CN110808859A - Regression model calculation method and system for MPTCP multi-path transmission buffer consumption - Google Patents
Regression model calculation method and system for MPTCP multi-path transmission buffer consumption Download PDFInfo
- Publication number
- CN110808859A CN110808859A CN201911060937.7A CN201911060937A CN110808859A CN 110808859 A CN110808859 A CN 110808859A CN 201911060937 A CN201911060937 A CN 201911060937A CN 110808859 A CN110808859 A CN 110808859A
- Authority
- CN
- China
- Prior art keywords
- mptcp
- value
- consumption
- model
- nornet
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
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
- H04L41/142—Network analysis or design using statistical or mathematical methods
-
- 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
- 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
- H04L43/0876—Network utilisation, e.g. volume of load or congestion level
- H04L43/0888—Throughput
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L47/00—Traffic control in data switching networks
- H04L47/10—Flow control; Congestion control
- H04L47/15—Flow control; Congestion control in relation to multipoint traffic
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L47/00—Traffic control in data switching networks
- H04L47/10—Flow control; Congestion control
- H04L47/19—Flow control; Congestion control at layers above the network layer
- H04L47/193—Flow control; Congestion control at layers above the network layer at the transport layer, e.g. TCP related
Landscapes
- Engineering & Computer Science (AREA)
- Signal Processing (AREA)
- Computer Networks & Wireless Communication (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Mathematical Physics (AREA)
- Probability & Statistics with Applications (AREA)
- Pure & Applied Mathematics (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Algebra (AREA)
- Environmental & Geological Engineering (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The application relates to a regression model calculation method and a regression model calculation system for MPTCP multi-path transmission buffer consumption. The method comprises the following steps: acquiring MPTCP information; extracting a network throughput value from the MPTCP information; inputting the network throughput value into a pre-established cache consumption model, and calculating to obtain an MPTCP cache consumption value; the buffer consumption model is obtained by analyzing and modeling NorNet Core experimental data based on a mathematical statistics regression analysis method, and is used for recording the relation between MPTCP buffer consumption and network throughput. The regression model calculation method for the MPTCP multi-path transmission buffer consumption adopts real data to establish the model, so that the result obtained by calculating the buffer consumption value according to the established model is very accurate.
Description
Technical Field
The application relates to the technical field of multipath network transmission, in particular to a regression model calculation method and system for MPTCP multipath transmission buffer consumption.
Background
With the development of multiple access technologies, smart mobile terminals have become more popular in recent years, and they all have multiple network interfaces (e.g. WLAN and 3G/4G, etc.), and even a personal computer is equipped with multiple network cards to access different network providers through multiple interfaces at the same time. The multi-homing characteristic of multiple network interfaces enables the equipment to have better mobility, quick recovery capability and good safety load sharing function.
The load sharing function is one of the important features that can aggregate the bandwidth of different links, enabling devices to achieve greater network throughput. The load sharing function may be implemented at multiple layers in a network protocol stack, where the transport layer is a very important network protocol stack. There are many methods for performing a load function on a transport layer, such as R-MTP, MPTCP, MCT-SCTP, and the like, where MPTCP is one of the most important protocols among multipath transport protocols for implementing load sharing end to end, and has been widely applied to load sharing in recent years. MPTCP is an extension of the conventional TCP protocol, i.e. a protocol that enables simultaneous transmission of information data over multiple paths at the transport layer. MPTCP uses TCP as a sub-stream transmission, and multiple paths means that there are multiple TCP sub-streams. It is very important to configure the cache reasonably in network transmission, where the transmission cache energy consumption is an important parameter for measuring whether the cache is reasonable, i.e. in practice, the cache is usually configured reasonably according to the transmission cache energy consumption. Therefore, it is important to determine the transmission buffer power consumption of MPTCP.
At present, the most common method for calculating the energy consumption of the MPTCP transmission buffer is to divide the MPTCP into a plurality of TCP subflows, then calculate the energy consumption of the transmission buffer of each TCP subflow, and finally simply superimpose the energy consumption of the transmission buffer of each TCP subflow to obtain the energy consumption of the MPTCP transmission buffer. However, the data transmission mode of the host under the MPTCP protocol is different from that of TCP, so that it is not easy to treat each sub-stream as a single TCP link and add the buffer values thereof, and a lot of test studies show that under multi-path transmission, the MPTCP transmission buffer consumption value obtained by simply overlapping multiple TCP transmission consumption values, and then configuring according to the obtained MPTCP transmission buffer consumption value, causes a lot of waste of buffer resources.
Disclosure of Invention
In view of the above, it is necessary to provide a regression model calculation method, system, computer device and storage medium for MPTCP multipath transmission buffer consumption, which can solve the above technical problems.
A regression model calculation method for MPTCP multi-path transmission buffer consumption comprises the following steps:
acquiring MPTCP information;
extracting a network throughput value from the MPTCP information;
inputting the network throughput value into a pre-established cache consumption model, and calculating to obtain an MPTCP cache consumption value; the buffer consumption model is obtained by analyzing and modeling NorNet Core experimental data based on a mathematical statistics regression analysis method, and is used for recording the relation between MPTCP buffer consumption and network throughput.
In one embodiment, the method for establishing the cache consumption model includes:
acquiring the NorNet Core experimental data from a NorNet Core international test bed; the NorNetCore experimental data comprise MPTCP buffer consumption experimental values and network throughput experimental values;
establishing a polynomial regression model, and performing learning training on the polynomial regression model by using the MPTCP cache energy consumption experimental value and the network throughput experimental value to obtain a trained regression model;
and performing performance evaluation on the trained regression model, and obtaining the cache consumption model after the evaluation is passed.
In one embodiment, the step of performing performance evaluation on the trained regression model includes:
calculating a determination coefficient and an assumed probability of the trained regression model;
and when the determined coefficient is larger than a preset coefficient value and the assumed probability is smaller than a preset probability value, judging that the trained model is evaluated to be passed.
In one embodiment, the step of obtaining the NorNet Core experimental data from the NorNet Core international test bed comprises:
selecting a NorNet Core international test bed system, wherein the NorNet Core international test bed system comprises a plurality of site hosts; all the site hosts are connected through network communication to form an MPTCP multi-path transmission system;
configuring network initial parameters for the NorNet Core international test bed system;
after the configuration of network parameters is finished, randomly selecting a transmission route from the MPTCP multi-path transmission system as an initial route, setting a cache consumption value on the initial route for data transmission, and measuring and recording a throughput value;
selecting transmission paths from the rest MPTCP multi-path transmission systems in sequence by adopting a path control algorithm, setting a buffer consumption value on the transmission paths, and measuring and recording corresponding throughput values;
and obtaining the NorNet Core experimental data according to each buffer consumption value and the throughput value corresponding to each buffer consumption value.
In one embodiment, the step of setting a buffer consumption value on the initial path for data transmission and calculating a throughput value by using a congestion control algorithm includes:
selecting different time points, setting a buffer consumption value on the initial path to carry out data transmission for multiple times, and measuring and recording a corresponding initial throughput value in each data transmission;
and carrying out average operation on each initial throughput value to obtain the throughput value.
In one embodiment, the step of establishing the polynomial regression model includes:
a polynomial regression model was built using the python toolkit.
In one embodiment, the congestion control algorithm comprises any one or more of a Cubic algorithm, a Hybla algorithm, an oli algorithm, a Reno algorithm, a Scalable algorithm, and a Vegas algorithm.
A regression model calculation system for MPTCP multipath transmission buffer consumption, the system comprising:
the information acquisition module is used for acquiring MPTCP information;
a network throughput value extraction module, configured to extract a network throughput value from the MPTCP information;
the cache consumption value calculation module is used for inputting the network throughput value into a pre-established cache consumption model and calculating to obtain an MPTCP cache consumption value; the buffer consumption model is obtained by analyzing and modeling NorNet Core experimental data based on a mathematical statistics regression analysis method, and is used for recording the relation between MPTCP buffer consumption and network throughput.
A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the following steps when executing the computer program:
acquiring MPTCP information;
extracting a network throughput value from the MPTCP information;
inputting the network throughput value into a pre-established cache consumption model, and calculating to obtain an MPTCP cache consumption value; the buffer consumption model is obtained by analyzing and modeling NorNet Core experimental data based on a mathematical statistics regression analysis method, and is used for recording the relation between MPTCP buffer consumption and network throughput.
A computer-readable storage medium, on which a computer program is stored which, when executed by a processor, carries out the steps of:
acquiring MPTCP information;
extracting a network throughput value from the MPTCP information;
inputting the network throughput value into a pre-established cache consumption model, and calculating to obtain an MPTCP cache consumption value; the buffer consumption model is obtained by analyzing and modeling NorNet Core experimental data based on a mathematical statistics regression analysis method, and is used for recording the relation between MPTCP buffer consumption and network throughput.
According to the MPTCP multi-path transmission buffer consumption regression model calculation method, the MPTCP multi-path transmission buffer consumption regression model calculation system, the MPTCP multi-path transmission buffer consumption regression model and the storage medium, MPTCP information is firstly acquired, wherein the MPTCP information comprises a network throughput value, then the network throughput value is input into a pre-established buffer consumption model to obtain the MPTCP buffer consumption value, and the buffer consumption model is obtained by analyzing and modeling NorNet Core experimental data (namely actual MPTCP buffer consumption and network throughput) according to a mathematical statistics regression analysis method. The regression model calculation method for the MPTCP multi-path transmission buffer consumption adopts real data to establish the model, so that the result obtained by calculating the buffer consumption value according to the established model is very accurate.
Drawings
FIG. 1 is a schematic diagram of an application environment of a regression model calculation method for MPTCP multi-path transmission buffer consumption according to an embodiment;
FIG. 2 is a flowchart illustrating a method for calculating a regression model of MPTCP multi-path transmission buffer consumption in one embodiment;
fig. 3 is a schematic flowchart of a method for establishing a cache consumption model in a regression model calculation method of MPTCP multipath transmission cache consumption in an embodiment;
FIG. 4 is a schematic flow chart illustrating the acquisition of NorNet Core experimental data in one embodiment;
FIG. 5 is a schematic view of the structure of a NorNet international test bed in another embodiment;
FIG. 6 is a graph illustrating the relationship between buffer consumption and throughput for an embodiment using the NorNet international test bed system;
FIG. 7 is a graph illustrating a relationship between fitting curves of experimental data of NorNet Core under different congestion control algorithms according to an embodiment;
FIG. 8 is a block diagram of a regression model calculation system for MPTCP multi-path transmission buffer consumption in an embodiment;
FIG. 9 is a diagram illustrating an internal structure of a computer device according to an embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
The method is applied to the terminal 102 in fig. 1, the terminal may be a personal computer, a notebook computer, or the like, the terminal 102 is in communication connection with the data acquisition device 104, and the data acquisition device 104 is generally an MPTCP information acquisition instrument, or the like.
In an embodiment, as shown in fig. 2, a regression model calculation method for MPTCP multipath transmission buffer consumption is provided, which is described by taking the method as an example applied to the terminal in fig. 1, and includes the following steps:
step S202, MPTCP information is obtained;
step S204, extracting a network throughput value from the MPTCP information;
MPTCP, among others, multi-connection TCP connection. MPTCP allows multiple sub-channels to be established in one TCP link. After a channel is established in a three-way handshake manner, other sub-channels may be established in a three-way handshake manner, and the channels are connected in a three-way handshake manner and disconnected in a four-way handshake manner. These channels are bound to MPTCP session, and data from the sending end can select one of the channels for transmission. MPTCP may select any one of a plurality of sub-channels to transmit data. MPTCP, if it uses the traditional TCP approach to send data, will have one part in one subchannel and another part in another subchannel. In this way, the intermediate device such as the firewall receives the packet with the sequence number jump of the TCP, and thus an abnormal situation such as packet loss occurs. To solve this problem, MPTCP manages packet transmission by adding a DSN (data sequence number) that counts the total segment sequence number, while the sequence numbers in each subchannel are always continuous. The packet receiving process of MPTCP is divided into two phases: firstly, each subchannel recombines the segments of the messages according to the sequence number of the subchannel; and secondly, recombining the message segments of all the sub-channels by the control module of the MPTCP according to the DSN.
Network throughput, the data in the network is composed of individual packets, and the firewall consumes resources to process each packet. Throughput refers to the maximum rate that a device can accept without frame loss. The test method comprises the following steps: sending a certain number of frames at a certain rate in the test, calculating the frames transmitted by the equipment to be tested, and if the number of the sent frames is equal to that of the received frames, increasing the sending rate and retesting; if the received frame is less than the transmitted frame, the transmission rate is reduced and the test is repeated until the final result is obtained. Throughput test results are expressed in bits/second or bytes/second.
The buffer consumption refers to the transmission amount of data of the buffer in unit time, and is related to the network throughput. In addition, the cache consumption affects the cache rate of the data in the buffer area, namely when the cache consumption is large and the cache speed is low, the data transmission speed can be greatly reduced; however, when the cache consumption is small and the cache speed is high, a large amount of data exists in the buffer, thereby causing the waste of the resources of the buffer. Therefore, it is important to accurately calculate the cache consumption.
In this embodiment, the MPTCP information refers to information related to MPTCP, and includes the number of site hosts, the number of paths in MPTCP, the network throughput in each path, the protocol type between networks, the IP version, and the like.
Step S206, inputting the network throughput value into a pre-established cache consumption model, and calculating to obtain an MPTCP cache consumption value; the buffer consumption model is obtained by analyzing and modeling NorNetCore experimental data based on a mathematical statistics regression analysis method, and is used for recording the relation between the MPTCP buffer consumption and the network throughput.
Specifically, the mathematical statistics regression analysis method refers to determining the interdependent regression relationship between two or more variables. Regression analysis methods can be divided into univariate regression analysis and multivariate regression analysis according to the number of related independent variables; according to the number of dependent variables, simple regression analysis and multiple regression analysis can be divided; according to the relationship between independent variables and dependent variables, linear regression analysis and nonlinear regression analysis can be classified. In this embodiment, the relationship between the network throughput and the MPTCP buffer consumption is to be found, i.e. it is recorded as a pre-established buffer consumption model.
According to the MPTCP multi-path transmission buffer consumption regression model calculation method, the MPTCP multi-path transmission buffer consumption regression model calculation system, the MPTCP multi-path transmission buffer consumption regression model and the storage medium, MPTCP information is firstly acquired, wherein the MPTCP information comprises a network throughput value, then the network throughput value is input into a pre-established buffer consumption model to obtain the MPTCP buffer consumption value, and the buffer consumption model is obtained by analyzing and modeling NorNet Core experimental data (namely actual MPTCP buffer consumption and network throughput) according to a mathematical statistics regression analysis method. The regression model calculation method for the MPTCP multi-path transmission buffer consumption adopts real data to establish the model, so that the result obtained by calculating the buffer consumption value according to the established model is very accurate.
In one embodiment, as shown in fig. 3, the method for establishing the cache consumption model includes:
step S302, acquiring NorNet Core experimental data from a NorNet Core international test bed; the NorNetCore experimental data comprise MPTCP buffer consumption experimental values and network throughput experimental values;
step S304, establishing a polynomial regression model, and performing learning training on the polynomial regression model by using an MPTCP (Multi-point Transmission control protocol) cache consumption experimental value and a network throughput experimental value to obtain a trained regression model;
and S306, performing performance evaluation on the trained regression model, and obtaining a cache consumption model after the evaluation is passed.
Specifically, the NorNet Core experimental data is obtained from the NorNet Core international test bed; specifically, under the NorNet Core architecture, different suitable working conditions are selected, different network throughput values are set or assumed on an MPTCP path, so that a cache consumption test is performed, a plurality of cache consumption values are obtained, and then the network throughput values and the cache consumption values obtained through measurement are recorded as NorNet Core experimental data. And establishing a polynomial regression model, wherein the essence of the polynomial regression model is to determine the relation between the network throughput and the cache consumption. And (4) learning and training the multiple regression models by using the MPTCP cache energy consumption experimental value and the network throughput experimental value to obtain the trained regression models. After the trained regression model is obtained, the performance of the model needs to be evaluated, i.e., the model is subjected to quality evaluation to determine whether the model is effectively usable. After the evaluation is passed, the regression model after training has good quality and performance and is effectively usable; and finally, obtaining a cache consumption model according to the trained regression model.
In an alternative embodiment, the step of performing the performance evaluation on the trained regression model includes: calculating a determination coefficient and an assumed probability of the trained regression model; and when the coefficient is determined to be larger than the preset coefficient value and the assumed probability is smaller than the preset probability value, judging that the trained model is evaluated to be passed.
Where the coefficient of certainty (i.e., R-Square) is the value of the degree of correlation between the variables, the change in data characterizes how well a fit is. From the above expression, it can be known that the normal value range of the "determination coefficient" is [ 01 ], and the closer to 1, the stronger the explanatory ability of the variable of the equation to y is, and the better the model fits the data. Hypothesis probability (also called hypothesis value, P-value) is an important element in the inference statistics of hypothesis testing, and is important evidence for determining whether the original hypothesis is correct. Statistics the P values obtained from the significance test method are generally significant with P <0.05 and very significant with P <0.01, meaning that the probability of sample-to-sample differences due to sampling errors is less than 0.05 or 0.01. The smaller P, the higher the probability of the result being accurate, and vice versa, the lower the probability of being accurate. In this embodiment, the determination coefficients and the assumed probabilities of the trained regression model are mainly calculated to determine the performance of the regression model.
In addition, the preset coefficient value is usually a value greater than 0 and less than 1, and in the actual process, a user can select the value according to the requirement of the user, but the selected value is not too small, otherwise, the selection of the regression model with good performance is not facilitated. The predetermined probability value is typically a real number less than 0.1, such as 0.05, 0.001, etc.
In one embodiment, as shown in FIG. 4, the step of obtaining the NorNet Core experimental data from the NorNet Core international test bed comprises:
step S402, selecting a NorNet Core international test bed system, wherein the NorNet Core international test bed system comprises a plurality of station hosts; all the site hosts are connected through network communication to form an MPTCP multi-path transmission system;
specifically, to obtain the NorNet Core experimental data, a test is first performed, which is performed on the NorNet Core international test bed system. The NorNet Core international test bed system comprises a plurality of site hosts, each site host can be distributed all over the world, each site host can simultaneously provide IPv4 and IPv6 address resources, and an operating system kernel integrates an MPTCP multi-path transmission kernel.
Step S404, configuring network initial parameters for the NorNet Core international test bed system;
wherein the initial parameters include: the network provider ISP parameters of the sending end host and the receiving end host, 2) the IP version (IPv4, IPv6) and the like.
Step S406, after the network parameter configuration is completed, randomly selecting a transmission route from the MPTCP multi-path transmission system as an initial route, setting a cache consumption value on the initial route for data transmission, and measuring and recording a throughput value;
step S408, selecting transmission paths from the rest MPTCP multi-path transmission systems in sequence by adopting a path control algorithm, setting a buffer consumption value on the transmission paths, and measuring and recording corresponding throughput values;
step S410, NorNet Core experimental data is obtained according to each buffer consumption value and the throughput value corresponding to each buffer consumption value.
Specifically, a congestion control algorithm and a path management algorithm are selected, and then different cache consumption values are set for data transmission, so that corresponding throughput values are obtained. All buffer consumption values and their corresponding throughput values are recorded as NorNet Core experimental data.
In one embodiment, the step of setting a buffer consumption value on an initial path for data transmission, and measuring and recording a throughput value includes:
selecting different time points, setting a buffer consumption value on an initial path to carry out data transmission for multiple times, and measuring and recording a corresponding initial throughput value in each data transmission; and carrying out average operation on each initial throughput value to obtain the throughput value.
Specifically, to avoid the influence of short network fluctuation during transmission, each different buffer consumption is set to perform data transmission for a period of time (for example, 30 seconds), and then an average throughput in the period of time is obtained.
In one embodiment, the step of establishing the polynomial regression model includes:
a polynomial regression model was built using the python toolkit.
Specifically, the python toolkit integrates a series of data processing methods and models, and can be used for data mining, model building and the like. The analysis of data using the python toolkit is simple and convenient.
In one embodiment, the congestion control algorithm comprises any one or more of a Cubic algorithm, a Hybla algorithm, an oli algorithm, a Reno algorithm, a Scalable algorithm, and a Vegas algorithm.
To facilitate understanding of the technical solution of the present invention, a detailed embodiment is given. Various regression analysis methods are employed herein in an attempt to find the best relationship between X (independent variables) and y, namely: where y represents throughput and X represents a number of factors that may affect throughput, including buffer consumption, congestion control algorithms, etc. Referred to as a regression model or a prediction model. Their relationships are quantified, compared, noise factors are eliminated, and given X vs y are subjected to regression prediction modeling analysis with minimal error. The method adopts a famous machine learning package SciKit-Learn in Python to carry out polynomial regression analysis modeling on the multipath transmission. Specifically, a linear model module in SciKit-Learn is utilized, the module adopts a linear regression algorithm, specifically a linear regression class is used for modeling, a large number of tests are carried out on a NorNet Core international test bed through scene design, a polynomial function relation is output by loading test data into the linear regression class, and a regression coefficient c can be output by calling the coef _ method of the classiAnd i is 0,1, …, n, the value of R-Squared can be obtained according to the definition of R-Squared and the value of P-values can be output by calling the f _ regression method of the class. In the modeling process: 1. selecting regression model quality evaluation indexes, wherein the cache consumption regression model algorithm is not enough, and the regression quality of the model is requiredAnd (3) carrying out evaluation, wherein evaluation indexes comprise: two R-Square and P-values. The larger the R-Square value of the former is, the better the value is, the closer the value is to 1, the better the regression model matching degree is; the smaller the value of the latter P-values, the better, the closer its value to 0, the smaller the probability that the regressed model is erroneous. The definition of R-Squarer is as follows:
where SST is the variance on the actual data y; SSR is the variance on the predicted values. R-square represents the ratio of the total variance of the predicted value to the total variance of the actual value, and the value range is in the interval [0, 1]]In the meantime. If R-Square is 0.9, this would mean that the regression model has a prediction accuracy of 90%. When R-Square is 1, it means that the actual values are perfectly matched by the regression model. Obviously, the larger the value of R-Square, the better the model matching. P-values are probability values that are statistically used to express significance test methods. When P is present<0.05 is significant, P<0.01 is very significant, meaning that the probability that the difference between samples is caused by a sampling error is less than 0.05 or 0.01. In the present embodiment, R-Square ═ 0.9 and P-values are selected<0.05 is an acceptable range. 2. Selecting potential influence factors of the throughput, constructing according to a multi-path cache model, and further confirming the following potential factors which can influence the network throughput, namely selection of ISP parameters, IP versions (IPv4 and IPv6), congestion control algorithms and initial paths of network providers of a sending end and a receiving end respectively. 3. Modeling regression prediction: (1) the buffer consumption model is designed for researching a scene, and data transmission is carried out between sites of the NorNet Core international test bed, wherein the architecture of the test bed is shown in FIG. 5; each Site shown in FIG. 5 is the NorNet International test bed worldwideIn each site distributed in each region, a host of each site can simultaneously provide IPv4 and IPv6 address resources, and an operating system kernel integrates multiple multi-path transmission of MPTCP; and selecting a congestion control algorithm and a path management algorithm, and setting different cache consumption values for data processing. And transmitting to obtain a corresponding throughput value. In order to avoid the influence of transient network fluctuation in the transmission process, setting each different cache consumption for 30 seconds of data transmission, and then solving the average throughput in the time period; wherein the buffer consumption is related to the throughput as shown in FIG. 6; (2) in order to avoid the influence of network fluctuation to the maximum extent, each experimental scene carries out ten data transmission experiments at different time, then the experimental results are averaged to obtain the throughput under each cache value, and then the experimental result data are used as NorNet Core experimental data; after the average value of the ten times of test data is obtained, the data can visually represent the relationship between each average value and a fitting curve under each congestion control algorithm on a coordinate axis, as shown in fig. 7; (3) and importing the NorNet Core experimental data into a python toolkit, establishing a polynomial regression model, training the model by using the experimental data, and outputting the model formula after the same items are obtained, thereby obtaining a cache consumption model. 4. And (3) testing the performance of the cache consumption model: the cache consumption model obtained by regression from certain experimental data is as follows: t125.49 + (3.12+0.38 × E)1+0.55*E2+0.54*E3+0.53*E4+0.21*E5+0.2*E6)*B-0.02*B2+(39.52*E1+30.22*E2+51.70*E3+28.6*E4+47.09*E5-61.8*E6) Wherein: t throughput (Mbit/s), B cache consumption (Mbit), EkWhere k ∈ {1, …,6}, respectively, represents the use of various congestion algorithms: taking the model as an example, if the congestion control algorithm selects E, during actual transmission, the congestion control algorithm selects E1(Cubic), i.e. E1＝1，E2＝E3＝E4＝E5＝E6If 0, the model is: t isE1＝165.01+3.5*B-0.02*B2According to the above formula, if 200Mbit/s is to be obtainedThroughput, the cache consumption only needs to be set to 10.65 Mbit; RTT measured at two sites of UiO-UiT in this scenariomax＝0.044089s，RTOmaxThe parameters are substituted into the existing MPTCP buffer consumption calculation formula for 1s
Calculating to obtain that the cache consumption of the scene is at least 145.6Mbit, and the cache consumption calculated by adopting the conventional MPTCP cache consumption calculation formula is far greater than the actual demand; if the congestion control algorithm is selected as E2(Hybla), i.e. E2＝1，E1＝E3＝E4＝E5＝E6When the model is 0: t isE2＝155.71+3.67*B-0.02*B2According to the formula, if the throughput of 200Mbit/s is to be obtained, the buffer consumption only needs to be set to 12.99Mbit, and the influence of a congestion control algorithm is not considered by adopting the conventional MPTCP buffer consumption calculation formula, so that the calculated buffer consumption is still 145.6 Mbit; it can be seen that, no matter which congestion control algorithm is selected, the result obtained according to the existing MPTCP cache consumption formula is much larger than the MPTCP cache consumption value calculated by the cache consumption model established in the embodiment. Further, in order to prove the correctness of the consumption model formula obtained by the method, the index formula is evaluated by using the previous regression model and the model is evaluated and calculated, the result is that R-Square is 0.92 and is close to 1, and P-values are far less than 0.01, so according to the mathematical statistics theory, the matching degree of the model is good, the probability caused by sampling errors is less than 0.05, and the cache consumption model is effective. In summary, the cache consumption model constructed in the embodiment is correct and effective.
It should be understood that although the various steps in the flow charts of fig. 2-4 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not performed in the exact order shown and described, and may be performed in other orders, unless explicitly stated otherwise. Moreover, at least some of the steps in fig. 2-4 may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at each time, and the order of performance of the sub-steps or stages is not necessarily sequential, but may be performed in turn or alternating with other steps or at least some of the sub-steps or stages of other steps.
In one embodiment, as shown in fig. 8, a regression model calculation system for MPTCP multi-path transmission buffer consumption is provided, including: an information obtaining module 802, configured to obtain MPTCP information;
a network throughput value extraction module 804, configured to extract a network throughput value from the MPTCP information;
a cache consumption value calculation module 806, configured to input the network throughput value into a pre-established cache consumption model, and calculate to obtain an MPTCP cache consumption value; the buffer consumption model is obtained by analyzing and modeling NorNet Core experimental data based on a mathematical statistics regression analysis method, and is used for recording the relation between MPTCP buffer consumption and network throughput.
In one embodiment, the method comprises the following steps:
the experimental data acquisition module is used for acquiring NorNet Core experimental data from a NorNet Core international test bed; the NorNet Core experimental data comprise MPTCP buffer consumption experimental values and network throughput experimental values;
the regression model establishing and training module is used for establishing a polynomial regression model, and learning and training the polynomial regression model by adopting an MPTCP (Multi-protocol Transmission control protocol) cache energy consumption experimental value and a network throughput experimental value to obtain a trained regression model;
and the cache consumption model establishing module is used for evaluating the performance of the trained regression model and obtaining a cache consumption model after the evaluation is passed.
In one embodiment, the method comprises the following steps:
the calculation module is used for calculating the determination coefficient and the assumed probability of the trained regression model;
and the model evaluation module is used for judging that the trained model evaluation is passed when the coefficient is determined to be larger than the preset coefficient value and the assumed probability is smaller than the preset probability value.
In one embodiment, the experimental data acquisition module comprises: the system comprises a system selection module, an initial parameter configuration module, a first throughput value calculation module and a second throughput value calculation module;
the system selection module is used for selecting a NorNet Core international test bed system, wherein the NorNet Core international test bed system comprises a plurality of station hosts; all the site hosts are connected through network communication to form an MPTCP multi-path transmission system;
the initial parameter configuration module is used for configuring network initial parameters for the NorNet Core international test bed system;
the first throughput value calculation module is used for randomly selecting a transmission route from the MPTCP multi-path transmission system as an initial route after the network parameter configuration is finished, setting a cache consumption value on the initial route for data transmission, and measuring and recording the throughput value;
the second throughput value calculation module is used for selecting transmission paths from the rest MPTCP multi-path transmission systems in sequence by adopting a path control algorithm, setting a buffer consumption value on the transmission paths, and measuring and recording the corresponding throughput value;
and the experimental data acquisition module is also used for obtaining NorNet Core experimental data according to each cache consumption value and the throughput value corresponding to each cache consumption value.
