CN108989880A - A kind of code rate adaptive method for switching and system - Google Patents
A kind of code rate adaptive method for switching and system Download PDFInfo
- Publication number
- CN108989880A CN108989880A CN201810644936.6A CN201810644936A CN108989880A CN 108989880 A CN108989880 A CN 108989880A CN 201810644936 A CN201810644936 A CN 201810644936A CN 108989880 A CN108989880 A CN 108989880A
- Authority
- CN
- China
- Prior art keywords
- code rate
- state
- current network
- network
- network state
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 44
- 230000003044 adaptive effect Effects 0.000 title claims abstract description 36
- 238000010801 machine learning Methods 0.000 claims description 19
- 238000012549 training Methods 0.000 claims description 13
- 238000004891 communication Methods 0.000 claims description 10
- 230000001052 transient effect Effects 0.000 claims description 7
- 230000002159 abnormal effect Effects 0.000 claims description 2
- 238000010586 diagram Methods 0.000 description 14
- 238000003066 decision tree Methods 0.000 description 10
- 238000007637 random forest analysis Methods 0.000 description 8
- 230000006978 adaptation Effects 0.000 description 6
- 238000012360 testing method Methods 0.000 description 5
- 238000004590 computer program Methods 0.000 description 4
- 238000004088 simulation Methods 0.000 description 4
- 241001269238 Data Species 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 239000000872 buffer Substances 0.000 description 2
- 230000000052 comparative effect Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 240000007594 Oryza sativa Species 0.000 description 1
- 235000007164 Oryza sativa Nutrition 0.000 description 1
- 206010044565 Tremor Diseases 0.000 description 1
- 230000001154 acute effect Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000005562 fading Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000005295 random walk Methods 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 235000009566 rice Nutrition 0.000 description 1
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 kind of code rate adaptive method for switching, comprising: identification current network state;If the recognition result of the current network state is first state, the first code rate switchover policy is used;If the recognition result of the current network state is the second state, the second code rate switchover policy is used;Wherein, the first code rate switchover policy is the code rate suitable according to the selection of the average throughput size of network, and the second code rate switchover policy is the code rate suitable according to the selection of the instantaneous throughput size of network.A kind of code rate adaptive method for switching provided in an embodiment of the present invention, by identifying network state, and pass through the corresponding code rate switchover policy of feature selecting of network state, suitable for the transmitting scene of DASH video traffic in a mobile network, average bit rate, in terms of it is with good performance.
Description
Technical field
The present embodiments relate to video traffic transmission technique field more particularly to a kind of code rate adaptive method for switching and
System.
Background technique
Universal with intelligent terminal with the development of mobile network, mobile video business has become mobile data services
Mainstream.DASH business is a kind of novel dynamic self-adapting streaming media service, and main feature is customer-centric, eventually
End has the function of that code rate is adaptive, and optimal video version can be dynamically selected according to own situation and is downloaded and broadcasts
It puts, to improve user experience quality.However, in mobile network the available bandwidth of user have the characteristics that it is unstable: on the one hand, move
Trend of the wireless channel of dynamic network because being influenced presentation dynamic change by factors such as noise, decline, interference;On the other hand,
DASH business is as data service, and wire link may be subjected to the influence of network congestion event in transmission process, causes can be used
Bandwidth is unstable.It therefore, is in a mobile network to influence the key factor of DASH service feature on the accurate estimation of available bandwidth.
Existing code rate adaptation scheme is broadly divided into three kinds: the code rate based on bandwidth estimation is adaptive, is based on terminal
The code rate adaptation scheme that the code rate of caching is adaptive and the two combines.But currently existing scheme is usually just for wireless communication
This unstable feature of road carries out code rate adaptive design, few in view of wireless channel is unstable and wire link congestion
The scene coexisted.In view of the scene in real network objective reality, and in the case of two kinds user's available bandwidth variation tendency
Difference, therefore need a kind of code rate adaptive method for switching now to solve the above problems.
Summary of the invention
To solve the above-mentioned problems, the embodiment of the present invention provides one kind and overcomes the above problem or at least be partially solved
State the code rate adaptive method for switching and system of problem.
The first aspect embodiment of the present invention provides a kind of code rate adaptive method for switching, comprising:
Identify current network state;
If the recognition result of the current network state is first state, the first code rate switchover policy is used;
If the recognition result of the current network state is the second state, the second code rate switchover policy is used;
Wherein, the first code rate switchover policy is the code rate suitable according to the selection of the average throughput size of network, institute
Stating the second code rate switchover policy is the code rate suitable according to the selection of the instantaneous throughput size of network.
