CN108989880B - Code rate self-adaptive switching method and system - Google Patents
Code rate self-adaptive switching method and system Download PDFInfo
- Publication number
- CN108989880B CN108989880B CN201810644936.6A CN201810644936A CN108989880B CN 108989880 B CN108989880 B CN 108989880B CN 201810644936 A CN201810644936 A CN 201810644936A CN 108989880 B CN108989880 B CN 108989880B
- Authority
- CN
- China
- Prior art keywords
- code rate
- state
- current network
- network
- throughput
- 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
- 238000000034 method Methods 0.000 title claims abstract description 48
- 230000003044 adaptive effect Effects 0.000 claims description 30
- 238000010801 machine learning Methods 0.000 claims description 20
- 238000012549 training Methods 0.000 claims description 7
- 230000002159 abnormal effect Effects 0.000 claims description 2
- 230000005540 biological transmission Effects 0.000 abstract description 7
- 238000010586 diagram Methods 0.000 description 14
- 238000003066 decision tree Methods 0.000 description 9
- 238000007637 random forest analysis Methods 0.000 description 8
- 238000004088 simulation Methods 0.000 description 8
- 230000008859 change Effects 0.000 description 6
- 238000004891 communication Methods 0.000 description 5
- 238000012360 testing method Methods 0.000 description 5
- 230000006978 adaptation Effects 0.000 description 3
- 238000004590 computer program Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000005562 fading Methods 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002085 persistent effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/442—Monitoring of processes or resources, e.g. detecting the failure of a recording device, monitoring the downstream bandwidth, the number of times a movie has been viewed, the storage space available from the internal hard disk
- H04N21/44227—Monitoring of local network, e.g. connection or bandwidth variations; Detecting new devices in the local network
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/08—Configuration management of networks or network elements
- H04L41/0803—Configuration setting
- H04L41/0823—Configuration setting characterised by the purposes of a change of settings, e.g. optimising configuration for enhancing reliability
-
- 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
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/436—Interfacing a local distribution network, e.g. communicating with another STB or one or more peripheral devices inside the home
- H04N21/4363—Adapting the video stream to a specific local network, e.g. a Bluetooth® network
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/60—Network structure or processes for video distribution between server and client or between remote clients; Control signalling between clients, server and network components; Transmission of management data between server and client, e.g. sending from server to client commands for recording incoming content stream; Communication details between server and client
- H04N21/63—Control signaling related to video distribution between client, server and network components; Network processes for video distribution between server and clients or between remote clients, e.g. transmitting basic layer and enhancement layers over different transmission paths, setting up a peer-to-peer communication via Internet between remote STB's; Communication protocols; Addressing
- H04N21/647—Control signaling between network components and server or clients; Network processes for video distribution between server and clients, e.g. controlling the quality of the video stream, by dropping packets, protecting content from unauthorised alteration within the network, monitoring of network load, bridging between two different networks, e.g. between IP and wireless
- H04N21/64746—Control signals issued by the network directed to the server or the client
- H04N21/64761—Control signals issued by the network directed to the server or the client directed to the server
- H04N21/64769—Control signals issued by the network directed to the server or the client directed to the server for rate control
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Multimedia (AREA)
- Databases & Information Systems (AREA)
- Computer Security & Cryptography (AREA)
- Mobile Radio Communication Systems (AREA)
Abstract
The embodiment of the invention provides a code rate self-adaptive switching method, which comprises the following steps: identifying a current network state; if the identification result of the current network state is a first state, adopting a first code rate switching strategy; if the identification result of the current network state is a second state, adopting a second code rate switching strategy; the first code rate switching strategy is to select a suitable code rate according to the average throughput of the network, and the second code rate switching strategy is to select a suitable code rate according to the instantaneous throughput of the network. The code rate self-adaptive switching method provided by the embodiment of the invention is suitable for a transmission scene of a DASH video service in a mobile network by identifying the network state and selecting a corresponding code rate switching strategy according to the characteristics of the network state, and has good performance in the aspects of average code rate, interruption characteristics and the like.
Description
Technical Field
The embodiment of the invention relates to the technical field of video service transmission, in particular to a code rate self-adaptive switching method and system.