In one embodiment, the first throughput value calculation module comprises: initial throughput value calculation module
The initial throughput value calculation module is used for selecting different time points, setting a buffer consumption value on an initial path to carry out data transmission for multiple times, and measuring and recording a corresponding initial throughput value in each data transmission;
the first throughput value calculation module is further configured to perform average operation on each initial throughput value to obtain a throughput value.
In one embodiment, the regression model building training module is further configured to build a polynomial regression model using a python toolkit.
In one embodiment, the congestion control algorithm comprises any one or more of a Cubic algorithm, a Hybla algorithm, an oli algorithm, a Reno algorithm, a Scalable algorithm, and a Vegas algorithm.
For specific limitations of the regression model calculation system for MPTCP multipath transmission buffer consumption, reference may be made to the above limitations of the regression model calculation method for MPTCP multipath transmission buffer consumption, which are not described herein again. All or part of each module in the regression model calculation system for the MPTCP multi-path transmission buffer consumption can be realized by software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as shown in fig. 9. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the computer equipment is used for storing data of the resistance equivalent model and the equivalent submodel, and storing equivalent resistance, working resistance and contact resistance obtained in the process of executing calculation. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to realize a regression model calculation method of MPTCP multi-path transmission buffer consumption.
Those skilled in the art will appreciate that the architecture shown in fig. 9 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have an arrangement of components for each.
In one embodiment, a computer device is provided, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the following steps when executing the computer program: acquiring MPTCP information; extracting a network throughput value from the MPTCP information; inputting the network throughput value into a pre-established cache consumption model, and calculating to obtain an MPTCP cache consumption value; the buffer consumption model is obtained by analyzing and modeling NorNet Core experimental data based on a mathematical statistics regression analysis method, and is used for recording the relation between MPTCP buffer consumption and network throughput.
In one embodiment, the processor, when executing the computer program, further performs the steps of: the method for establishing the cache consumption model comprises the following steps: acquiring NorNet Core experimental data from a NorNet Core international test bed; the NorNet Core experimental data comprise MPTCP buffer consumption experimental values and network throughput experimental values; establishing a polynomial regression model, and performing learning training on the polynomial regression model by using an MPTCP (Multi-point Transmission control protocol) cache energy consumption experimental value and a network throughput experimental value to obtain a trained regression model; and performing performance evaluation on the trained regression model, and obtaining a cache consumption model after the evaluation is passed.
In one embodiment, the processor when executing the computer program further performs the steps of: the step of performing performance evaluation on the trained regression model comprises the following steps: calculating a determination coefficient and an assumed probability of the trained regression model; and when the coefficient is determined to be larger than the preset coefficient value and the assumed probability is smaller than the preset probability value, judging that the trained model is evaluated to be passed.
In one embodiment, the processor, when executing the computer program, further performs the steps of: the step of obtaining NorNet Core experimental data from a NorNet Core international test bed comprises: selecting a NorNet Core international test bed system, wherein the NorNet Core international test bed system comprises a plurality of site hosts; all the site hosts are connected through network communication to form an MPTCP multi-path transmission system; configuring network initial parameters for the NorNet Core international test bed system; after the network parameter configuration is finished, a transmission route is randomly selected from the MPTCP multi-path transmission system to be an initial route, a cache consumption value is set on the initial route for data transmission, and a throughput value is measured and recorded; selecting transmission paths from the rest MPTCP multi-path transmission systems in sequence by adopting a path control algorithm, setting a buffer consumption value on the transmission paths, and measuring and recording corresponding throughput values; and obtaining NorNet Core experimental data according to each buffer consumption value and the throughput value corresponding to each buffer consumption value.
In one embodiment, the processor, when executing the computer program, further performs the steps of: the steps of setting a buffer consumption value on an initial path for data transmission, measuring and recording a throughput value comprise: selecting different time points, setting a buffer consumption value on an initial path to carry out data transmission for multiple times, and measuring and recording a corresponding initial throughput value in each data transmission; and carrying out average operation on each initial throughput value to obtain the throughput value.
In one embodiment, the processor, when executing the computer program, further performs the steps of: the step of establishing the polynomial regression model comprises the following steps: a polynomial regression model was built using the python toolkit.
In one embodiment, the processor, when executing the computer program, further performs the steps of: the congestion control algorithm comprises any one or more of a Cubic algorithm, a Hybla algorithm, an oli algorithm, a Reno algorithm, a Scalable algorithm, and a Vegas algorithm.
In one embodiment, a computer-readable storage medium is provided, having a computer program stored thereon, which when executed by a processor, performs the steps of: acquiring MPTCP information; extracting a network throughput value from the MPTCP information; inputting the network throughput value into a pre-established cache consumption model, and calculating to obtain an MPTCP cache consumption value; the buffer consumption model is obtained by analyzing and modeling NorNet Core experimental data based on a mathematical statistics regression analysis method, and is used for recording the relation between MPTCP buffer consumption and network throughput.
In one embodiment, the computer program when executed by the processor implements the steps of: the method for establishing the cache consumption model comprises the following steps: acquiring NorNet Core experimental data from a NorNet Core international test bed; the NorNet Core experimental data comprise MPTCP buffer consumption experimental values and network throughput experimental values; establishing a polynomial regression model, and performing learning training on the polynomial regression model by using an MPTCP (Multi-point Transmission control protocol) cache energy consumption experimental value and a network throughput experimental value to obtain a trained regression model; and performing performance evaluation on the trained regression model, and obtaining a cache consumption model after the evaluation is passed.
In one embodiment, the computer program when executed by the processor implements the steps of: the step of performing performance evaluation on the trained regression model comprises the following steps: calculating a determination coefficient and an assumed probability of the trained regression model; and when the coefficient is determined to be larger than the preset coefficient value and the assumed probability is smaller than the preset probability value, judging that the trained model is evaluated to be passed.
In one embodiment, the computer program when executed by the processor implements the steps of: the step of obtaining NorNet Core experimental data from a NorNet Core international test bed comprises: selecting a NorNet Core international test bed system, wherein the NorNet Core international test bed system comprises a plurality of site hosts; all the site hosts are connected through network communication to form an MPTCP multi-path transmission system; configuring network initial parameters for the NorNet Core international test bed system; after the network parameter configuration is finished, a transmission route is randomly selected from the MPTCP multi-path transmission system to be an initial route, a cache consumption value is set on the initial route for data transmission, and a throughput value is measured and recorded; selecting transmission paths from the rest MPTCP multi-path transmission systems in sequence by adopting a path control algorithm, setting a buffer consumption value on the transmission paths, and measuring and recording corresponding throughput values; and obtaining NorNet Core experimental data according to each buffer consumption value and the throughput value corresponding to each buffer consumption value.
In one embodiment, the computer program when executed by the processor implements the steps of: the steps of setting a buffer consumption value on an initial path for data transmission, measuring and recording a throughput value comprise: selecting different time points, setting a buffer consumption value on an initial path to carry out data transmission for multiple times, and measuring and recording a corresponding initial throughput value in each data transmission; and carrying out average operation on each initial throughput value to obtain the throughput value.
In one embodiment, the computer program when executed by the processor implements the steps of: the step of establishing the polynomial regression model comprises the following steps: a polynomial regression model was built using the python toolkit.
In one embodiment, the computer program when executed by the processor implements the steps of: the congestion control algorithm comprises any one or more of a Cubic algorithm, a Hybla algorithm, an oli algorithm, a Reno algorithm, a Scalable algorithm, and a Vegas algorithm.
It will be understood by those of ordinary skill in the art that all or part of the processes of the methods of the embodiments may be implemented by hardware related to instructions of a computer program, which may be stored in a non-volatile computer-readable storage medium, and when executed, may comprise processes such as those of the embodiments of the methods. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the embodiments are not described, however, as long as there is no contradiction between the combinations of the technical features, the scope of the present description should be considered as being described in the present specification.
The above examples only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. A regression model calculation method for MPTCP multi-path transmission buffer consumption is characterized by comprising the following steps:
acquiring MPTCP information;
extracting a network throughput value from the MPTCP information;
inputting the network throughput value into a pre-established cache consumption model, and calculating to obtain an MPTCP cache consumption value; the buffer consumption model is obtained by analyzing and modeling NorNet Core experimental data based on a mathematical statistics regression analysis method, and is used for recording the relation between MPTCP buffer consumption and network throughput.
2. The method according to claim 1, wherein the method for establishing the cache consumption model comprises:
acquiring the NorNet Core experimental data from a NorNet Core international test bed; the NorNet Core experimental data comprise MPTCP buffer consumption experimental values and network throughput experimental values;
establishing a polynomial regression model, and performing learning training on the polynomial regression model by using the MPTCP cache energy consumption experimental value and the network throughput experimental value to obtain a trained regression model;
and performing performance evaluation on the trained regression model, and obtaining the cache consumption model after the evaluation is passed.
3. The method of claim 2, wherein the step of performing the performance evaluation on the trained regression model comprises:
calculating a determination coefficient and an assumed probability of the trained regression model;
and when the determined coefficient is larger than a preset coefficient value and the assumed probability is smaller than a preset probability value, judging that the trained model is evaluated to be passed.
4. The method of claim 2, wherein the step of obtaining the NorNet Core experimental data from a NorNet Core international test bed comprises:
selecting a NorNet Core international test bed system, wherein the NorNet Core international test bed system comprises a plurality of site hosts; all the site hosts are connected through network communication to form an MPTCP multi-path transmission system;
configuring network initial parameters for the NorNet Core international test bed system;
after the configuration of network parameters is finished, randomly selecting a transmission route from the MPTCP multi-path transmission system as an initial route, setting a cache consumption value on the initial route for data transmission, and measuring and recording a throughput value;
selecting transmission paths from the rest MPTCP multi-path transmission systems in sequence by adopting a path control algorithm, setting a buffer consumption value on the transmission paths, and measuring and recording corresponding throughput values;
and obtaining the NorNet Core experimental data according to each buffer consumption value and the throughput value corresponding to each buffer consumption value.
5. The method of claim 4, wherein the step of setting the buffer consumption value on the initial path for data transmission, measuring and recording the throughput value comprises:
selecting different time points, setting a buffer consumption value on the initial path to carry out data transmission for multiple times, and measuring and recording a corresponding initial throughput value in each data transmission;
and carrying out average operation on each initial throughput value to obtain the throughput value.
6. The method according to any one of claims 2 to 5, wherein the step of establishing a polynomial regression model comprises:
a polynomial regression model was built using the python toolkit.
7. The method of claim 4, wherein the congestion control algorithm comprises any one or more of a Cubic algorithm, a Hybla algorithm, an OLIA algorithm, a Reno algorithm, a Scalable algorithm, and a Vegas algorithm.
8. A regression model calculation system for MPTCP multipath transmission buffer consumption, the system comprising:
the information acquisition module is used for acquiring MPTCP information;
a network throughput value extraction module, configured to extract a network throughput value from the MPTCP information;
the cache consumption value calculation module is used for inputting the network throughput value into a pre-established cache consumption model and calculating to obtain an MPTCP cache consumption value; the buffer consumption model is obtained by analyzing and modeling NorNetCore experimental data based on a mathematical statistics regression analysis method, and is used for recording the relation between MPTCP buffer consumption and network throughput.
9. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the steps of the method of any of claims 1 to 7 are implemented when the computer program is executed by the processor.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911060937.7A CN110808859B (en) | 2019-11-01 | 2019-11-01 | Regression model calculation method and system for MPTCP multi-path transmission buffer consumption |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911060937.7A CN110808859B (en) | 2019-11-01 | 2019-11-01 | Regression model calculation method and system for MPTCP multi-path transmission buffer consumption |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110808859A true CN110808859A (en) | 2020-02-18 |
| CN110808859B CN110808859B (en) | 2020-12-01 |
Family
ID=69500927
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911060937.7A Active CN110808859B (en) | 2019-11-01 | 2019-11-01 | Regression model calculation method and system for MPTCP multi-path transmission buffer consumption |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110808859B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113271256A (en) * | 2021-04-06 | 2021-08-17 | 北京邮电大学 | Information age multi-path transmission method and system |
| CN114071563A (en) * | 2020-08-03 | 2022-02-18 | 中国电信股份有限公司 | Multi-path transmission control method and device based on cache space and mobile terminal |
| CN114615201A (en) * | 2022-03-15 | 2022-06-10 | 海南大学 | MPTCP (Multi-protocol Transmission control protocol) cache prediction model training method and MPTCP cache prediction method |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101656653A (en) * | 2008-08-21 | 2010-02-24 | 中国移动通信集团公司 | Method and device for configuring receive buffer applied to multi-path transmission |
| EP2899929A1 (en) * | 2014-01-28 | 2015-07-29 | Samsung Electronics Co., Ltd | Method and apparatus for traffic distribution control using Multi-Path Transport Control Protocol in wireless heterogeneous networks |
| CN105490933A (en) * | 2015-12-28 | 2016-04-13 | 中国电子科技集团公司第五十四研究所 | MPTCP path management method based on multi-path transmission protocol and device |
| CN105873096A (en) * | 2016-03-24 | 2016-08-17 | 重庆邮电大学 | Optimization method of efficient throughput capacity of multipath parallel transmission system |
| CN106656856A (en) * | 2016-12-16 | 2017-05-10 | 浙江大学 | Data package scheduling method for resisting blockage of MPTCP receiving buffer zone |
| CN107682886A (en) * | 2017-09-01 | 2018-02-09 | 北京邮电大学 | A kind of data transmission method of multipath |
-
2019
- 2019-11-01 CN CN201911060937.7A patent/CN110808859B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101656653A (en) * | 2008-08-21 | 2010-02-24 | 中国移动通信集团公司 | Method and device for configuring receive buffer applied to multi-path transmission |
| EP2899929A1 (en) * | 2014-01-28 | 2015-07-29 | Samsung Electronics Co., Ltd | Method and apparatus for traffic distribution control using Multi-Path Transport Control Protocol in wireless heterogeneous networks |
| CN105490933A (en) * | 2015-12-28 | 2016-04-13 | 中国电子科技集团公司第五十四研究所 | MPTCP path management method based on multi-path transmission protocol and device |
| CN105873096A (en) * | 2016-03-24 | 2016-08-17 | 重庆邮电大学 | Optimization method of efficient throughput capacity of multipath parallel transmission system |
| CN105873096B (en) * | 2016-03-24 | 2019-05-10 | 重庆邮电大学 | A kind of optimization method of multipath parallel transmission system effective throughput |
| CN106656856A (en) * | 2016-12-16 | 2017-05-10 | 浙江大学 | Data package scheduling method for resisting blockage of MPTCP receiving buffer zone |
| CN107682886A (en) * | 2017-09-01 | 2018-02-09 | 北京邮电大学 | A kind of data transmission method of multipath |
Non-Patent Citations (1)
| Title |
|---|
| 符发等: "多场景的MPTCP谢意性能分析研究", 《计算机工程与应用》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114071563A (en) * | 2020-08-03 | 2022-02-18 | 中国电信股份有限公司 | Multi-path transmission control method and device based on cache space and mobile terminal |
| CN114071563B (en) * | 2020-08-03 | 2023-11-14 | 中国电信股份有限公司 | Multipath transmission control method and device based on cache space and mobile terminal |
| CN113271256A (en) * | 2021-04-06 | 2021-08-17 | 北京邮电大学 | Information age multi-path transmission method and system |
| CN113271256B (en) * | 2021-04-06 | 2022-08-30 | 北京邮电大学 | Information age multi-path transmission method and system |
| CN114615201A (en) * | 2022-03-15 | 2022-06-10 | 海南大学 | MPTCP (Multi-protocol Transmission control protocol) cache prediction model training method and MPTCP cache prediction method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110808859B (en) | 2020-12-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110808859B (en) | Regression model calculation method and system for MPTCP multi-path transmission buffer consumption | |
| CN110046794B (en) | Network quality evaluation method and device, computer equipment and storage medium | |
| JP7123590B2 (en) | Network health assessment | |
| CN113037624A (en) | Data flow control method and device | |
| US20150131445A1 (en) | Similarity matching method and related device and communication system | |
| EP3614627B1 (en) | Telecommunications network and services qoe assessment | |
| CN109905257B (en) | Method and device for determining bandwidth transmission capacity | |
| CN110912768A (en) | Grey correlation and fuzzy evaluation method and system for multi-path transmission network performance | |
| US11134409B2 (en) | Determining whether a flow is to be added to a network | |
| US8879403B2 (en) | Link microbenchmarking with idle link correction | |
| CN112165408B (en) | Test method and device for simulating client serial deployment environment | |
| US20220368606A1 (en) | Fault Detection Model Training Method, Apparatus, and System | |
| CN115460572A (en) | Application program acceleration method, device, equipment and storage medium | |
| CN113207146B (en) | Wireless communication network quality monitoring system and method | |
| EP1489865A1 (en) | Method and system for analysing data quality measurements in wireless data communication networks | |
| Abadleh et al. | Comparative analysis of TCP congestion control methods | |
| US8243607B2 (en) | Packet delay characteristic measuring apparatus and method | |
| CN110475244B (en) | Terminal management method, system, device, terminal and storage medium | |
| US20220368590A1 (en) | Fault Detection Method, Apparatus, and System | |
| CN111404841A (en) | Data scheduling method, device and storage medium | |
| CN112637055B (en) | Multi-link aggregation method, system and storage medium based on VPN tunnel | |
| CN111711946B (en) | IoT (internet of things) equipment identification method and identification system under encrypted wireless network | |
| CN114615201B (en) | MPTCP (Multi-protocol Transmission control protocol) cache prediction model training method and MPTCP cache prediction method | |
| JP4668851B2 (en) | Quality class determination apparatus, quality class determination method, and program | |
| Lara et al. | Understanding and characterizing transmission times for compressed IP packets over LoRaWAN |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |