CN105338372B - A kind of adaptive video crossfire code-transferring method applied to game live streaming platform - Google Patents
A kind of adaptive video crossfire code-transferring method applied to game live streaming platform Download PDFInfo
- Publication number
- CN105338372B CN105338372B CN201510736948.8A CN201510736948A CN105338372B CN 105338372 B CN105338372 B CN 105338372B CN 201510736948 A CN201510736948 A CN 201510736948A CN 105338372 B CN105338372 B CN 105338372B
- Authority
- CN
- China
- Prior art keywords
- transcoding
- user
- game
- live
- version
- 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
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]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/23—Processing of content or additional data; Elementary server operations; Server middleware
- H04N21/234—Processing of video elementary streams, e.g. splicing of video streams, manipulating MPEG-4 scene graphs
- H04N21/2343—Processing of video elementary streams, e.g. splicing of video streams, manipulating MPEG-4 scene graphs involving reformatting operations of video signals for distribution or compliance with end-user requests or end-user device requirements
- H04N21/234309—Processing of video elementary streams, e.g. splicing of video streams, manipulating MPEG-4 scene graphs involving reformatting operations of video signals for distribution or compliance with end-user requests or end-user device requirements by transcoding between formats or standards, e.g. from MPEG-2 to MPEG-4 or from Quicktime to Realvideo
-
- 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]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
- H04N21/254—Management at additional data server, e.g. shopping server, rights management server
- H04N21/2543—Billing, e.g. for subscription services
-
- 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]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
- H04N21/262—Content or additional data distribution scheduling, e.g. sending additional data at off-peak times, updating software modules, calculating the carousel transmission frequency, delaying a video stream transmission, generating play-lists
- H04N21/26208—Content or additional data distribution scheduling, e.g. sending additional data at off-peak times, updating software modules, calculating the carousel transmission frequency, delaying a video stream transmission, generating play-lists the scheduling operation being performed under constraints
- H04N21/26216—Content or additional data distribution scheduling, e.g. sending additional data at off-peak times, updating software modules, calculating the carousel transmission frequency, delaying a video stream transmission, generating play-lists the scheduling operation being performed under constraints involving the channel capacity, e.g. network bandwidth
-
- 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
- H04N21/47—End-user applications
- H04N21/478—Supplemental services, e.g. displaying phone caller identification, shopping application
- H04N21/4781—Games
Abstract
The present invention discloses a kind of adaptive video crossfire code-transferring method applied to game live streaming platform, comprising: the game live streaming platform cycle of operation is cut into several periods；Within each period, the status information in platform is updated；Go out transcoding Resource Allocation Formula according to current state information decision, constraint condition of the program within the cycle of operation is: minimizing the costs of services of game direct broadcast service provider, while maximizing the QoE summation of user；Transcoding Resource Allocation Formula is used for current live stream.The present invention constructs the definition of user's QoE model, and the present invention provides unified QoE model for different type of play, be the foundation stone of user resources allocation algorithm of the present invention by introducing the factor of type of play.
Description
Technical field
The present invention relates to game live streamings and cloud computing resources management domain, and in particular to it is a kind of applied to game live streaming from
Adapt to stream resource allocation methods.
Background technique
Video-game originate from mid-twentieth century, earliest video-game be Thomas T.Goldsmith Jr. and
Cathode-ray tube entertainment device (the Cathode Ray Tube Amusement that Estle Ray Mann is invented in nineteen forty-seven
Device).It is developed so far, video-game has become one of main entertainment way of people.With network technology and Streaming Media
The development of technology people are no longer content with oneself playing game, and thirsts for the game experience for sharing oneself with other people, therefore game is straight
It broadcasts and comes into being.Service provider provides game live streaming platform (such as bucket fish) and player carries out in real time live play
Live streaming, spectators can carry out online viewing by webpage or software and mutually exchange, to build a kind of novel game body
It tests.The game live streaming platform of current domestic mainstream has: bucket fish, protruding canine teeth and war flag etc..External has Twitch, Ustream,
Dailymotion。
Game direct broadcast service provider often uses adaptive crossfire to provide better user experience (QoE)
(ABS) technology is to adapt to the network environment of different terminal processing capacity and dynamic change.So service provider is not only real
When carry out transmission of video, also video stream transcoding at different versions (such as different code rate versions of same video).It passes
The mode of system is to pre-define seldom several versions (such as smooth, standard and high definition) to select for user, cannot thus be had
Effect ground adapts to the Network status of access device (such as computer, set-top box and mobile phone) and dynamic change of user's high isomerism.And
If only only simply increasing version quantity, computing cost brought by transcoding will be difficult to bear, especially for picture
Game is broadcast live for this service for possessing thousands of while online direct broadcast band.One relatively good solution is to utilize
The flexible resource of cloud computing platform supplies service.Service provider can dynamically adjust according to the real time status information of live streaming platform
Its whole transcoding strategy reduces costs of services to adapt to the live streaming user and viewing user of height change.
In conclusion from game direct broadcast service provider angle, in order to minimize costs of services (transcoding expense), together
When guarantee good user experience, game live streaming platform needs to design the shape that a kind of strategy carrys out according to live streaming user and watch user
State information carries out resource allocation in real time, game direct broadcast service provider is provided with the smallest expense as well as possible
User experience.
K.Pires and G.Simon,“DASH in Twitch:Adaptive Bitrate Streaming in
Live Game Streaming Platforms, " In ACM VideoNext Conext Workshop, 2014. its basis are directly
The status information for broadcasting platform proposes two kinds of simple online transcoding strategies (on-the-fly and at-startup), is guaranteeing
In the case that most spectators are satisfied, the video flowing of the video flowing of preferential transcoding hot topic or popular live streaming person reduce simultaneously
Bandwidth and computing cost.Both transcoding strategies are fairly simple, but not fine enough, and there are also very big room for improvement, the choosings of threshold value
Excessively subjectivity is selected, and the version sets of transcoding are also fewer.
R.Apricio-Pardo,K.Pires,A.Blanc,and G.Simon,“Transcoding Live
Adaptive Video Streams at a Massive Scale in the Cloud,”In Proc.ACM
How Multimedia Systems Conference, 2015. papers discuss in given costs of services (transcoding expense)
Under, the service quality of user is maximized, proposes a kind of heuritic approach based on budget allocation, i.e., according to the temperature of video flowing
It allocates transcoding resource in advance, preferentially selects QoE to improve fast version further according to the status information of each video flowing, until resource
It uses up.In the art, the effect of subsequent heuritic approach will be directly affected by how allocating transcoding resource in advance, and not had
Consider the tradeoff between price factor and user experience quality.
Z.Wang,L.F.Sun,C.Wu,W.W.Zhu,and S.Q.Yang,“Joint Online Transcoding
and Geo-distributed Delivery for Dynamic Adaptive Streaming,”In Proc.IEEE
INFOCOM, 2014. document take video code conversion and video distribution into consideration, according to user to server preference degree kimonos
Device be engaged in the preference degree of version, proposes a kind of online transcoding and Task Assigned Policy, minimizing costs of services, (bandwidth is opened
Pin and transcoding expense), maximize user experience quality.The heuristic strategies that the technology uses in transcoding strategy, do not account for
Influencing each other between the same video clip difference code rate version selection, and be based under CDN framework.
F.Chen,C.Zhang,F.Wang,and J.C.Liu,“Crowdsourced Live Streaming over
The Cloud, " In Proc.IEEE INFOCOM, 2015., this document propose the Dynamic Renting strategy of cloud resource, pass through clothes
The mode of business migration, minimizes costs of services.The technology only provides the Dynamic Renting strategy of cloud resource, but there is no with regard to how
It distributes transcoding resource and proposes a specific solution.
Summary of the invention
For overcome the deficiencies in the prior art, the present invention proposes a kind of adaptive video string applied to game live streaming platform
Code-transferring method is flowed, the decision of user resources distribution can dynamically be made according to limited system status information using this method,
It reduces the costs of services of game live streaming platform and improves the QoE of user.