The embodiment of the invention also provides a kind of adaptive switching systems of code rate for second aspect, comprising:
Identification module, for identification current network state;
Switching module is cut if the recognition result for the current network state is first state using the first code rate
Change strategy;If the recognition result of the current network state is the second state, the second code rate switchover policy is used;Wherein, institute
Stating the first code rate switchover policy is the code rate suitable according to the selection of the average throughput size of network, and second code rate switches plan
Code rate slightly suitable according to the selection of the instantaneous throughput size of network.
The embodiment of the invention provides a kind of adaptive switching equipments of code rate for the third aspect, comprising:
Processor, memory, communication interface and bus;Wherein, the processor, memory, communication interface pass through described
Bus completes mutual communication;The memory is stored with the program instruction that can be executed by the processor, the processor
Described program instruction is called to be able to carry out a kind of code rate adaptive method for switching described above.
The embodiment of the invention provides a kind of non-transient computer readable storage medium, the non-transient calculating for fourth aspect
Machine readable storage medium storing program for executing stores computer instruction, and the computer instruction makes the computer execute the above method.
A kind of code rate adaptive method for switching provided in an embodiment of the present invention by identifying network state, and passes through network
The corresponding code rate switchover policy of the feature selecting of state, suitable for the transmitting scene of DASH video traffic in a mobile network,
Average bit rate, break feature etc. are with good performance.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is this hair
Bright some embodiments for those of ordinary skill in the art without creative efforts, can be with root
Other attached drawings are obtained according to these attached drawings.
Fig. 1 is a kind of code rate adaptive method for switching flow diagram provided in an embodiment of the present invention;
Fig. 2 is throughput fluctuations schematic diagram under wireless channel instability condition provided in an embodiment of the present invention;
Fig. 3 is throughput fluctuations schematic diagram under wire link congestion condition provided in an embodiment of the present invention;
Fig. 4 is the network state identification schematic diagram provided in an embodiment of the present invention based on machine learning;
Fig. 5 is random forest method identification network state schematic diagram provided in an embodiment of the present invention;
Fig. 6 is code rate self-adapting simulation Comparative result schematic diagram provided in an embodiment of the present invention;
Fig. 7 is a kind of adaptive switching system structure chart of code rate provided in an embodiment of the present invention;
Fig. 8 is the structural block diagram of the adaptive switching equipment of code rate provided in an embodiment of the present invention.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical solution in the embodiment of the present invention is explicitly described, it is clear that described embodiment is the present invention
A part of the embodiment, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art are not having
Every other embodiment obtained under the premise of creative work is made, shall fall within the protection scope of the present invention.
Currently, the prior art when code rate adaptively switches generally can it is adaptive using the code rate based on bandwidth estimation,
The code rate adaptation scheme that code rate based on terminal buffers is adaptive and the two combines.In three kinds of schemes usually both for
The solution that this unstable feature of wireless channel proposes, but under practical application scene, in addition to wireless channel shakiness
Except fixed, wire link congestion is also to cause the principal element of unstable networks.And wireless channel is unstable under normal circumstances
It is coexisted under Same Scene with wire link congestion, then the adaptive side of switching of the code rate of the prior art in the above scenario
The effect is unsatisfactory for method, also further affects the experience of user.
In view of the above-mentioned problems, Fig. 1 is a kind of code rate adaptive method for switching flow diagram provided in an embodiment of the present invention,
As shown in Figure 1, comprising:
110, current network state is identified;
If 120, the recognition result of the current network state is first state, the first code rate switchover policy is used;If
The recognition result of the current network state is the second state, then uses the second code rate switchover policy;Wherein, first code rate
Switchover policy is the code rate suitable according to the selection of the average throughput size of network, and the second code rate switchover policy is according to net
The suitable code rate of the instantaneous throughput size selection of network.
It should be noted that code rate adaptive method for switching provided in an embodiment of the present invention is mainly in DASH business,
It can also be directed under other scenes for needing to carry out video code rate switching.In all embodiments of the invention, with DASH business
For the embodiment of the present invention is illustrated, remaining business application can be with analogy, details are not described herein for the embodiment of the present invention.It cuts
The main purpose changed is to allow users to be dynamically selected optimal video code rate according to own situation to be downloaded and play,
To improve user experience quality.So in order to preferably adaptively selected, need to carry out the available bandwidth in mobile network
Accurate estimation, so that selection is suitble to the video code rate played.
