D, E with the SDN switch D, E is calculated based on a preset reinforcement learning algorithm.

Then, some of the links are configured with VLAN groups through a hybrid SDN network communication module, specifically, the links between a traditional switch A and traditional switches B and C, between the traditional switch C and the traditional switch G, between the traditional switch G and a traditional switch J, between the traditional switch B and an SDN switch E, between the traditional switch H and the SDN switch D, and between the traditional switch H and the traditional switch J are all VLAN1 links; links between the traditional switch J and the traditional switches H and I, between the traditional switch I and the traditional switch F, between the traditional switch F and the SDN switch E and between the traditional switch F and the SDN switch E are all VLAN2 links; the link between SDN switch D and SDN switch E is a VLAN3 link, where the link between legacy switch H and legacy switch J belongs to both VLAN1 and VLAN2, and the link between SDN switch D and legacy switch B and legacy switch G is a normal link.

104. And establishing a virtual local network VLAN group according to the initial SDN node deployment position and a preset reinforcement learning algorithm.

And the server establishes a virtual local network VLAN group according to the initial SDN node deployment position and a preset reinforcement learning algorithm. For example, an optimal deployment node is selected by using a preset reinforcement learning algorithm. After a plurality of deployment nodes are selected, VLAN group division is carried out to obtain a set of VLAN groups. The process of dividing the VLAN group is specifically as follows: firstly, SDN node VLAN grouping is carried out on SDN switch nodes to obtain VLAN grouping sets and isolated switch sets at the current stage, and then isolated node VLAN grouping, VLAN combination and VLAN group decomposition are carried out in sequence.

The SDN node VLAN grouping process comprises the following steps: 1. the individual switches vi in the SDN switch set Vs in the hybrid SDN network are first sorted by degrees from large to small, because the deployment node already considers the link problem, here only the degree of the switch (i.e. the node) will be considered as the priority of the VLAN packet. 2. Two variables, Valready and Valone, are set, Valready indicates a switch that has performed VLAN grouping, Valone indicates a switch that has no VLAN grouping left, and Valready and Valone initialize as an empty set and all switches V-Vs, respectively. 3. Traversing the set V of all switches in the hybrid SDN network for the SDN switch nodes with the sequenced priorities. If Valready is an empty set, the node vi is directly added into the set, and the next node is continuously traversed. If the Valready has only one node, calculating the shortest path of the unique node in the Valready by the vi, establishing a VLAN group, adding information into a VLAN set VL in the hybrid SDN network, and removing the node on the new VLAN group from the Valone. If at least two nodes exist in the Valready, calculating two nodes nearest to the vi in the Valready, establishing two new VLAN groups, adding the two established new VLAN groups into a VLAN set VL in the hybrid SDN network, and removing the nodes on the two new VLAN groups from the Valone; if at least two nodes exist in the Valready, two nodes nearest to vi in the set Valready are calculated and two new VLAN groups are established, wherein two VLAN groups may have a common link, but VLAN resources are wasted, so that the two VLAN groups are reduced to one, only the VLAN group established with the nearest node vi is added into the VL, and the switch on the VLAN group is removed from Valone. Finally, two values of VL and Valone are returned, which respectively represent the stage VLAN group set and the isolated switch (i.e. the switch without VLAN grouping).

The grouping process of the isolated node VLAN comprises the following steps: and sequencing the isolated nodes in the isolated node set by taking the degree as the priority to obtain a node set in which VLAN group communication is established in the isolated nodes, traversing nodes except the node set in which the VLAN group communication is established in the isolated nodes, establishing a new VLAN group according to the number of public paths in a link path set between two nearest nodes, and adding the new VLAN group to the VLAN grouping set at the current stage to obtain a first transition VLAN grouping set. Specifically, the method comprises the following steps: 1. the input isolated nodes are sorted by taking the degree as the priority, and then a Valready set is initialized, wherein the Valready set represents the nodes of the isolated nodes, which have established VLAN group communication. 2. Traversing an isolated node set Valone, if nodes for establishing VLAN group communication skip, if not, calculating two SDN nodes closest to vi in a Vs set, and recording two link path sets E1 and E2. In the two link path sets E1 and E2, if there is a common path, only the link path set corresponding to the vi nearest SDN node is left, a new VLAN group is established for the link path set, and information of the new VLAN group is added to the VL group, and finally switches on the new VLAN group are added to the Valready set. If the two link paths do not have a common path, the sets of the two link paths are merged, a new VLAN group is established, the information of the new VLAN group is added into the VL group, and finally the switch on the new VLAN group is added into the Valready set.