To achieve the goals above, the technical solution of the present invention is as follows:
A kind of adaptive video crossfire code-transferring method applied to game live streaming platform,
(S101) the game live streaming platform cycle of operation is cut into several periods；
(S102) within each period, the status information in platform is updated；
(S103) transcoding Resource Allocation Formula, constraint of the program within the cycle of operation are gone out according to current state information decision
Condition is: minimizing the costs of services of game direct broadcast service provider, while maximizing the QoE summation of user；
(S104) transcoding resource allocation is carried out to current live stream (video streaming) based on transcoding Resource Allocation Formula；
User QoE model is constructed, in game live streaming platform, QoE index has measured user to the satisfaction of service, is
Measure one of most important index of system, specific building mode are as follows:
QoE index relevant to type of play is defined, i.e. the version of institute's transcoding must be basic not less than needed for this game
Release requirement, the basic version, which represents, smooth can watch lowest bit rate size and lowest resolution required for game is broadcast live
Size；
Lb(G(i))≤vb≤ib∧Lr(G(i))≤vr≤ir
Wherein, i represents live stream, and V (i) represents the corresponding candidate transcoding collection of live stream i, and G (i) represents live stream i game
Type, Lb(g) and Lr(g) basic bit rate needed for respectively representing g game and base resolution, vb、vrRespectively represent transcoding version
Bit rate and resolution ratio, ibAnd irRespectively represent the original code rate and original resolution of live stream i.
The global opposite satisfaction Q of definition:
Wherein, I represents the set of current live stream, UiRepresent user's set of viewing live stream i, AiIt represents to live stream i
The transcoding strategy of applicationIt represents system and transcoding strategy A is being taken to live stream iiWhen give
The highest version (not higher than the highest version of user bandwidth and resolution ratio) of user u, expected (i, u), which represents user u, to wish
Obtain the version of live stream i, the version that the version and user bandwidth and resolution ratio match；The value range of Q between 0~1,
It is the major criterion for measuring whole user satisfaction, shows that user is more satisfied more greatly；
Costs of services model is constructed, for different data centers, since the geographical location of distribution is different, transcoding valence
Lattice are not also identical, and as time change fluctuates, and game direct broadcast service provider wishes to reduce transcoding bring expense as far as possible
Ctran；
Wherein,It indicates to carry out the unit price of transcoding, w in website jjThe task amount that website j needs transcoding is represented, M is indicated
The set of the different websites of transcoding service is provided.
In order to which balancing user is to the satisfaction of service quality and the costs of services of system, following linear combination letter is defined
Number F:
Wherein, p and q respectively represents service fee weight and user satisfaction weight, and Budget represents the pre- of system transcoding
It calculates, Ctran≤Budget；Transcoding expense CtranLower, user satisfaction Q is higher, and corresponding F value is with regard to smaller.
Preferably, the status information includes the number of current live stream, the type of play of each live stream, image quality parameter
And the number of users of viewing, the bandwidth distribution of spectators and the unit transcoding expense of data center.
Preferably, the specific implementation that transcoding Resource Allocation Formula is gone out according to current state information decision are as follows: adopt
With online heuristic strategies, can expand under large scale system；
It is defined as follows heuristic function:
Wherein,It represents for live stream i in transcoding strategy AiIn the case where reselection version v performance evaluation, c (i,
V) it represents and live stream i is transcoded into costs of services required for version v, it is related with the unit costs of website of transcoding are carried out；It is bigger, show that the priority of the v version of live stream i wants high, i.e., higher user quality experience is obtained with smaller cost；
By all versions to be transcoded according to benefit valueDescending sort successively selects transcoding version from front to back.
A kind of application of the adaptive video crossfire code-transferring method, comprising:
S1. user and central server communication is broadcast live, carries out authentication and login, and it is straight to set live streaming parameter progress
It broadcasts；Central server distributes streaming media server for it；
S2. live streaming user directly uploads game video to the streaming media server of distribution；Streaming media server stores user
Live stream and under the control of central server, distribute transcoding resource, generate the video of different editions, the cloud then sent
End；The central server distributes transcoding using adaptive video crossfire code-transferring method control live stream；
S3. distribute game video to viewing user using cloud resource；Spectators can watch game by webpage or client
Live streaming, and online interaction.