The executing subject of the embodiment of the present invention can for terminal or server and all to can be realized code rate adaptive
The entity or virtual unit of switching, the present invention is not especially limit this.
In step 110, it is to be understood that be in a mobile network to influence DASH industry on the accurate estimation of available bandwidth
The key factor for performance of being engaged in, DASH video data issues from DASH server first, by routing and forward, then reaches through gateway
Video data is issued in the terminal of user by base station by base station distribution wireless bandwidth resource.So passed in real network data
During defeated, in view of wireless channel is unstable and wire link congestion coexistence scenario objective reality in real network, and two kinds
In the case of user's available bandwidth variation tendency it is different, can refer to shown in Fig. 2 and Fig. 3, Fig. 2 is nothing provided in an embodiment of the present invention
Throughput fluctuations schematic diagram under line channel instability condition, Fig. 3 are under wire link congestion condition provided in an embodiment of the present invention
Throughput fluctuations schematic diagram.In Fig. 2 and Fig. 3, abscissa is the time, and ordinate is handling capacity, has been counted altogether in user 50 seconds
Handling capacity situation of change, it can be seen from Fig. 2 and Fig. 3 due to wireless channel it is unstable caused by throughput fluctuations variation frequency
Rate is higher, and the mean value of handling capacity is more stable, and since wire link congestion then will lead to the lifting that handling capacity generates steep cliff formula, that
Actually network state can be divided into two states, by identifying that current network state is to belong to that wireless channel is unstable to be caused
Or determine subsequent how to carry out code rate switching as caused by wire link congestion.
In the step 120, it is to be understood that in step 110, current network state can be identified, thus
Judge that current network state is caused by wireless channel is unstable or as caused by wire link congestion, then in this hair
The unstable caused referred to as first state of wireless channel will be known as the second state by bright embodiment caused by wire link congestion,
To select corresponding first code rate switchover policy and the second code rate to switch plan respectively according to the recognition result of current network state
Slightly.
Further, first state is throughput fluctuations caused by Radio Link is unstable, and feature is that duration is steady
Fluctuation, change frequency is higher, and the mean value of handling capacity is more stable, then corresponding first code rate switchover policy is then only needed according to flat
The size of equal handling capacity selects suitable video code rate.It is understood that average throughput can smooth network mistake
The fluctuation occurred is gone, so that the bandwidth estimated is relatively stable, so that user carries out the number meeting of code rate switching and interruption
It is opposite to reduce.
Second state is throughput fluctuations caused by wire link congestion, and feature is the fluctuation of instantaneity non-stationary, user
Handling capacity can generate the lifting of steep cliff formula, then corresponding second code rate switchover policy needs the size according to instantaneous throughput
To determine the video version of request.It is understood that instantaneous throughput is only reflected apart from current time nearest network-like
Condition information, can accurately capture network variation so that the bandwidth of estimation and actual network throughput are relatively, from
And the acute variation of network can be timely responded to, the interruption times of user are reduced and improves video pictures quality.
A kind of code rate adaptive method for switching provided in an embodiment of the present invention by identifying network state, and passes through network
The corresponding code rate switchover policy of the feature selecting of state, suitable for the transmitting scene of DASH video traffic in a mobile network,
Average bit rate, break feature etc. are with good performance.
On the basis of the above embodiments, before the identification current network state, the method also includes:
Characteristic information based on historical network data is trained preset machine learning model, after being trained
Machine learning model.
Correspondingly, the identification current network state, comprising:
Based on the machine learning model after the training, current network state is identified.
The machine learning model based on after training, identifies current network state, comprising:
The characteristic information of real-time network data is extracted from the real-time network data of acquisition;
In machine learning model after the characteristic information input of the real-time network data is trained, according to described real-time
The characteristic information of network data identifies current network state.
By the content of above-described embodiment it is found that the embodiment of the present invention needs to identify current network state, to judge
What current network met is first state or the second state.
Preferably, the embodiment of the invention provides a kind of modes of machine learning to identify to current network state,
It should be noted that remaining can identify that the mode of current network state may be applicable to the embodiment of the present invention, machine learning by
It is preferable in recognition effect, so the embodiment of the present invention is illustrated the embodiment of the present invention as preferred embodiment.