Background
With the development of mobile networks and the popularization of intelligent terminals, mobile video services have become the mainstream of mobile data services. The DASH service is a novel dynamic adaptive streaming service, and is mainly characterized in that a user is taken as a center, a terminal has a code rate adaptive function, and an optimal video version can be dynamically selected to be downloaded and played according to self conditions so as to improve the user experience quality. However, the available bandwidth of users in mobile networks has the characteristics of instability: on one hand, the wireless channel of the mobile network shows a trend of dynamic change due to the influence of factors such as noise, fading and interference; on the other hand, in DASH service as data service, the wired link may be affected by network congestion event during transmission, resulting in unstable available bandwidth. Therefore, accurate estimation of available bandwidth in mobile networks is a key factor affecting DASH service performance.
The existing code rate adaptive schemes can be roughly divided into three types: the code rate self-adaption scheme comprises code rate self-adaption based on bandwidth estimation, code rate self-adaption based on terminal caching and a code rate self-adaption scheme combining the code rate self-adaption and the terminal caching. However, the existing scheme usually performs code rate adaptive design only for the characteristic of wireless channel instability, and rarely considers the coexistence scenario of wireless channel instability and wired link congestion. In view of the fact that the scenario exists objectively in an actual network and the variation trend of the available bandwidth of the user is different in the two cases, a code rate adaptive switching method is needed to solve the above problem.
Disclosure of Invention
To solve the above problems, embodiments of the present invention provide a method and system for rate adaptive handover, which overcome the above problems or at least partially solve the above problems.
In a first aspect, an embodiment of the present invention provides a code rate adaptive handover method, including:
identifying a current network state;
if the identification result of the current network state is a first state, adopting a first code rate switching strategy;
if the identification result of the current network state is a second state, adopting a second code rate switching strategy;
the first code rate switching strategy is to select a suitable code rate according to the average throughput of the network, and the second code rate switching strategy is to select a suitable code rate according to the instantaneous throughput of the network.
In a second aspect, an embodiment of the present invention further provides a code rate adaptive handover system, including:
the identification module is used for identifying the current network state;
the switching module is used for adopting a first code rate switching strategy if the identification result of the current network state is a first state; if the identification result of the current network state is a second state, adopting a second code rate switching strategy; the first code rate switching strategy is to select a suitable code rate according to the average throughput of the network, and the second code rate switching strategy is to select a suitable code rate according to the instantaneous throughput of the network.
A third aspect of the present invention provides a code rate adaptive switching device, including:
a processor, a memory, a communication interface, and a bus; the processor, the memory and the communication interface complete mutual communication through the bus; the memory stores program instructions executable by the processor, and the processor calls the program instructions to perform a code rate adaptive switching method as described above.
A fourth aspect of the present invention provides a non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform the above method.
The code rate self-adaptive switching method provided by the embodiment of the invention is suitable for a transmission scene of a DASH video service in a mobile network by identifying the network state and selecting a corresponding code rate switching strategy according to the characteristics of the network state, and has good performance in the aspects of average code rate, interruption characteristics and the like.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and those skilled in the art can also obtain other drawings according to the drawings without creative efforts.
Fig. 1 is a schematic flow chart of a code rate adaptive handover method according to an embodiment of the present invention;
fig. 2 is a schematic diagram of throughput fluctuation under unstable wireless channel conditions according to an embodiment of the present invention;
fig. 3 is a schematic diagram of throughput fluctuation under congestion conditions of a wired link according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of network state identification based on machine learning according to an embodiment of the present invention;
FIG. 5 is a schematic diagram illustrating a network state identified by a random forest method according to an embodiment of the present invention;
FIG. 6 is a schematic diagram illustrating a comparison of code rate adaptive simulation results provided by an embodiment of the present invention;
fig. 7 is a structural diagram of a code rate adaptive switching system according to an embodiment of the present invention;
fig. 8 is a block diagram of a code rate adaptive switching device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some embodiments, but not all embodiments, of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Currently, in the prior art, a rate adaptation scheme based on bandwidth estimation, a rate adaptation scheme based on terminal caching, and a combination of the two schemes may be generally adopted in rate adaptation handover. In the three schemes, solutions are generally provided for the characteristic that a wireless channel is unstable, but in an actual application scenario, besides the instability of the wireless channel, the congestion of a wired link is also a main factor causing the instability of a network. In addition, in general, wireless channel instability and wired link congestion coexist in the same scene, so the effect of the rate adaptive switching method in the prior art in the above scene is not ideal, and the user experience is further affected.