Compared with prior art, the invention has the benefit that
Customized QoE model, the present invention provide unification by introducing the factor of type of play, for different type of play
QoE model, be the basis realizing user resources of the present invention and distributing.The present invention is based on unified QoE models, according to limited system
System status information, dynamically makes the decision of user resources distribution, and the costs of services for reducing game live streaming platform simultaneously improves user
QoE.
Detailed description of the invention
Fig. 1 is the game live streaming paralell composition that the present invention uses.
Fig. 2 is transcoding resource allocation algorithm flow chart.
Specific embodiment
The present invention will be further described with reference to the accompanying drawing, but embodiments of the present invention are not limited to this.
Optimize user service strategy in order to make full use of cloud resource for game direct broadcast service provider, meeting user
On the basis of Quality of experience, operation cost is further decreased, the invention proposes the adaptive strings in a kind of game live streaming platform
Circulate code-resource distribution method.Using adaptive Video Streaming, this method fully considers the side such as user demand and resource constraint
Face factor reasonably selects Online Video transcoding version, provides good viewing experience for user, cut operating costs.The present invention
By establishing user QoE model and platform cost model, it is based on cloud computing service platform, is designed based on adaptive Video Streaming
Online transcoding resource allocation optimization method.
Basic fundamental of the invention includes: game live streaming platform architecture, user QoE model, costs of services model, resource point
With algorithm.
Platform architecture is broadcast live in game
The present invention considers that game live streaming platform architecture scene is as shown in Figure 1.User is broadcast live from different regions, and can
According to the game video of the hobby of oneself and bandwidth conditions live streaming different type, different editions (code rate and resolution ratio).It is different
Requirement of the game of type for video is different (needing higher code rate for first person shooting game).Spectators can lead to
Cross the favorite game live streaming of peripheral hardware access internet viewing oneself.
Firstly, live streaming user and central server communication, carry out authentication and login, and sets live streaming parameter and carry out
Live streaming.Central server distributes streaming media server for it.
Then, live streaming user directly uploads game video to the streaming media server of distribution.Streaming media server storage is used
The live stream at family and under the control of central server, reasonable distribution transcoding resource generates the video of different editions, then sends
Cloud.
Finally, distributing game video to viewing user using cloud resource.Spectators can pass through webpage or client viewing trip
Play live streaming, and online interaction.
Algorithm proposed by the invention is run on central server, and central server comprehensively considers game live stream,
Spectators' bandwidth distribution, the factors such as cloud resource value of leass and QoS of customer select suitable transcoding version for each live stream
This, and suitable cloud resource is leased for carrying out transcoding.Video flowing after transcoding is distributed to each spectators by way of cloud.
User's QoE model
In game live streaming platform, it is that one system of measurement is most heavy that QoE index, which has measured user to the satisfaction of service,
One of index wanted.
Firstly, the present invention is directed to different types of live game, QoE index relevant to type of play, i.e. institute are defined
The version of transcoding must be represented not less than the requirement of basic version needed for this game, basic version here and smooth can be watched
Lowest bit rate size required for game is broadcast live and lowest resolution size.
Lb(G(i))≤vb≤ib∧Lr(G(i))≤vr≤ir
Wherein, i represents some live stream, and V (i) represents the corresponding candidate transcoding collection of live stream i, and G (i) represents live stream i
Type of play, Lb(g) and Lr(g) basic bit rate needed for respectively representing g game and base resolution, vb、vrRespectively represent transcoding
The bit rate and resolution ratio of version, ibAnd irRespectively represent the original code rate and original resolution of live stream i.
