CN109039885A - A kind of data transfer path selection method and device - Google Patents
A kind of data transfer path selection method and device Download PDFInfo
- Publication number
- CN109039885A CN109039885A CN201810979689.5A CN201810979689A CN109039885A CN 109039885 A CN109039885 A CN 109039885A CN 201810979689 A CN201810979689 A CN 201810979689A CN 109039885 A CN109039885 A CN 109039885A
- Authority
- CN
- China
- Prior art keywords
- data
- data transmission
- communication
- communication equipment
- transmission link
- 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.)
- Granted
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L45/00—Routing or path finding of packets in data switching networks
- H04L45/02—Topology update or discovery
- H04L45/08—Learning-based routing, e.g. using neural networks or artificial intelligence
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L45/00—Routing or path finding of packets in data switching networks
- H04L45/14—Routing performance; Theoretical aspects
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L45/00—Routing or path finding of packets in data switching networks
- H04L45/22—Alternate routing
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
A kind of data transfer path selection method and device, comprising: establish the neural network model for selecting recommending data transmission line;The data transfer request message that receiving communication device is sent determines to include originating a plurality of data transmission link of routing node and purpose routing node, and determine the recommending data transmission line of preset quantity from a plurality of data transmission link by neural network model;The recommending data transmission line of preset quantity is sent to communication equipment, current data transmission link is switched to the recommending data transmission line selected from the recommending data transmission line of preset quantity using communication equipment.As it can be seen that a plurality of data transfer path can intelligently be filtered out and be recommended communication equipment and be selected by implementing data transfer path selection method and device, be conducive to promote data transmission quality, and then improving data transmission efficiency.
Description
Technical field
The present invention relates to data communication technology fields, in particular to a kind of data transfer path selection method and dress
It sets.
Background technique
With the development of network, more and more users use the mobile terminal Internet access such as mobile phone or ipad, data transmission route
Diameter selection has extremely important influence for the performance of network.Existing data transfer path selection method is according to flow point
With carrying out data transmission Path selection, a plurality of data transmission route usually between network source node and network purpose routing node
In diameter, select the shortest data transmission path of transmission range as optimal data transfer path.However it sends out in practice
It is existing, it is transmitted often due to a large number of users is all made of the shortest data transfer path of the transmission range, causes network congestion, into
And data transmission quality is influenced, data transmission efficiency is low, and time delay is big.
Summary of the invention
In view of the above problems, it the present invention provides a kind of data transfer path selection method and device, can intelligently sieve
It selects a plurality of data transfer path and is recommended communication equipment and selected, be conducive to promote data transmission quality, in turn
Improving data transmission efficiency.
To achieve the goals above, the present invention adopts the following technical scheme that:
First aspect present invention discloses a kind of data transfer path selection method, comprising:
Establish the neural network model for selecting recommending data transmission line;
The data transfer request message that receiving communication device is sent, the data transfer request message include that the communication is set
Preparation send the starting routing node of data information and receives the data information purpose routing node;
Determine to include a plurality of data transmission link for originating routing node and the purpose routing node, and passes through
The neural network model from a plurality of data transmission link determine preset quantity have good data communication feature
Recommending data transmission line;
The Decision Making of Line Schemes of recommending data transmission line including the preset quantity is sent to the communication equipment, is used
Current data transmission link is switched to from the recommending data transmission line of the preset quantity by the communication equipment
One recommending data transmission line of selection.
As an alternative embodiment, in first aspect present invention, the method also includes:
The line information of data transmission link after obtaining the communication equipment switching, and using the line information as foundation
Whether the data transmission link after judging the communication equipment switching is unimpeded;
If it is judged that the data transmission link after the communication equipment switching is not smooth, it is determined that including the starting road
By a plurality of data transmission link of node and the purpose routing node, and by the neural network model from described a plurality of
The recommending data transmission line of preset quantity is determined in data transmission link.
As an alternative embodiment, in first aspect present invention, after the acquisition communication equipment switching
Data transmission link line information, and be according to judge the data biography after communication equipment switching with the line information
Whether defeated route is unimpeded to include:
The occupation proportion of the transmission bandwidth of data transmission link after obtaining the communication equipment switching;
Whether the occupation proportion for judging the transmission bandwidth is more than preset ratio threshold value;
If it is determined that the occupation proportion of the transmission bandwidth is less than the preset ratio threshold value, it is determined that the communication is set
Data transmission link after standby switching is not smooth.