To solve the above problem, fig. 1 is a schematic flow chart of a code rate adaptive handover method provided in an embodiment of the present invention, as shown in fig. 1, including:
110. identifying a current network state;
120. if the identification result of the current network state is a first state, adopting a first code rate switching strategy; if the identification result of the current network state is a second state, adopting a second code rate switching strategy; the first code rate switching strategy is to select a suitable code rate according to the average throughput of the network, and the second code rate switching strategy is to select a suitable code rate according to the instantaneous throughput of the network.
It should be noted that the rate adaptive switching method provided in the embodiment of the present invention is mainly directed to DASH services, and may also be directed to other scenes that need to perform video rate switching. In all embodiments of the present invention, the DASH service is taken as an example to describe the embodiments of the present invention, and applications of other services may be similar, and the embodiments of the present invention are not described herein again. The main purpose of switching is to enable a user to dynamically select the optimal video code rate to download and play according to the self condition, so that the user experience quality is improved. Then for better adaptive selection an accurate estimate of the available bandwidth in the mobile network is needed to select a video bitrate that is suitable for playback.
The execution subject of the embodiment of the present invention may be a terminal or a server, and any entity or virtual device capable of implementing code rate adaptive switching, which is not specifically limited in the embodiment of the present invention.
In step 110, it can be understood that accurate estimation of available bandwidth in the mobile network is a key factor affecting DASH service performance, and DASH video data is first sent from the DASH server, routed and forwarded, and then reaches the base station through the gateway, and the base station allocates wireless bandwidth resources to send the video data to the terminal of the user. In the actual network data transmission process, in view of the fact that the wireless channel instability and wired link congestion coexisting scenario objectively exist in the actual network and the variation trends of the available bandwidth of the user in the two cases are different, reference may be made to fig. 2 and fig. 3, where fig. 2 is a schematic diagram of the fluctuation of the throughput under the unstable wireless channel condition provided by the embodiment of the present invention, and fig. 3 is a schematic diagram of the fluctuation of the throughput under the congested wired link condition provided by the embodiment of the present invention. In fig. 2 and 3, the abscissa is time, the ordinate is throughput, and throughput change conditions within 50 seconds of a user are counted together, and it can be seen from fig. 2 and 3 that the throughput fluctuation change frequency is high due to instability of a wireless channel, the average value of throughput is stable, and throughput is raised and lowered in a cliff manner due to congestion of a wired link, so that a network state can be actually divided into two states, and whether a current network state is caused by instability of a wireless channel or caused by congestion of a wired link is identified to determine how to perform subsequent rate switching.
In step 120, it can be understood that, in step 110, the current network state can be identified, so as to determine that the current network state is caused by the instability of the wireless channel or caused by the congestion of the wired link, in the embodiment of the present invention, the current network state is referred to as a first state caused by the instability of the wireless channel, and the current network state is referred to as a second state caused by the congestion of the wired link, so that the corresponding first code rate switching policy and the corresponding second code rate switching policy are respectively selected according to the identification result of the current network state.
Further, the first state is throughput fluctuation caused by unstable wireless link, and is characterized by persistent and stable fluctuation, high variation frequency and stable average value of throughput, so that the corresponding first code rate switching strategy only needs to select a proper video code rate according to the average throughput. It can be understood that the average throughput can smooth the past fluctuation of the network, so that the estimated bandwidth is relatively stable, and the number of rate switching and interruption of the user can be relatively reduced.
And the second state is the throughput fluctuation caused by the congestion of the wired link, and is characterized in that the throughput fluctuation is instantaneous and non-stable, the throughput of the user can generate cliff type rise and fall, and then the corresponding second code rate switching strategy needs to determine the requested video version according to the magnitude of the instantaneous throughput. It can be understood that the instantaneous throughput only reflects the network condition information nearest to the current moment, and can more accurately capture the change of the network, so that the estimated bandwidth is closer to the actual network throughput, thereby being capable of responding to the drastic change of the network in time, reducing the interruption times of users and improving the video picture quality.
The code rate self-adaptive switching method provided by the embodiment of the invention is suitable for a transmission scene of a DASH video service in a mobile network by identifying the network state and selecting a corresponding code rate switching strategy according to the characteristics of the network state, and has good performance in the aspects of average code rate, interruption characteristics and the like.