For each user comes, its assigned video version is closer to original version, and video image quality is better, user
Satisfaction it is higher.Use common Y-PSNR (PSNR) as the mark for measuring transcoding rear video quality in the present embodiment
Standard, and the global opposite satisfaction Q that such as gives a definition:
Wherein I represents the set of current live stream, UiRepresent user's set of viewing live stream i, AiSystem is represented to live streaming
Flow the transcoding strategy of i applicationIt represents system and A is being taken to live stream iiThe transcoding strategy time-division
To the highest version (not higher than the highest version of user bandwidth and resolution ratio) of user u, it is uncommon that expected (i, u) represents user u
Hope the version (version to match with user bandwidth and resolution ratio) for obtaining live stream i.The value range of Q is between 0~1
The major criterion for measuring whole user satisfaction, shows that more greatly user is more satisfied.As each user is assigned to and its equipment
The version (bandwidth and resolution ratio are all the same) matched, then the value up and down of fraction is all the same, Q is equal to 1.
Costs of services model
The present invention further defines the costs of services model of game direct broadcast service provider, and the present invention is meeting user
On the basis of QoE, costs of services is reduced as far as possible, saves operation cost.
For different data centers, since the geographical location of distribution is different, transcoding price is also not quite similar, and with
Time change fluctuation, game direct broadcast service provider wish as far as possible reduce transcoding bring expense Ctran。
Wherein,It indicates to carry out the unit price of transcoding, w in website jjThe task amount that website j needs transcoding is represented, M is indicated
The set of the different websites of transcoding service is provided.
In order to which balancing user is to the satisfaction of service quality and the costs of services of system, following linear combination letter is defined
Number F:
Wherein, p and q respectively represents service fee weight and user satisfaction weight, and Budget represents the pre- of system transcoding
Calculate (Ctran≤Budget).System transcoding expense CtranLower, user satisfaction Q is higher, and corresponding F value is with regard to smaller.
User's distribution and resource allocation algorithm
With reference to the accompanying drawing 2 and embodiment transcoding resource allocation algorithm is described further.
As shown in Fig. 2, for the flow chart of resource allocation in the present invention, the specific steps are as follows:
(S101) the game live streaming platform cycle of operation is cut into several periods；
(S102) in each period, the states letter such as user information and cloud resource lease in plateform system is updated
Breath；
(S103) transcoding Resource Allocation Formula is gone out according to current system conditions decision, the program within the system cycle of operation most
The costs of services of smallization game direct broadcast service provider, while maximizing the QoE summation of user.
(S104) transcoding Resource Allocation Formula is used for current live stream.
In the present embodiment, status information includes the number of current live stream, the type of play of each live stream, image quality ginseng
Number and the number of users of viewing, the bandwidth distribution of spectators, unit transcoding expense of data center etc..
Go out the transcoding Resource Allocation Formula of this period by optimisation strategy decision according to these status informations.In fact,
This is that a solution integral linear programming problem is that can not accomplish line solver optimal solution for large scale system
's.
So proposing an online heuristic strategies in the present embodiment, large scale system can be expanded to well
Under.Here following heuristic function is defined:
WhereinRepresentative is selecting transcoding version sets A for live stream iiIn the case where reselection version v performance evaluation,
C (i, v), which is represented, is transcoded into costs of services required for version v live stream i, it and the unit costs of website for carrying out transcoding have
It closes.It is bigger, show that the priority of the v version of live stream i wants high, i.e., higher-quality user's body is obtained with smaller cost
It tests.
By all versions to be transcoded according to benefit valueDescending sort successively selects transcoding version from front to back.Here
It should be noted that after some version is selected, other versions of corresponding live streamAlso it can change, need to update
Benefit value simultaneously rearranges its position in candidate transcoding queue.Here is the pseudocode of transcoding resource allocation algorithm:
The invention proposes a kind of self adaptation stream resource allocation algorithms applied to game live streaming platform, and are described in detail
A kind of heuristic online transcoding resource allocation algorithm, in the specific implementation can there are many methods, including but not limited to:
(1) fine tune is done to user's QoE model, for example increases grade (payment) for user, the high-grade use of priority processing
Family.