As an alternative embodiment, in first aspect present invention, after the acquisition communication equipment switching
Data transmission link line information, and be according to judge the data biography after communication equipment switching with the line information
Whether defeated route is unimpeded, comprising:
Data transmission link after being switched by the communication equipment sends test data packet, and determines and receive described in response
The consuming duration of the response data packet of test data packet;
Judge whether the consuming duration is greater than preset duration threshold value;
If it is determined that the consuming duration is greater than the preset duration threshold value, it is determined that the number after the communication equipment switching
It is not smooth according to transmission line.
As an alternative embodiment, the foundation is for selecting recommending data to pass in first aspect present invention
The neural network model of defeated route includes:
The data information of communication network locating for the communication equipment is obtained, the data information includes the communication network
The route framework of all communication node data and the communication network;
Using the data information as foundation, the neural network model corresponding with the telecommunication network is constructed;Wherein, institute
The topological structure for stating neural network model corresponds to the route framework of the communication network, each neuron pair of the topological structure
Answer the communication node data of the communication network.
Second aspect of the present invention discloses a kind of data transfer path selection device, comprising:
Model building module, for establishing the neural network model for selecting recommending data transmission line;
Receiving module, for the data transfer request message that receiving communication device is sent, the data transfer request message
The starting routing node of data information is sent including the communication equipment and receives the data information purpose routing node;
Route determining module includes the starting routing node and the mesh for being determined by the neural network model
Routing node a plurality of data transmission link, and by the neural network model from a plurality of data transmission link
Determine the recommending data transmission line of preset quantity;
Sending module, for by include the preset quantity recommending data transmission line Decision Making of Line Schemes be sent to it is described
Current data transmission link is switched to the recommendation number from the preset quantity using the communication equipment by communication equipment
According to the recommending data transmission line selected in transmission line.
As an alternative embodiment, the data transfer path selection device is also in second aspect of the present invention
Include:
The unimpeded judgment module of line, for obtaining the line information of the data transmission link after the communication equipment switches, and
It is foundation judges whether the data transmission link after the communication equipment switching is unimpeded with the line information;
The route determining module is also used to after the unimpeded judgment module of the line judges the communication equipment switching
When data transmission link is not unimpeded, it is determined that a plurality of data including the starting routing node and the purpose routing node pass
Defeated route, and the recommending data by the neural network model determining preset quantity from a plurality of data transmission link
Transmission line.
As an alternative embodiment, in second aspect of the present invention, the model building module, comprising:
First submodule, for obtaining the data information of communication network locating for the communication equipment, the data packets
Include all communication node data of the communication network and the route framework of the communication network;
Second submodule, for constructing the nerve corresponding with the telecommunication network using the data information as foundation
Network model;Wherein, the topological structure of the neural network model corresponds to the route framework of the communication network, the topology frame
Each neuron of structure corresponds to the communication node data of the communication network.
Third aspect present invention discloses a kind of computer equipment, including memory and processor, and the memory is used for
Computer program is stored, the processor runs the computer program so that the computer equipment executes first aspect and discloses
The some or all of data transfer path selection method.
Fourth aspect present invention discloses a kind of computer readable storage medium, is stored with computer described in the third aspect
The computer program used in equipment.
The data transfer path selection method and device provided according to the present invention, is first established for selecting recommending data to transmit
The neural network model of route;When receiving the data transfer request message of communication equipment transmission, data transfer request letter
The communication equipment that breath includes sends the starting routing node of data information and receives data information purpose routing node, then can root
A plurality of data transmission link is determined according to data transfer request message, which may be implemented by originating road
It is transmitted by the data of node to purpose routing node;Further, by the neural network model previously established from a plurality of data
The recommending data transmission line with good data communication feature of preset quantity is determined in transmission line, finally, will packet
The Decision Making of Line Schemes for including the recommending data transmission line of the preset quantity is sent to communication equipment, and communication equipment receives the route side
After case, current data transmission link is switched to the recommendation selected from the recommending data transmission line of preset quantity
Data transmission link is effectively avoided being transmitted using the shortest single data transfer path of the transmission range, is conducive to be promoted
Data transmission quality, and then improving data transmission efficiency.
To enable the above objects, features and advantages of the present invention to be clearer and more comprehensible, preferred embodiment is cited below particularly, and cooperate
Appended attached drawing, is described in detail below.
Detailed description of the invention
In order to illustrate the technical solution of the embodiments of the present invention more clearly, below will be to needed in the embodiment attached
Figure is briefly described, it should be understood that the following drawings illustrates only certain embodiments of the present invention, therefore is not construed as pair
The restriction of the scope of the invention.
Fig. 1 is a kind of flow diagram for data transfer path selection method that the embodiment of the present invention one provides;
Fig. 2 is a kind of flow diagram of data transfer path selection method provided by Embodiment 2 of the present invention;
Fig. 3 is a kind of structural schematic diagram for data transfer path selection device that the embodiment of the present invention three provides.