The VLAN combination merging process comprises the following steps: and determining the link with the most VLAN groups in the first transition VLAN grouping set, and selecting the VLAN groups on any two links to be combined to obtain a second transition VLAN grouping set. Specifically, the method comprises the following steps: 1. and finding out the link with the most VLAN groups in the links in the hybrid SDN network. In the left diagram of FIG. 3, link e_B,D、e_D,GAnd e_H,JThese three, the VLAN groups on the first two links are merged, here with link e_B,DFor example, VLmine is a group of VLANs 2, and VLmaxe is a group of VLANs 1. 2. VLmine and VLmaxe information are removed from VL, and then VLmine covered legacy switches are denoted as Vminc (legacy switch B), SDN switches are denoted as Vmins (SDN switch D, E), VLmaxe covered legacy switches are denoted as Vmaxc (legacy switches A, B, C and G), SDN switches are denoted as Vmaxs (SDN switch D, E), and SDN switch union Vs is set. 3. Traversals are performed for the legacy switches in Vmaxc-Vminc, adding all switches to VLmaxe. 4. Adding VLmaxe into VL, and finally mixing SDN networkVLAN information is shown in the right diagram of fig. 3.

The VLAN group decomposition process comprises the following steps: and determining a VLAN group set needing to be recombined, a traditional switch node set needing to be recombined and a traditional switch set of the recombined VLAN according to the second transition VLAN grouping set, then assigning values to the VLAN group set needing to be recombined and the traditional switch node set needing to be recombined, deleting the VLAN group set needing to be recombined from the VLAN group set, and finally carrying out VLAN group division on the newly added SDN switch and the rest traditional switches to obtain the recombined VLAN group set. Specifically, the method comprises the following steps: 1. three variables VLregroup, Vnewc and Valready are initialized to represent a VLAN group set to be reassembled, a conventional switch node set to be reassembled and a conventional switch set that has completed the reassembly of VLANs, respectively. 2. And assigning VLregroup and Vnewc variables, and removing the VLAN set needing to be recombined from the VLAN group set VL. 3. And VLAN group division is carried out on the newly added SDN switch in the same way as the grouping process of the SDN node VLAN. 4. The VLAN group division is carried out on the rest traditional switches, and the division mode is the same as the VLAN grouping process of the isolated nodes. 5. And obtaining the recombined VLAN group set VL.

It should be noted that the whole network can be regarded as a mesh structure, the routers and the servers are regarded as nodes of the mesh structure, and the degree refers to the number of links connected by the nodes of the routers.

According to the embodiment of the invention, the initial deployment strategy of the hybrid SDN network is executed on the traditional network according to the actual condition of the network, so that the deployment process is smoother and more effective, and the coordination between the network control rate and the link load balance is more reasonable; meanwhile, the whole mixed software self-defined network is divided into different local virtual network groups in a virtual local network group division mode, and each network node needs to communicate through the local virtual network groups, so that the network working efficiency is improved.

Optionally, on the basis of the embodiment corresponding to fig. 1, in an optional embodiment of the deployment method of the hybrid software-defined network provided in the embodiment of the present invention, the method further includes: and if the target network is the hybrid SDN, executing a hybrid SDN network transition deployment strategy, wherein the hybrid SDN network transition deployment strategy is used for calculating a newly added SDN node deployment position.