(2) online transcoding resource allocation policy can be solved by solving the method for linear programming problem, although adopting herein
It is heuritic approach, but expands in large scale system with can be convenient in practical applications, and obtain good effect.
(3) combined application of above-mentioned implementation method.
The present invention has fully considered difference of the type of play in game live streaming platform, defines the concept of basic version,
A unified QoE model is proposed for different type of play, while proposing Dynamic Renting money under cloud computing background
The costs of services model of cloud resource.The present invention additionally uses self adaptation stream adaptation technique, and the adaptive of platform is broadcast live in Lai Shixian game
Resource allocation problem should be flowed, dynamically transcoding resource is distributed for live stream and to the greatest extent may be used on the basis for meeting viewer experience quality
The costs of services of game direct broadcast service provider can be reduced.
This invention takes the tradeoff optimizations between costs of services and user QoE, and by adjusting tradeoff parameter, game is straight
Broadcast service provider can adjusting and optimizing target according to the actual situation, bigger freedom degree and the scope of application are provided for algorithm.
In the present invention, the implementation method of algorithm be it is variable, based on the technical solution of the present invention, it is all according to the present invention
The improvement and equivalents that principle carries out the single realization process of the algorithm, should not exclude protection scope of the present invention it
Outside.
Claims (4)
1. a kind of adaptive video crossfire code-transferring method applied to game live streaming platform, which is characterized in that
(S101) the game live streaming platform cycle of operation is cut into several periods；
(S102) within each period, the status information in platform is updated；
(S103) transcoding Resource Allocation Formula, constraint condition of the program within the cycle of operation are gone out according to current state information decision
It is: minimizes the costs of services of game direct broadcast service provider, while maximizing the QoE summation of user；
(S104) transcoding resource allocation is carried out to current live stream based on transcoding Resource Allocation Formula；
User QoE model is constructed, it is to measure that in game live streaming platform, QoE index, which has measured user to the satisfaction of service,
One of one most important index of system, specific building mode are as follows:
QoE index relevant to type of play is defined, i.e. the version of institute's transcoding must be not less than basic version needed for this game
It is required that the basic version representative smooth can be watched, required lowest bit rate size is broadcast live in game and lowest resolution is big
It is small；
Lb(G(i))≤vb≤ib∧Lr(G(i))≤vr≤ir
Wherein, i represents live stream, and V (i) represents the corresponding candidate transcoding collection of live stream i, and G (i) represents live stream i type of play,
Lb(g) and Lr(g) basic bit rate needed for respectively representing g game and base resolution, vbAnd vrRespectively represent the ratio of transcoding version
Special rate and resolution ratio, ibAnd irRespectively represent the original code rate and original resolution of live stream i；
The global opposite satisfaction Q of definition:
Wherein, I represents the set of current live stream, UiRepresent user's set of viewing live stream i, AiIt represents and live stream i is applied
Transcoding strategy, It represents system and transcoding strategy A is being taken to live stream iiWhen give user u
The highest version not higher than user bandwidth and resolution ratio, expected (i, u) represent user u wishes obtain live stream i version
This, which is the version to match with user bandwidth and resolution ratio；The value range of Q is to measure whole use between 0~1
The major criterion of family satisfaction shows that more greatly user is more satisfied；PSNR represents Y-PSNR；
Costs of services model is constructed, for different data centers, since the geographical location of distribution is different, transcoding price
It is not identical, and as time change fluctuates, game direct broadcast service provider wishes to reduce transcoding bring expense C as far as possibletran；
Wherein,It indicates to carry out the unit price of transcoding, w in website jjThe task amount that website j needs transcoding is represented, M indicates to provide
The set of the different websites of transcoding service；
In order to which balancing user is to the satisfaction of service quality and the costs of services of system, following linear combination function F is defined:
Wherein, p and q respectively represents service fee weight and user satisfaction weight, and Budget represents the budget of system transcoding,
Ctran≤Budget；Transcoding expense CtranLower, user satisfaction Q is higher, and corresponding F value is with regard to smaller.