Specific embodiment
Below in conjunction with attached drawing in the embodiment of the present invention, technical solution in the embodiment of the present invention carries out clear, complete
Ground description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.Usually exist
The component of the embodiment of the present invention described and illustrated in attached drawing can be arranged and be designed with a variety of different configurations herein.Cause
This, is not intended to limit claimed invention to the detailed description of the embodiment of the present invention provided in the accompanying drawings below
Range, but it is merely representative of selected embodiment of the invention.Based on the embodiment of the present invention, those skilled in the art are not doing
Every other embodiment obtained under the premise of creative work out, shall fall within the protection scope of the present invention.
For the problems of the prior art, the present invention provides a kind of data transfer path selection method and devices;First build
Found the neural network model for selecting recommending data transmission line;In the data transfer request letter for receiving communication equipment transmission
When breath, the communication equipment which includes sends the starting routing node of data information and receives data information
Purpose routing node can then determine a plurality of data transmission link according to data transfer request message, a plurality of data transmission
Route may be implemented to be transmitted by the data of starting routing node to purpose routing node;Further, by previously having established
Neural network model determines the recommendation with good data communication feature of preset quantity from a plurality of data transmission link
Data transmission link, finally, the Decision Making of Line Schemes of the recommending data transmission line including the preset quantity is sent to communication equipment,
After communication equipment receives the Decision Making of Line Schemes, current data transmission link is switched to from the recommending data of preset quantity and is passed
The recommending data transmission line selected in defeated route is effectively avoided using the shortest single data transmission route of the transmission range
Diameter is transmitted, and is conducive to promote data transmission quality, and then improving data transmission efficiency.Also, the technology can use phase
The software or hardware realization of pass, are described below by embodiment.
Embodiment 1
Referring to Fig. 1, Fig. 1 is a kind of process signal of data transfer path selection method provided in an embodiment of the present invention
Figure.Wherein, as shown in Figure 1, the data transfer path selection method may comprise steps of:
S101, neural network model for selecting recommending data transmission line is established.
In the present embodiment, which can be fluid threshold velocity model.Fluid threshold velocity is a kind of tool
There is the neural network model of characteristic of fluid, it is assumed that each neuron of fluid threshold velocity is the container for filling fluid, then
In fluid threshold velocity comprising n container (neuron), the behavioral characteristics of i-th of container (neuron) are shown below:
Wherein, ωijFor describing the same negotiability arrived of connection container (neuron) i and j, IiIndicate container (nerve
Member) input, siFor describing the height of liquid level, uiFor describing the volume of i-th of container (neuron).In fluid nerve net
In network, the probability that single fluid molecule flows through certain channel is related to the flow in the channel.
The data transfer request message that S102, receiving communication device are sent, the data transfer request message include that communication is set
Preparation send the starting routing node of data information and receives data information purpose routing node.
In the present embodiment, which can be smart phone (such as Android phone, iOS mobile phone), plate electricity
The equipment such as brain, palm PC, smartwatch and mobile internet device (Mobile Internet Devices, MID), PC,
To this, this embodiment is not limited.
The executing subject of data transfer path selection method provided by the present embodiment can be the communication server, operator
Base station server, data transfer path selection device etc., to being not construed as limiting in this present embodiment.
S103, determine to include originating a plurality of data transmission link of routing node and purpose routing node, and pass through mind
The recommending data with good data communication feature of preset quantity is determined from a plurality of data transmission link through network model
Transmission line.
In the present embodiment, which can be 1,2,3 etc., and to this, this embodiment is not limited.
In the present embodiment, starting routing node is that communication equipment sends used network node when initial data, also known as
For source node;Correspondingly, purpose routing node is used network node when receiving end receives data, also known as the purpose of save
Point.
S104, the Decision Making of Line Schemes of the recommending data transmission line including preset quantity is sent to communication equipment, using logical
Current data transmission link is switched to the recommendation selected from the recommending data transmission line of preset quantity by letter equipment
Data transmission link.
As an alternative embodiment, the route can be exported after communication equipment receives the Decision Making of Line Schemes
Scheme, and current data transmission link is switched to by the corresponding data line of selection instruction according to the selection instruction received
Road.
As another optional embodiment, after communication equipment receives the Decision Making of Line Schemes, will can work as automatically
Preceding data transmission link is switched to matched data transmission link.
In the data transfer path selection method described in Fig. 1, first establish for selecting recommending data transmission line
Neural network model;When receiving the data transfer request message of communication equipment transmission, which includes
Communication equipment send data information starting routing node and receive data information purpose routing node, then can be according to data
Transmission solicited message determines a plurality of data transmission link, which may be implemented by starting routing node
Data to purpose routing node are transmitted;Further, by the neural network model previously established from a plurality of data line
The recommending data transmission line with good data communication feature of preset quantity is determined in road, finally, will include that this is pre-
If the Decision Making of Line Schemes of the recommending data transmission line of quantity is sent to communication equipment, communication equipment receive the Decision Making of Line Schemes it
Afterwards, a recommending data transmission line current data transmission link being switched in the recommending data transmission line of preset quantity
Road.As it can be seen that implementing data transfer path selection method described in Fig. 1, a plurality of data transfer path can be intelligently filtered out
And recommended communication equipment and selected, it effectively avoids carrying out using the shortest single data transfer path of the transmission range
Transmission is conducive to promote data transmission quality, and then improving data transmission efficiency.
Embodiment 2
Referring to Fig. 2, Fig. 2 is a kind of process signal of data transfer path selection method provided in an embodiment of the present invention
Figure.Wherein, as shown in Fig. 2, the data transfer path selection method may comprise steps of:
S201, neural network model for selecting recommending data transmission line is established.
The data transfer request message that S202, receiving communication device are sent, the data transfer request message include that communication is set
Preparation send the starting routing node of data information and receives data information purpose routing node.
S203, determine to include originating a plurality of data transmission link of routing node and purpose routing node, and pass through mind
The recommending data with good data communication feature of preset quantity is determined from a plurality of data transmission link through network model
Transmission line.
S204, the Decision Making of Line Schemes of the recommending data transmission line including preset quantity is sent to communication equipment, using logical
Current data transmission link is switched to the recommendation selected from the recommending data transmission line of preset quantity by letter equipment
Data transmission link.
The occupation proportion of the transmission bandwidth of data transmission link after S205, acquisition communication equipment switching.
Whether S206, the occupation proportion for judging transmission bandwidth are more than preset ratio threshold value, if it does, executing step S203
~step S206;If be less than, terminate this process.
In the present embodiment, which can be 30%, 60%, 80% etc., and to this, this embodiment is not limited.
In the present embodiment, above-mentioned steps S205~step S206 is executed, the data after capable of obtaining communication equipment switching pass
The line information of defeated route, and it is foundation judges whether the data transmission link after communication equipment switching is unimpeded with line information.
As an alternative embodiment, when the occupation proportion for judging just transmission bandwidth is less than preset ratio threshold value
When, after preset time period, the line information of the data transmission link after obtaining communication equipment switching, and be with line information
Foundation judges whether the data transmission link after communication equipment switching is unimpeded, if not smooth, thens follow the steps S203~step
S206。
As an alternative embodiment, the line information of the data transmission link after communication equipment switching is obtained, and
With line information be according to judge communication equipment switch after data transmission link it is whether unimpeded, can with the following steps are included:
Data transmission link after being switched by communication equipment sends test data packet, and determines and receive response test data
The consuming duration of the response data packet of packet;
Judge to expend whether duration is greater than preset duration threshold value;
If it is judged that when expending duration greater than preset duration threshold value, it is determined that the data line after communication equipment switching
Road is not smooth.
In the above-described embodiment, which can be 34ms, 46ms etc., not limit this present embodiment
It is fixed.
As an alternative embodiment, the neural network model for selecting recommending data transmission line is established, it can
With the following steps are included:
The data information of communication network locating for communication equipment is obtained, data information includes all communication nodes of communication network
The route framework of data and communication network;
Using data information as foundation, neural network model corresponding with telecommunication network is constructed;Wherein, neural network model
Topological structure corresponds to the route framework of communication network, and each neuron of topological structure corresponds to a communication node of communication network
Data.
In the present embodiment, communication node data include multiple communication nodes, the capacity of each communication node and each lead to
Believe the connection weight relational expression etc. of node and its neighbors, this embodiment is not limited.
In the present embodiment, which can be fluid threshold velocity model.Fluid threshold velocity is a kind of tool
There is the neural network model of characteristic of fluid, it is assumed that each neuron of fluid threshold velocity is the container for filling fluid, then
In fluid threshold velocity comprising n container (neuron), the behavioral characteristics of i-th of container (neuron) are shown below:
Wherein, ωijFor describing the same negotiability arrived of connection container (neuron) i and j, IiIndicate container (nerve
Member) input, siFor describing the height of liquid level in container (neuron), uiFor describing the body of i-th of container (neuron)
Product.In fluid threshold velocity, the probability that single fluid molecule flows through certain channel is related to the flow in the channel.
In the present embodiment, judgment condition is added in neural network model, to optimize as selected by single judgment condition
The problem of route sheet one out, wherein the judgment condition can be packet loss, time delay, shake, bandwidth etc., to this present embodiment
It is not construed as limiting.Further, with different judgment conditions, multiple recommendations with good data communication feature can be determined
Data transmission link.
In the present embodiment, when judgment condition is bandwidth, above-mentioned communication node data further include the band of each communication node
Wide occupation proportion then determines the mistake with the recommending data transmission line of good data communication feature by neural network model
Journey is as follows:
If s1, s2..., snFor the height of liquid level in container (neuron), u1, u2..., unFor fluid volume, relationship is such as
Shown in following formula:
si=g (ui);
Assuming that initial state is s1(0)=s2(0)=...=sn(0)=s0, u1(0)=u2(0)=...=un(0)=u0, then
Outputting and inputting to starting routing node and purpose routing node for same flow velocity is added.
Then enable neural network model iterate to side by side neuron expression formula it is constant until, at this point, each neuron
Expression formula is as follows:
Wherein, work as IiWhen=I, i is starting routing node;Work as IiWhen=- I, i is purpose routing node;Work as IiWhen=0, i
For other nodes.
That maximum flow (i.e. bandwidth occupancy ratio is minimum) is searched for by starting routing node s is routed to next node
i1, then by i1Search maximum flow is routed to i2, above operation searches for the road of approach up to searching destination node d repeatedly
Line s → i1→i2→…→ikWhat → d, as neural network model were determined from a plurality of data transmission link has good
The recommending data transmission line of data communication feature.
As it can be seen that implementing data transfer path selection method described in Fig. 2, a plurality of data transmission can be intelligently filtered out
Path is simultaneously recommended communication equipment and is selected, and effectively avoids using the shortest single data transfer path of the transmission range
It is transmitted, is conducive to promote data transmission quality, and then improving data transmission efficiency.
Embodiment 3
Referring to Fig. 3, Fig. 3 is a kind of structural representation of data transfer path selection device provided in an embodiment of the present invention
Figure.Wherein, as shown in figure 3, the data transfer path selection device includes:
Model building module 301, for establishing the neural network model for selecting recommending data transmission line.
Receiving module 302, for the data transfer request message that receiving communication device is sent, the data transfer request message
The starting routing node of data information is sent including communication equipment and receives data information purpose routing node.
Route determining module 303 includes starting routing node and purpose routing section for being determined by neural network model
The a plurality of data transmission link of point, and pushing away for preset quantity is determined from a plurality of data transmission link by neural network model
Recommend data transmission link.
Sending module 304, for will include that the Decision Making of Line Schemes of recommending data transmission line of preset quantity is sent to communication
Current data transmission link is switched to using communication equipment and is selected from the recommending data transmission line of preset quantity by equipment
A recommending data transmission line.
As an alternative embodiment, data transfer path selection device further include:
The unimpeded judgment module 305 of line, for obtain communication equipment switching after data transmission link line information, and with
Line information is foundation judges whether the data transmission link after communication equipment switching is unimpeded.
In the present embodiment, sending module 304 will include the Decision Making of Line Schemes hair of the recommending data transmission line of preset quantity
It send to communication equipment, the data transmission link after communication equipment switching can be obtained with the unimpeded judgment module 305 of firing line
Line information.
Route determining module 303 is also used to judge that the data after communication equipment switching pass in the unimpeded judgment module 305 of line
When defeated route is not unimpeded, it is determined that a plurality of data transmission link including originating routing node and purpose routing node, Yi Jitong
Cross the recommending data transmission line that neural network model determines preset quantity from a plurality of data transmission link.
As an alternative embodiment, model building module 301, comprising:
First submodule 3011, for obtaining the data information of communication network locating for communication equipment, data information includes logical
All communication node data of communication network and the route framework of communication network.
Second submodule 3012, for constructing neural network model corresponding with telecommunication network using data information as foundation;
Wherein, the topological structure of neural network model corresponds to the route framework of communication network, and each neuron of topological structure is corresponding logical
One communication node data of communication network.
As it can be seen that data transfer path selection device described in implementing Fig. 3, can intelligently filter out a plurality of data transmission
Path is simultaneously recommended communication equipment and is selected, and effectively avoids using the shortest single data transfer path of the transmission range
It is transmitted, is conducive to promote data transmission quality, and then improving data transmission efficiency.
In addition, the present invention also provides a kind of computer equipments.The computer equipment includes memory and processor, storage
Device can be used for storing computer program, and processor is by operation computer program, so that the computer equipment be made to execute above-mentioned side
The function of method or the modules in above-mentioned data transfer path selection device.