For example, if the target network is a hybrid SDN, the server executes a hybrid SDN network transition deployment policy, and the server upgrades the target network, that is, adds an SDN node (switch) to the hybrid SDN network to upgrade the network, so as to enhance the flow control and the network fault tolerance of the network. The hybrid SDN network transition deployment strategy is used for calculating a deployment position of a newly added SDN node (switch).

As shown in fig. 4, fig. 4 is a schematic diagram of a process of adding SDN nodes to a hybrid SDN network (i.e., implementing a hybrid SDN network transition deployment policy), where a target network includes legacy switch a, legacy switch B, legacy switch C, SDN, switch D, SDN, switch E, legacy switch F, legacy switch G, legacy switch H, legacy switch I, and legacy switch J; and replacing the traditional switch H with the SDN switch H according to the calculation of a preset reinforcement learning algorithm. The specific process is similar to that of fig. 2, and is not described herein again.

According to the embodiment of the invention, a hybrid SDN network transition deployment strategy is executed on the hybrid SDN according to the actual situation of the network, so that the deployment process is smoother and more effective, and the coordination between the network control rate and the link load balance is more reasonable.

Optionally, on the basis of the embodiment corresponding to fig. 1, in an optional embodiment of the deployment method for a hybrid software-defined network provided in the embodiment of the present invention, after the executing a hybrid SDN network transition deployment policy, the method further includes: and establishing a new virtual local network VLAN group according to the deployment position of the new SDN node, wherein the new VLAN group comprises VLAN group decomposition and VLAN group combination.

For example, the server establishes a new virtual local network VLAN group according to the new SDN node deployment location, where the new VLAN group includes VLAN group decomposition and VLAN group merging. For example, as shown in fig. 4, after it is determined that an SDN switch H needs to be added, a VLAN group is configured again through the hybrid SDN network communication module, and after the VLAN group is reconfigured, links between a conventional switch a and a conventional switch B, between a conventional switch C and a conventional switch G, between a conventional switch G and a conventional switch J, between a conventional switch B and an SDN switch E, and links between the SDN switch H and the conventional switch J are all VLAN1 links; links between the traditional switch J and the SDN switch H, between the traditional switch I and the traditional switch F, and between the traditional switch F and the SDN switch E are all VLAN2 links; the link between the SDN switch D and the SDN switch E is a VLAN3 link, the link between the SDN switch H and the SDN switch D is a VLAN4 link, and the link between the SDN switch H and the SDN switch E is a VLAN5 link, wherein the link between the legacy switch H and the legacy switch J belongs to both VLAN1 and VLAN 2.

According to the embodiment of the invention, through the division of the VLAN group, the whole hybrid SDN network has the functions of making full use of the SDN network, such as self-defined forwarding mode, flow statistics and the like, so that more flows are controlled by the SDN controller.

Optionally, on the basis of the embodiment corresponding to fig. 1, in an optional embodiment of the deployment method of the hybrid software-defined network provided in the embodiment of the present invention, the establishing a virtual local network VLAN group according to the initial SDN node deployment location and a preset reinforcement learning algorithm includes: performing SDN node VLAN grouping according to the initial SDN node deployment position and a preset reinforcement learning algorithm to obtain a VLAN grouping set and an isolated node set at the present stage; sorting the isolated nodes in the isolated node set by taking the degree as the priority to obtain a node set in which VLAN group communication is established in the isolated nodes, traversing nodes except the node set in which the VLAN group communication is established in the isolated nodes, establishing a new VLAN group according to the number of public paths in a link path set between two nearest nodes, and adding the new VLAN group to the VLAN grouping set at the current stage to obtain a first transition VLAN grouping set; determining the link with the most VLAN groups in the first transition VLAN grouping set, and selecting the VLAN groups on any two links to be combined to obtain a second transition VLAN grouping set; and determining a VLAN group set needing to be recombined, a traditional switch node set needing to be recombined and a traditional switch set of completed recombined VLANs according to the second transition VLAN group set, then assigning values to the VLAN group set needing to be recombined and the traditional switch node set needing to be recombined, deleting the VLAN group set needing to be recombined from the VLAN group set, and finally carrying out VLAN group division on the newly added SDN switch and the rest traditional switches to obtain the recombined VLAN group set.