On the basis of the above embodiment, before the identifying the current network status, the method further includes:
and training a preset machine learning model based on the characteristic information of the historical network data to obtain the trained machine learning model.
Correspondingly, the identifying the current network state includes:
and identifying the current network state based on the trained machine learning model.
The identifying the current network state based on the trained machine learning model comprises the following steps:
extracting characteristic information of the real-time network data from the acquired real-time network data;
and inputting the characteristic information of the real-time network data into the trained machine learning model so as to identify the current network state according to the characteristic information of the real-time network data.
As can be seen from the above description of the embodiment, the embodiment of the present invention needs to identify the current network state to determine whether the current network conforms to the first state or the second state.
Preferably, the embodiment of the present invention provides a machine learning manner to identify the current network state, it should be noted that other manners capable of identifying the current network state are all applicable to the embodiment of the present invention, and the machine learning is good in identification effect, so the embodiment of the present invention is described as a preferred manner.
Fig. 4 is a schematic diagram illustrating network state recognition based on machine learning according to an embodiment of the present invention, and as shown in fig. 4, in an embodiment of the present invention, a preset machine learning model is trained according to feature information of historical network data, so that the trained machine learning model can effectively determine and recognize a network state. And then inputting the network data acquired in real time into the trained machine learning model, so that the trained machine learning model compares the extracted characteristic information of the real-time network data to judge whether the real-time network state belongs to the first state or the second state.
Specifically, the embodiment of the present invention is described with TCP congestion window data as an example. The embodiment of the invention obtains real-time network operation data based on an LTE DASH simulation platform, takes 1 second as a time window for characteristic extraction, sets 10000 simulation time for total, obtains 10000 pieces of data of network congestion windows, wherein the data comprises data when the network is congested and the network is normal, and marks the category of the data. And then randomly scrambling the obtained characteristic information with the label, taking three quarters of the characteristic information as a training data set, and taking one quarter of the characteristic information as a testing data set.
The pre-set machine learning model is then trained using the training data set. The machine learning model adopted by the embodiment of the invention is a random forest classification method. The random forest is evolved from the decision tree model and can be regarded as a result of a common decision of a plurality of decision trees. The method mainly comprises two stages of classifying the characteristics of network congestion window data by using a random forest method, and firstly, generating a decision tree, namely training a model by using sample data with labels. And selecting the features (mean or variance) with higher purity as the optimal division features so as to divide the first layer. And then, selecting the optimal features in the remaining features to further classify the divided sample data set, and so on until the feature value of the congestion window data is used up or the sample data can be completely separated or the purity requirement is met. And secondly, classifying the test data by using the generated model and the thought of the random forest. The random forest method can reduce the influence of overfitting possibly occurring in the decision tree algorithm on the accuracy. In the invention, original congestion window data is subjected to playback sampling to obtain a plurality of subdata sets with the same number as the original data sets, and a plurality of decision trees are generated by utilizing the subdata sets. The characteristics of the congestion window data used by these decision trees may also be randomly chosen from the original set of characteristics. And according to the output result of each decision tree, adopting a majority voting system to decide the category to which the current input belongs.
The original training data set used in the embodiment of the present invention has 7500 pieces of training data, and after sampling, a plurality of different sub data sets can be generated, and each sub data set also has 7500 pieces of data, but the sub data sets may have repeated data. And finally, when testing, adopting a majority voting system to determine the category of the current test data according to the output result of each decision tree. Fig. 5 is a schematic diagram of network state identification by a random forest method according to an embodiment of the present invention, as shown in fig. 5, assuming that a total of 10 decision trees are generated, when a characteristic value of a network congestion window is input for identification, classification results of the 10 trees are 0110010000, 0 represents a normal state of the network, 1 represents a congestion state of the network, and according to a rule of majority voting, the current network should be in a normal state.
Secondly, after the random forest model is trained, the prediction accuracy of the model is analyzed. Statistical results show that the recognition accuracy of 2500 test data reaches 98.64%, and the following results can be obtained: by utilizing the characteristic information of the network congestion window, the current network state can be accurately identified, namely, whether the current network is in the first state or the second state is judged.