Fig. 4 is the network state identification schematic diagram provided in an embodiment of the present invention based on machine learning, as shown in figure 4, this
Inventive embodiments can be trained preset machine learning model according to the characteristic information of historical network data first, so that instruction
Machine learning model after white silk effectively can be judged and be identified to network state.And then it is the network data obtained in real time is defeated
In machine learning model after entering training, so that the machine learning model after training passes through the spy for the real-time network data that will be extracted
Reference breath carries out aspect ratio pair, to judge that real-time network state belongs to first state or the second state.
Specifically, the embodiment of the present invention is illustrated the embodiment of the present invention with TCP congestion window data instance.The present invention
Embodiment is based on LTE DASH emulation platform acquisition network real-time running data and is set altogether using 1 second time window as feature extraction
Fixed 10000 seconds simulation times, obtain the data of 10000 network congestion windows, when including network congestion and network just
Data when often, and the classification of data is marked.Then, upset the characteristic information that gained has label at random, take therein
3/4ths are used as training dataset, and a quarter is as test data set.
Next using the preset machine learning model of training dataset training.Machine learning used in the embodiment of the present invention
Model is random forest classification method.Random forest can regard multiple decision trees as and determine jointly from decision-tree model evolution
The result of plan.Classification, which is carried out, using feature of the random forest method to network congestion window data is broadly divided into two stages, it is first
Decision tree is generated before this, that is, utilizes the sample data training pattern of tape label.It chooses the higher feature of purity (mean value or variance),
As optimal dividing feature, first layer is divided with this.Then after needing to choose the optimal characteristics in residue character again to division
Sample data set is further classified, and so on, until the characteristic value of congestion window data has used or sample data
Until can dividing completely or reach purity requirement.Followed by using the thought of the model and random forest that generate to test number
According to classifying.Random forest method can reduce influence of the over-fitting being likely to occur in decision Tree algorithms to accuracy.?
In the present invention, by carrying out sampling with replacement to original congestion window data, obtain multiple identical as raw data set quantity
Sub Data Set, and generate more decision trees using these Sub Data Sets.Congestion window data used in these decision trees
Feature can also be concentrated from primitive character and be randomly selected.According to the output of every decision tree as a result, majority voting system is taken to determine
Current input generic.
Original training data collection used in the embodiment of the present invention has 7500 training datas, after sampling with replacement,
It can produce multiple and different Sub Data Sets, and each Sub Data Set also has 7500 datas, but can in Sub Data Set
Duplicate data can be will appear.Then, decision tree is generated respectively using these Sub Data Sets, finally when testing, according to
Each decision tree exports as a result, the generic for taking majority voting system to determine current test data.Fig. 5 is implementation of the present invention
The random forest method that example provides identifies network state schematic diagram, as shown in fig. 5, it is assumed that 10 decision trees are generated altogether, when defeated
When entering the characteristic value of network congestion window and being identified, the classification results of this 10 trees are successively 0110010000,0 to represent network
Normal condition, 1 represents network congestion condition, and according to the rule of majority voting system, current network should be at normal condition.
Secondly, analyzing after the complete Random Forest model of training the prediction accuracy of the model.Through counting, 2500
The test data identification accuracy of item reaches 98.64%, can obtain from the result:, can using the characteristic information of network congestion window
Relatively accurately to identify current network state, that is, judge that current network is in first state or the second state.
On the basis of the above embodiments, the first state be as Radio Link it is unstable caused by link fluctuations shape
State;If using the first code rate switchover policy correspondingly, the recognition result of the current network state is first state,
Include:
If the recognition result of the current network state is first state, obtain in one time window of current network
Average throughput;
Based on the average throughput, the video code rate size of switching is determined.
By the content of above-described embodiment it is found that the embodiment of the present invention can be judged currently by identification current network state
Network state is in first state or the second state.Wherein, first state be as Radio Link it is unstable caused by link
Fluctuation status, in the first state, the switchover policy that the embodiment of the present invention is taken are carried out according to the size of average throughput
Code rate determines.