According to the embodiment of the invention, the SDN switch is dynamically deployed by using the reinforcement learning algorithm, so that the problem of stable transition from the whole network to the SDN network is solved, and the requirement of gradually replacing the old switch in the traditional network or the hybrid SDN network is met.

Optionally, on the basis of the embodiment corresponding to fig. 1, in an optional embodiment of the deployment method of the hybrid software-defined network provided in the embodiment of the present invention, the performing SDN node VLAN grouping according to the initial SDN node deployment position and a preset reinforcement learning algorithm to obtain a current-stage VLAN grouping set and an isolated node set includes: sequencing single switches vi in an SDN switch set Vs in the hybrid SDN according to degrees from large to small according to a preset reinforcement learning algorithm; setting two variables Valready and Valone, wherein the Valready represents a node set subjected to VLAN grouping, the Valone represents a node set without VLAN grouping, the Valready is initialized to an empty set, the Valone is initialized to V-Vs, and the V represents all nodes; traversing the SDN nodes with the sequenced priorities; if the Valready is an empty set, directly adding the node vi into the Valready set, and continuously traversing the next node; if the Valready only has one node, calculating the shortest path of the unique node in the Valready through the vi, establishing a new VLAN group, adding the information of the new VLAN group into the VL, and removing the node on the new VLAN group from the Valone; if at least two nodes exist in the Valready, calculating two nodes nearest to the vi in the Valready, establishing two new VLAN groups, adding the two established VLAN groups into a set VL of VLANs in a hybrid SDN network, and removing the nodes on the two new VLAN groups from the Valone; and obtaining the VL and Valone values, wherein the VL represents a current-stage VLAN group set, and the Valone represents an isolated node set.

The embodiment of the invention refines the grouping process of the SDN node VLAN and increases the implementation mode of the embodiment of the invention.

Optionally, on the basis of the embodiment corresponding to fig. 1, in an optional embodiment of the deployment method of the hybrid software-defined network provided in the embodiment of the present invention, the method further includes: when the hybrid SDN fails, optimizing the hybrid SDN.

For example, the server optimizes the hybrid SDN, and the server calculates a dynamic deployment cost variation value of the hybrid SDN network according to a preset formula. The cost value is obtained by inverse calculation of an optimization target, the minimum value of the cost value is obtained to be the optimization target, and the maximum control rate of the network and the link load balance are both in a proportion of 50%. For example, as shown in fig. 5, where the X axis is the number of iterations, each iteration is performed in a loop, the Y axis is a cost value, the experiment loop is performed 120 times, the first time, the sixteenth time and the twenty-first time are selected as references, each loop is iterated 600 times (only 400 times are shown in the figure), the learning rate is 1e-3, the reward attenuation degree is 0.99, the random factor is 0.4, the VLAN group is fixed to 10 groups, the number of selected replacement conventional switches is 3, and the selected network topology is TW Telecom.

Wherein the optimization value target is defined as:

wherein, γ and β are network flow coefficient and link load balancing coefficient, the sum of γ and β is 1, ConMax (G) is maximum control network function, LinkBal (G) is load balancing function;

it can be seen that in the first 100 iterations, the cost value will become more floating due to the random factor, and then it can be seen that the basic trend is more moderate, but because in the loop, the state matrix is continuously trained. After multiple training, it can be found that after 450 iterations, the data after the first time, the sixteenth time and the twenty-first time can ignore the factor of the random factor, the cost value of the twenty-first cycle is obviously smaller than that of the other two times, wherein the sixteenth cycle occasionally shakes afterwards, and the cost value may shake due to the fact that the state matrix is not comprehensive enough, and the optimal point needs to be randomly selected when a new state is faced. Although the one hundred and twenty times jitter, it is stable relative to the sixteenth time. The cost value of the first loop can be steady and has no change because the first loop is trapped in local optimization.

According to the embodiment of the invention, when the hybrid SDN fails, the hybrid SDN is optimized, the influence of the failure on the hybrid SDN is eliminated, and the working efficiency is improved.

Optionally, on the basis of the embodiment corresponding to fig. 1, in an optional embodiment of the deployment method of a hybrid software-defined network provided in the embodiment of the present invention, when the hybrid SDN fails, optimizing the hybrid SDN includes: when the hybrid SDN fails, determining the fault type of the hybrid SDN, wherein the fault type comprises VLAN inter-group communication fault, VLAN inter-group communication fault and SDN inter-group communication fault; when the fault type is communication fault in the VLAN group, executing a fault tolerance strategy in the VLAN group, and recalculating a fault tolerance link; when the fault type is communication fault between VLAN groups, a fault tolerance strategy between VLAN groups is executed, and a fault tolerance link is recalculated; and when the fault type is communication fault between SDN groups, executing a fault tolerance strategy between the SDN groups, and recalculating the fault tolerance link.

According to the embodiment of the invention, different fault tolerance strategies are adopted aiming at different fault scenes, so that the recovery performance of the fault tolerance of the hybrid software self-defined network is improved.

With reference to fig. 6, the above description is provided for a deployment method of a hybrid software-defined network in an embodiment of the present invention, and a deployment apparatus of a hybrid software-defined network in an embodiment of the present invention is described below, where an embodiment of the deployment apparatus of a hybrid software-defined network in an embodiment of the present invention includes:

an obtaining unit 601, configured to obtain node information of a target network;

a determining unit 602, configured to determine, according to the node information, whether the target network is a hybrid software defined network SDN;

a first executing unit 603, configured to execute a hybrid SDN network initial deployment policy if the target network is not the hybrid SDN, where the hybrid SDN network initial deployment policy is used to calculate an initial SDN node deployment location;

a first establishing unit 604, configured to establish a virtual local network VLAN group according to the initial SDN node deployment location and a preset reinforcement learning algorithm.

Referring to fig. 7, another embodiment of a deployment apparatus of a hybrid software-defined network according to the embodiment of the present invention includes:

Optionally, the deployment apparatus of the hybrid software-defined network further includes:

a second executing unit 605, configured to execute a hybrid SDN network transition deployment policy if the target network is the hybrid SDN, where the hybrid SDN network transition deployment policy is used to calculate a deployment location of a new SDN node.

a second establishing unit 606, configured to establish a new VLAN group of a virtual local network according to the new SDN node deployment location, where the new VLAN group includes VLAN group decomposition and VLAN group combination.

Optionally, the first establishing unit 603 is specifically configured to:

performing SDN node VLAN grouping according to the initial SDN node deployment position and a preset reinforcement learning algorithm to obtain a VLAN grouping set and an isolated node set at the present stage; sorting the isolated nodes in the isolated node set by taking the degree as the priority to obtain a node set in which VLAN group communication is established in the isolated nodes, traversing nodes except the node set in which the VLAN group communication is established in the isolated nodes, establishing a new VLAN group according to the number of public paths in a link path set between two nearest nodes, and adding the new VLAN group to the VLAN grouping set at the current stage to obtain a first transition VLAN grouping set; determining the link with the most VLAN groups in the first transition VLAN grouping set, and selecting the VLAN groups on any two links to be combined to obtain a second transition VLAN grouping set; and determining a VLAN group set needing to be recombined, a traditional switch node set needing to be recombined and a traditional switch set of completed recombined VLANs according to the second transition VLAN group set, then assigning values to the VLAN group set needing to be recombined and the traditional switch node set needing to be recombined, deleting the VLAN group set needing to be recombined from the VLAN group set, and finally carrying out VLAN group division on the newly added SDN switch and the rest traditional switches to obtain the recombined VLAN group set.

Optionally, the first establishing unit 603 is further specifically configured to:

sequencing single switches vi in an SDN switch set Vs in the hybrid SDN according to degrees from large to small according to a preset reinforcement learning algorithm; setting two variables Valready and Valone, wherein the Valready represents a node set subjected to VLAN grouping, the Valone represents a node set without VLAN grouping, the Valready is initialized to an empty set, the Valone is initialized to V-Vs, and the V represents all nodes; traversing the SDN nodes with the sequenced priorities; if the Valready is an empty set, directly adding the node vi into the Valready set, and continuously traversing the next node; if the Valready only has one node, calculating the shortest path of the unique node in the Valready through the vi, establishing a new VLAN group, adding the information of the new VLAN group into the VL, and removing the node on the new VLAN group from the Valone; if at least two nodes exist in the Valready, calculating two nodes nearest to the vi in the Valready, establishing two new VLAN groups, adding the two established VLAN groups into a set VL of VLANs in a hybrid SDN network, and removing the nodes on the two new VLAN groups from the Valone; and obtaining the VL and Valone values, wherein the VL represents a current-stage VLAN group set, and the Valone represents an isolated node set.

an optimizing unit 607, configured to optimize the hybrid SDN when the hybrid SDN fails.

Optionally, the optimization unit 607 is specifically configured to:

when the hybrid SDN fails, determining the fault type of the hybrid SDN, wherein the fault type comprises VLAN inter-group communication fault, VLAN inter-group communication fault and SDN inter-group communication fault; when the fault type is communication fault in the VLAN group, executing a fault tolerance strategy in the VLAN group, and recalculating a fault tolerance link; when the fault type is communication fault between VLAN groups, a fault tolerance strategy between VLAN groups is executed, and a fault tolerance link is recalculated; and when the fault type is communication fault between SDN groups, executing a fault tolerance strategy between the SDN groups, and recalculating the fault tolerance link.

According to the embodiment of the invention, the initial deployment strategy of the hybrid SDN network is executed on the traditional network according to the actual condition of the network, so that the deployment process is smoother and more effective, and the coordination between the network control rate and the link load balance is more reasonable; meanwhile, the whole mixed software self-defined network is divided into different local virtual network groups in a virtual local network group division mode, and each network node needs to communicate through the local virtual network groups, so that the network working efficiency is improved. Meanwhile, different fault tolerance strategies are adopted for different fault scenes, and the recovery performance of the self-defined network fault tolerance of the hybrid software is improved.

Fig. 6 to fig. 7 describe in detail the deployment apparatus of the hybrid software-defined network in the embodiment of the present invention from the perspective of the modular functional entity, and in the following, describe in detail the deployment device of the hybrid software-defined network in the embodiment of the present invention from the perspective of hardware processing.

Fig. 8 is a schematic structural diagram of a deployment apparatus of a hybrid software-defined network according to an embodiment of the present invention, where the deployment apparatus 800 of the hybrid software-defined network may generate a relatively large difference due to different configurations or performances, and may include one or more processors (CPUs) 801 (e.g., one or more processors) and a memory 809, and one or more storage media 808 (e.g., one or more mass storage devices) storing applications 807 or data 806. Memory 809 and storage media 808 can be, among other things, transient or persistent storage. The program stored on the storage medium 808 may include one or more modules (not shown), each of which may include a series of instruction operations on a deployment device of the hybrid software customized network. Still further, the processor 801 may be configured to communicate with the storage medium 808 to execute a series of instruction operations in the storage medium 808 on the hybrid software custom network deployed device 800.

The hybrid software-customized network deployment apparatus 800 may also include one or more power supplies 802, one or more wired or wireless network interfaces 803, one or more input-output interfaces 804, and/or one or more operating systems 805, such as Windows Server, Mac OSX, Unix, Linux, FreeBSD, etc. Those skilled in the art will appreciate that the hybrid software-customized network deployment device architecture shown in FIG. 8 does not constitute a limitation on the hybrid software-customized network deployment devices, and may include more or fewer components than shown, or some components in combination, or a different arrangement of components. The processor 801 may perform the functions of the acquisition unit 601, the judgment unit 602, the first execution unit 603, the first establishment unit 604, the second execution unit 605, the second establishment unit 606, and the optimization unit 607 in the above embodiments.

The following specifically describes each component of the deployment device of the hybrid software customized network with reference to fig. 8:

the processor 801 is a control center of a deployment device of the hybrid software-defined network, and can perform processing according to a set deployment method of the hybrid software-defined network. The processor 801 connects various portions of the deployment device of the entire hybrid software-defined network using various interfaces and lines, and performs various functions of the deployment device of the hybrid software-defined network and processes data by running or executing software programs and/or modules stored in the memory 809 and calling data stored in the memory 809, thereby implementing the deployment of the hybrid software-defined network. The storage medium 808 and the memory 809 are carriers for storing data, in the embodiment of the present invention, the storage medium 808 may refer to an internal memory with a small storage capacity and a high speed, and the memory 809 may refer to an external memory with a large storage capacity and a low storage speed.

The memory 809 can be used to store software programs and modules, and the processor 801 executes various functional applications and data processing of the deployment device 800 of the hybrid software customized network by running the software programs and modules stored in the memory 809. The memory 809 may mainly include a storage program area and a storage data area, where the storage program area may store an operating system, an application program required by at least one function (for example, determining whether a target network is a hybrid software defined network SDN or not according to node information), and the like; the storage data area may store data (such as a virtual local network VLAN group, etc.) created according to the use of the deployment device of the hybrid software-customized network, and the like. Further, the memory 809 can include high speed random access memory, and can also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid state storage device. The deployment method program of the hybrid software custom network provided in the embodiment of the present invention and the received data stream are stored in the memory, and when they are needed to be used, the processor 801 calls from the memory 809.

When loaded and executed on a computer, cause the processes or functions described in accordance with the embodiments of the invention to occur, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another computer readable storage medium, for example, the computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by wire (e.g., coaxial cable, optical fiber, twisted pair) or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can store or a data storage device, such as a server, a data center, etc., that is integrated with one or more available media. The usable medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., compact disk), or a semiconductor medium (e.g., Solid State Disk (SSD)), among others.

It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.

In the embodiments provided in the present invention, it should be understood that the disclosed system, apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.

The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.

The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a read-only memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.

The above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.

Claims

1. A deployment method of a hybrid software custom network is characterized by comprising the following steps:

acquiring node information of a target network;

judging whether the target network is a mixed Software Defined Network (SDN) or not according to the node information;

if the target network is not the hybrid SDN, executing a hybrid SDN initial deployment strategy, wherein the hybrid SDN initial deployment strategy is used for calculating an initial SDN node deployment position;

establishing a virtual local network VLAN group according to the initial SDN node deployment position and a preset reinforcement learning algorithm;

the establishing of the virtual local network VLAN group according to the initial SDN node deployment position and a preset reinforcement learning algorithm comprises the following steps:

performing SDN node VLAN grouping according to the initial SDN node deployment position and a preset reinforcement learning algorithm to obtain a VLAN grouping set and an isolated node set at the present stage;

sorting the isolated nodes in the isolated node set by taking the degree as the priority to obtain a node set in which VLAN group communication is established in the isolated nodes, traversing nodes except the node set in which the VLAN group communication is established in the isolated nodes, establishing a new VLAN group according to the number of public paths in a link path set between two nearest nodes, and adding the new VLAN group to the VLAN grouping set at the current stage to obtain a first transition VLAN grouping set;

determining the link with the most VLAN groups in the first transition VLAN grouping set, and selecting the VLAN groups on any two links to be combined to obtain a second transition VLAN grouping set;

and determining a VLAN group set needing to be recombined, a traditional switch node set needing to be recombined and a traditional switch set of completed recombined VLANs according to the second transition VLAN group set, then assigning values to the VLAN group set needing to be recombined and the traditional switch node set needing to be recombined, deleting the VLAN group set needing to be recombined from the VLAN group set, and finally carrying out VLAN group division on the newly added SDN switch and the rest traditional switches to obtain the recombined VLAN group set.

2. The method of deploying a hybrid software custom network of claim 1, further comprising:

and if the target network is the hybrid SDN, executing a hybrid SDN network transition deployment strategy, wherein the hybrid SDN network transition deployment strategy is used for calculating a newly added SDN node deployment position.

3. The method of deploying a hybrid software custom network of claim 2, wherein after the executing the hybrid SDN network grace deployment policy, the method further comprises:

and establishing a new virtual local network VLAN group according to the deployment position of the new SDN node, wherein the new VLAN group comprises VLAN group decomposition and VLAN group combination.

4. The deployment method of the hybrid software defined network as claimed in claim 1, wherein the performing SDN node VLAN grouping according to the initial SDN node deployment location and a preset reinforcement learning algorithm to obtain a current-stage VLAN grouping set and an isolated node set includes:

sequencing single switches vi in an SDN switch set Vs in the hybrid SDN according to degrees from large to small according to a preset reinforcement learning algorithm;

setting two variables Valready and Valone, wherein the Valready represents a node set subjected to VLAN grouping, the Valone represents a node set without VLAN grouping, the Valready is initialized to an empty set, the Valone is initialized to V-Vs, and the V represents all nodes;

traversing the SDN nodes with the sequenced priorities;

if the Valready is an empty set, directly adding the node vi into the Valready set, and continuously traversing the next node;

if the Valready only has one node, calculating the shortest path of the unique node in the Valready through the vi, establishing a new VLAN group, adding the information of the new VLAN group into the VL, and removing the node on the new VLAN group from the Valone;

if at least two nodes exist in the Valready, calculating two nodes nearest to the vi in the Valready, establishing two new VLAN groups, adding the two established VLAN groups into a set VL of VLANs in a hybrid SDN network, and removing the nodes on the two new VLAN groups from the Valone;

and obtaining the VL and Valone values, wherein the VL represents a current-stage VLAN group set, and the Valone represents an isolated node set.

5. The deployment method of the hybrid software-defined network as claimed in any one of claims 1 to 4, further comprising:

when the hybrid SDN fails, optimizing the hybrid SDN.

6. The deployment method of the hybrid software custom network as claimed in claim 5, wherein the optimizing the hybrid SDN when the hybrid SDN fails comprises:

when the hybrid SDN fails, determining the fault type of the hybrid SDN, wherein the fault type comprises VLAN inter-group communication fault, VLAN inter-group communication fault and SDN inter-group communication fault;

when the fault type is communication fault in the VLAN group, executing a fault tolerance strategy in the VLAN group, and recalculating a fault tolerance link;

when the fault type is communication fault between VLAN groups, a fault tolerance strategy between VLAN groups is executed, and a fault tolerance link is recalculated;

and when the fault type is communication fault between SDN groups, executing a fault tolerance strategy between the SDN groups, and recalculating the fault tolerance link.

7. A deployment device for a hybrid software-defined network, comprising:

an acquisition unit configured to acquire node information of a target network;

a judging unit, configured to judge whether the target network is a hybrid software defined network SDN according to the node information;

a first execution unit, configured to execute a hybrid SDN network initial deployment policy if the target network is not the hybrid SDN, where the hybrid SDN network initial deployment policy is used to calculate an initial SDN node deployment location;

the first establishing unit is used for establishing a virtual local network VLAN group according to the initial SDN node deployment position and a preset reinforcement learning algorithm;

8. A deployment device of a hybrid software-defined network, comprising a memory, a processor and a computer program stored on the memory and operable on the processor, wherein the processor executes the computer program to implement the deployment method of the hybrid software-defined network according to any one of claims 1 to 6.

9. A computer-readable storage medium comprising instructions that when executed on a computer cause the computer to perform the method of deploying a hybrid software-customized network according to any one of claims 1-6.