On the basis of the above embodiment, the first state is a link fluctuation state caused by instability of a wireless link; correspondingly, if the identification result of the current network state is the first state, a first code rate switching strategy is adopted, and the method comprises the following steps:
if the identification result of the current network state is the first state, acquiring the average throughput of the current network in a time window;
and determining the video code rate size of switching based on the average throughput.
As can be seen from the above description of the embodiments, the embodiments of the present invention can determine whether the current network state is in the first state or the second state by identifying the current network state. The first state is a link fluctuation state caused by instability of a wireless link, and in the first state, the switching strategy adopted by the embodiment of the invention is to determine the code rate according to the average throughput.
Specifically, if the identification result determines that the current network state is in the first state, acquiring all throughput data in a time window of the current network, and obtaining the size of the average throughput in the time window, wherein the time window can be selected according to actual conditions, and then estimating the available bandwidth of the mobile network according to the size of the average throughput, and if the average throughput is larger, the available bandwidth is higher, and the corresponding video code rate can be correspondingly improved; the smaller the average throughput, the lower the available bandwidth, and the corresponding video bitrate may also be reduced correspondingly, and the determination of the specific video bitrate may be set according to the value of the average throughput, for example: setting the average throughput to correspond to a video code rate in a certain interval, and adjusting the video code rate in time when the average throughput exceeds the interval (is lower than or higher than the interval).
On the basis of the above embodiment, if a time window of the current network includes a first time interval when the network state is normal and a second time interval when the network state is abnormal, the method further includes:
acquiring the average throughput of the current network in a first time interval;
and determining the video code rate size of the switching based on the average throughput of the current network in a first time interval.
It can be understood that if the current network state is in the first state, a first rate switching strategy should be selected for switching, and the first rate switching strategy is determined according to the average throughput. But in a practical time window, the throughput data in the time window necessarily includes the data in the congestion state and the normal state during the period from the congestion state to the restoration of the network to the normal state. The throughput is usually low during congestion, and the estimated value of the overall average throughput is lowered, so that the video version is reduced, and meanwhile, the network bandwidth utilization rate is insufficient.
In view of the above situation, the embodiment of the present invention, by observing the time when the network state changes from congestion to normal, and when calculating the average throughput, only the throughput in the time interval when the network state is normal is counted, without considering the data in the whole time window, so that the influence of the data when the network is congested on the calculation of the average throughput can be eliminated, and the video version selected by the user is further improved, so that the utilization rate of the network bandwidth becomes higher.
On the basis of the above embodiment, the second state is a link fluctuation state caused by congestion of a wired link; correspondingly, if the identification result of the current network state is the second state, a second code rate switching strategy is adopted, which includes:
if the identification result of the current network state is a second state, acquiring the instantaneous throughput of the current network;
and determining the video code rate size of the switching based on the instantaneous throughput.
As can be seen from the above description of the embodiments, the embodiments of the present invention can determine whether the current network state is in the first state or the second state by identifying the current network state. The second state is a link fluctuation state caused by congestion of the wired link, and in the second state, the switching strategy adopted by the embodiment of the invention is to determine the code rate according to the instantaneous throughput.
Specifically, if the current network state is determined to be in the second state by the identification result, the instantaneous throughput of the current network at each moment is obtained, the instantaneous throughput only reflects the network condition information closest to the current moment, and the change of the network can be captured more accurately, so that the estimated bandwidth is closer to the actual network throughput. Further, the higher the instantaneous throughput is, the higher the available bandwidth of the actual network is proved to be, and the video code rate can be correspondingly improved; the lower the instantaneous throughput is, the smaller the available bandwidth of the actual network at the moment is proved, and the video code rate can be correspondingly reduced.
In order to further verify the code rate adaptive method provided by the embodiment of the invention, the embodiment of the invention carries out simulation experiments. The simulation conditions are set as follows: the method comprises the steps that 10 users walk randomly in a cell, the radius of the cell is 500 meters, the height of a base station is 10 meters, the transmitting power of the base station is 46dBm, the total number of resource blocks is 100, a resource scheduling mode is proportional fairness, a path loss model is logarithmic distance loss, a fading model is EPA, and a TCP protocol model is New Reno. On an LTE network simulation platform, the QoE performance is compared with other code rate self-adaptive schemes. Fig. 6 is a schematic diagram illustrating comparison of code rate adaptive simulation results provided in an embodiment of the present invention, wherein an AVG scheme is a scheme that always selects a code rate by adopting an average throughput, and belongs to a DASH default code rate adaptive scheme; the INST scheme is a scheme for always selecting code rate by adopting instantaneous throughput; BVR and BVR _ A are the schemes provided in the examples of the present invention; the FDASH scheme is a code rate adaptive scheme based on bandwidth estimation and terminal caching, and as shown in fig. 6, simulation results show that the scheme provided by the embodiment of the invention can greatly improve the interrupt performance and has a higher code rate (namely video quality).
Fig. 7 is a structural diagram of a code rate adaptive handover system provided in an embodiment of the present invention, and as shown in fig. 7, the system includes: an identification module 710 and a switching module 720, wherein:
the identifying module 710 is used for identifying the current network state;
the switching module 720 is configured to, if the identification result of the current network state is the first state, adopt a first code rate switching policy; if the identification result of the current network state is a second state, adopting a second code rate switching strategy; the first code rate switching strategy is to select a suitable code rate according to the average throughput of the network, and the second code rate switching strategy is to select a suitable code rate according to the instantaneous throughput of the network.
Specifically, how to perform the code rate adaptive switching through the identification module 710 and the switching module 720 can be used to implement the technical solution of the embodiment of the code rate adaptive switching method shown in fig. 1, and the implementation principle and the technical effect are similar, which are not described herein again.
The code rate self-adaptive switching method provided by the embodiment of the invention is suitable for a transmission scene of a DASH video service in a mobile network by identifying the network state and selecting a corresponding code rate switching strategy according to the characteristics of the network state, and has good performance in the aspects of average code rate, interruption characteristics and the like.
The embodiment of the invention provides code rate self-adaptive switching equipment, which comprises: at least one processor; and at least one memory communicatively coupled to the processor, wherein:
fig. 8 is a block diagram of a structure of a code rate adaptive switching device according to an embodiment of the present invention, and referring to fig. 8, the code rate adaptive switching device includes: a processor (processor)810, a communication Interface 820, a memory 830 and a bus 840, wherein the processor 810, the communication Interface 820 and the memory 830 communicate with each other via the bus 840. The processor 810 may call logic instructions in the memory 830 to perform the following method: identifying a current network state; if the identification result of the current network state is a first state, adopting a first code rate switching strategy; if the identification result of the current network state is a second state, adopting a second code rate switching strategy; the first code rate switching strategy is to select a suitable code rate according to the average throughput of the network, and the second code rate switching strategy is to select a suitable code rate according to the instantaneous throughput of the network.
An embodiment of the present invention discloses a computer program product, which includes a computer program stored on a non-transitory computer readable storage medium, the computer program including program instructions, when the program instructions are executed by a computer, the computer can execute the methods provided by the above method embodiments, for example, the method includes: identifying a current network state; if the identification result of the current network state is a first state, adopting a first code rate switching strategy; if the identification result of the current network state is a second state, adopting a second code rate switching strategy; the first code rate switching strategy is to select a suitable code rate according to the average throughput of the network, and the second code rate switching strategy is to select a suitable code rate according to the instantaneous throughput of the network.
Embodiments of the present invention provide a non-transitory computer-readable storage medium, which stores computer instructions, where the computer instructions cause the computer to perform the methods provided by the above method embodiments, for example, the methods include: identifying a current network state; if the identification result of the current network state is a first state, adopting a first code rate switching strategy; if the identification result of the current network state is a second state, adopting a second code rate switching strategy; the first code rate switching strategy is to select a suitable code rate according to the average throughput of the network, and the second code rate switching strategy is to select a suitable code rate according to the instantaneous throughput of the network.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A method for rate adaptive handover, comprising:
identifying a current network state;
if the identification result of the current network state is a first state, adopting a first code rate switching strategy; the first state is a link fluctuation state caused by wireless link instability;
if the identification result of the current network state is a second state, adopting a second code rate switching strategy; the second state is a link fluctuation state caused by wired link congestion;
the first code rate switching strategy is to select a suitable code rate according to the average throughput of the network, and the second code rate switching strategy is to select a suitable code rate according to the instantaneous throughput of the network.
2. The method of claim 1, wherein prior to said identifying a current network state, the method further comprises:
and training a preset machine learning model based on the characteristic information of the historical network data to obtain the trained machine learning model.