Specifically, if recognition result is determined as that current network state is in first state, when obtaining current network one
Between all throughput datas in window, and acquire the size of the average throughput in the time window, time window can basis
Actual conditions are chosen, and then the available bandwidth of the size estimation mobile network according to average throughput, average throughput are got over
Big then available bandwidth is higher, corresponding video code rate can also be promoted accordingly;The smaller then available bandwidth of average throughput is lower, phase
The video code rate answered can also be reduced accordingly, and the determination of specific video code rate can be configured according to the value of average throughput,
Such as: setting average throughput corresponds to a kind of video code rate in some section, when being more than the section (being below or above), and
The adjustment of Shi Jinhang video code rate.
On the basis of the above embodiments, if when normal including network state first in one time window of current network
Between section and abnormal second time interval of network state, then the method also includes:
Obtain average throughput of the current network in first time section;
Average throughput based on the current network in first time section determines the video code rate size of switching.
It is understood that if current network state is in first state, then the first code rate switchover policy should be selected
It switches over, and is to carry out what video code rate determined according to the size of average throughput in the first code rate switchover policy.But
In an actual time window, in handling capacity number of the network from congestion state to recovery normal this period, in time window
According to the data for necessarily including congestion state and normal condition.Handling capacity is usually lower when congestion, can drag down ensemble average handling capacity
Estimated value, thereby reduce video version, while but also network bandwidth utilization factor is insufficient.
For said circumstances, at the time of the embodiment of the present invention is transformed into normal by congestion by observing network state, counting
When calculating average throughput, handling capacity in the normal time interval of statistics network state, without considering in overall time window
Data so as to weed out the influence that data when network congestion calculate average throughput, and then promote user's selection
Video version, so that the utilization rate of network bandwidth becomes higher.
On the basis of the above embodiments, second state is the link fluctuations state as caused by wire link congestion;
If using the second code rate switchover policy, packet correspondingly, the recognition result of the current network state is the second state
It includes:
If the recognition result of the current network state is the second state, the instantaneous throughput of current network is obtained;
Based on the instantaneous throughput, the video code rate size of switching is determined.
By the content of above-described embodiment it is found that the embodiment of the present invention can be judged currently by identification current network state
Network state is in first state or the second state.Wherein, the second state is the link wave as caused by wire link congestion
Dynamic state, in the second condition, the switchover policy that the embodiment of the present invention is taken is to carry out code according to the size of instantaneous throughput
Rate determines.
Specifically, obtaining current network per a period of time if recognition result is determined as that current network state is in the second state
The instantaneous throughput at quarter, instantaneous throughput only reflect the Network status information nearest apart from current time, can be accurately
The variation of capture network, so that the bandwidth of estimation and actual network throughput are relatively.Further, instantaneous throughput is got over
Available bandwidth is larger at this time for high so proof real network, can accordingly promote video code rate;The instantaneous throughput the low so to prove
Available bandwidth is smaller at this time for real network, can accordingly reduce video code rate.
In order to further verify code rate adaptive approach provided in an embodiment of the present invention, the embodiment of the present invention is imitated
True experiment.Simulated conditions setting are as follows: set 10 user's random walks in cell, radius of society is 500 meters, and base station height is 10
Rice, base station transmitting power 46dBm, resource block sum are 100, and scheduling of resource mode is that ratio is fair, and path loss model is
Logarithm distance loss, fading model EPA, Transmission Control Protocol model are New Reno.It, will be of the invention on LTE network emulation platform
It suggests plans and has carried out the comparison of QoE performance with other several code rate adaptation schemes.Fig. 6 is code provided in an embodiment of the present invention
Rate self-adapting simulation Comparative result schematic diagram, wherein AVG scheme is the side for taking average throughput to carry out code rate selection always
Case belongs to the default code rate adaptation scheme of DASH;INST scheme is the side for taking instantaneous throughput to carry out code rate selection always
Case;BVR and BVR_A is scheme provided by the embodiment of the present invention;FDASH scheme is based on bandwidth estimation and terminal buffers
Code rate adaptation scheme, as shown in fig. 6, simulation result shows that scheme provided in an embodiment of the present invention can substantially improve interruptibility
Can, while code rate (i.e. video quality) also with higher.
Fig. 7 is a kind of adaptive switching system structure chart of code rate provided in an embodiment of the present invention, as shown in fig. 7, the system
System includes: identification module 710 and switching module 720, in which:
The current network state for identification of identification module 710;
If switching module 720 is first state for the recognition result of the current network state, the first code rate is used
Switchover policy;If the recognition result of the current network state is the second state, the second code rate switchover policy is used;Wherein,
The first code rate switchover policy is the code rate suitable according to the selection of the average throughput size of network, the second code rate switching
Strategy is the code rate suitable according to the selection of the instantaneous throughput size of network.
Specific how adaptively to be switched by identification module 710 and switching module 720 to code rate can be used for executing Fig. 1
Shown in code rate adaptive method for switching embodiment technical solution, it is similar that the realization principle and technical effect are similar, no longer superfluous herein
It states.
A kind of code rate adaptive method for switching provided in an embodiment of the present invention by identifying network state, and passes through network
The corresponding code rate switchover policy of the feature selecting of state, suitable for the transmitting scene of DASH video traffic in a mobile network,
Average bit rate, break feature etc. are with good performance.
The embodiment of the present invention provides a kind of adaptive switching equipment of code rate, comprising: at least one processor;And with it is described
At least one processor of processor communication connection, in which:
Fig. 8 is the structural block diagram of the adaptive switching equipment of code rate provided in an embodiment of the present invention, referring to Fig. 8, the code rate
Adaptive switching equipment, comprising: processor (processor) 810, communication interface (Communications Interface)
820, memory (memory) 830 and bus 840, wherein processor 810, communication interface 820, memory 830 pass through bus
840 complete mutual communication.Processor 810 can call the logical order in memory 830, to execute following method: knowing
Other current network state;If the recognition result of the current network state is first state, the first code rate switchover policy is used;
If the recognition result of the current network state is the second state, the second code rate switchover policy is used;Wherein, described first yard
Rate switchover policy is that suitable code rate is selected according to the average throughput size of network, according to the second code rate switchover policy
The suitable code rate of the instantaneous throughput size selection of network.
The embodiment of the present invention discloses a kind of computer program product, and the computer program product is non-transient including being stored in
Computer program on computer readable storage medium, the computer program include program instruction, when described program instructs quilt
When computer executes, computer is able to carry out method provided by above-mentioned each method embodiment, for example, identification current network
State;If the recognition result of the current network state is first state, the first code rate switchover policy is used;If described current
The recognition result of network state is the second state, then uses the second code rate switchover policy;Wherein, the first code rate switchover policy
For the code rate suitable according to the selection of the average throughput size of network, the second code rate switchover policy is according to the instantaneous of network
The suitable code rate of handling capacity size selection.
The embodiment of the present invention provides a kind of non-transient computer readable storage medium, the non-transient computer readable storage
Medium storing computer instruction, the computer instruction make the computer execute side provided by above-mentioned each method embodiment
Method, for example, identification current network state;If the recognition result of the current network state is first state, using the
One code rate switchover policy;If the recognition result of the current network state is the second state, the second code rate switchover policy is used;
Wherein, the first code rate switchover policy is the code rate suitable according to the selection of the average throughput size of network, the second code
Rate switchover policy is the code rate suitable according to the selection of the instantaneous throughput size of network.
Through the above description of the embodiments, those skilled in the art can be understood that each embodiment can
It realizes by means of software and necessary general hardware platform, naturally it is also possible to pass through hardware.Based on this understanding, on
Stating technical solution, substantially the part that contributes to existing technology can be embodied in the form of software products in other words, should
Computer software product may be stored in a computer readable storage medium, such as ROM/RAM, magnetic disk, CD, including several fingers
It enables and using so that a computer equipment (can be personal computer, server or the network equipment etc.) executes each implementation
Method described in certain parts of example or embodiment.
Finally, it should be noted that the above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations;Although
Present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that: it still may be used
To modify the technical solutions described in the foregoing embodiments or equivalent replacement of some of the technical features;
And these are modified or replaceed, technical solution of various embodiments of the present invention that it does not separate the essence of the corresponding technical solution spirit and
Range.
Claims (10)
1. a kind of code rate adaptive method for switching characterized by comprising
Identify current network state;
If the recognition result of the current network state is first state, the first code rate switchover policy is used;
If the recognition result of the current network state is the second state, the second code rate switchover policy is used;
Wherein, the first code rate switchover policy is the code rate suitable according to the selection of the average throughput size of network, described the
Two code rate switchover policy are the code rate suitable according to the selection of the instantaneous throughput size of network.
2. the method according to claim 1, wherein the method is also before the identification current network state
Include:
Characteristic information based on historical network data, is trained preset machine learning model, the machine after being trained
Learning model.
3. according to the method described in claim 2, it is characterized in that, the identification current network state, comprising:
Based on the machine learning model after the training, current network state is identified.
4. according to the method described in claim 3, it is characterized in that, the machine learning model based on after training, to current
Network state is identified, comprising:
The characteristic information of real-time network data is extracted from the real-time network data of acquisition;
In machine learning model after the characteristic information input of the real-time network data is trained, according to the real-time network
The characteristic information of data identifies current network state.
5. method according to claim 1 or 4, which is characterized in that the first state is to be made by Radio Link is unstable
At link fluctuations state;If using first correspondingly, the recognition result of the current network state is first state
Code rate switchover policy, comprising:
If the recognition result of the current network state is first state, being averaged in one time window of current network is obtained
Handling capacity;
Based on the average throughput, the video code rate size of switching is determined.
6. according to the method described in claim 5, it is characterized in that, if in one time window of current network including network state
Normal first time section and abnormal second time interval of network state, then the method also includes:
Obtain average throughput of the current network in first time section;
Average throughput based on the current network in first time section determines the video code rate size of switching.
7. method according to claim 1 or 4, which is characterized in that second state is to be caused by wire link congestion
Link fluctuations state;If using second code correspondingly, the recognition result of the current network state is the second state
Rate switchover policy, comprising:
If the recognition result of the current network state is the second state, the instantaneous throughput of current network is obtained;
Based on the instantaneous throughput, the video code rate size of switching is determined.
8. a kind of adaptive switching system of code rate characterized by comprising
Identification module, for identification current network state;
Switching module switches plan using the first code rate if the recognition result for the current network state is first state
Slightly;If the recognition result of the current network state is the second state, the second code rate switchover policy is used;Wherein, described
One code rate switchover policy is the code rate suitable according to the selection of the average throughput size of network, and the second code rate switchover policy is
According to the code rate that the selection of the instantaneous throughput size of network is suitable.
9. a kind of adaptive switching equipment of code rate, which is characterized in that including memory and processor, the processor and described deposit
Reservoir completes mutual communication by bus;The memory is stored with the program instruction that can be executed by the processor, institute
Stating processor calls described program instruction to be able to carry out the method as described in claim 1 to 7 is any.
10. a kind of non-transient computer readable storage medium, which is characterized in that the non-transient computer readable storage medium is deposited
Computer instruction is stored up, the computer instruction makes the computer execute the method as described in claim 1 to 7 is any.
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 true CN108989880A (en) | 2018-12-11 |
CN108989880B 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) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110012324A (en) * | 2019-03-28 | 2019-07-12 | 武汉大学 | A kind of the code rate adaptive approach and system of embedded radio transmission of video |
CN110992963A (en) * | 2019-12-10 | 2020-04-10 | 腾讯科技(深圳)有限公司 | Network communication method, device, computer equipment and storage medium |
CN113141524A (en) * | 2020-01-17 | 2021-07-20 | 北京达佳互联信息技术有限公司 | Resource transmission method, device, terminal and storage medium |
CN114885215A (en) * | 2022-04-28 | 2022-08-09 | 清华大学 | Method and device for training code rate adaptive model and method and device for video code rate adaptation |
WO2023015499A1 (en) * | 2021-08-11 | 2023-02-16 | Oppo广东移动通信有限公司 | Wireless communication method and device |
WO2023155747A1 (en) * | 2022-02-18 | 2023-08-24 | 百果园技术(新加坡)有限公司 | Data coding bitrate adaptive adjustment method, apparatus and device, and storage medium |
CN116916113A (en) * | 2023-09-06 | 2023-10-20 | 联通(江苏)产业互联网有限公司 | Data stream smoothing method based on 5G video customer service |
Citations (9)
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 |
US20160150255A1 (en) * | 2014-11-20 | 2016-05-26 | Alcatel Lucent | System and method for enabling network based rate determination for adaptive video streaming |
CN105872615A (en) * | 2016-06-27 | 2016-08-17 | 北京邮电大学 | Method and device for adjusting video transmission code rates |
US20170111278A1 (en) * | 2012-06-21 | 2017-04-20 | Microsoft Technology Licensing, Llc | Ensuring predictable and quantifiable networking performance |
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 |
US20180047398A1 (en) * | 2015-11-03 | 2018-02-15 | T-Mobile Usa, Inc. | Using bandwidth allocation data to determine a breakdown of volte calls by amr coding mode |
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 |
-
2018
- 2018-06-21 CN CN201810644936.6A patent/CN108989880B/en active Active
Patent Citations (9)
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 |
US20170111278A1 (en) * | 2012-06-21 | 2017-04-20 | Microsoft Technology Licensing, Llc | Ensuring predictable and quantifiable networking performance |
CN105451099A (en) * | 2014-08-19 | 2016-03-30 | 北京大学 | Method and device for adjusting video code rate |
US20160150255A1 (en) * | 2014-11-20 | 2016-05-26 | Alcatel Lucent | System and method for enabling network based rate determination for adaptive video streaming |
US20180047398A1 (en) * | 2015-11-03 | 2018-02-15 | T-Mobile Usa, Inc. | Using bandwidth allocation data to determine a breakdown of volte calls by amr coding mode |
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 |
---|
SIYUAN XIANG,MINXING: "Dynamic rate adaptation for adaptive video streaming in wireless networks", 《SIGNAL PROCESSING: IMAGE COMMUNICATION》 * |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110012324A (en) * | 2019-03-28 | 2019-07-12 | 武汉大学 | A kind of the code rate adaptive approach and system of embedded radio transmission of video |
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 |
CN110992963A (en) * | 2019-12-10 | 2020-04-10 | 腾讯科技(深圳)有限公司 | Network communication method, device, computer equipment and storage medium |
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 |
CN113141524A (en) * | 2020-01-17 | 2021-07-20 | 北京达佳互联信息技术有限公司 | Resource transmission method, device, terminal 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 |
WO2023155747A1 (en) * | 2022-02-18 | 2023-08-24 | 百果园技术(新加坡)有限公司 | Data coding bitrate adaptive adjustment method, apparatus and device, and storage medium |
CN114885215A (en) * | 2022-04-28 | 2022-08-09 | 清华大学 | Method and device for training code rate adaptive model and method and device for video code rate adaptation |
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 |
CN116916113A (en) * | 2023-09-06 | 2023-10-20 | 联通(江苏)产业互联网有限公司 | Data stream smoothing method based on 5G video customer service |
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 |
Also Published As
Publication number | Publication date |
---|---|
CN108989880B (en) | 2020-04-14 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108989880A (en) | A kind of code rate adaptive method for switching and system | |
CN108259367B (en) | Service-aware flow strategy customization method based on software defined network | |
CN110365503B (en) | Index determination method and related equipment thereof | |
CN105791151B (en) | A kind of dynamic flow control method and device | |
CN112887217B (en) | Control data packet sending method, model training method, device and system | |
Quan et al. | Cybertwin-driven DRL-based adaptive transmission scheduling for software defined vehicular networks | |
CN109699089A (en) | A kind of channel access method and device | |
CN113038187A (en) | Practical network bandwidth allocation method with fair video experience quality | |
US11558769B2 (en) | Estimating apparatus, system, method, and computer-readable medium, and learning apparatus, method, and computer-readable medium | |
CN109348486B (en) | Heterogeneous wireless network resource allocation method | |
WO2018194888A1 (en) | Dynamic computer network classification using machine learning | |
CN110535705B (en) | Service function chain construction method capable of adapting to user time delay requirement | |
CN115580568B (en) | Method and system for realizing network service quality guarantee based on IPv6 flow label | |
CN110442786A (en) | A kind of method, apparatus, equipment and the storage medium of prompt information push | |
CN114423049A (en) | Perception prediction method and device, electronic equipment and storage medium | |
ur Rahman et al. | QoE optimization for HTTP adaptive streaming: Performance evaluation of MEC-assisted and client-based methods | |
Kon et al. | Autonomous parameter optimization of a heterogeneous wireless network aggregation system using machine learning algorithms | |
Coronado et al. | An AIFSN prediction scheme for multimedia wireless communications | |
CN105827547B (en) | Stream is transmitted the stream scheduling method of time in a kind of reduction data center network | |
US20240080706A1 (en) | End-to-end wi-fi optimization | |
CN117880605B (en) | Short message video quick playing method and system based on 5G technology | |
CN113206782B (en) | Communication method and device for wireless network intelligent control platform and home edge gateway | |
CN109685101A (en) | A kind of adaptive acquisition method of multidimensional data and system | |
CN117114113B (en) | Collaborative reasoning acceleration method based on queuing theory | |
KR102408248B1 (en) | Diagnostic system for performing diagnostics of network through diagnostic packet matching to service type |
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 |