CN110445652A - Network distance prediction method, apparatus, end host and medium - Google Patents
Network distance prediction method, apparatus, end host and medium Download PDFInfo
- Publication number
- CN110445652A CN110445652A CN201910731086.8A CN201910731086A CN110445652A CN 110445652 A CN110445652 A CN 110445652A CN 201910731086 A CN201910731086 A CN 201910731086A CN 110445652 A CN110445652 A CN 110445652A
- Authority
- CN
- China
- Prior art keywords
- terrestrial reference
- node
- reference node
- network
- ordinary
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/145—Network analysis or design involving simulating, designing, planning or modelling of a network
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/147—Network analysis or design for predicting network behaviour
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/08—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/10—Active monitoring, e.g. heartbeat, ping or trace-route
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Health & Medical Sciences (AREA)
- Cardiology (AREA)
- General Health & Medical Sciences (AREA)
- Environmental & Geological Engineering (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
This application discloses a kind of network distance prediction method, apparatus, end host and media, tie up network system model, n >=2 by the n that n+1 terrestrial reference node forms this method comprises: establishing;Determine the coordinate value of terrestrial reference node;At least two ordinary nodes are added in network system model, the coordinate value of each ordinary node is determined according to the coordinate value of terrestrial reference node;According to the coordinate value of ordinary node, the network distance between any two ordinary node is determined.Cyberspace is mapped as geometric space in the technical solution, and network node is mapped as the point in geometric space, after determining each node coordinate, network distance can be gone out with quick predict, overcome the delay issue by the network distance between third-party server transfer computing terminal host, and effectively promotes the precision that network distance calculates.
Description
Technical field
The present invention relates generally to technical field of the computer network, and in particular to network distance prediction method, apparatus, terminal master
Machine and medium.
Background technique
In recent years, as the rapid growth of Internet-scale, new network technology and distributed network application continuously emerge,
The overall performance of many distributed network applications depends on the performance of bottom-layer network communication, and such as distributed file sharing is distributed
File storage, cover type multicast, for P2P video on demand etc. in the case where there is multiple candidate network resources, selection has smaller net
The node of network distance, which carries out service, becomes the key of optimization top service performance, wherein in computer network field, between node
Network distance be influence network application performance one of the major reasons.
Carrying out prediction to network distance in traditional technology is the measurement scheme by IDMaps, is the server by HOPS
Include that the virtual topology map of end host and several special hosts is constituted come what is safeguarded, when end host want to obtain with it is another
When the distance between platform end host, inquiry request is sent to obtain distance to HOPS server.
But since traditional IDMaps is to be based on CS (client/server) framework, and there are clients for CS framework
When the delay communicated between server, especially network system popularization, cause network distance prediction cost higher and
It is time-consuming excessive.
Summary of the invention
In view of drawbacks described above in the prior art or deficiency, it is intended to provide a kind of network distance prediction method, apparatus, terminal
Host and medium overcome by the delay issue of the network distance between third-party server transfer computing terminal host, and effectively
Ground promotes the precision that network distance calculates.
In a first aspect, the present invention provides a kind of network distance prediction methods, this method comprises:
It establishes and network system model, n >=2 is tieed up by the n that n+1 terrestrial reference node forms;
Determine the coordinate value of the terrestrial reference node;
At least two ordinary nodes are added in the network system model, according to the coordinate value of the terrestrial reference node, really
The coordinate value of the fixed ordinary node;
According to the coordinate value of the ordinary node, the network distance between ordinary node described in any two is determined.
Second aspect, the present invention provides a kind of network distance prediction device, which includes:
Module is established, network system model, n >=2 are tieed up by the n that n+1 terrestrial reference node forms for establishing;
First determining module, for determining the coordinate value of the terrestrial reference node;
Second determining module, at least two ordinary nodes to be added in the network system model, according to describedly
The coordinate value for marking node, determines the coordinate value of each ordinary node;
Third determining module, for the coordinate value according to the ordinary node, determine ordinary node described in any two it
Between network distance.
The third aspect, the embodiment of the present application provide a kind of end host, including memory and processor, the memory
It is stored with computer program, the processor realizes the prediction side of network distance described above when executing the computer program
Method.
Fourth aspect, the embodiment of the present application provide a kind of computer readable storage medium, are stored thereon with computer journey
Sequence, the computer program realize the prediction technique of network distance described above when being executed by processor.
Network distance prediction method, apparatus, end host and medium provided by the present application, by establishing by n+1 terrestrial reference
The n of node composition ties up network system model, and determines the coordinate value of terrestrial reference node, is then added at least in network system model
Two ordinary nodes determine the coordinate value of each ordinary node according to the coordinate value of terrestrial reference node, so that it is determined that any two are general
Network distance between logical node.Cyberspace is mapped as geometric space in the technical solution, and network node is mapped as
Point in geometric space, the geometric space modeling for realizing network without shared server, disappear compared with prior art
In addition to traditional CS framework leads to the performance bottleneck of communication delay, and after determining each node coordinate, can be gone out with quick predict
Network distance greatly enhances computational accuracy and ensure that the safety of network.