Memory may include storing program area and storage data area, wherein storing program area can storage program area, at least
Application program needed for one function (such as sound-playing function, image player function etc.) etc.;Storage data area can store root
Created data (such as audio data, phone directory etc.) etc. are used according to mobile terminal.In addition, memory may include high speed
Random access memory, can also include nonvolatile memory, a for example, at least disk memory, flush memory device or
Other volatile solid-state parts.
The present embodiment additionally provides a kind of computer storage medium, for storing calculating used in above-mentioned computer equipment
Machine program.
In several embodiments provided herein, it should be understood that disclosed device and method can also pass through
Other modes are realized.The apparatus embodiments described above are merely exemplary, for example, flow chart and structure in attached drawing
Figure shows the system frame in the cards of the device of multiple embodiments according to the present invention, method and computer program product
Structure, function and operation.In this regard, each box in flowchart or block diagram can represent a module, section or code
A part, a part of the module, section or code includes one or more for implementing the specified logical function
Executable instruction.It should also be noted that function marked in the box can also be to be different from the implementation as replacement
The sequence marked in attached drawing occurs.For example, two continuous boxes can actually be basically executed in parallel, they are sometimes
It can execute in the opposite order, this depends on the function involved.It is also noted that in structure chart and/or flow chart
The combination of each box and the box in structure chart and/or flow chart, can function or movement as defined in executing it is dedicated
Hardware based system realize, or can realize using a combination of dedicated hardware and computer instructions.
In addition, each functional module or unit in each embodiment of the present invention can integrate one independence of formation together
Part, be also possible to modules individualism, an independent part can also be integrated to form with two or more modules.
It, can be with if the function is realized and when sold or used as an independent product in the form of software function module
It is stored in a computer readable storage medium.Based on this understanding, technical solution of the present invention is substantially in other words
The part of the part that contributes to existing technology or the technical solution can be embodied in the form of software products, the meter
Calculation machine software product is stored in a storage medium, including some instructions with use a computer equipment (can be intelligence
Can mobile phone, personal computer, server or network equipment etc.) execute each embodiment the method for the present invention whole or
Part steps.And storage medium above-mentioned include: USB flash disk, mobile hard disk, read-only memory (ROM, Read-Only Memory),
Random access memory (RAM, Random Access Memory), magnetic or disk etc. be various to can store program code
Medium.
The above description is merely a specific embodiment, but scope of protection of the present invention is not limited thereto, any
Those familiar with the art in the technical scope disclosed by the present invention, can easily think of the change or the replacement, and should all contain
Lid is within protection scope of the present invention.Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. a kind of data transfer path selection method characterized by comprising
Establish the neural network model for selecting recommending data transmission line;
The data transfer request message that receiving communication device is sent, the data transfer request message include the communication equipment hair
It send the starting routing node of data information and receives the data information purpose routing node;
Determine to include a plurality of data transmission link for originating routing node and the purpose routing node, and by described
Neural network model determines the pushing away with good data communication feature of preset quantity from a plurality of data transmission link
Recommend data transmission link;
The Decision Making of Line Schemes of recommending data transmission line including the preset quantity is sent to the communication equipment, using described
Current data transmission link is switched to and selects from the recommending data transmission line of the preset quantity by communication equipment
A recommending data transmission line.
2. data transfer path selection method according to claim 1, which is characterized in that the method also includes:
The line information of data transmission link after obtaining the communication equipment switching, and be according to judgement with the line information
Whether the data transmission link after the communication equipment switching is unimpeded;
If it is judged that the data transmission link after the communication equipment switching is not smooth, it is determined that route and save including the starting
The a plurality of data transmission link of point and the purpose routing node, and by the neural network model from a plurality of data
The recommending data transmission line of preset quantity is determined in transmission line.
3. data transfer path selection method according to claim 2, which is characterized in that described to obtain the communication equipment
The line information of data transmission link after switching, and be after foundation judges the communication equipment switching with the line information
Whether data transmission link is unimpeded to include:
The occupation proportion of the transmission bandwidth of data transmission link after obtaining the communication equipment switching;
Whether the occupation proportion for judging the transmission bandwidth is more than preset ratio threshold value;
If it is determined that the occupation proportion of the transmission bandwidth is less than the preset ratio threshold value, it is determined that the communication equipment is cut
Data transmission link after changing is not smooth.