2. the adaptive video crossfire code-transferring method according to claim 1 applied to game live streaming platform, feature exist
In the status information includes the number of current live stream, type of play, image quality parameter and the user of viewing of each live stream
Number, the bandwidth distribution of spectators and the unit transcoding expense of data center.
3. the adaptive video crossfire code-transferring method according to claim 2 applied to game live streaming platform, feature exist
In the specific implementation for going out transcoding Resource Allocation Formula according to current state information decision are as follows: use online inspiration
Formula strategy can expand under large scale system；
It is defined as follows heuristic function:
Wherein,It represents for live stream i in transcoding strategy AiIn the case where reselection version v performance evaluation, c (i, v) represent
Live stream i is transcoded into costs of services required for version v, c (i, v) is related with the unit costs of website of transcoding are carried out；
It is bigger, show that the priority of the v version of live stream i wants high, i.e., higher user quality experience is obtained with smaller cost；
By all versions to be transcoded according to benefit valueDescending sort successively selects transcoding version from front to back.
4. a kind of a kind of adaptive video crossfire turn applied to game live streaming platform according to claim 1-3
The method of code characterized by comprising
S1. user and central server communication is broadcast live, carries out authentication and login, and sets live streaming parameter and is broadcast live；
Central server distributes streaming media server for it；
S2. live streaming user directly uploads game video to the streaming media server of distribution；Streaming media server stores the straight of user
Broadcast stream and under the control of central server, distribute transcoding resource, generate the video of different editions, be then sent to cloud；Institute
Central server is stated using adaptive video crossfire code-transferring method control live stream distribution transcoding；
S3. distribute game video to viewing user using cloud resource；Spectators can watch game live streaming by webpage or client,
And online interaction.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510736948.8A CN105338372B (en) | 2015-10-30 | 2015-10-30 | A kind of adaptive video crossfire code-transferring method applied to game live streaming platform |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510736948.8A CN105338372B (en) | 2015-10-30 | 2015-10-30 | A kind of adaptive video crossfire code-transferring method applied to game live streaming platform |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105338372A CN105338372A (en) | 2016-02-17 |
| CN105338372B true CN105338372B (en) | 2019-04-26 |
Family
ID=55288599
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510736948.8A Active CN105338372B (en) | 2015-10-30 | 2015-10-30 | A kind of adaptive video crossfire code-transferring method applied to game live streaming platform |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105338372B (en) |
Families Citing this family (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105933727B (en) * | 2016-05-20 | 2019-05-31 | 中山大学 | A kind of video stream transcoding and distribution method applied to game live streaming platform |
| CN106454551B (en) * | 2016-09-23 | 2019-06-04 | 西安交通大学 | A kind of HTTP adaptive stream media direct broadcast server clustered deploy(ment) method of QoE driving |
| CN108616378A (en) * | 2016-12-13 | 2018-10-02 | 北京唱吧科技股份有限公司 | A kind of the chat optimization method and server of bandwidth self-adaption |
| CN107070817B (en) * | 2017-05-18 | 2020-10-09 | 中山大学 | Uploading bandwidth optimization method applied to cloud live broadcast platform |
| US11388464B2 (en) | 2018-09-25 | 2022-07-12 | Microsoft Technology Licensing, Llc | Increasing video bit rates while maintaining video quality |
| CN110113632A (en) * | 2019-04-22 | 2019-08-09 | 武汉星汉互娱科技有限公司 | A kind of Streaming Media low delay transcoding method for scheduling task and device |
| US11612813B2 (en) | 2019-09-30 | 2023-03-28 | Dolby Laboratories Licensing Corporation | Automatic multimedia production for performance of an online activity |
| CN110896490B (en) * | 2019-12-06 | 2023-03-07 | 网易（杭州）网络有限公司 | Identity display method, device and equipment and readable storage medium |
| CN112616053B (en) * | 2020-11-30 | 2023-09-05 | 北京达佳互联信息技术有限公司 | Transcoding method and device for live video and electronic equipment |
| CN112788357B (en) * | 2020-12-30 | 2022-01-25 | 北京达佳互联信息技术有限公司 | Network live broadcast method, device, server and computer readable storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103309748A (en) * | 2013-06-19 | 2013-09-18 | 上海交通大学 | Adaptive scheduling host system and scheduling method of GPU virtual resources in cloud game |
| CN104104973A (en) * | 2014-06-12 | 2014-10-15 | 中山大学 | Group bandwidth management optimization method applied to cloud media system |
| CN104598292A (en) * | 2014-12-15 | 2015-05-06 | 中山大学 | Adaptive streaming adaptation and resource optimization method applied to cloud-game system |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9842004B2 (en) * | 2008-08-22 | 2017-12-12 | Red Hat, Inc. | Adjusting resource usage for cloud-based networks |
| US8769531B2 (en) * | 2011-05-25 | 2014-07-01 | International Business Machines Corporation | Optimizing the configuration of virtual machine instances in a networked computing environment |
-
2015
- 2015-10-30 CN CN201510736948.8A patent/CN105338372B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103309748A (en) * | 2013-06-19 | 2013-09-18 | 上海交通大学 | Adaptive scheduling host system and scheduling method of GPU virtual resources in cloud game |
| CN104104973A (en) * | 2014-06-12 | 2014-10-15 | 中山大学 | Group bandwidth management optimization method applied to cloud media system |
| CN104598292A (en) * | 2014-12-15 | 2015-05-06 | 中山大学 | Adaptive streaming adaptation and resource optimization method applied to cloud-game system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105338372A (en) | 2016-02-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105338372B (en) | A kind of adaptive video crossfire code-transferring method applied to game live streaming platform | |
| He et al. | Coping with heterogeneous video contributors and viewers in crowdsourced live streaming: A cloud-based approach | |
| US10032199B2 (en) | Aggregation of multiple media streams to a user | |
| Zhao et al. | A segment-based storage and transcoding trade-off strategy for multi-version VoD systems in the cloud | |
| US11297364B2 (en) | Video content streaming bitrate selection using an edge computing system for improving user experience | |
| CN105933727A (en) | Video stream transcoding and distributing method applied to live game video streaming platform | |
| CN113645471B (en) | Multi-cloud video distribution strategy optimization method and system | |
| Kreuzberger et al. | A comparative study of DASH representation sets using real user characteristics | |
| JP2015507882A (en) | System, method and device for selecting content delivery method based on customer demand for specific content | |
| Hu et al. | Toward Wi-Fi AP-assisted content prefetching for an on-demand TV series: A learning-based approach | |
| US11750722B2 (en) | Media transcoding based on priority of media | |
| Shah et al. | Newsman: Uploading videos over adaptive middleboxes to news servers in weak network infrastructures | |
| Konstantoudakis et al. | Serverless streaming for emerging media: towards 5G network-driven cost optimization: A real-time adaptive streaming FaaS service for small-session-oriented immersive media | |
| Lee et al. | Cost-effective, quality-oriented transcoding of live-streamed video on edge-servers | |
| Hu et al. | Content to cash: Understanding and improving crowdsourced live video broadcasting services with monetary donations | |
| Nguyen et al. | Provisioning overlay distribution networks | |
| KR101271237B1 (en) | System and Method for providing customized custom-view | |
| Liu et al. | QoE-driven HAS live video channel placement in the media cloud | |
| CN105706412B (en) | Band-width tactics management in self-correcting content delivery network | |
| Chang et al. | Video management and resource allocation for a large-scale vod cloud | |
| Diab et al. | Joint content distribution and traffic engineering of adaptive videos in telco-cdns | |
| Liu et al. | Resource allocation in underprovisioned multioverlay peer-to-peer live video sharing services | |
| CN114339311A (en) | Video cloud transcoding and distribution joint decision method and system | |
| Maldonado | Congestion v Content Provision in Net Neutrality: The Case of Amazon's Twitch. tv | |
| Tudón | Prioritization vs. Neutrality on Platforms: Evidence from Amazon’s Twitch. tv |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |