CN104580006B - A kind of mobile network's method of controlling transmission rate, apparatus and system - Google Patents
A kind of mobile network's method of controlling transmission rate, apparatus and system Download PDFInfo
- Publication number
- CN104580006B CN104580006B CN201410817412.4A CN201410817412A CN104580006B CN 104580006 B CN104580006 B CN 104580006B CN 201410817412 A CN201410817412 A CN 201410817412A CN 104580006 B CN104580006 B CN 104580006B
- Authority
- CN
- China
- Prior art keywords
- network delay
- time window
- new time
- window
- delay time
- 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.)
- Active
Links
Landscapes
- Data Exchanges In Wide-Area Networks (AREA)
- Mobile Radio Communication Systems (AREA)
Abstract
The invention discloses a kind of mobile network data transfer control method, device and system.This method includes：The network delay and confidential interval of the new time window of ensemble prediction are sampled according to web-based history time delay, the network-induced delay estimate of new time window is calculated, transmission rate is controlled according to the network delay of the network-induced delay estimate of the new time window and the new time window of the prediction.This method network delay monitoring accuracy is high, and can adapt to different mobile network's standards, can make corresponding adjustment to transmission rate according to the change of network delay, and then reduces caching load, effectively solves the problems, such as buffering expansion.
Description
Technical Field
The embodiment of the invention relates to the technical field of mobile networks, in particular to a method, a device and a system for controlling data transmission of a mobile network.
Background
With the continuous development of mobile network technology, modern mobile networks are providing fast and convenient network access for more and more users. Considering the unstable channel quality and the high dynamic of the base station load, a large buffer is generally reserved at the base station, which is beneficial to absorb the bursty data stream. However, during normal operation, the reserved buffer is usually too large, which causes unnecessary delay for normal use by the user and also degrades network performance, which is often referred to as buffer inflation.
The root cause of the formation of buffer expansion is mainly derived from two aspects. First, the buffering is set too large compared to the link speed bottleneck; secondly, a Transmission layer Protocol adopted by the modern mobile network is a Transmission Control Protocol (TCP) based on packet loss, and packet loss caused by channel interference is very uncommon in the modern network because the packet loss situation often occurs in a time period when a buffer area becomes full in a general operation process. During transmission, a sender using the TCP protocol based on packet loss will increase the sending rate until the buffer is filled. For the first reason, the sending rate is likely to exceed the bottleneck rate, which is not able to drain the buffer quickly, and the queuing time for this period is significantly increased. In this case, the user experience is greatly affected, for example, when the user is experiencing online game and there is a download program in the background, the user will likely experience a long end-to-end delay in the game. Because the TCP protocol based on packet loss cannot significantly control the transmission rate in the absence of packet loss information, a high queue-in/queue delay becomes a common phenomenon in the case of multitasking.
To address the problem of cushioning expansion, researchers have proposed two types of solutions. Based on different deployment areas, the two types of solutions are specifically divided into: a base station side deployment method and a receiver side deployment method. The method comprises the steps of monitoring the length change of a base station queue aiming at the base station end deployment, and feeding back an adjustment strategy of a sending rate, wherein the actual network deployment is very complicated, and the strategy needs to change the topological structure of the network, so that the large-scale deployment in the actual application cannot be realized. For the deployment of a receiving end, the method has a great advantage compared with a base station deployment method because the network topology does not need to be modified, but the existing strategy mostly adopts a fixed sending rate control method, namely, a reference value of Round-Trip Time (RTT) is set as a basis for judgment, and the characteristic obviously cannot adapt to the current situation of coexistence of different current mobile networks.
Disclosure of Invention
The invention aims to provide a mobile network data transmission control method, a device and a system, which are used for detecting a network delay state and accurately controlling a transmission rate, so that a cache load is reduced, and the problem of buffer expansion is effectively solved.
In a first aspect, an embodiment of the present invention provides a method for controlling data transmission in a mobile network, including:
predicting the network delay and the confidence interval of the new time window according to the historical network delay time sampling set;
calculating the estimated value of the network delay time of the new time window;
and controlling the sending rate according to the estimated value of the network delay time of the new time window and the predicted network delay of the new time window.
In a second aspect, an embodiment of the present invention provides a mobile network data transmission control apparatus, including:
the prediction module is used for predicting the network delay and the confidence interval of the new time window;
the estimated value calculation module is used for calculating the estimated value of the network delay time of the new time window;
and the sending rate control module is used for controlling the sending rate according to the estimated value of the network delay time of the new time window and the predicted network delay of the new time window.
In a third aspect, an embodiment of the present invention provides a mobile network data transmission control system, including:
the receiving end equipment and the sending end equipment of any mobile network data transmission control device in the embodiment of the invention are configured.
According to the mobile network data transmission control method, the device and the system provided by the embodiment of the invention, the network delay and the confidence interval of a new time window are predicted according to a historical network delay time sampling set, the network delay time estimation value of the new time window is calculated, the sending rate is controlled according to the network delay time estimation value of the new time window and the predicted network delay of the new time window, the network delay monitoring accuracy is high, different mobile network standards can be adapted, the sending rate can be correspondingly adjusted according to the change of the network delay, the cache load is further reduced, and the problem of buffer expansion is effectively solved.
Drawings
Fig. 1 is a flowchart illustrating a mobile network data transmission control method according to an embodiment of the present invention;
fig. 2 is a flowchart illustrating a mobile network data transmission control method according to a second embodiment of the present invention,
fig. 3 is a mobile network delay measurement environment according to a second embodiment of the present invention;
FIG. 4 is a graph illustrating the prediction accuracy measured under the kernel length γ values of different kernel functions according to a second embodiment of the present invention;
fig. 5 is a schematic flowchart of a method for updating a historical network delay time sample set according to a third embodiment of the present invention;
fig. 6 is a block diagram of a mobile network data transmission control device according to a fourth embodiment of the present invention;
fig. 7 is a block diagram of a mobile network data transmission control system according to a fifth embodiment of the present invention;
fig. 8 is a schematic diagram of a specific topology according to a fifth embodiment of the present invention;
fig. 9 is a network delay prediction accuracy image obtained by a mobile network data transmission control system test according to a fifth embodiment of the present invention;
fig. 10 is a comparison graph of bandwidth prediction errors obtained from five tests and bandwidth prediction errors obtained from DRWA algorithm according to an embodiment of the present invention.
Detailed Description
The technical scheme of the invention is further explained by the specific implementation mode in combination with the attached drawings. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some structures related to the present invention are shown in the drawings, not all of them.
Example one
Fig. 1 is a flowchart illustrating a mobile network data transmission control method according to an embodiment of the present invention, where the method may be executed by a mobile network data transmission control apparatus, where the apparatus may be implemented by software and/or hardware, and may be built in a receiving end device as a part of the receiving end device. As shown in fig. 1, the method includes:
step 101, predicting the network delay and the confidence interval of the new time window according to the historical network delay time sampling set.
Selecting the size of a proper historical network delay time sampling set according to the application scene requirement, predicting the network delay of a new time window according to the data of the selected historical network delay time sampling set, and calculating the network delay and the confidence interval of the predicted new time window.
And 102, calculating the estimated value of the network delay time of the new time window.
The new time window network delay time estimate is a time interval from a time point when a first Acknowledgement Character (ACK) is transmitted to a time point when a last data packet in the receiving window is received.
And 103, controlling the sending rate according to the estimated value of the network delay time of the new time window and the predicted network delay of the new time window.
And adjusting the sending rate of the sending end in real time according to the predicted network delay of the new time window obtained in the step 101 and the estimated value of the network delay time of the new time window obtained in the step 102. The mobile network data transmission control method provided in the first embodiment of the present invention predicts the network delay and the confidence interval of the new time window according to the historical network delay time sampling set, calculates the network delay time estimation value of the new time window, and controls the transmission rate according to the network delay time estimation value of the new time window and the predicted network delay of the new time window, so that the network delay monitoring accuracy is high, and the method can adapt to different mobile network standards, and can make corresponding adjustment on the transmission rate according to the change of the network delay, thereby reducing the buffer load and effectively solving the problem of buffer expansion.
Example two
Fig. 2 is a schematic flow chart of a mobile network data transmission control method according to a second embodiment of the present invention, where the present embodiment is optimization based on the foregoing embodiment, and specifically the method includes:
step 201, predicting the network delay and the confidence interval of the new time window according to the historical network delay time sampling set.
In order to accurately predict the Mobile network delay, two sites are selected from a campus as measurement sampling points of a Universal Mobile Telecommunications System (UMTS) and a High-Speed Packet Access (HSPA), and a verification experiment is performed on each sampling point. During the experiment, the distribution of the network delay is found to be concentrated around the average value of the measurement in a shorter time window. In two locations, 5 websites were selected for testing on different mobile networks as shown in fig. 3. For the obtained sampling points, the test was performed using Kolmogorov-Smirnov with a default confidence level of 0.01, and the test results are shown in table 1 below:
TABLE 1 Kolmogorov-Smirnov test results
Table 1 shows that even under validation conditions of smaller confidence levels, an average of 90.93% of the samples passed the Kolmogorov-Smirnov test. Thus, for a fixed far end IP, the end-to-end mobile network delay follows a gaussian distribution over a small time interval. For different periods of time in practice, in the same placeAnd (4) moving network delay, and performing real-time network delay test by adopting a Gaussian process. The gaussian process is a random process that spreads static gaussian variables over a time sequence. Unlike traditional training methods, the gaussian process does not model the random variables. Mobile network delay r i Obeying the following formula:
r u ＝f(x i )+∈，i＝1，2，3，…
where e is white gaussian noise, obeying an N (0, Σ) distribution. x is the number of i To sample the time window value, r i For mobile network delays, f is a mapping from a sampling time window to the mobile network delay. Without loss of generality, the delays within the time window are different and are Gaussian independent, i.e., r i ≠r j (i ≠ j). Selecting a historical mobile network delay time sampling set r 1 ，…，r n Are and r 1 +…+r n ～N(μ 1 +…+μ n N Σ), where μ 1 Is a time window x 1 Is the variance. If x A And x B Are two continuous variables derived from a gaussian process that obey a joint gaussian distribution: n (mu, sigma). Their conditional probability distribution:
also obey a gaussian distribution, i.e.:
wherein
Exemplary, selectionDelaying a time sample set for a historical network, the historical network delayThe sampling value of the set of late time samples is n, i.e. the number of sampling points is n, r n Is a time window x n Network delay in (2).
If the network delay time follows a Gaussian distribution with a mean of 0 and a covariance of K, then the new time window x * Network delay r in * And network delay time sampling setA joint gaussian distribution is satisfied as follows:
wherein the covariance K is represented by a kernel function. The kernel function K measures the correlation between two time windows, and this correlation determines the influence of the data of the historical network delay sample set on the final prediction result. Typically, the kernel function K is a semi-positive definite matrix:
order toWhere γ represents the kernel length of the kernel function. If the two time windows are relatively close together, then there is a strong correlation between the signal strengths in the two windows, i.e., K ≈ 1. Download tests were performed under both UMTS and HSPA network standards, respectively, finding the optimal gamma value, and testing the case of the receiving end in static and moving (static) states. For each download, 100000 packets were sampled to calculate the effect of different gamma values on download performance. For each measurement, a data packet within a download window is selected as historical data. As shown in FIG. 4, when γ ≦ 1, the prediction accuracy can be close to 1 for both network types (UMTS and HSPA) and both moving states static (static) and dynamic (move). Thus setting the nucleus length γ to1。
Therefore, the number of the first and second electrodes is increased,
wherein, the first and the second end of the pipe are connected with each other,
∑ * for a new time window x * Network delay r in * The variance of (c). Finally, obtaining a network delay confidence interval of a new time window:
wherein r is * For the network delay of the new time window,network delay r for new time window * Confidence interval of (d), μ * Is the average value of the network delays for the new time window,for student's distribution, sigma * A network delay variance for the new time window;network delay r for a new time window * Lower limit value of Network delay r for a new time window * Upper limit value of
For the case that the end-to-end network delay does not follow the gaussian distribution with mean value of 0, let r ' = r- μ, let r ' follow the gaussian process with mean value of 0, i.e. r ' — GP (0, K). Therefore, the method is also suitable for the case that the end-to-end network delay does not follow the Gaussian distribution with the average value of 0.
Preferably, the effect of noise on the distribution of network delays is taken into account, then
It can be calculated that:
wherein, I is an identity matrix, and Σ is a variance of a sampling set of historical network delay time.
Step 202, calculating the estimated value of the network delay time of the new time window.
And 203, controlling the sending rate according to the estimated value of the network delay time of the new time window and the predicted network delay of the new time window.
In particular, byAn estimate of network delay time representing a new time window when the estimate of network delay time for the new time window is presentWhen the network delay is greater than the upper limit value of the confidence interval of the network delay of the new time window, making rwnd '= rwnd beta, wherein rwnd is an original receiving window, and rwnd' is an adjusted receiving window; the value of β should be less than 1, preferably, β is set to 0.875 by default. Network delay when the new time window is reachedLate time estimateUpper limit value of confidence interval of network delay larger than the new time windowWhen the time is over, the sending rate is over, and the original receiving window rwnd should be adjusted to be small.
Network delay time estimate when the new time window is presentWhen the lower limit value of the confidence interval of the network delay of the new time window is less thanWherein rwnd is the original receive window and rwnd' is the adjusted receive window. Network delay time estimate when the new time window is reachedUpper limit value of confidence interval of network delay smaller than the new time windowIn this case, the sending rate is too low, and the original receiving window rwnd should be increased.
Network delay time estimate when the new time window is presentWhen the confidence interval of the network delay belongs to the new time window, making rwnd '= rwnd +1, wherein rwnd is an original receiving window, and rwnd' is an adjusted receiving window; network delay time estimate when the new time window is presentThe confidence interval of the network delay belonging to the new time window indicates that the sending rate is close to the bottleneck rateAnd (3) adopting a conservative strategy, and adding 1 to the original receiving window rwnd to obtain an adjusted receiving window.
Sending the adjusted receiving window rwnd' to a sending end; the sending rate is proportional to the adjusted receiving window. The adjustment of the transmission rate can be achieved by adjusting the size of the reception window.
And step 204, updating the historical network delay time sampling set.
The purpose of this step is to select a suitable historical network delay time sampling set in order to realize dynamic sampling adjustment, so as to predict the network delay and confidence interval of a new time window more accurately.
The mobile network data transmission control method provided in the second embodiment of the present invention adds a step of updating the historical network delay time sampling set on the basis of the first embodiment, and can implement dynamic sampling adjustment, further improve the network delay monitoring accuracy, reduce the buffer load, and effectively solve the problem of buffer expansion.
EXAMPLE III
Fig. 5 is a flowchart illustrating a method for updating a historical network delay time sample set according to a third embodiment of the present invention, as shown in fig. 5, including:
step 301, calculate the new time window receiving rate.
For packets received within a new time window, a formula may be usedTo calculate a reception rate, whereinWhich is indicative of the rate of reception of the data,indicating the number of received data packets，Representing an estimate of the network delay time.
Step 302, calculating net network delay time of the new time window according to the new time window receiving rate and the new time window network delay time estimated value.
According to the sequence number difference between two confirmation character messages sent by a receiving end, the number of data packets transmitted in a link can be obtained, and a formula is utilizedTo calculate the net network delay time of the net new time windowWhere Gap (ACK Seq) indicates the difference in sequence numbers between two ACKs.
Step 303, calculating a confidence interval of the historical network delay time sampling set.
Specifically, the confidence interval of the historical network delay time sampling set is as follows:
wherein u is the mean value of the historical network delay time sampling set, Σ is the variance of the historical network delay time sampling set, and n is the number of sampling time windows in the historical network delay time sampling set.
Step 304, updating the sample set according to the net network delay time of the new time window.
Considering the prediction accuracy, a sample set that is too large or too small cannot provide a high prediction accuracy, and the sample data is analyzed, the sample value of the sample set is preferably 3, and the prediction accuracy is the highest, so that the following description will be made with the sample set size being 3.
Updating the sample set according to the net network delay time of the new time window obtained in step 302, specifically including:
net network delay time when the new time window is reachedConfidence intervals belonging to a set of historical network delay time samplesAnd when the sampling value of the historical network delay time sampling set is less than a preset sampling value 3, adding the sampling point of the new time window into the sampling set. In this case, when mobile network data transmission control is started, for example, after sampling in 1 time window, and sampling in a new time window is performed, the number of historical network delay time samples is 1, and the sampling value of the historical network delay time sample set is equal to 1 and smaller than the preset sampling value 3, so that the sampling point of the new time window is added to the sample set. And adding the sampling point of the new time window, increasing the sampling value, if the current sampling value is 1, adding the sampling point of the new time window, and then increasing the new sampling value to 2, and if the current sampling value is 2, adding the sampling point of the new time window, then increasing the new sampling value to 3.
Net network delay time when the new time window is reachedConfidence intervals belonging to a set of historical network delay time samplesWhen the sampling value of the historical network delay time sampling set is equal to a preset sampling value, the sampling window is moved to the right, and the sampling point of a new time window is added; i.e., equivalent to the current sample value =3, the sample window is shifted to the right, discarding the earliest timestamp in the historical network delay time sample setAnd (4) historical sampling points, wherein sampling points of a new time window are added, and the sampling values are still 3 when unchanged.
Net network delay time when the new time window is reachedConfidence intervals not belonging to historical network delay time sample setsThen, a historical sample of the most recent timestamp is retained and the sample of the new time window is added. That is, only one historical sampling point of the latest timestamp in the historical network delay time sampling set is reserved, and a sampling point of a new time window is added, wherein the sampling value is 2 at this time.
According to the embodiment of the invention, the historical network delay time sampling set is dynamically updated by comparing the sampling values of the historical network delay time sampling set according to the confidence interval of the net network delay time of the new time window and the historical network delay time sampling set, so that the influence of the outdated historical network delay time sampling point on the network delay prediction of the new time window is avoided, the network delay monitoring accuracy is improved, the cache load is reduced, and the problem of buffer expansion is effectively solved.
Example four
Fig. 6 is a block diagram of a mobile network data transmission control apparatus according to a fourth embodiment of the present invention, which may be embedded in a receiving end device as a part of the receiving end device. As shown in fig. 6, the apparatus includes:
the prediction module 401 is configured to predict the network delay and the confidence interval of the new time window.
An estimated value calculating module 402, configured to calculate an estimated value of the network delay time of the new time window.
And a sending rate control module 403, configured to control a sending rate according to the estimated network delay time of the new time window and the predicted network delay of the new time window.
The mobile network data transmission control device provided by the first embodiment of the invention predicts the network delay and the confidence interval of the new time window according to the historical network delay time sampling set, calculates the network delay time estimation value of the new time window, and controls the sending rate according to the network delay time estimation value of the new time window and the predicted network delay of the new time window, so that the network delay monitoring accuracy is high, the device can adapt to different mobile network standards, the sending rate can be correspondingly adjusted according to the change of the network delay, the cache load is further reduced, and the problem of buffer expansion is effectively solved.
Further, the network delay of the new time window is predicted to follow gaussian distribution, and the confidence interval calculation formula of the network delay of the new time window is as follows:
wherein r is * For the network delay of the new time window,network delay r for a new time window * Confidence interval of (d), μ * Is the average value of the network delays for the new time window,for student's distribution, n is historical network delay time sampling set sampling value, sigma * The network delay variance for the new time window.Network delay r for a new time window * Lower limit value of Network delay r for a new time window * Upper limit value of
Further, the sending rate control module 403 is specifically configured to:
when the estimated value of the network delay time of the new time window is greater than the upper limit value of the confidence interval of the network delay of the new time window, making rwnd '= rwnd beta, wherein rwnd is an original receiving window, and rwnd' is an adjusted receiving window;
when the estimated value of the network delay time of the new time window is smaller than the lower limit value of the confidence interval of the network delay of the new time window, the network delay time of the new time window is orderedWherein rwnd is an original receiving window, and rwnd' is an adjusted receiving window;
when the estimated value of the network delay time of the new time window belongs to the confidence interval of the network delay of the new time window, making rwnd '= rwnd +1, wherein rwnd is an original receiving window, and rwnd' is an adjusted receiving window;
sending the adjusted receiving window to a sending end; the sending rate is proportional to the adjusted receiving window.
Preferably, the apparatus further comprises: and the sampling set updating module is used for updating the historical network delay time sampling set.
The sampling set updating module specifically includes: a receiving rate calculating subunit, configured to calculate a receiving rate of the new time window; a new time window net network delay time calculating subunit, configured to calculate the net network delay time of the new time window according to the new time window receiving rate and the new time window network delay time estimated value; the historical sampling set confidence interval calculation subunit is used for calculating the confidence interval of the historical network delay time sampling set; a sample set update subunit, configured to update the historical network delay time sample set according to the net network delay time of the new time window.
The sampling set updating subunit is specifically configured to:
when the net network delay time of the new time window belongs to a confidence interval of a historical network delay time sampling set and the sampling value of the historical network delay time sampling set is smaller than a preset sampling value, adding the sampling point of the new time window;
when the net network delay time of the new time window belongs to the confidence interval of the historical network delay time sampling set and the sampling value of the historical network delay time sampling set is equal to the preset sampling value, the sampling window moves to the right, and the sampling point of the new time window is added;
and when the net network delay time of the new time window does not belong to the confidence interval of the historical network delay time sampling set, reserving a historical sampling point of the latest timestamp, and adding the sampling point of the new time window. The mobile network data transmission control device provided by the embodiment of the invention can be used for executing the mobile network data transmission control method provided by any embodiment of the invention, has corresponding functional modules and realizes the same beneficial effect.
EXAMPLE five
Fig. 7 is a block diagram of a mobile network data transmission control system according to a fifth embodiment of the present invention, where as shown in the figure, the system includes a receiving end device 501 configured with any one of the mobile network data transmission control apparatuses according to the fifth embodiment of the present invention, and a sending end device 502.
For example, fig. 8 shows a specific topology of the system, where the topology is a single-hop network, the server is used as the sending end, the user mobile phone is used as the receiving end, and the relay is a base station. Of course, the receiving end may also be a PC (Personal Computer), a notebook Computer, or the like. It should be noted that the embodiments of the present invention can also be used in a multi-hop network, i.e. a case where the relay is a plurality of base stations. The link bandwidth of the server and the base station is 100Mbps, and the delay is 10ms. For the link between the base station and the user, the UMTS bandwidth is 400kbps, the delay is 100ms, the HSPA link bandwidth is 4Mbps, and the delay is 50ms. When the system with the topological structure is used for controlling the data transmission of the mobile network, the accuracy rate of the network delay time prediction of a new time window is calculated for the static condition and the motion condition of a receiving end, as shown in fig. 9. Compared with the conventional DRWA (dynamic receive window adjustment algorithm), the bandwidth estimation error rate is reduced by 20%, as shown in fig. 10, the bandwidth defines the link rate, so the wide estimation error rate is reduced, which indicates that the sending rate can be ensured to be close to the link rate through the mobile network data transmission control, the buffer load is reduced, the in-and-out delay is further reduced, and the problem of buffer expansion is effectively solved.
It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.
Claims (10)
1. A method for controlling data transmission in a mobile network, comprising:
predicting the network delay and the confidence interval of the new time window according to the historical network delay time sampling set;
calculating the estimated value of the network delay time of the new time window;
and controlling the sending rate according to the estimated value of the network delay time of the new time window and the predicted confidence interval of the network delay of the new time window.
2. The method of claim 1, wherein controlling the transmission rate based on the estimated network delay time for the new time window and a confidence interval for the predicted network delay for the new time window, further comprises:
updating the set of historical network delay time samples.
3. The method of claim 1, wherein predicting the network delay for the new time window is based on a Gaussian distribution with covariance K, and wherein the confidence interval for the network delay for the new time window is calculated as:
wherein r is * For the network delay of the new time window,
network delay r for new time window * Confidence interval of (d), μ * Is the average value of the network delays for the new time window,for student's distribution, n is the historical network delay time sampling set sampling value, sigma * For a new time window x * Network delay r * The variance of (a) is calculated,
network delay r for a new time window * Lower limit value of (2) Network delay r for a new time window * Upper limit value of
4. The method according to any of claims 1-3, wherein said controlling the transmission rate based on the estimated value of the network delay time of the new time window and the confidence interval of the predicted network delay of the new time window comprises:
when the estimated value of the network delay time of the new time window is greater than the upper limit value of the confidence interval of the network delay of the new time window, making rwnd '= rwnd beta, wherein rwnd is an original receiving window, and rwnd' is an adjusted receiving window;
when the estimated value of the network delay time of the new time window is smaller than the lower limit value of the confidence interval of the network delay of the new time window, the network delay time of the new time window is orderedWherein rwnd is an original receiving window, and rwnd' is an adjusted receiving window;
when the estimated value of the network delay time of the new time window belongs to the confidence interval of the network delay of the new time window, making rwnd '= rwnd +1, wherein rwnd is an original receiving window, and rwnd' is an adjusted receiving window;
wherein, beta is a receiving window size adjusting coefficient, and beta is less than 1;
sending the adjusted receiving window to a sending end; the sending rate is proportional to the adjusted receiving window.
5. The method according to claim 2, wherein the updating the historical set of network delay time samples specifically comprises:
calculating a new time window receiving rate;
calculating net network delay time of the new time window according to the new time window receiving rate and the new time window network delay time estimated value;
calculating a confidence interval of a historical network delay time sampling set;
updating the sample set according to the net network delay time of the new time window.
6. The method of claim 5, wherein updating the sample set according to the net network delay time of the new time window comprises:
when the net network delay time of the new time window belongs to the confidence interval of the historical network delay time sampling set and the sampling value of the historical network delay time sampling set is smaller than the preset sampling value, adding the sampling point of the new time window;
when the net network delay time of the new time window belongs to a confidence interval of a historical network delay time sampling set and the sampling value of the historical network delay time sampling set is equal to a preset sampling value, the sampling window is moved to the right, and the sampling point of the new time window is added;
and when the net network delay time of the new time window does not belong to the confidence interval of the historical network delay time sampling set, reserving a historical sampling point of the latest timestamp, and adding the sampling point of the new time window.
7. A mobile network data transmission control apparatus, comprising:
the prediction module is used for predicting the network delay of the new time window and the confidence interval of the network delay;
the estimated value calculation module is used for calculating the estimated value of the network delay time of the new time window;
and the sending rate control module controls the sending rate according to the estimated value of the network delay time of the new time window and the predicted confidence interval of the network delay of the new time window.
8. The apparatus of claim 7, further comprising:
and the sampling set updating module is used for updating the historical network delay time sampling set.
9. The apparatus of claim 8, wherein the sample set update module specifically comprises:
a receiving rate calculating subunit, configured to calculate a receiving rate of the new time window;
a new time window net network delay time calculating subunit, configured to calculate a net network delay time of a new time window according to the new time window receiving rate and a new time window network delay time estimated value;
the historical sampling set confidence interval calculation subunit is used for calculating the confidence interval of the historical network delay time sampling set;
a sample set update subunit, configured to update the historical network delay time sample set according to the net network delay time of the new time window.
10. A mobile network data transmission control system, comprising: a receiving end device configured with the mobile network data transmission control apparatus according to any one of claims 7 to 9, and a transmitting end device.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410817412.4A CN104580006B (en) | 2014-12-24 | 2014-12-24 | A kind of mobile network's method of controlling transmission rate, apparatus and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410817412.4A CN104580006B (en) | 2014-12-24 | 2014-12-24 | A kind of mobile network's method of controlling transmission rate, apparatus and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104580006A CN104580006A (en) | 2015-04-29 |
| CN104580006B true CN104580006B (en) | 2018-02-09 |
Family
ID=53095227
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410817412.4A Active CN104580006B (en) | 2014-12-24 | 2014-12-24 | A kind of mobile network's method of controlling transmission rate, apparatus and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104580006B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112087399A (en) * | 2019-06-12 | 2020-12-15 | 阿里巴巴集团控股有限公司 | LoRa data transmission method, device, equipment and storage medium |
| CN110266611B (en) * | 2019-07-08 | 2023-06-23 | 腾讯科技（上海）有限公司 | Method, device and system for processing buffered data |
| CN115119216B (en) * | 2022-06-24 | 2024-05-14 | 深圳友讯达科技股份有限公司 | LoRaWAN network communication method and system with constant power supply |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101057439A (en) * | 2004-11-17 | 2007-10-17 | 夏普株式会社 | Transmitter, receiver and communication system |
| CN101326842A (en) * | 2005-12-12 | 2008-12-17 | 卢森特技术有限公司 | Method of downlink rate control |
| CN101803304A (en) * | 2007-09-04 | 2010-08-11 | 奥斯佩拉股份公司 | Method and system for aggregate bandwidth control |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2012257010A (en) * | 2011-06-08 | 2012-12-27 | Hitachi Ltd | Communication device, communication method, and remote monitoring system |
-
2014
- 2014-12-24 CN CN201410817412.4A patent/CN104580006B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101057439A (en) * | 2004-11-17 | 2007-10-17 | 夏普株式会社 | Transmitter, receiver and communication system |
| CN101326842A (en) * | 2005-12-12 | 2008-12-17 | 卢森特技术有限公司 | Method of downlink rate control |
| CN101803304A (en) * | 2007-09-04 | 2010-08-11 | 奥斯佩拉股份公司 | Method and system for aggregate bandwidth control |
Non-Patent Citations (1)
| Title |
|---|
| 《计算机科学》;张雨晴等;《分组网上多媒体实时业务双时间尺度速率控制方法》;20031215;第34页-第37页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104580006A (en) | 2015-04-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9455925B2 (en) | Method, device, and system for self-adaptively adjusting data transmission rate | |
| CN107624232B (en) | Apparatus and method for controlling downlink throughput in communication system | |
| EP3780542B1 (en) | Data transmission method and device | |
| JP6274113B2 (en) | Data transmission apparatus, data transmission method, and program thereof | |
| US20200267083A1 (en) | Transmit data volume control device, method, and recording medium | |
| KR20090036765A (en) | Output bit rate set method for adaptive video data transmission in wibro system | |
| EP2627117A2 (en) | Method and apparatus for controlling traffic transfer rate based on cell capacity in mobile communication system | |
| CN113329413B (en) | Multipath transmission data pre-scheduling method and system for high-speed rail scene | |
| CN104580006B (en) | A kind of mobile network's method of controlling transmission rate, apparatus and system | |
| CN110380978B (en) | Scheduling method and device for multipath transmission, computer equipment and storage medium | |
| EP3471458B1 (en) | Method and apparatus for controlling data transmission speed in wireless communication system | |
| CN114945926A (en) | Network entity and user equipment for transmission rate control | |
| Moon et al. | Rate-adaptive snoop: a TCP enhancement scheme over rate-controlled lossy links | |
| WO2014171543A1 (en) | Data transmission device, data transmission method, and program therefor | |
| KR100365788B1 (en) | Method and Apparatus for deciding traffic capacity in Wireless Packet Data System | |
| JP2016072824A (en) | Radio communication equipment capable of changing aggregation amount in accordance with radio communication environment, radio communication program and method | |
| Shiu et al. | Performance analysis of TCP over wireless link with dedicated buffers and link level error control | |
| JP6897769B2 (en) | Data transmitters, methods and programs | |
| KR102131427B1 (en) | Method and apparatus for performing a congestion control in stream control transmission protocol | |
| JP5787707B2 (en) | COMMUNICATION SYSTEM, DATA TRANSMITTING TERMINAL, DATA RECEIVING TERMINAL, AND TRANSMISSION RATE CONTROL METHOD | |
| CN115314939A (en) | Method for sending acknowledged mode RLC entity data | |
| CN116962258A (en) | Bandwidth detection method, device, system, equipment and storage medium | |
| Lee et al. | Correlation analysis of available bandwidth estimators for mobile HCI | |
| Mahapatra et al. | RCM-BR: An efficient rate control protocol for multimedia delivery in Wireless Internet | |
| Yi et al. | A Scheme of Improving TCP Performance in Wireless Environment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP01 | Change in the name or title of a patent holder | ||
| CP01 | Change in the name or title of a patent holder |
Address after: 214135 Room 501, A District, Qingyuan Road, Wuxi science and Technology Park, Wuxi New District, Jiangsu Patentee after: RUN TECHNOLOGY CO.,LTD. Address before: 214135 Room 501, A District, Qingyuan Road, Wuxi science and Technology Park, Wuxi New District, Jiangsu Patentee before: WUXI RUN TECHNOLOGY CO.,LTD. |
|
| CP03 | Change of name, title or address | ||
| CP03 | Change of name, title or address |
Address after: 201800 room j1958, building 6, 1288 Yecheng Road, Jiading District, Shanghai Patentee after: Ruan Internet of things Technology Group Co.,Ltd. Address before: 214135 Room 501, A District, Qingyuan Road, Wuxi science and Technology Park, Wuxi New District, Jiangsu Patentee before: RUN TECHNOLOGY CO.,LTD. |