4. data transfer path selection method according to claim 2, which is characterized in that described to obtain the communication equipment
The line information of data transmission link after switching, and be after foundation judges the communication equipment switching with the line information
Whether data transmission link is unimpeded to include:
Data transmission link after being switched by the communication equipment sends test data packet, and determines to receive and respond the test
The consuming duration of the response data packet of data packet;
Judge whether the consuming duration is greater than preset duration threshold value;
If it is determined that the consuming duration is greater than the preset duration threshold value, it is determined that the data after the communication equipment switching pass
Defeated route is not smooth.
5. data transfer path selection method according to claim 1, which is characterized in that described to establish for selecting to recommend
The neural network model of data transmission link includes:
The data information of communication network locating for the communication equipment is obtained, the data information includes all of the communication network
The route framework of communication node data and the communication network;
Using the data information as foundation, the neural network model corresponding with the telecommunication network is constructed;Wherein, the mind
Topological structure through network model corresponds to the route framework of the communication network, and each neuron of the topological structure corresponds to institute
State the communication node data of communication network.
6. a kind of data transfer path selection device characterized by comprising
Model building module, for establishing the neural network model for selecting recommending data transmission line;
Receiving module, for the data transfer request message that receiving communication device is sent, the data transfer request message includes
The communication equipment sends the starting routing node of data information and receives the data information purpose routing node;
Route determining module includes the starting routing node and the purpose road for being determined by the neural network model
It is determined from a plurality of data transmission link by a plurality of data transmission link of node, and by the neural network model
The recommending data transmission line of preset quantity;
Sending module, for will include that the Decision Making of Line Schemes of recommending data transmission line of the preset quantity is sent to the communication
Current data transmission link is switched to from the recommending data of the preset quantity using the communication equipment and is passed by equipment
The recommending data transmission line selected in defeated route.
7. data transfer path selection device according to claim 6, which is characterized in that the data transfer path selection
Device further include:
The unimpeded judgment module of line, for obtaining the line information of the data transmission link after the communication equipment switches, and with institute
It states line information and is foundation judges whether the data transmission link after the communication equipment switching is unimpeded;
The route determining module, the data being also used to after the unimpeded judgment module of the line judges the communication equipment switching
When transmission line is not unimpeded, it is determined that a plurality of data line including the starting routing node and the purpose routing node
Road, and determine that the recommending data of preset quantity is transmitted from a plurality of data transmission link by the neural network model
Route.
8. data transfer path selection device according to claim 6, which is characterized in that the model building module, packet
It includes:
First submodule, for obtaining the data information of communication network locating for the communication equipment, the data information includes institute
State all communication node data of communication network and the route framework of the communication network;
Second submodule, for constructing the neural network corresponding with the telecommunication network using the data information as foundation
Model;Wherein, the topological structure of the neural network model corresponds to the route framework of the communication network, the topological structure
Each neuron corresponds to the communication node data of the communication network.
9. a kind of computer equipment, which is characterized in that including memory and processor, the memory is for storing computer
Program, the processor runs the computer program so that the computer equipment perform claim requires any one of 1 to 5 institute
The data transfer path selection method stated.
10. a kind of computer readable storage medium, which is characterized in that it is stored in computer equipment as claimed in claim 9
The used computer program.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810979689.5A CN109039885B (en) | 2018-08-27 | 2018-08-27 | Data transmission path selection method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810979689.5A CN109039885B (en) | 2018-08-27 | 2018-08-27 | Data transmission path selection method and device |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109039885A true CN109039885A (en) | 2018-12-18 |
CN109039885B CN109039885B (en) | 2022-01-07 |
Family
ID=64625020
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810979689.5A Active CN109039885B (en) | 2018-08-27 | 2018-08-27 | Data transmission path selection method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109039885B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113900978A (en) * | 2021-10-27 | 2022-01-07 | 海光信息技术股份有限公司 | Data transmission method, device and chip |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101873249A (en) * | 2009-04-27 | 2010-10-27 | 华为技术有限公司 | Method and device for computing service transmission path in optical transport network |
CN102025628A (en) * | 2010-12-07 | 2011-04-20 | 北京邮电大学 | Distribution method of network flow |
US9755948B1 (en) * | 2015-09-01 | 2017-09-05 | Netronome Systems, Inc. | Controlling an optical bypass switch in a data center based on a neural network output result |
CN107547379A (en) * | 2016-06-23 | 2018-01-05 | 华为技术有限公司 | The method and relevant device of route test action are generated in software defined network |
CN107749819A (en) * | 2017-09-14 | 2018-03-02 | 北京东土科技股份有限公司 | Route selection method and device under the conditions of a kind of grid network |
CN108307435A (en) * | 2018-01-29 | 2018-07-20 | 大连大学 | A kind of multitask route selection method based on SDSIN |
CN108540384A (en) * | 2018-04-13 | 2018-09-14 | 西安交通大学 | Intelligent heavy route method and device based on congestion aware in software defined network |
-
2018
- 2018-08-27 CN CN201810979689.5A patent/CN109039885B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101873249A (en) * | 2009-04-27 | 2010-10-27 | 华为技术有限公司 | Method and device for computing service transmission path in optical transport network |
CN102025628A (en) * | 2010-12-07 | 2011-04-20 | 北京邮电大学 | Distribution method of network flow |
US9755948B1 (en) * | 2015-09-01 | 2017-09-05 | Netronome Systems, Inc. | Controlling an optical bypass switch in a data center based on a neural network output result |
CN107547379A (en) * | 2016-06-23 | 2018-01-05 | 华为技术有限公司 | The method and relevant device of route test action are generated in software defined network |
CN107749819A (en) * | 2017-09-14 | 2018-03-02 | 北京东土科技股份有限公司 | Route selection method and device under the conditions of a kind of grid network |
CN108307435A (en) * | 2018-01-29 | 2018-07-20 | 大连大学 | A kind of multitask route selection method based on SDSIN |
CN108540384A (en) * | 2018-04-13 | 2018-09-14 | 西安交通大学 | Intelligent heavy route method and device based on congestion aware in software defined network |
Non-Patent Citations (3)
Title |
---|
程杰,张西芝: "《基于动态权重的传感网络路径选择算法仿真》", 《计算机仿真》 * |
薄华,马缚龙: "《基于流体神经网络的路径选择算法》", 《西安电子科技大学学报》 * |
马玉祥,马缚龙,雷震甲: "《流体神经网络模型用于通信网络的路径选择》", 《西安电子科技大学学报》 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113900978A (en) * | 2021-10-27 | 2022-01-07 | 海光信息技术股份有限公司 | Data transmission method, device and chip |
CN113900978B (en) * | 2021-10-27 | 2024-05-10 | 海光信息技术股份有限公司 | Data transmission method, device and chip |
Also Published As
Publication number | Publication date |
---|---|
CN109039885B (en) | 2022-01-07 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106656801B (en) | Reorientation method, device and the Business Stream repeater system of the forward-path of Business Stream | |
CN105591937B (en) | A kind of acquisition method and equipment of network topological information | |
CN110601973A (en) | Route planning method, system, server and storage medium | |
CN108965141A (en) | A kind of calculation method and device of Multi-path route tree | |
CN104904166A (en) | Intelligent routing of network packets on telecommunication devices | |
CN112752321B (en) | Method, device, equipment and storage medium for switching routes of Mesh network | |
CN103348639A (en) | Path selection method and control server | |
CN106685745B (en) | A kind of constructing network topology method and device | |
CN105791169A (en) | Switch transmission control method, switch transmitting method and related equipment in SDN (Software Defined Network) | |
US9935832B2 (en) | Automated placement of measurement endpoint nodes in a network | |
CN107948271A (en) | It is a kind of to determine to treat the method for PUSH message, server and calculate node | |
CN109617810A (en) | Data transmission method and device | |
CN105515977A (en) | Method, device and system for obtaining transmission path in network | |
CN111835564A (en) | Self-adaptive recovery method and system for power Internet of things communication link fault | |
CN117499297B (en) | Method and device for screening data packet transmission paths | |
CN107454630A (en) | Load-balancing method and load balancing router | |
CN101986605B (en) | Method and system for processing web surfing data of user based on backbone network | |
CN110661704B (en) | Calculation method of forwarding path and SDN controller | |
CN109039885A (en) | A kind of data transfer path selection method and device | |
CN107454647A (en) | The sending method and device of periodicity routing iinformation | |
CN109104376A (en) | A kind of retransmission method of data, device, stack equipment and computer-readable medium | |
Cao et al. | A mobility-supported routing mechanism in industrial IoT networks | |
CN105207905B (en) | Route selection method and device | |
CN108923964A (en) | Aggregated links setting method, device and electronic equipment | |
CN102404159A (en) | Method for discovering cognitive network topology based on event triggering |
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 | ||
TA01 | Transfer of patent application right | ||
TA01 | Transfer of patent application right |
Effective date of registration: 20210331 Address after: 510000 Room 202, 59 Jianzhong Road, Tianhe District, Guangzhou City, Guangdong Province Applicant after: Guangzhou lieyou Information Technology Co.,Ltd. Address before: 510000 Room 202, west block, 59 Jianzhong Road, software park, Tianhe District, Guangzhou City, Guangdong Province Applicant before: GUANGZHOU AIPAI NETWORK TECHNOLOGY Co.,Ltd. |
|
GR01 | Patent grant | ||
GR01 | Patent grant |