Detailed description of the invention
By reading a detailed description of non-restrictive embodiments in the light of the attached drawings below, the application's is other
Feature, objects and advantages will become more apparent upon:
Fig. 1 is the flow diagram of network distance prediction method provided in an embodiment of the present invention;
Fig. 2 is the structural schematic diagram of the network architecture provided in an embodiment of the present invention;
Fig. 3 is the flow diagram of network distance prediction method provided in an embodiment of the present invention;
Fig. 4 is the flow diagram of network distance prediction method provided in an embodiment of the present invention;
Fig. 5 is the structural schematic diagram of network distance prediction device provided in an embodiment of the present invention;
Fig. 6 is the structural schematic diagram of end host provided in an embodiment of the present invention.
Specific embodiment
The application is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched
The specific embodiment stated is used only for explaining related invention, rather than the restriction to the invention.It also should be noted that in order to
Convenient for description, part relevant to invention is illustrated only in attached drawing.
It should be noted that in the absence of conflict, the features in the embodiments and the embodiments of the present application can phase
Mutually combination.
As mentioned in the background art, with the rapid growth of Internet user and application, the network architecture becomes increasingly multiple
Miscellaneous and huge, in order to preferably excavate the great potential of the network architecture, the selection of network path is particularly important, such as in point
To on dot file sharing platform, system has very big flexibility when selecting network communication path, can be by real on demand
Shi Jinhang network measure, but it is larger to work as point-to-point distributed system, and considers in system there are when more end host node
To a large amount of wide area span there are network delay and the probability of congestion are larger, so that executing measurement on demand network distance is not sound feasible
Border, in order to further be optimized to network performance, needs to measure the distance between network terminal host, propose later
The measurement scheme of IDMaps, the program are safeguarded by the server of multiple HOPS including end host and several special hosts
Virtual topology map constitute, when end host want obtain at a distance from another end host when, need to multiple HOPS
Server sends inquiry request to obtain distance, so that be required to every time when obtaining network distance by multiple servers,
The delay communicated between a client and a server is deposited, causes network distance prediction cost more costly and time consuming excessive.
Based on drawbacks described above, this application provides a kind of network distance prediction method and apparatus, by establishing by n+1 ground
The n for marking node composition ties up network system model, and determines the coordinate value of the terrestrial reference node in network system model, then in net
Ordinary node is added in network system model, and according to the coordinate value of terrestrial reference node, determines the coordinate value of ordinary node, so that it is determined that
Network distance between any two ordinary node out is eliminated without shared server in the point-to-point distributed network
The performance bottleneck of communication delay in traditional CS framework.
In order to facilitate understanding and illustrate, network distance provided by the embodiments of the present application is described in detail below by Fig. 1 to Fig. 6
Prediction technique, device, end host and medium.
Fig. 1 is the flow diagram of network distance prediction method provided by the embodiments of the present application, as shown in Figure 1, this method
Include:
Step S101, it establishes and network system model is tieed up by the n that n+1 terrestrial reference node forms.
Distributed network is also mesh network, it is interconnected by the computer system for being distributed in different location, in net
Non-stop layer node.Communication subnet is enclosed construction, and communication control function is distributed on each node.
The point-to-point distributed network system (DNS) that above-mentioned network system model can be made of multiple end hosts, according to terminal
Network distance between host carries out space reflection, and point-to-point distributed network system (DNS) is mapped as geometric space, network system
In each node (network terminal host) be mapped as the point in geometric space, to construct the geometric space of network system
Model.Wherein, each one coordinate value of network terminal host independent maintenance in point-to-point distributed network system (DNS), which can
Being made of set of number, for describing position of the network terminal host in network system.
Network performance refers to the performance between the network path between node end to end in distributed network system (DNS).Example
Such as, network path performance is measured, the response delay between two nodes is can be, can be the relevant message transmission rate of bandwidth
Deng, can also be by predict network distance.Wherein, network distance is the essential attribute for influencing network application and service.
Each end host can be regarded as terrestrial reference node, base coordinate of the terrestrial reference node as network system model, can be with
The structural schematic diagram of the network architecture shown in Figure 2.Wherein, P1 is the n dimension network system model established, and L1, L2 and L3 are
Terrestrial reference node, H1 and H2 are the ordinary node being added, and P2 is the network system model constituted after ordinary node is added.
In geometric space modeling, node number is depending on the dimension of the geometric space model of foundation, for example, if building
The geometric space of vertical n dimension, then at least need n+1 terrestrial reference node, wherein n >=2.
Step S102, the coordinate value of terrestrial reference node is determined.
Specifically, wherein V={ 1,2 ..., m } is terrestrial reference node collection for a distributed network space G=(V, E)
It closes, E={ (i, j) | i, j ∈ V ∧ i ≠ j } is the set on side, wherein the weight d on t moment side (i, j)ij(t) this time is indicated
Network distance between point i and node j.Since there may be error, Ke Yitong for the network distance between different moments measuring node
The real network distance for measuring terrestrial reference node is crossed, and determines Euclidean distance, so that real network distance is equal to Euclidean distance,
So that it is determined that the coordinate value of the terrestrial reference node in network system model out.
Optionally, as a kind of achievable mode of step S102, it may refer to Fig. 3, this method comprises:
Step S201, determine the first real network distance between terrestrial reference node i and terrestrial reference node j and first it is European away from
From 0 < i < j≤n+1.
Step S202, it is based on the first real network distance and the first Euclidean distance, calculates terrestrial reference node i and terrestrial reference node j
Total squared error function.
It should be noted that network distance can be indicated with two-way time value (Round-Trip Time, abbreviation RTT).
Such as it can directly be measured by tools such as network diagnostic tools (Packet Internet Groper, abbreviation ping).In
Measure the first real network between terrestrial reference node i and terrestrial reference node j apart from when, can be by terrestrial reference node i to terrestrial reference node j
Ping order is sent, to measure the RTT time value (i.e. two-way time value) between two nodes.According between two nodes
Two-way time value determines the first real network distance between terrestrial reference node i and terrestrial reference node j, wherein 0 < i < j≤n+1.
Wherein, RTT is an important performance indicator in a computer network, is indicated since transmitting terminal sends data,
The time that the confirmation from receiving end is undergone in total is received to transmitting terminal.Ping language is Windows, Unix and Linux system
An order under system, is a part of TCP/IP agreement.Can be used to check whether network unobstructed and network connection speed
Order.The process for sending ping order, which may is that target ip address, sends a data packet, then other side is required to return to one together
The data packet of sample size communicates to determine whether two net machines connect, and time delay is how many.
It further, can be first according to pre- when determining the first Euclidean distance between terrestrial reference node i and terrestrial reference node j
The n dimension network system model first established, the n for setting terrestrial reference node i tie up European coordinate as CRi(Xi1,Xi2,…,Xin), terrestrial reference node
It is C that the n of j, which ties up European coordinate,Rj(Xj1,Xj2,…, Xjn), then the first Europe between available terrestrial reference node i and terrestrial reference node j
Formula distance indicates are as follows:
By taking three-dimensional space as an example, considers limitation of the terrestrial reference node number to building space, need first to determine R1,R2,R3,
R4For four terrestrial reference nodes.Then, by sending ping order between node two-by-two, to measure the between node two-by-two
One real network distanceFinally, total squared error function between egress can be calculated are as follows:
Wherein,Indicate node RiWith RjBetween square error,Respectively terrestrial reference node R1,R2,R3,...,RnCorresponding coordinate value,For terrestrial reference node i and terrestrial reference section
The first real network distance between point j,For the first Euclidean distance between terrestrial reference node i and terrestrial reference node j.
Step S203, total squared error function of terrestrial reference node i and terrestrial reference node j is solved using simplex descent algorithm,
To determine the coordinate value of terrestrial reference node i and the coordinate value of terrestrial reference node j.
It should be noted that after the total squared error function for determining terrestrial reference node i and terrestrial reference node j, using simple
It is required seat that shape decline (Simplex Downhill) algorithm, which solves one group that total square error is minimized optimal unknown numerical value,
Scale value CRiAnd CRj, similarly, the coordinate value of all terrestrial reference nodes is determined by the above method.Wherein, Simplex Downhill
Algorithm is the multidimensional function optimization algorithm that Nelder is proposed in nineteen sixty-five, constantly approaches function minimum by successive ignition.
By sending ping order between two terrestrial reference nodes in the embodiment of the present application, with measure two terrestrial reference nodes it
Between the first real network distance, determine the first Euclidean distance between two terrestrial reference nodes, then pass through simplex decline and calculate
Method further determines that out the coordinate value of terrestrial reference node.This method can be based on some metastable spies such as two-way time value RTT
Sign is quickly to determine the coordinate value of terrestrial reference node, to greatly reduce time and the computing cost of network measure.
Step S103, at least two ordinary nodes are added in network system model, according to the coordinate value of terrestrial reference node, really
The coordinate value of fixed each ordinary node.
It, can be in the network system after the coordinate value of the terrestrial reference node in the network system model for determining to pre-establish
Ordinary node is added in system model, can be arrived based on the coordinate value for the terrestrial reference node determined, and by measuring ordinary node
The second real network distance between terrestrial reference node, and determine the second Euclidean distance between it, so that it is determined that going out common section
The coordinate value of point.
Optionally, on the basis of the above embodiments, as a kind of achievable mode of step S103, it may refer to Fig. 4,
This method comprises:
Step S301, the second real network distance between ordinary node k and each terrestrial reference node and second European is determined
Distance, k > 0.
Step S302, it is based on the second real network distance and the second Euclidean distance, calculates the square error letter of ordinary node k
Number.
Assuming that ordinary node k is added in network system model, then ordinary node k uses the ping order of ICMP agreement
Ping command request is repeatedly sent to terrestrial reference node i, to get its multiple two-way time value between terrestrial reference node i, and from
The shortest two-way time value of outbound path is determined in multiple two-way time value, is then based on the shortest two-way time value, is determined
The second real network distance between ordinary node k and the terrestrial reference node i out
Further, it when determining the second Euclidean distance between ordinary node k and terrestrial reference node i, can set common
The European coordinate of node k is CHK(XK1,XK2,…,XKn), then available ordinary node k to the second Europe between terrestrial reference node i
Formula distance are as follows:
Obtain the mean error function of ordinary node k Yu terrestrial reference node i:
Wherein,For the European coordinate of ordinary node k,It is real to second between terrestrial reference node i for ordinary node k
Internet distance,For ordinary node k to the second Euclidean distance between terrestrial reference node i,Indicate the square error between terrestrial reference node i and ordinary node k.
Step S303, the squared error function that ordinary node k is solved using simplex descent algorithm, determines ordinary node k
Coordinate value.
It should be noted that after the squared error function for determining terrestrial reference node i and ordinary node k, using simplex
Descent method solves the coordinate for one group of the ordinary node k that squared error function is minimizedAnd successively determine that other are general
The coordinate of logical node.
Further, before determining the coordinate value of ordinary node, exist in order to avoid the coordinate value of ordinary node calculates
Inaccuracy, can detect whether each terrestrial reference node in network system model is evil based on preset triangle inequality rule
Meaning node, i.e., first determine terrestrial reference node to be detected, and selects one of ordinary node and a terrestrial reference node etc. three sections
Point constitutes triangle, then calculates separately the terrestrial reference node to be detected to the network between ordinary node and another terrestrial reference node
Network distance between distance and the ordinary node and a terrestrial reference node;It similarly, can be general with this by the node to be detected
Logical node and other terrestrial reference nodes carry out the verifying of triangle inequality rule, when not meeting rule of the sum of the both sides greater than third side
When then, then illustrate the terrestrial reference node to be detected be malicious node, wherein a side refer to the network between node two-by-two away from
From.
Illustratively, it is assumed that there are four terrestrial reference node Rs in three-dimensional network system model1,R2,R3,R4With an ordinary node
H1, when detecting whether terrestrial reference node is malicious node in the network system model, obtains and first determine terrestrial reference node to be detected, it can be with
Any one terrestrial reference node is chosen at random as terrestrial reference node to be detected, for example, terrestrial reference node to be detected is R1When, then it can choose
Ordinary node H1With terrestrial reference node R2Triangle is constituted, node R is calculated1With H1、R1With R2、H1With R2Network distance;If R1
With H1Network distance, R1With R2The sum of network distance be greater than H1With R2Network distance, then continue select ordinary node H1With
Terrestrial reference node R3New triangle is constituted, R is similarly calculated1With H1、R1With R3、H1With R3Network distance, if R1With H1Net
Network distance, R1With R3The sum of network distance be greater than H1With R3Network distance;Then continue to select ordinary node H1With terrestrial reference node
R4Another new triangle is constituted, R is similarly calculated1With H1、R1With R4、 H1With R4Network distance, if R1With H1Network
Distance, R1With R4The sum of network distance be greater than H1With R4Network distance, then illustrate the terrestrial reference node R to be detected1Meet triangle
Inequality rule, i.e., terrestrial reference node R to be detected1It is on the contrary then be malicious node for normal node.
When terrestrial reference node violate triangle inequality rule, i.e., if when terrestrial reference node is malicious node, excluding dislike
Anticipate after node, according to the coordinate value of terrestrial reference node, determine the coordinate value of ordinary node, so determine any two ordinary node it
Between network distance.
By being detected based on preset triangle inequality rule to malicious node in the embodiment of the present application, to exclude
To fall malicious node, and further determines the coordinate value of ordinary node, this method can carry out safety judgement to terrestrial reference node,
Malicious node camouflage terrestrial reference node is avoided, the range prediction precision of whole network system is had an impact, so that calculating eventually
It is more efficient when the distance between end main frame.
Step S104, according to the coordinate value of ordinary node, the network distance between any two ordinary node is determined.
It should be noted that after excluding malicious node and determining the coordinate value of ordinary node, it can be by European
Range formula further determines that out the network distance between any two ordinary node, while the coordinate value of terrestrial reference node is also
It is known, ordinary node can also be determined to the network distance between terrestrial reference node.
Network distance prediction method provided by the present application ties up network system by the n that n+1 terrestrial reference node forms by establishing
Model, and determine the coordinate value of terrestrial reference node, at least one ordinary node is then added in network system model, according to terrestrial reference
The coordinate value of node determines the coordinate value of ordinary node, so that it is determined that the network distance between any two ordinary node.The skill
Cyberspace is mapped as geometric space in art scheme, and network node is mapped as the point in geometric space, realizes network
Geometric space modeling, compared with prior art, without shared server, eliminating traditional CS framework causes communication to be prolonged
Slow performance bottleneck, and after determining each node coordinate, network distance can be gone out with quick predict, greatly enhance meter
It calculates precision and ensure that the safety of network.
It should be noted that although describing the operation of the method for the present invention in the accompanying drawings with particular order, this is not required that
Or hint must execute these operations in this particular order, or have to carry out operation shown in whole and be just able to achieve the phase
The result of prestige.On the contrary, the step of describing in flow chart can change and execute sequence.Additionally or alternatively, it is convenient to omit certain
Multiple steps are merged into a step and executed, and/or a step is decomposed into execution of multiple steps by step.
Fig. 5 is the structural schematic diagram of network distance prediction device provided in an embodiment of the present invention.As shown in figure 5, the device
Method as shown in Figure 1 to 4 may be implemented, the apparatus may include:
Module 10 is established, network system model, n >=2 are tieed up by the n that n+1 terrestrial reference node forms for establishing;
First determining module 20, for determining the coordinate value of the terrestrial reference node;
Second determining module 30, at least two ordinary nodes to be added in the network system model, according to described
The coordinate value of terrestrial reference node determines the coordinate value of each ordinary node;
Third determining module 40 determines ordinary node described in any two for the coordinate value according to the ordinary node
Between network distance.
Optionally, first determining module 20, comprising:
First determination unit 201, for determining in the network system model between terrestrial reference node i and terrestrial reference node j
First real network distance and the first Euclidean distance, 0 < i < j≤n+1;
First computing unit 202 calculates institute for being based on the first real network distance and first Euclidean distance
State total squared error function of terrestrial reference node i Yu terrestrial reference node j;
Third determination unit 203, for solving the terrestrial reference node i and terrestrial reference node j's using simplex descent algorithm
Total squared error function, to determine the coordinate value of terrestrial reference node i and the coordinate value of terrestrial reference node j.
Optionally, first determination unit 201, is specifically used for:
The terrestrial reference node i sends to the terrestrial reference node j and requests, to measure the terrestrial reference node i and terrestrial reference node j
Between two-way time value;
Based on the two-way time value, determine the first real network of the terrestrial reference node i and the terrestrial reference node j away from
From.
Optionally, first determination unit 201, is specifically used for:
Determine that the n of terrestrial reference node i and terrestrial reference node j tie up European coordinate;
European coordinate is tieed up according to the n of the terrestrial reference node i and terrestrial reference node j, obtains the terrestrial reference node i and the terrestrial reference
The first Euclidean distance between node j.
Optionally, second determining module 30, comprising:
4th determination unit 301, for determining the second reality between the ordinary node k and each terrestrial reference node
Network distance and the second Euclidean distance, k > 0;
Second computing unit 302 calculates institute for being based on the second real network distance and second Euclidean distance
State the squared error function of ordinary node k;
5th determination unit 303, for solving the square error letter of the ordinary node k using simplex descent algorithm
Number, determines the coordinate value of the ordinary node k.
Optionally, the 4th determination unit 302, is specifically used for:
The ordinary node k repeatedly sends ping command request to each terrestrial reference node, to obtain the common section
Multiple two-way time values between point k and the terrestrial reference node;
Determine shortest two-way time value in the multiple two-way time value;
Based on the shortest two-way time value, determine that second between the ordinary node k and the terrestrial reference node is real
Internet distance.
Optionally, described device is also used to:
Based on preset triangle inequality rule, detect in the network system model each terrestrial reference node whether be
Malicious node, the malicious node are the node for violating preset triangle inequality rule;
If the terrestrial reference node is malicious node, the malicious node is deleted, if the terrestrial reference node is not to dislike
Meaning node then enters the coordinate value according to the terrestrial reference node, determines the coordinate value of the ordinary node.
Network distance prediction device provided in this embodiment, can execute the embodiment of the above method, realization principle and
Technical effect is similar, and details are not described herein.
Fig. 6 is a kind of structural schematic diagram of end host provided in an embodiment of the present invention.As shown in fig. 6, it illustrates suitable
In the structural schematic diagram of the computer system 600 for the end host for being used to realize the embodiment of the present application.
As shown in fig. 6, computer system 600 includes central processing unit (CPU) 601, it can be read-only according to being stored in
Program in memory (ROM) 602 is loaded into the program in random access storage device (RAM) 603 from storage section 608
And execute various movements appropriate and processing.In RAM603, also it is stored with system 600 and operates required various program sum numbers
According to.CPU601, ROM602 and RAM603 are connected with each other by bus 604.Input/output (I/O) interface 606 is also connected to
Bus 604.
I/O interface 605 is connected to lower component: the importation 606 including keyboard, mouse etc.;It is penetrated including such as cathode
The output par, c 607 of spool (CRT), liquid crystal display (LCD) etc. and loudspeaker etc.;Storage section 608 including hard disk etc.;
And the communications portion 609 of the network interface card including LAN card, modem etc..Communications portion 609 via such as because
The network of spy's net executes communication process.Driver 610 is also connected to I/O interface 606 as needed.Detachable media 611, it is all
Such as disk, CD, magneto-optic disk, semiconductor memory are mounted on as needed on driver 610, in order to read from thereon
Computer program out is mounted into storage section 608 as needed.
Particularly, in accordance with an embodiment of the present disclosure, it is soft to may be implemented as computer for the process above with reference to Fig. 2-4 description
Part program.For example, embodiment of the disclosure includes a kind of computer program product comprising be tangibly embodied in machine readable Jie
Computer program in matter, the computer program include the program code for executing the method for Fig. 2-4.In such implementation
In example, which can be downloaded and installed from network by communications portion 609, and/or from detachable media 611
It is mounted.
Flow chart and block diagram in attached drawing are illustrated according to the system of various embodiments of the invention, method and computer journey
The architecture, function and operation in the cards of sequence product.In this regard, each box in flowchart or block diagram can generation
A part of one module, program segment or code of table, a part of aforementioned modules, program segment or code include one or more
Executable instruction for implementing the specified logical function.It should also be noted that in some implementations as replacements, institute in box
The function of mark can also occur in a different order than that indicated in the drawings.For example, two boxes succeedingly indicated are practical
On can be basically executed in parallel, they can also be executed in the opposite order sometimes, and this depends on the function involved.Also it wants
It is noted that the combination of each box in block diagram and or flow chart and the box in block diagram and or flow chart, Ke Yiyong
The dedicated hardware based system of defined functions or operations is executed to realize, or can be referred to specialized hardware and computer
The combination of order is realized.
Being described in the embodiment of the present application involved unit or module can be realized by way of software, can also be with
It is realized by way of hardware.Described unit or module also can be set in the processor, for example, can be described as:
A kind of processor includes establishing module, the first determining module, the second determining module and third determining module.Wherein, these units
Or the title of module does not constitute the restriction to the unit or module itself under certain conditions, for example, establishing module can be with
It is described as " tieing up network system model, n >=2 " by the n that n+1 terrestrial reference node forms for establishing.
As on the other hand, present invention also provides a kind of computer-readable medium, which be can be
Included in electronic equipment described in above-described embodiment;It is also possible to individualism, and without in the supplying electronic equipment.
Above-mentioned computer-readable medium carries one or more program, when the electronics is set by one for said one or multiple programs
When standby execution, so that the electronic equipment realizes such as above-mentioned network distance prediction method as described in the examples.
For example, the electronic equipment may be implemented as shown in Figure 1: step S101 is established by n+1 terrestrial reference node group
At n tie up network system model, n >=2;Step S102 determines the coordinate value of the terrestrial reference node;Step S103, in the net
At least two ordinary nodes are added in network system model, according to the coordinate value of the terrestrial reference node, determine each common section
The coordinate value of point;Step S104 determines the net between ordinary node described in any two according to the coordinate value of the ordinary node
Network distance.For another example, each step as shown in Fig. 2-Fig. 4 may be implemented in the electronic equipment.
It should be noted that although being referred to several modules or list for acting the equipment executed in the above detailed description
Member, but this division is not enforceable.In fact, according to embodiment of the present disclosure, it is above-described two or more
Module or the feature and function of unit can embody in a module or unit.Conversely, an above-described mould
The feature and function of block or unit can be to be embodied by multiple modules or unit with further division.
In addition, although describing each step of method in the disclosure in the accompanying drawings with particular order, this does not really want
These steps must be executed in this particular order by asking or implying, or having to carry out step shown in whole could realize
Desired result.It is additional or it is alternatively possible to omit certain steps, multiple steps are merged into a step and are executed, and/
Or a step is decomposed into execution of multiple steps etc..Through the above description of the embodiments, those skilled in the art
It can be readily appreciated that example embodiment described herein can also combine necessary hardware by software by software realization
Mode realize.
Claims (12)
1. a kind of network distance prediction method characterized by comprising
It establishes and network system model, n >=2 is tieed up by the n that n+1 terrestrial reference node forms;
Determine the coordinate value of the terrestrial reference node;
At least two ordinary nodes are added in the network system model, according to the coordinate value of the terrestrial reference node, determine every
The coordinate value of a ordinary node;
According to the coordinate value of the ordinary node, the network distance between ordinary node described in any two is determined.
2. network distance prediction method according to claim 1, which is characterized in that determine the coordinate of the terrestrial reference node
Value, comprising:
Determine the first real network distance in the network system model between terrestrial reference node i and terrestrial reference node j and the first Europe
Formula distance, 0 < i < j≤n+1;
Based on the first real network distance and first Euclidean distance, the terrestrial reference node i and terrestrial reference node j's are calculated
Total squared error function;
Total squared error function of the terrestrial reference node i Yu terrestrial reference node j is solved, using simplex descent algorithm to determine terrestrial reference
The coordinate value of node i and the coordinate value of terrestrial reference node j.
3. network distance prediction method according to claim 2, which is characterized in that determine the terrestrial reference node i and terrestrial reference
The first real network distance between node j, comprising:
The terrestrial reference node i sends ping command request to the terrestrial reference node j, to measure the terrestrial reference node i and terrestrial reference section
Two-way time value between point j;
Based on the two-way time value, the first real network distance of the terrestrial reference node i and the terrestrial reference node j is determined.
4. network distance prediction method according to claim 2, which is characterized in that determine terrestrial reference node i and terrestrial reference node j
Between the first Euclidean distance, comprising:
Determine that the n of terrestrial reference node i and terrestrial reference node j tie up European coordinate;
European coordinate is tieed up according to the n of the terrestrial reference node i and terrestrial reference node j, obtains the terrestrial reference node i and the terrestrial reference node
The first Euclidean distance between j.
5. network distance prediction method according to claim 1, which is characterized in that according to the coordinate of the terrestrial reference node
Value, determines the coordinate value of each ordinary node, comprising:
Determine the second real network distance and the second Euclidean distance between the ordinary node k and each terrestrial reference node, k
>0;
Based on the second real network distance and second Euclidean distance, the square error letter of the ordinary node k is calculated
Number;
The squared error function that the ordinary node k is solved using simplex descent algorithm determines the coordinate of the ordinary node k
Value.
6. network distance prediction method according to claim 5, which is characterized in that determine the ordinary node k with it is described
The second real network distance between each terrestrial reference node, comprising:
The ordinary node k repeatedly sends ping command request to each terrestrial reference node, with obtain the ordinary node k with
Multiple two-way time values between the terrestrial reference node;
Determine shortest two-way time value in the multiple two-way time value;
Based on the shortest two-way time value, the second practical net between the ordinary node k and the terrestrial reference node is determined
Network distance.
7. network distance prediction method according to claim 1, which is characterized in that described according to the terrestrial reference node
Coordinate value, before the coordinate value for determining each ordinary node, the method also includes:
Based on preset triangle inequality rule, detect whether each terrestrial reference node in the network system model is malice
Node, the malicious node are the node for violating preset triangle inequality rule;
If the terrestrial reference node is malicious node, the malicious node is deleted;
If the terrestrial reference node is not malicious node, enter the coordinate value according to the terrestrial reference node, determines described common
The coordinate value of node.
8. a kind of network distance prediction device, which is characterized in that described device includes:
Module is established, network system model, n >=2 are tieed up by the n that n+1 terrestrial reference node forms for establishing;
First determining module, for determining the coordinate value of the terrestrial reference node;
Second determining module, at least two ordinary nodes to be added in the network system model, according to the terrestrial reference section
The coordinate value of point, determines the coordinate value of each ordinary node;
Third determining module determines between ordinary node described in any two for the coordinate value according to the ordinary node
Network distance.
9. network distance prediction device according to claim 8, which is characterized in that first determining module, comprising:
First determination unit, for determining the first reality in the network system model between terrestrial reference node i and terrestrial reference node j
Network distance and the first Euclidean distance, 0 < i < j≤n+1;
First computing unit calculates the terrestrial reference for being based on the first real network distance and first Euclidean distance
Total squared error function of node i and terrestrial reference node j;
Third determination unit, for solving total square of mistake of the terrestrial reference node i Yu terrestrial reference node j using simplex descent algorithm
Difference function, to determine the coordinate value of terrestrial reference node i and the coordinate value of terrestrial reference node j.
10. network distance prediction device according to claim 9, which is characterized in that first determination unit is specific to use
In:
The terrestrial reference node i sends to the terrestrial reference node j and requests, to measure between the terrestrial reference node i and terrestrial reference node j
Two-way time value;
Based on the two-way time value, the first real network distance of the terrestrial reference node i and the terrestrial reference node j is determined.
11. a kind of end host including memory, processor and stores the meter that can be run on a memory and on a processor
Calculation machine program, which is characterized in that the processor realizes such as side of any of claims 1-7 when executing described program
Method.
12. a kind of computer readable storage medium, is stored thereon with computer program, the computer program is executed by processor
Shi Shixian method for example of any of claims 1-7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910731086.8A CN110445652A (en) | 2019-08-08 | 2019-08-08 | Network distance prediction method, apparatus, end host and medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910731086.8A CN110445652A (en) | 2019-08-08 | 2019-08-08 | Network distance prediction method, apparatus, end host and medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110445652A true CN110445652A (en) | 2019-11-12 |
Family
ID=68434050
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910731086.8A Pending CN110445652A (en) | 2019-08-08 | 2019-08-08 | Network distance prediction method, apparatus, end host and medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110445652A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115442179A (en) * | 2022-09-01 | 2022-12-06 | 中国船舶重工集团公司第七0三研究所无锡分部 | TTCAN communication architecture, intelligent node and gas turbine distributed control system |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101399713A (en) * | 2008-09-28 | 2009-04-01 | 腾讯科技(深圳)有限公司 | Method for measuring proximity of network node |
CN103209102A (en) * | 2013-03-11 | 2013-07-17 | 北京邮电大学 | Web quality of service distributed measurement system and method |
CN103973837A (en) * | 2014-05-27 | 2014-08-06 | 北京瑞汛世纪科技有限公司 | Method and device for determining physical location information |
CN105245627A (en) * | 2015-08-31 | 2016-01-13 | 罗向阳 | IP positioning method based on network coordinate system |
CN106162865A (en) * | 2015-01-15 | 2016-11-23 | 中兴通讯股份有限公司 | The localization method of terminal and device |
CN108605305A (en) * | 2016-09-30 | 2018-09-28 | 华为技术有限公司 | Method and apparatus for predicting network distance |
-
2019
- 2019-08-08 CN CN201910731086.8A patent/CN110445652A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101399713A (en) * | 2008-09-28 | 2009-04-01 | 腾讯科技(深圳)有限公司 | Method for measuring proximity of network node |
CN103209102A (en) * | 2013-03-11 | 2013-07-17 | 北京邮电大学 | Web quality of service distributed measurement system and method |
CN103973837A (en) * | 2014-05-27 | 2014-08-06 | 北京瑞汛世纪科技有限公司 | Method and device for determining physical location information |
CN106162865A (en) * | 2015-01-15 | 2016-11-23 | 中兴通讯股份有限公司 | The localization method of terminal and device |
CN105245627A (en) * | 2015-08-31 | 2016-01-13 | 罗向阳 | IP positioning method based on network coordinate system |
CN108605305A (en) * | 2016-09-30 | 2018-09-28 | 华为技术有限公司 | Method and apparatus for predicting network distance |
Non-Patent Citations (4)
Title |
---|
NG T S E, ZHANG H: "Predicting Internet Network Distance WithCoordinates-based Approaches", 《TWENTY-FIRST ANNUALJOINT CONFERENCE OF THE IEEE COMPUTER AND COMMUNICATIONS SOCIETIES》 * |
张一飞等: "网络距离预测方法的研究", 《电信科学》 * |
王意洁等: "网络距离预测技术研究", 《软件学报》 * |
邢长友等: "网络距离预测技术", 《软件学报》 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115442179A (en) * | 2022-09-01 | 2022-12-06 | 中国船舶重工集团公司第七0三研究所无锡分部 | TTCAN communication architecture, intelligent node and gas turbine distributed control system |
CN115442179B (en) * | 2022-09-01 | 2023-07-21 | 中国船舶重工集团公司第七0三研究所无锡分部 | TTCAN intelligent node and gas turbine distributed control system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111400001B (en) | Online computing task unloading scheduling method facing edge computing environment | |
Li et al. | Latency estimation for fog-based internet of things | |
EP1825654B1 (en) | Routing a service query in an overlay network | |
US11740815B2 (en) | Intelligent path selection and load balancing | |
JP5245711B2 (en) | Distributed data processing system, distributed data processing method, and distributed data processing program | |
JP2003030012A5 (en) | ||
JP2014504484A (en) | State synchronization between load balancer components | |
CN105657006B (en) | A kind of access acceleration method and system for the first time accelerating network based on online | |
WO2014159047A2 (en) | Using latency and route information to estimate location | |
CN112100279B (en) | Data sharing system based on block chain | |
Zhang et al. | IoV scenario: Implementation of a bandwidth aware algorithm in wireless network communication mode | |
US8682611B2 (en) | Distance metric estimating system, coordinate calculating node, distance metric estimating method, and program | |
US10469335B2 (en) | Service placement on hosts for a consumer based on their geographic location | |
WO2017101400A1 (en) | Data transmission method, apparatus and system | |
WO2021051570A1 (en) | Data storage method based on distributed cluster, and related device thereof | |
US20090136142A1 (en) | Memory optimized cache generation for image tiling in gis/cad browser applications | |
Islam et al. | Task scheduling for big data management in fog infrastructure | |
CN110445652A (en) | Network distance prediction method, apparatus, end host and medium | |
CN103209102A (en) | Web quality of service distributed measurement system and method | |
CN105677492B (en) | A kind of reliability application execution method of terminaloriented | |
Javadpour et al. | Mapping and embedding infrastructure resource management in software defined networks | |
CN114726776B (en) | CDN scheduling method, device, equipment and medium for content delivery network | |
JP6178113B2 (en) | Communications system | |
CN115357401A (en) | Task scheduling and visualization method and system based on multiple data centers | |
CN107959577A (en) | Credible route computing method between domain |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191112 |
|
RJ01 | Rejection of invention patent application after publication |