3. The method of claim 2, wherein the identifying a current network state comprises:
and identifying the current network state based on the trained machine learning model.
4. The method of claim 3, wherein identifying the current network state based on the trained machine learning model comprises:
extracting characteristic information of the real-time network data from the acquired real-time network data;
and inputting the characteristic information of the real-time network data into the trained machine learning model so as to identify the current network state according to the characteristic information of the real-time network data.
5. The method according to claim 1 or 4, wherein if the identification result of the current network state is the first state, the employing a first code rate switching policy includes:
if the identification result of the current network state is the first state, acquiring the average throughput of the current network in a time window;
and determining the video code rate size of switching based on the average throughput.
6. The method of claim 5, wherein if a time window of the current network includes a first time interval with normal network status and a second time interval with abnormal network status, the method further comprises:
acquiring the average throughput of the current network in a first time interval;
and determining the video code rate size of the switching based on the average throughput of the current network in a first time interval.
7. The method according to claim 1 or 4, wherein if the identification result of the current network state is the second state, the employing a second code rate switching policy includes:
if the identification result of the current network state is a second state, acquiring the instantaneous throughput of the current network;
and determining the video code rate size of the switching based on the instantaneous throughput.
8. A code rate adaptive handoff system, comprising:
the identification module is used for identifying the current network state;
the switching module is used for adopting a first code rate switching strategy if the identification result of the current network state is a first state; if the identification result of the current network state is a second state, adopting a second code rate switching strategy; wherein the first state is a link fluctuation state caused by wireless link instability; the second state is a link fluctuation state caused by wired link congestion; the first code rate switching strategy is to select a proper code rate according to the average throughput of the network, and the second code rate switching strategy is to select a proper code rate according to the instantaneous throughput of the network.
9. The code rate self-adaptive switching equipment is characterized by comprising a memory and a processor, wherein the processor and the memory are communicated with each other through a bus; the memory stores program instructions executable by the processor, the processor invoking the program instructions to perform the method of any of claims 1 to 7.
10. A non-transitory computer-readable storage medium storing computer instructions that cause a computer to perform the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810644936.6A CN108989880B (en) | 2018-06-21 | 2018-06-21 | Code rate self-adaptive switching method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810644936.6A CN108989880B (en) | 2018-06-21 | 2018-06-21 | Code rate self-adaptive switching method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108989880A CN108989880A (en) | 2018-12-11 |
| CN108989880B true CN108989880B (en) | 2020-04-14 |
Family
ID=64537972
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810644936.6A Active CN108989880B (en) | 2018-06-21 | 2018-06-21 | Code rate self-adaptive switching method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108989880B (en) |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110012324B (en) * | 2019-03-28 | 2020-10-13 | 武汉大学 | Code rate self-adaption method, WIFI camera, control device and code rate self-adaption system for embedded wireless video transmission |
| CN110992963B (en) * | 2019-12-10 | 2023-09-29 | 腾讯科技（深圳）有限公司 | Network communication method, device, computer equipment and storage medium |
| CN113141524B (en) * | 2020-01-17 | 2023-09-29 | 北京达佳互联信息技术有限公司 | Resource transmission method, device, terminal and storage medium |
| WO2023015499A1 (en) * | 2021-08-11 | 2023-02-16 | Oppo广东移动通信有限公司 | Wireless communication method and device |
| CN114390320B (en) * | 2022-02-18 | 2024-02-13 | 百果园技术(新加坡)有限公司 | Data coding rate self-adaptive adjusting method, device, equipment and storage medium |
| CN114885215B (en) * | 2022-04-28 | 2023-07-25 | 清华大学 | Training method of code rate self-adaptive model, video code rate self-adaptive method and device |
