CN110784399A - Multi-path optimization combined transmission method and system for MPTCP (Multi-path Transmission control protocol) network - Google Patents
Multi-path optimization combined transmission method and system for MPTCP (Multi-path Transmission control protocol) network Download PDFInfo
- Publication number
- CN110784399A CN110784399A CN201911064677.0A CN201911064677A CN110784399A CN 110784399 A CN110784399 A CN 110784399A CN 201911064677 A CN201911064677 A CN 201911064677A CN 110784399 A CN110784399 A CN 110784399A
- Authority
- CN
- China
- Prior art keywords
- data
- sub
- network
- transmission
- mptcp
- 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
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L45/00—Routing or path finding of packets in data switching networks
- H04L45/24—Multipath
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L69/00—Network arrangements, protocols or services independent of the application payload and not provided for in the other groups of this subclass
- H04L69/14—Multichannel or multilink protocols
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Computer Security & Cryptography (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention belongs to the technical field of network data transmission, and discloses a multi-path combination selection system and a multi-path combination selection method for an MPTCP (Multi-protocol Transmission control protocol) network, which are used for classifying transmitted data streams according to the size of data to be transmitted of the current data streams; putting all sub-flow paths in a network into an initial path set, updating the round-trip delay of the paths in real time every time a sending end receives 1 ACK data packet, and sequencing the paths from small to large according to the current round-trip delay of the paths and sub-flow influence factors; and then, path selection is carried out according to the category of the data stream. The invention combines the size of the transmission data and the influence factors of the sub-flow, and selectively utilizes part of the sub-flows to carry out network transmission; the network resources are fully utilized, and better network service is provided. The invention improves the performance of the MPTCP in the transmission of the heterogeneous network; the network performance of the MPTCP in the heterogeneous network when small data are transmitted is improved; the computing resources of the computer are saved; network resources are utilized more efficiently.
Description
Technical Field
The invention belongs to the technical field of network data transmission, and particularly relates to a multi-path combination selection method and a multi-path combination selection system for an MPTCP (multi-path transmission control protocol) network.
Background
Currently, the closest prior art: MPTCP (multipass TCP (MPTCP) developed by the Internet Engineering Task Force (IETF) MultiPath TCP working group, which aims to allow a Transmission Control Protocol (TCP) connection to use multiple paths to maximize channel resource usage) is an extension of the conventional TCP protocol, which only supports single-path transmission, and the introduction of a MultiPath transmission mechanism enables simultaneous utilization and sharing of multi-homed resources without changing the TCP basic architecture. The MPTCP idea is a resource sharing manner, and can distribute data streams to multiple parallel paths for simultaneous transmission, thereby increasing the bandwidth of the network.
Currently, the performance of MPTCP is affected by many factors, among which congestion control and path scheduling are two important influencing factors. MPTCP is in a large-scale experimental research stage, and a lot of research has proved that MPTCP can utilize effective multi-ISP resources to increase throughput and improve user experience, but in a large-scale heterogeneous communication network, whether simultaneous transmission of sub-streams can improve the communication performance of MPTCP still remains a problem, for example, in a case of a network with very large heterogeneous differences, when the performance differences of the sub-streams participating in concurrent transmission are too large, sub-streams with relatively poor performance are added to participate in the co-transmission, and the overall network performance of multi-path concurrent transmission is reduced. Currently, four path management algorithms are implemented in the MPTCP kernel: the four algorithms of 'default', 'fullmesh', 'ndiffports' and 'binder' select the sub-streams, some of the sub-streams utilize all available paths, some of the sub-streams passively receive new sub-streams, some of the sub-streams can be used in a special network environment, and the contribution rate of each sub-stream to the whole network connection is not considered from the aspects of the size of transmission data, the influence factors of the sub-streams and the like. With the rapid development of the internet, the amount of data transmitted on the internet is increasing. According to the related literature, 99% of data flow in the network is less than 100MB, but 90% of data flow is provided by data flow between 100MB and 1GB, and the characteristics of large number of small flow and small amount of transmitted data are presented. Real-time analysis and online interactive applications such as web search and query services, various social networking sites, online retail services, and the like often generate a large amount of small traffic, so most of the traffic in the network is very small, while the small traffic is sensitive to completion time and the large traffic requires higher throughput, so the traffic is classified before selecting a path, and different paths are selected for transmission.
In summary, the problems of the prior art are as follows: the existing path management algorithm can not achieve an ideal effect by starting multi-path concurrent transmission, even the result of point reduction is caused, and the MPTCP communication performance is reduced.
The difficulty of solving the technical problems is as follows: what combination of sub-streams to transmit in the current network environment achieves the best network performance.
The significance of solving the technical problems is as follows: the problem that the transmission performance of the MPTCP in the heterogeneous network is poor is effectively solved, so that the purposes of effectively utilizing network resources and improving user experience are achieved.
Disclosure of Invention
Aiming at the problems in the prior art, the invention provides a multi-path combination selection method and a multi-path combination selection system for an MPTCP (Multi-path Transmission control protocol) network.
The invention is realized in this way, a MPTCP network multipath combination selection method, which comprises the following steps:
step one, classifying the transmitted data stream according to the size of data to be transmitted of the current data stream;
step two, putting all sub-flow paths in the network into the initial path set S ═ S
1，S
2,...，S
nIn the method, the round-trip delay of a path is updated in real time every time a sending end receives 1 ACK data packet, and S ' ═ S ' is sequenced from small to large according to the current round-trip delay of the path and the influence factors of sub-streams '
1，S’
2,...，S’
n}；
Step three, on the basis of a data flow set classification algorithm, path selection is carried out according to the category of the data flow, and for the data flow with smaller data volume, 1 or more paths with the minimum round-trip delay in all the current paths are always selected for data transmission; for the data stream with larger data volume, all available paths are used for concurrent data stream transmission, and each data stream establishes a plurality of sub-streams for data transmission.
Further, in the first step, the method for classifying the data stream according to the size of the data to be transmitted of the current data stream includes:
the data size of the transmission is firstly obtained, then the data streams in different data size ranges are classified, and the data streams belong to L1 when the size of the data streams meets 0< Si < α, belong to L2 when the size of the data streams meets α < Si < β, and belong to L3 when the size of the data streams does not meet the two ranges.
Further, in step two, the step of putting all sub-flow paths in the network into the initial path set S ═ S
1，S
2,...，S
nIn the method, the round-trip delay of a path is updated in real time every time a sending end receives 1 ACK data packet, and S ' ═ S ' is sequenced from small to large according to the current round-trip delay of the path and the influence factors of sub-streams '
1，S’
2,...，S’
nThe method specifically comprises the following steps:
first, the comparison relationship of the sizes of the sub-streams is defined, i.e. when
And is greater than omega
i>At 0, S
i>S
j(ii) a The substream impact factor Ω is then removed
i<Sub-stream of 0; and finally, according to the defined size relationship, the larger self-flow is sequenced in front, and finally the ordered sub-flow set is returned.
Further, in the third step, based on the data stream set classification algorithm, the path selection is performed according to the category to which the data stream belongs, and for the data stream with a smaller data volume, 1 or more paths with the smallest round-trip delay among all the current paths are always selected for data transmission; for a data stream with a large data volume, performing concurrent data stream transmission by using all available paths, wherein establishing a plurality of sub-streams for data transmission for each data stream specifically includes:
firstly, acquiring the category of a data stream needing to be transmitted currently; and then selecting proper sub-streams according to the categories for transmission, selecting the first sub-stream for transmission when the sub-streams belong to the class L1, selecting the first two sub-streams in the set for transmission when the sub-streams belong to the class L2, and selecting all the sub-streams in the set for transmission when the sub-streams belong to the class L3.
Further, an influence factor quantization formula of the MPTCP substream influence factor stream of the MPTCP network multipath combination selection method;
is set at [ l, T]During the time period, each substream of multipath transmission works normally, when all n MPTCP substreams carry out network data transmission normally, the sum of the total throughput of all MPTCP substream transmission network data of each time unit is represented by TP (T), wherein T belongs to [ l, T ∈]TP (t) is a time-dependent function with an argument of time t; when the MPTCP transmission time reaches T moment, after the sub-stream i interrupts the network connection service, the sum of the throughput of all MPTCP sub-streams in each time unit in the multi-path transmission uses TP
i(T) represents, wherein T ∈ [ T + l, 2T]When the sub-stream i is removed from the connection at the time 2T, the connection is restored.
Further, the step of calculating the importance factor of the subflow i in MPTCP transmission of the MPTCP network multipath combination selection method is as follows:
1) collecting the sum of the throughput of the network transmission data in the same time unit when all the sub-streams work normally in the time length [ l, T ], and recording as TP (T), wherein T belongs to [ l, T ];
2) blocking the connection of sub-stream i for the same length of time [ T + l, 2T]The sum of the throughputs of all the sub-stream network transmission data in the same time unit in the internal acquisition MPTCP transmission is recorded as TP
i(t),t∈[T+l，2T]；
3) Substituting the data obtained in 1) and 2) into a formula to calculate omega
iA value of (d);
classifying the data stream L;
first, the data stream is divided into L according to its data amount
1、L
2And L
3Class 3, the data flow range of each class can be expressed as follows:
L
1＝(0KB,α)
L
2＝(α,β)
α represents the upper and lower bounds of the traffic classification, which is simply KB;
a network data flow set F, which defines the data flow set F of the current network as:
F＝{F
1,F
2,...，F
i}；
wherein: f
iAnd transmitting data stream flow for the ith sub-stream.
Another object of the present invention is to provide an MPTCP network multipath combination selection system based on the MPTCP network multipath combination selection method, the MPTCP network multipath combination selection system comprising:
the data flow classification module is used for realizing the classification of the transmitted data flow, and the size of the data needing to be transmitted by the current data flow;
a sub-stream ordering module, configured to put all sub-stream paths in the network into an initial path set S ═ S
1，S
2,...，S
nIn the method, the round-trip delay of a path is updated in real time every time a sending end receives 1 ACK data packet, and S ' ═ S ' is sequenced from small to large according to the current round-trip delay of the path and the influence factors of sub-streams '
1，S’
2,...，S’
n}；
And the concurrent transmission path optimization combination selection module is used for carrying out path selection according to the category of the data stream on the basis of a data stream set classification algorithm.
Further, the concurrent transmission path optimization combination selection module includes:
the first data flow processing unit is used for selecting 1 or more paths with the minimum round-trip delay in all current paths for data transmission for the data flow with smaller data volume;
and the second data stream processing unit is used for carrying out concurrent data stream transmission on the data stream with larger data volume by using all available paths, and each data stream establishes a plurality of sub-streams for carrying out data transmission.
Another object of the present invention is to provide an information data processing terminal implementing the MPTCP network multipath selection method.
Another object of the present invention is to provide a computer-readable storage medium, which includes instructions that, when executed on a computer, cause the computer to execute the MPTCP network multipath combination selection method.
In summary, the advantages and positive effects of the invention are: the invention provides a concurrent transmission path optimization combination algorithm based on sub-path contribution factors for a communication network with larger heterogeneity difference, MPTCP sub-streams are dynamically selected for concurrent transmission of data according to the size of data to be transmitted, the influence of sub-stream addition and concurrent transmission on the total throughput is judged according to the influence factor of each sub-stream, and the tired transmission sub-streams are selectively abandoned. The invention solves the problem of poor MPTCP performance in a heterogeneous network, effectively improves the network performance and fully utilizes the network resources.
The invention combines the size of the transmission data and the influence factors of the sub-flow, and selectively utilizes part of the sub-flows to carry out network transmission; the network resources are fully utilized, and better network service is provided. The invention improves the performance of the MPTCP in the transmission of the heterogeneous network; the network performance is improved when the transmission data is small; the computing resources of the computer are saved; network resources are utilized more efficiently.
Drawings
Fig. 1 is a flowchart of a multi-path selection method for an MPTCP network according to an embodiment of the present invention.
Fig. 2 is a schematic structural diagram of an MPTCP network multipath selection system according to an embodiment of the present invention;
in the figure: 1. a data stream classification module; 2. a sub-stream ordering module; 3. and a concurrent transmission path optimization combination selection module.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail with reference to the following embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
In view of the problems in the prior art, the present invention provides a multi-path combination selection system, method and readable storage medium for MPTCP network, and the present invention is described in detail below with reference to the accompanying drawings.
As shown in fig. 1, the method for selecting a multipath combination of an MPTCP network according to an embodiment of the present invention includes the following steps:
s101: classifying the transmitted data stream according to the size of data to be transmitted of the current data stream;
s102: putting all sub-flow paths in the network into an initial set of paths S ═ S
1，S
2,...，S
nIn the method, the round-trip delay of a path is updated in real time every time a sending end receives 1 ACK data packet, and S ' ═ S ' is sequenced from small to large according to the current round-trip delay of the path and the influence factors of sub-streams '
1，S’
2,...，S’
n}；
S103: on the basis of a data stream set classification algorithm, path selection is carried out according to the category to which the data stream belongs, and for the data stream with smaller data volume, 1 or more paths with the minimum round-trip delay in all the current paths are always selected for data transmission; for the data stream with larger data volume, all available paths are used for concurrent data stream transmission, and each data stream establishes a plurality of sub-streams for data transmission.
As shown in fig. 2, the MPTCP network multipath combination selection system provided in the embodiment of the present invention includes:
and the data flow classification module 1 is used for realizing the classification of the transmitted data flow, and the size of the data to be transmitted of the current data flow.
A sub-stream ordering module 2, configured to put all sub-stream paths in the network into an initial path set S ═ S
1，S
2,...，S
nIn the method, the round-trip delay of a path is updated in real time every time a sending end receives 1 ACK data packet, and S ' ═ S ' is sequenced from small to large according to the current round-trip delay of the path and the influence factors of sub-streams '
1，S’
2,...，S’
n}。
The concurrent transmission path optimization combination selection module 3 is used for performing path selection according to the category to which the data stream belongs on the basis of a data stream set classification algorithm, and for the data stream with smaller data volume, always selecting 1 or more paths with the minimum round-trip delay in all the current paths for data transmission; for the data stream with larger data volume, all available paths are used for concurrent data stream transmission, and each data stream establishes a plurality of sub-streams for data transmission.
The technical solution of the present invention is further described with reference to the following specific examples.
The MPTCP network multipath combination selection method provided by the embodiment of the invention comprises the following steps: the method comprises the following steps of 'data flow set classification algorithm', 'substream sorting algorithm' and 'concurrent transmission path optimization combination selection algorithm'.
(1) The data flow set classification algorithm firstly obtains the size of data transmitted this time, then classifies the data flows in different data size ranges, and belongs to L1 when the size of the data flow satisfies 0< Si < α, and belongs to L2 when satisfying α < Si < β, and belongs to L3 when not within the two ranges.
(2) A sub-stream ordering algorithm, which puts all sub-stream paths in the network into an initial path set S ═ S
1，S
2,...，S
nIn the method, the round-trip delay of a path is updated in real time every time a sending end receives 1 ACK data packet, and S ' ═ S ' is sequenced from small to large according to the current round-trip delay of the path and the influence factors of sub-streams '
1，S’
2,...，S’
nThe method specifically comprises the following steps:
first, the comparison relationship of the sizes of the sub-streams is defined, i.e. when
And is greater than omega
i>At 0, S
i>S
j(ii) a The substream impact factor Ω is then removed
i<Sub-stream of 0; and finally, according to the defined size relationship, the larger self-flow is sequenced in front, and finally the ordered sub-flow set is returned.
(3) The optimization combination selection algorithm of the concurrent transmission path is based on the data stream set classification algorithm, and then the path selection is carried out according to the category of the data stream, and for the data stream with smaller data volume, 1 or more paths with the minimum round-trip delay in all the current paths are always selected for data transmission, so that the average completion time when the smaller data is transmitted can be shortened theoretically. For the data flow with larger data volume, all available paths are used for concurrent data flow transmission, and each data flow establishes a plurality of sub-flows for data transmission, thereby improving the throughput rate of the long flow. The general flow is as follows:
firstly, acquiring the category of a data stream needing to be transmitted currently; and then selecting proper sub-streams according to the categories for transmission, selecting the first sub-stream for transmission when the sub-streams belong to the class L1, selecting the first two sub-streams in the set for transmission when the sub-streams belong to the class L2, and selecting all the sub-streams in the set for transmission when the sub-streams belong to the class L3.
TABLE 1 Alphabet meanings explanation
| Character(s) | Means of | Examples of such applications are |
| F | Data flow in a network | F 1Representing a certain data stream |
| L | Classification of network transport traffic | L 1Data streams representing the first class (classified according to flow size) |
| S | Initial path set | Alternative initial set of substream paths |
| S’ | Sorted set of paths | Subset of substream paths ordered according to their characteristics |
| U | Currently selected set of paths | Set of currently selected sub-flow paths for a certain data flow |
| α | Upper bound, unit KB of classification in the Algorithm | E.g. 400KB |
| β | Lower bound of the classification in the Algorithm, Unit KB | E.g. 1024KB |
In the preferred embodiment of the present invention, the impact factor quantization formula of the MPTCP subflow impact factor subflow is as follows;
is set at [ l, T]During the time period, each substream of multipath transmission works normally, when all n MPTCP substreams carry out network data transmission normally, the sum of the total throughput of all MPTCP substream transmission network data of each time unit is represented by TP (T), wherein T belongs to [ l, T ∈]TP (t) is a time-dependent function with an argument of time t; when the MPTCP transmission time reaches T moment, after the sub-stream i interrupts the network connection service, the sum of the throughput of all MPTCP sub-streams in each time unit in the multi-path transmission uses TP
i(T) represents, wherein T ∈ [ T + l, 2T]When the sub-stream i is removed from the connection at the time 2T, the connection is restored.
The following steps are taken to calculate the importance factor of substream i in MPTCP transmission:
1) collecting the sum of the throughput of the network transmission data in the same time unit when all the sub-streams work normally in the time length [ l, T ], and recording as TP (T), wherein T belongs to [ l, T ];
2) blocking the connection of sub-stream i for the same length of time [ T + l, 2T]The sum of the throughputs of all the sub-stream network transmission data in the same time unit in the internal acquisition MPTCP transmission is recorded as TP
i(t),t∈[T+l，2T]；
3) The omega can be obtained by substituting the data obtained in 1) and 2) into a formula to calculate
iThe value of (c).
And dynamically selecting the required sub-streams to be added into the network for concurrent transmission according to the sub-stream influence factors and the round-trip delay of the sub-streams of the MPTCP by using the data volume of the current network transmission, namely, determining the path used by the data stream and establishing the number of the required sub-streams according to the data volume required to be sent by the MPTCP data stream.
In a preferred embodiment of the invention, the data stream L is classified;
first, the data stream is divided into L according to its data amount
1、L
2And L
3Class 3, the data flow range of each class can be expressed as follows:
L
1＝(0KB,α)
L
2＝(α,β)
L
3and (β, + ∞), wherein α is the upper and lower bounds of the transport traffic classification, just KB.
In the preferred embodiment of the present invention, the network data flow set F defines the data flow set F of the current network as:
F＝{F
1,F
2,...，F
i}；
wherein: f
iAnd transmitting data stream flow for the ith sub-stream.
In the preferred embodiment of the present invention, the relationship between the network heterogeneity difference and the sub-stream ordering, i.e. two heterogeneity meansOne or more communication systems employ different access technologies (e.g., wireline, 5G, 4G, 3G, WIFI, etc.), or the same access technology but belong to different operators. The network heterogeneity in the invention is caused by large difference of network performance or quality of the wired access provider in the multi-host system, and specifically, a network with large difference of indexes such as Round Trip Time (RTT) round trip delay, bandwidth and the like of the network can be used. As is well known, the larger the delay, the more congested the current path, the less suitable such path should be selected for the current transmission, and such sub-streams should be placed in the back in the ordering (the more difficult the path is to be selected for transmission). Whereas the MPTCP subflow impact factor omega
iWhen Ω is
i>0 shows that adding the current sub-stream into transmission is beneficial to improving network performance when the omega
i<0 shows that the network transmission performance is affected by adding the current sub-stream into the transmission, and omega also needs to be added during the sequencing
i<The path of 0 is removed. The algorithm of the invention mainly aims to improve the performance of the MPTCP in small flow transmission, the required bandwidth is very small when the data volume is small, and all available paths (omega) are always utilized as much as possible when the data volume to be transmitted is large enough
i>0) The total throughput is improved, so the bandwidth is not considered in the sorting, and the time delay and the sub-stream influence factor are used as main sub-stream performance indexes.
It should be noted that the embodiments of the present invention can be realized by hardware, software, or a combination of software and hardware. The hardware portion may be implemented using dedicated logic; the software portions may be stored in a memory for execution by a suitable instruction execution system, such as a microprocessor or specially designed hardware. Those skilled in the art will appreciate that the apparatus and methods described above may be implemented using computer executable instructions and/or embodied in processor control code, such code being provided on a carrier medium such as a disk, CD-or DVD-ROM, programmable memory such as read only memory (firmware), or a data carrier such as an optical or electronic signal carrier, for example. The apparatus and its modules of the present invention may be implemented by hardware circuits such as very large scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, or programmable hardware devices such as field programmable gate arrays, programmable logic devices, etc., or by software executed by various types of processors, or by a combination of hardware circuits and software, e.g., firmware.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents and improvements made within the spirit and principle of the present invention are intended to be included within the scope of the present invention.
Claims (10)
1. A MPTCP network multipath combination selection method is characterized by comprising the following steps:
step one, classifying the transmitted data stream according to the size of data to be transmitted of the current data stream;
step two, putting all sub-flow paths in the network into the initial path set S ═ S
1，S
2,...，S
nIn the method, the round-trip delay of a path is updated in real time every time a sending end receives 1 ACK data packet, and S ' ═ S ' is sequenced from small to large according to the current round-trip delay of the path and the influence factors of sub-streams '
1，S’
2,...，S’
n}；
Step three, on the basis of a data stream set classification algorithm, path selection is carried out according to the category to which the data stream belongs, and for the data stream with smaller data volume, 1 or more paths with the minimum round-trip delay in all the current paths are always selected for data transmission; for the data stream with larger data volume, all available paths are used for concurrent data stream transmission, and each data stream establishes a plurality of sub-streams for data transmission.
2. The MPTCP network multipath combination selection method of claim 1, wherein in step one, the method for classifying the data stream according to the size of the data to be transmitted by the current data stream comprises:
the data size of the transmission is firstly obtained, then the data streams in different data size ranges are classified, and the data streams belong to L1 when the size of the data streams meets 0< Si < α, belong to L2 when the size of the data streams meets α < Si < β, and belong to L3 when the size of the data streams does not meet the two ranges.
3. The MPTCP network multipath combination selection method of claim 1, wherein in step two, all the sub-flow paths in the network are put into an initial path set S ═ { S ═ in the network
1，S
2,...，S
nIn the method, the sending end updates the round trip delay of the path in real time every time it receives 1 ACK packet, and performs sorting according to the current round trip delay and the sub-stream impact factor of the path from small to large, where S ' ═ S ' 1, S ' 2.
First, the comparison relationship of the sizes of the sub-streams is defined, i.e. when
And is greater than omega i>At 0, Si>Sj; the substream impact factor Ω i is then removed<Sub-stream of 0; and finally, according to the defined size relationship, the larger self-flow is sequenced in front, and finally the ordered sub-flow set is returned.
4. The MPTCP network multipath combination selection method according to claim 1, wherein in step three, based on the data stream set classification algorithm, the path selection is performed according to the category to which the data stream belongs, and for the data stream with smaller data volume, 1 or more paths with the smallest round-trip delay among all the current paths are always selected for data transmission; for a data stream with a large data volume, performing concurrent data stream transmission by using all available paths, wherein establishing a plurality of sub-streams for data transmission for each data stream specifically includes:
firstly, acquiring the category of a data stream needing to be transmitted currently; and then selecting proper sub-streams according to the categories for transmission, selecting the first sub-stream for transmission when the sub-streams belong to the class L1, selecting the first two sub-streams in the set for transmission when the sub-streams belong to the class L2, and selecting all the sub-streams in the set for transmission when the sub-streams belong to the class L3.
5. The MPTCP network multipath combination selection method of claim 1, wherein an influence factor quantization formula of the MPTCP subflow influence factor stream of the MPTCP network multipath selection method;
is set at [ l, T]During the time period, each substream of multipath transmission works normally, when all n MPTCP substreams carry out network data transmission normally, the sum of the total throughput of all MPTCP substream transmission network data of each time unit is represented by TP (T), wherein T belongs to [ l, T ∈]TP (t) is a time-dependent function with an argument of time t; when the MPTCP transmission time reaches T moment, after the sub-stream i interrupts the network connection service, the sum of the throughput of all MPTCP sub-streams in each time unit in the multi-path transmission uses TP
i(T) represents, wherein T ∈ [ T + l, 2T]When the sub-stream i is removed from the connection at the time 2T, the connection is restored.
6. The MPTCP network multipath combination selection method according to claim 5, wherein the step of calculating the importance factor of subflow i in MPTCP transmission of the MPTCP network multipath selection method comprises:
1) collecting the sum of the throughput of the network transmission data in the same time unit when all the sub-streams work normally in the time length [ l, T ], and recording as TP (T), wherein T belongs to [ l, T ];
2) blocking the connection of sub-stream i for the same length of time [ T + l, 2T]The sum of the throughputs of all the sub-stream network transmission data in the same time unit in the internal acquisition MPTCP transmission is recorded as TP
i(t),t∈[T+l，2T]；
3) Substituting the data obtained in 1) and 2) into a formula to calculate omega
iA value of (d);
classifying the data stream L;
first, the data stream is divided into L according to its data amount
1、L
2And L
3Class 3, the data flow range of each class can be expressed as follows:
L
1＝(0KB,α)
L
2＝(α,β)
α represents the upper and lower boundaries of the transport traffic classification, which is simply KB;
a network data flow set F, which defines the data flow set F of the current network as:
F＝{F
1,F
2,...，F
i}；
wherein, F
iAnd transmitting data stream flow for the ith sub-stream.
7. An MPTCP network multipath combination selection system based on the MPTCP network multipath combination selection method of claim 1, the MPTCP network multipath combination selection system comprising:
the data flow classification module is used for realizing the classification of the transmitted data flow, and the size of the data needing to be transmitted by the current data flow;
a sub-stream ordering module, configured to put all sub-stream paths in the network into an initial path set S ═ S
1，S
2,...，S
nIn the method, the round-trip delay of a path is updated in real time every time a sending end receives 1 ACK data packet, and S ' ═ S ' is sequenced from small to large according to the current round-trip delay of the path and the influence factors of sub-streams '
1，S’
2,...，S’
n}；
And the concurrent transmission path optimization combination selection module is used for carrying out path selection according to the category of the data stream on the basis of a data stream set classification algorithm.
8. The MPTCP network multipath combination selection system of claim 7, wherein the concurrent transmission path optimization combination selection module comprises:
the first data flow processing unit is used for selecting 1 or more paths with the minimum round-trip delay in all current paths for data transmission for the data flow with smaller data volume;
and the second data stream processing unit is used for carrying out concurrent data stream transmission on the data stream with larger data volume by using all available paths, and each data stream establishes a plurality of sub-streams for carrying out data transmission.
9. An information data processing terminal implementing the MPTCP network multipath combination selection method of any one of claims 1 to 6.
10. A computer-readable storage medium comprising instructions which, when executed on a computer, cause the computer to perform the MPTCP network multipath combination selection method of any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911064677.0A CN110784399A (en) | 2019-11-04 | 2019-11-04 | Multi-path optimization combined transmission method and system for MPTCP (Multi-path Transmission control protocol) network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911064677.0A CN110784399A (en) | 2019-11-04 | 2019-11-04 | Multi-path optimization combined transmission method and system for MPTCP (Multi-path Transmission control protocol) network |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110784399A true CN110784399A (en) | 2020-02-11 |
Family
ID=69388734
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911064677.0A Pending CN110784399A (en) | 2019-11-04 | 2019-11-04 | Multi-path optimization combined transmission method and system for MPTCP (Multi-path Transmission control protocol) network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110784399A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112054966A (en) * | 2020-09-01 | 2020-12-08 | 首都师范大学 | Method, device and equipment for scheduling multi-path transmission data |
| CN112422421A (en) * | 2020-11-23 | 2021-02-26 | 北京交通大学 | Multi-path data packet transmission method of heterogeneous network |
| CN112671660A (en) * | 2020-12-24 | 2021-04-16 | 海南大学 | Multi-performance parameter parallel optimization method and device for heterogeneous multi-path transmission network system |
| CN113364559A (en) * | 2021-06-30 | 2021-09-07 | 清华大学 | Multipath-oriented data secure transmission method, device and system |
| CN114024896A (en) * | 2021-11-02 | 2022-02-08 | 海南大学 | Self-adaptive dynamic path management method and device based on MPTCP |
| CN115379469A (en) * | 2022-08-12 | 2022-11-22 | 江苏省电力试验研究院有限公司 | Multi-access heterogeneous network MPTCP substream scheduling method based on machine learning |
| CN115665060A (en) * | 2022-12-26 | 2023-01-31 | 中国华能集团清洁能源技术研究院有限公司 | Multi-path transmission scheduling method and device for heterogeneous network |
| WO2023109794A1 (en) * | 2021-12-16 | 2023-06-22 | Huawei Technologies Co., Ltd. | Methods and systems for adaptive stochastic-based load balancing |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101656674A (en) * | 2009-09-23 | 2010-02-24 | 中国人民解放军信息工程大学 | Congestion control method and network nodes |
| CN105791054A (en) * | 2016-04-22 | 2016-07-20 | 西安交通大学 | Autonomous controllable and reliable multicast transmission method based on flow classification realization |
| KR101694271B1 (en) * | 2015-07-07 | 2017-01-23 | 공주대학교 산학협력단 | Multipath Cubic for Congestion control |
| CN109005124A (en) * | 2018-06-25 | 2018-12-14 | 成都鼎桥通信技术有限公司 | A kind of MPTCP load share method and device |
-
2019
- 2019-11-04 CN CN201911064677.0A patent/CN110784399A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101656674A (en) * | 2009-09-23 | 2010-02-24 | 中国人民解放军信息工程大学 | Congestion control method and network nodes |
| KR101694271B1 (en) * | 2015-07-07 | 2017-01-23 | 공주대학교 산학협력단 | Multipath Cubic for Congestion control |
| CN105791054A (en) * | 2016-04-22 | 2016-07-20 | 西安交通大学 | Autonomous controllable and reliable multicast transmission method based on flow classification realization |
| CN109005124A (en) * | 2018-06-25 | 2018-12-14 | 成都鼎桥通信技术有限公司 | A kind of MPTCP load share method and device |
Non-Patent Citations (2)
| Title |
|---|
| 叶宁等: "基于数据流特性的MPTCP数据流调度算法研究", 《中南大学学报（自然科学版）》 * |
| 谭齐宁等: "MPTCP协议的鲁棒性评估模型研究及分析", 《海南大学学报自然科学版》 * |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112054966A (en) * | 2020-09-01 | 2020-12-08 | 首都师范大学 | Method, device and equipment for scheduling multi-path transmission data |
| CN112054966B (en) * | 2020-09-01 | 2023-11-07 | 首都师范大学 | Method, device and equipment for scheduling multiplex transmission data |
| CN112422421A (en) * | 2020-11-23 | 2021-02-26 | 北京交通大学 | Multi-path data packet transmission method of heterogeneous network |
| CN112422421B (en) * | 2020-11-23 | 2022-02-22 | 北京交通大学 | Multi-path data packet transmission method of heterogeneous network |
| CN112671660B (en) * | 2020-12-24 | 2022-03-22 | 海南大学 | Multi-performance parameter parallel optimization method and device for heterogeneous multi-path transmission network system |
| CN112671660A (en) * | 2020-12-24 | 2021-04-16 | 海南大学 | Multi-performance parameter parallel optimization method and device for heterogeneous multi-path transmission network system |
| CN113364559A (en) * | 2021-06-30 | 2021-09-07 | 清华大学 | Multipath-oriented data secure transmission method, device and system |
| CN113364559B (en) * | 2021-06-30 | 2022-08-12 | 清华大学 | Multipath-oriented data secure transmission method, device and system |
| CN114024896A (en) * | 2021-11-02 | 2022-02-08 | 海南大学 | Self-adaptive dynamic path management method and device based on MPTCP |
| WO2023109794A1 (en) * | 2021-12-16 | 2023-06-22 | Huawei Technologies Co., Ltd. | Methods and systems for adaptive stochastic-based load balancing |
| CN115379469A (en) * | 2022-08-12 | 2022-11-22 | 江苏省电力试验研究院有限公司 | Multi-access heterogeneous network MPTCP substream scheduling method based on machine learning |
| CN115379469B (en) * | 2022-08-12 | 2023-11-28 | 江苏省电力试验研究院有限公司 | Multi-access heterogeneous network MPTCP substream scheduling method based on machine learning |
| CN115665060A (en) * | 2022-12-26 | 2023-01-31 | 中国华能集团清洁能源技术研究院有限公司 | Multi-path transmission scheduling method and device for heterogeneous network |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110784399A (en) | Multi-path optimization combined transmission method and system for MPTCP (Multi-path Transmission control protocol) network | |
| US11411865B2 (en) | Network resource scheduling method, apparatus, electronic device and storage medium | |
| CN107454017B (en) | Mixed data stream cooperative scheduling method in cloud data center network | |
| US20150003249A1 (en) | Cognitive Data Delivery Optimizing System | |
| CN104023408B (en) | Scheduler and its data dispatching method based on network multipath footpath parallel transmission | |
| US11582146B2 (en) | High-quality adaptive bitrate video through multiple links | |
| CN102195875A (en) | Combined hardware/software forwarding mechanism and method | |
| CN102780637A (en) | Routing method for data transmission in space delay/disruption tolerant network | |
| CN109614215A (en) | Stream scheduling method, device, equipment and medium based on deeply study | |
| Wang et al. | High-speed data-plane packet aggregation and disaggregation by P4 switches | |
| CN111935031B (en) | NDN architecture-based traffic optimization method and system | |
| CN107154897B (en) | Isomery stream partition method based on packet scattering in DCN | |
| CN114071582A (en) | Service chain deployment method and device for cloud-edge collaborative Internet of things | |
| JPWO2011089899A1 (en) | Semiconductor system, repeater and chip circuit | |
| CN106412043B (en) | CDN network flow bootstrap technique and device | |
| Tang et al. | A MPTCP scheduler combined with congestion control for short flow delivery in signal transmission | |
| Xu et al. | DarkTE: towards dark traffic engineering in data center networks with ensemble learning | |
| Habeeb et al. | Dynamic bandwidth slicing for time-critical IoT data streams in the edge-cloud continuum | |
| Guo et al. | IEEE SA Industry Connections-IEEE 802 Nendica Report: Intelligent Lossless Data Center Networks | |
| Liebeherr et al. | Rate allocation and buffer management for differentiated services | |
| Tatbul et al. | Dealing with overload in distributed stream processing systems | |
| Xiao et al. | A sub-action aided deep reinforcement learning framework for latency-sensitive network slicing | |
| US11489904B2 (en) | Poor-QoE assessment method and related device | |
| Divakaran | A spike-detecting AQM to deal with elephants | |
| WO2018019018A1 (en) | Distribution policy generating method and device, and network optimization system |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200211 |