| CN116916113B (en) * | 2023-09-06 | 2023-12-22 | 联通(江苏)产业互联网有限公司 | Data stream smoothing method based on 5G video customer service |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102231898A (en) * | 2011-07-05 | 2011-11-02 | 深圳市融创天下科技股份有限公司 | Network bandwidth self-adaptive QOS (quality of service) transmission method and system and terminal device |
| CN105451099A (en) * | 2014-08-19 | 2016-03-30 | 北京大学 | Method and device for adjusting video code rate |
| CN105872615A (en) * | 2016-06-27 | 2016-08-17 | 北京邮电大学 | Method and device for adjusting video transmission code rates |
| CN107182097A (en) * | 2017-06-28 | 2017-09-19 | 努比亚技术有限公司 | A kind of method for switching network, terminal and computer-readable recording medium |
| CN107613330A (en) * | 2017-10-20 | 2018-01-19 | 清华大学 | A kind of video code rate adaptive approach |
| CN108184152A (en) * | 2018-01-03 | 2018-06-19 | 湖北大学 | A kind of DASH Transmission systems two benches client code rate selection method |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8804523B2 (en) * | 2012-06-21 | 2014-08-12 | Microsoft Corporation | Ensuring predictable and quantifiable networking performance |
| US9854282B2 (en) * | 2014-11-20 | 2017-12-26 | Alcatel Lucent | System and method for enabling network based rate determination for adaptive video streaming |
| US9812134B2 (en) * | 2015-11-03 | 2017-11-07 | T-Mobile Usa, Inc. | Using bandwidth allocation data to determine a breakdown of VoLTE calls by AMR coding mode |
-
2018
- 2018-06-21 CN CN201810644936.6A patent/CN108989880B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102231898A (en) * | 2011-07-05 | 2011-11-02 | 深圳市融创天下科技股份有限公司 | Network bandwidth self-adaptive QOS (quality of service) transmission method and system and terminal device |
| CN105451099A (en) * | 2014-08-19 | 2016-03-30 | 北京大学 | Method and device for adjusting video code rate |
| CN105872615A (en) * | 2016-06-27 | 2016-08-17 | 北京邮电大学 | Method and device for adjusting video transmission code rates |
| CN107182097A (en) * | 2017-06-28 | 2017-09-19 | 努比亚技术有限公司 | A kind of method for switching network, terminal and computer-readable recording medium |
| CN107613330A (en) * | 2017-10-20 | 2018-01-19 | 清华大学 | A kind of video code rate adaptive approach |
| CN108184152A (en) * | 2018-01-03 | 2018-06-19 | 湖北大学 | A kind of DASH Transmission systems two benches client code rate selection method |
Non-Patent Citations (1)
| Title |
|---|
| Dynamic rate adaptation for adaptive video streaming in wireless networks;Siyuan Xiang，MinXing;《Signal Processing: Image Communication》;20150928;第305-315页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108989880A (en) | 2018-12-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108989880B (en) | Code rate self-adaptive switching method and system | |
| US10582526B2 (en) | System and method for measuring end-to-end channel capacity entropy | |
| CN107787015B (en) | Network adjusting method and device based on big data | |
| CN110505105B (en) | Method, device, equipment and storage medium for controlling network service quality | |
| CN112312427A (en) | Method for optimizing network quality and electronic equipment | |
| EP2304905A1 (en) | Method and apparatus to inspect wireless traffic and mitigate packet elimination for wireless saturation avoidance | |
| WO2016026509A1 (en) | Technique for handling rules for operating a self-organizing network | |
| US20220182864A1 (en) | Detection Method, Apparatus, and System | |
| CN112868265A (en) | Network resource management method, management device, electronic device and storage medium | |
| Petrangeli et al. | Network-based dynamic prioritization of http adaptive streams to avoid video freezes | |
| JP7036225B2 (en) | Estimator, system and method and program and learning device and method and program | |
| CN111343666A (en) | Congestion adjustment method, device, equipment and medium based on LTE network | |
| CN108243506B (en) | L TE system service scheduling method and device | |
| CN110662264A (en) | Switching method, system, core network device and computer readable storage medium | |
| US20170019806A1 (en) | Method and device for adjusting network quality of service strategies | |
| JP7400042B2 (en) | Communication terminal and program | |
| CN109981656B (en) | CC protection method based on CDN node log | |
| JP6276206B2 (en) | Bandwidth allocation control device and bandwidth allocation control method | |
| CN114423049A (en) | Perception prediction method and device, electronic equipment and storage medium | |
| CN116846771A (en) | Service operation method, device, terminal and readable storage medium | |
| AT&T | CMSY8 | |
| CN114980148B (en) | Network capability determining method and device | |
| Coronado et al. | An AIFSN prediction scheme for multimedia wireless communications | |
| Kon et al. | Autonomous parameter optimization of a heterogeneous wireless network aggregation system using machine learning algorithms | |
| CN114079619A (en) | Port flow sampling method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |