CN109040854B - Stream connection scheduling method suitable for multi-server self-adaptive stream media system - Google Patents
Stream connection scheduling method suitable for multi-server self-adaptive stream media system Download PDFInfo
- Publication number
- CN109040854B CN109040854B CN201810904114.7A CN201810904114A CN109040854B CN 109040854 B CN109040854 B CN 109040854B CN 201810904114 A CN201810904114 A CN 201810904114A CN 109040854 B CN109040854 B CN 109040854B
- Authority
- CN
- China
- Prior art keywords
- stream
- media
- connection
- bit rate
- server
- 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
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/80—Generation or processing of content or additional data by content creator independently of the distribution process; Content per se
- H04N21/83—Generation or processing of protective or descriptive data associated with content; Content structuring
- H04N21/845—Structuring of content, e.g. decomposing content into time segments
- H04N21/8456—Structuring of content, e.g. decomposing content into time segments by decomposing the content in the time domain, e.g. in time segments
-
- 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
- H04N21/238—Interfacing the downstream path of the transmission network, e.g. adapting the transmission rate of a video stream to network bandwidth; Processing of multiplex streams
- H04N21/2385—Channel allocation; Bandwidth allocation
-
- 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]
- H04N21/80—Generation or processing of content or additional data by content creator independently of the distribution process; Content per se
- H04N21/83—Generation or processing of protective or descriptive data associated with content; Content structuring
- H04N21/84—Generation or processing of descriptive data, e.g. content descriptors
-
- 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]
- H04N21/80—Generation or processing of content or additional data by content creator independently of the distribution process; Content per se
- H04N21/85—Assembly of content; Generation of multimedia applications
- H04N21/858—Linking data to content, e.g. by linking an URL to a video object, by creating a hotspot
- H04N21/8586—Linking data to content, e.g. by linking an URL to a video object, by creating a hotspot by using a URL
Abstract
The invention discloses a stream connection scheduling method suitable for a multi-server self-adaptive stream media system, which comprises the steps of generating a media description file according to media content, establishing stream connection between a stream media client and a stream media server, and pre-downloading the media description file; each stream connection caches media content slices according to a bit rate corresponding to network throughput, evaluates data transmission performance of each stream connection according to data transmission conditions of each stream connection, performs stream connection scheduling according to different stable conditions, evaluates performance improvement of stream scheduling, and selects whether to perform stream recovery operation according to evaluation results. The invention can evaluate the quality of the scheduling strategy, provides reference for the system to cope with the change of the network condition, simplifies the connection and does not lose the robustness and high fault-tolerant capability brought to the streaming media system by the multiple servers.
Description
Technical Field
The invention belongs to the field of dynamic self-adaptive streaming media transmission based on an HTTP (hyper text transport protocol), and particularly relates to a streaming connection scheduling algorithm of a server self-adaptive streaming media system.
Background
With the development of the internet, especially the development of new internet services represented by online videos, live webcasts and the like, the demand of the streaming media services for bandwidth gradually becomes the main demand of the internet bandwidth. Streaming technology has gradually evolved from traditional connection-oriented protocols to stateless adaptive streaming over HTTP. Such HTTP protocol-based streaming solutions have many advantages over traditional streaming solutions, such as multiplexing of existing HTTP infrastructure (including servers, proxies, and caches), reliable transport, and ease of passage through firewalls, among others.
In existing HAS (adaptive streaming over HTTP protocol) technology, media content (e.g., video) is sliced into a set of media content slices (chunks), each containing several seconds of video content. These slices of media content are encoded into several bit rates and a bit rate adaptation algorithm is deployed at the client. The algorithm adaptively selects the media content slice with the appropriate bit rate for downloading and playing according to the current available bandwidth of the client.
However, through observation and analysis, we have found that the performance of the adaptive streaming technology that has been applied so far is still insufficient in some cases. For example, when multiple users enjoy streaming media services over the same bandwidth limited connection, performance issues may arise that affect the user experience. The existing systems are deficient in three major respects: (1) fairness: under the same bandwidth-limited connection, a plurality of players should fairly share the bandwidth of the connection; (2) and (3) robustness: in the face of the continuous change of the network environment, the streaming media system should be able to timely and accurately respond, and ensure the stability and high efficiency of the system data transmission.
On the other hand, as the demand of internet users for high-resolution streaming media content is more and more vigorous, internet service providers increasingly use multiple servers instead of a single server, because the solution of multiple servers can improve the stability and reliability of the service while satisfying the user demand. In a multi-server adaptive streaming system, one player may request and download streaming media data from multiple network servers simultaneously. Obviously, in a multi-server system, when a plurality of servers are geographically dispersed, the fault tolerance of the multi-server system against the bandwidth change of the internet is greatly improved.
Through extensive reading of the existing relevant documents, we analyze and believe that the existing algorithm cannot guarantee fairness, effectiveness and stability in a multi-server adaptive streaming media system. Taking fairness as an example, when we apply the existing algorithm, the bandwidth that each player can occupy will be directly determined by the TCP stream connection it uses. Thus, when a player requests data by establishing multiple streams, it can occupy a large amount of bandwidth resources. While other players that create small streams will not be able to fairly obtain the bandwidth they should have. In addition, the performance of the existing algorithm in the multi-server adaptive streaming media system is not satisfactory in terms of effectiveness and stability.
The invention content is as follows:
in order to overcome the defects of the background art, on the basis of the existing dynamic self-adaptive streaming media transmission algorithm based on the HTTP protocol, a streaming connection scheduling method suitable for a self-adaptive streaming media system under a multi-server framework is provided, and fairness and robustness of data transmission when a plurality of users share the same bandwidth-limited connection are guaranteed.
In order to solve the technical problems, the invention adopts the technical scheme that:
a stream connection scheduling method suitable for a multi-server self-adaptive stream media system comprises the following steps:
generating a media description file according to the media content, establishing stream connection between the stream media client and the stream media server, and pre-downloading the media description file; each stream connection caches media content slices according to a bit rate corresponding to network throughput, evaluates data transmission performance of each stream connection according to data transmission conditions of each stream connection, performs stream connection scheduling according to different stable conditions, evaluates performance improvement of stream scheduling, and selects whether to perform stream recovery operation according to evaluation results.
Preferably, it comprises:
step 1, generating a media description file, wherein a streaming media server encodes media contents provided by a streaming media content provider with different bit rates, aligns and cuts content copies with various bit rates into content slices with fixed sizes, and generates the media description file according to the bit rate, the slice length and a data download URL of each content copy;
step 2, the streaming media client side simultaneously initiates network requests to a plurality of streaming media servers, and respectively establishes streaming connection with the streaming media servers;
step 3, the streaming media client downloads the media description file from the server;
step 4, the client performs initial caching on the media content;
step 5, each stream connection caches the media content slice, and if all the media contents are downloaded, the process is finished;
step 6, judging whether the number m of the current active stream connections is greater than 1, if so, executing step 7, and if not, executing step 10;
step 7, judging whether the flow connection states of the m pieces of activities are all stable, if so, entering step 9, and if not, entering step 8;
step 8, judging the stream scheduling condition in the unstable state, calculating the maximum difference value Gap of the bit rate grade of the media content slice between each stream connection, judging whether the Gap is more than or equal to H, if yes, executing step 9, if no, executing step 10, wherein,
l is the level of the maximum bit rate that the server can provide;
step 9, stopping the stream connection, according to the bit rate of all the stream connections of the current or latest cached media content slices, stopping the activity of the stream connection with the lowest bit rate, making the stream connection enter a dormant state, and returning to the step 5;
and step 10, judging whether the overall performance of the system is improved by the flow scheduling operation, if so, jumping back to the step 5, and if not, entering the step 11.
Step 11, flow recovery: awakening all stream connections in the dormant state, initializing data transmission of all stream connections at the bit rate selected by the current system, and returning to the step 5.
Preferably, each streaming connection in step 5 is an adaptive transmission of the buffered media content slice according to the network throughput selection adaptive bitrate.
Preferably, when the step 7 determines whether each flow connection state is a stable method, the step sequentially determines the state of each flow connection i, i being 1,2, …, m, and the determining method includes:
step 7.1, recording the bit rate of the streaming media transmission media content slice, setting an array with the length of k for the streaming connection by the client, and recording the bit rate of the media content slice cached in the latest k times of the streaming connection;
step 7.2, obtaining the maximum difference G in k media content slice bit rate grade samples downloaded recently by the streaming mediaiObtaining a maximum value M of k media content slice bitrate level samplesi；
Step 7.3, judge GiLess than or equal to 1 and MiAnd if the bit rate is less than or equal to L, if so, the state of the streaming media is stable, and if not, the state of the streaming media is unstable, wherein L is the level of the maximum bit rate which can be provided by the server.
Preferably, the method for determining whether the flow scheduling operation improves the overall performance of the system in step 10 is as follows:
firstly, whether the maximum bit rate level L in the current active stream of k continuous media blocks is judgedcurrentEqual to or less than the highest bit rate level SID before stream pruningbeforeIf yes, the quality of the video streaming media is reduced after the stream reduction operation, the overall performance of the system is not improved by the stream scheduling operation,
if not, further judging SIDhighest≥SIDbeforeAnd
if yes, it indicates that the overall performance of the system is not improved by the flow scheduling operation, if no, it indicates that the overall performance of the system is improved by the flow scheduling operation,
wherein SIDhighestIndicating the highest bit rate ultimately reached by the player, etcLevel, L represents the level of the maximum bit rate that the server can provide, 0 < ρ < 1.
Preferably, the method of performing the stream restoration operation includes: and waking up all stream connections in the dormant state, and initializing data transmission of all stream connections at the bit rate selected by the current system.
Preferably, the content slice is 2-10 seconds in size.
Preferably, the step 3 of downloading the media description file from the server by the streaming client is performed before the data transmission, and the storage location of the media content is obtained by parsing the media description file.
Preferably, in step 4, when the client performs initial caching of the media content, the media content slice with the lowest bit rate is selected first for caching.
The invention has the beneficial effects that: the invention provides the idea of flow connection scheduling in the multi-server self-adaptive streaming media, selects and stores the flow connection with better quality through a reasonable evaluation strategy, and gradually eliminates the flow connection with poorer quality, so that different users have fair bandwidth competition conditions in the final stable state; the client eliminates the poor connection, provides a chance of acquiring more bandwidth resources for the good connection, and enables the whole system to more fully utilize the bandwidth resources; the method provides a feedback for stream scheduling, can evaluate the quality of a scheduling strategy, provides a reference for the system to cope with the change of the network condition, simplifies the connection, and does not lose the robustness and high fault-tolerant capability brought to the stream media system by the multiple servers.
The invention improves the data transmission performance of the multi-server self-adaptive streaming media through the flow reduction algorithm, the scheduling performance evaluation and the flow recovery strategy, ensures the fairness, gradually balances the flow connection quantity among different users through the flow reduction algorithm, ensures that a plurality of users can fairly obtain bandwidth resources when sharing the same bandwidth limited connection, and no matter how many flow connections are initially established by each user; the robustness is ensured, when the network condition changes, the flow scheduling performance is evaluated in time, all flow connections are recovered when necessary, and the flow scheduling algorithm is operated again to adapt to the new network condition.
Drawings
FIG. 1 is a system framework diagram of an embodiment of the present invention,
figure 2 is a schematic diagram of steady state flow reduction of an embodiment of the present invention,
FIG. 3 is a schematic diagram of flow reduction in an unsteady state according to an embodiment of the present invention.
Detailed Description
The invention is further described below with reference to the accompanying drawings and examples.
The system framework of the invention is shown in fig. 1, the core algorithm mainly comprises two parts of a flow reduction algorithm and scheduling performance evaluation, and the specific implementation steps are as follows:
step 1, generating a media description file MPD: the streaming media server will encode the media content provided by the streaming media content provider with different bit rates, which are { b }1,b2,...,bLAnd b, and b1＜b2＜...＜bLWherein for any of i and j, if i < j, then b is presenti＜bjThen, aligning and cutting the content copies with various bit rates into content slices with fixed sizes (2-10 seconds), and then aggregating parameter information such as the bit rate, the slice length, the URL (uniform resource locator) for data downloading and the like of each content copy to form a media description file;
step 2, establishing stream connection: the streaming media client simultaneously initiates network requests to a plurality of streaming media servers and then respectively establishes streaming connection with the streaming media servers;
step 3, pre-downloading the media description file: before data transmission, a streaming media client downloads a media description file from a server, and acquires key information and a storage position of media content by analyzing the media description file;
step 4, initial caching: when the client side starts media content caching, the media content slice with the lowest bit rate is selected for caching, so that the starting delay is the lowest;
step 5, self-adaptive transmission stage: at this stage, a self-adaptive algorithm is run, each stream connection selects a proper bit rate to cache media content slices according to the network throughput, and if all media content is downloaded, the process is finished.
Step 6, judging whether the number m of the current active stream connections is greater than 1, if so, executing step 7, otherwise, skipping to step 10;
step 7, judging whether the flow connection states of the m pieces of activities are all stable, if so, entering step 9, and if not, entering step 8; the following steps are performed on the connections i (i is 1,2, …, m) one by one to judge whether the respective stream connection is stable:
step 7.1, recording media content slice bit rate: the client sets an array with the length of k (usually set to 4) for the stream connection, and records the bit rate of the media content slice cached for the latest k times of the stream connection;
step 7.2, calculating key data GiAnd Mi：GiRepresents the maximum difference, M, among the most recently downloaded k media content slice bit rate level samples of the streamiThen represents the maximum of the k media content slice bit rate level samples;
step 7.3, if G is satisfiediLess than or equal to 1 and MiL is less than L, which is the grade of the maximum bit rate that the server can provide, otherwise, the stream is unstable.
Step 8, judging the flow scheduling conditions in the unstable state: calculating the maximum difference Gap of the bit rate levels of the media content slices between the stream connections, as shown in FIG. 3, if Gap ≧ H, step 9 is performed, where H is generally equal to
I.e. half the level of the maximum bit rate that the server can provide, otherwise jump to step 10;
step 9, disabling the stream connection: selecting the stream connection with the lowest bit rate according to the bit rate of all the stream connections of the current or latest cached media content slices, stopping the stream connection, entering a dormant state, and returning to the step 5;
step 10, flow scheduling performance detection: the method comprises the following steps of continuously detecting the operation performance of a flow scheduling strategy before, wherein a specific detection algorithm is as follows:
SIDbeforerepresenting the highest bit rate level, SID, before stream thinninghighestIt indicates the highest bit rate level that the player eventually reaches. Let LcurrentIndicating the maximum bit rate level of all currently active streams and L the maximum bit rate level that can be provided by the server. We will define performance degradation and meaningless performance improvement based on these variables.
Performance degradation: if the current maximum bit rate level Lcurrent≤SIDbeforeAnd k (═ 4) media blocks last, the quality of the video streaming media is considered to have degraded after the stream thinning operation.
Meaningless performance improvement: if SIDhighest≥SIDbeforeAnd is
Where 0 < ρ < 1, i.e., the stream thinning operation does not significantly improve the quality of the video streaming media.
If the overall performance of the system is obviously improved for the stream scheduling operation according to the detection result of the method, the step 5 is skipped, otherwise, the step 11 is carried out for stream recovery operation;
step 11, flow recovery: awakening all stream connections in the dormant state, initializing data transmission of all stream connections at the bit rate selected by the current system, and returning to the step 5.
The invention adopts the technical scheme and has the following advantages:
the idea of flow connection scheduling in the multi-server self-adaptive streaming media is put forward for the first time, the flow connection with better quality is selected and stored through a reasonable evaluation strategy, and the flow connection with poorer quality is gradually eliminated, so that different users have fair bandwidth competition conditions in the final stable state;
as described in the first paragraph, the client eliminates the poor connection, and provides a chance of acquiring more bandwidth resources for the better connection, so that the whole system can more fully utilize the bandwidth resources;
the scheduling performance evaluation of the invention provides a feedback for stream scheduling, which can evaluate the quality of a scheduling strategy and provide reference for the system to cope with the change of network conditions, thereby simplifying connection without losing the robustness and high fault-tolerant capability brought to a stream media system by a plurality of servers.
It will be understood that modifications and variations can be made by persons skilled in the art in light of the above teachings and all such modifications and variations are intended to be included within the scope of the invention as defined in the appended claims.
Claims (7)
1. A stream connection scheduling method suitable for a multi-server self-adaptive stream media system is characterized in that:
the server generates a media description file according to the media content, establishes stream connection between the stream media client and the stream media server, and pre-downloads the media description file; caching media content slices by each stream connection according to a bit rate corresponding to network throughput, evaluating data transmission performance of each stream connection according to the data transmission condition of the stream connection, scheduling the stream connection according to different stable conditions, evaluating performance improvement of stream scheduling, and selecting whether to perform stream recovery operation according to an evaluation result;
the method comprises the following steps:
step 1, generating a media description file, wherein a streaming media server encodes media contents provided by a streaming media content provider with different bit rates, aligns and cuts content copies with various bit rates into content slices with fixed sizes, and generates the media description file according to the bit rate, the slice length and a data download URL of each content copy;
step 2, the streaming media client side simultaneously initiates network requests to a plurality of streaming media servers, and respectively establishes streaming connection with the streaming media servers;
step 3, the streaming media client downloads the media description file from the server;
step 4, the client performs initial caching on the media content;
step 5, the stream of each activity is connected with the cached media content slice, if all the media contents are downloaded, the process is finished, otherwise, the process enters step 6;
step 6, judging whether the number m of the current active stream connections is greater than 1, if so, executing step 7, and if not, executing step 10;
step 7, judging whether the flow connection states of the m pieces of activities are all stable, if so, entering step 9, and if not, entering step 8;
step 8, judging the stream scheduling condition in the unstable state, calculating the maximum difference value Gap of the bit rate grade of the media content slice between each stream connection, judging whether the Gap is more than or equal to H, if yes, executing step 9, if no, executing step 10, wherein,
l is the level of the maximum bit rate that the server can provide;
step 9, stopping the stream connection, stopping the activity of the stream connection with the lowest bit rate according to the bit rate of the media content slice currently or recently cached by all the stream connections, making the stream connection enter a dormant state, and returning to the step 5;
step 10, judging whether the overall performance of the system is improved by the flow scheduling operation, if so, jumping back to the step 5, and if not, entering the step 11;
step 11, flow recovery: awakening all stream connections in the dormant state, initializing data transmission of all stream connections at the bit rate selected by the current system, and returning to the step 5.
2. The stream connection scheduling method for the multi-server adaptive streaming media system according to claim 1, wherein:
and in the step 5, each active stream connection is self-adaptive transmission of the media content slice of the adaptive bit rate cache according to the network throughput selection.
3. The streaming connection scheduling method for the multi-server adaptive streaming media system according to claim 1, wherein the step 7 of determining whether each current active streaming connection state is stable is to sequentially determine the state of each streaming connection i, i is 1,2, …, m, and the determining method includes:
step 7.1, recording the bit rate of the streaming media transmission media content slice, setting an array with the length of k for the streaming connection by the client, and recording the bit rate of the media content slice cached in the latest k times of the streaming connection;
step 7.2, obtaining the maximum difference G in k media content slice bit rate grade samples downloaded recently by the streaming mediaiObtaining a maximum value M of k media content slice bitrate level samplesi；
Step 7.3, judge GiLess than or equal to 1 and MiAnd if the bit rate is less than or equal to L, if so, the state of the streaming media is stable, and if not, the state of the streaming media is unstable, wherein L is the level of the maximum bit rate which can be provided by the server.
4. The method for scheduling stream connection in adaptive multi-server streaming media system according to claim 3, wherein the method for determining whether the stream scheduling operation improves the overall performance of the system in step 10 is:
firstly, whether the maximum bit rate level L in the current active stream of k continuous media blocks is judgedcurrentEqual to or less than the highest bit rate level SID before stream pruningbeforeIf yes, the quality of the video streaming media is reduced after the stream reduction operation, the overall performance of the system is not improved by the stream scheduling operation,
if not, further judging SIDhighest≥SIDbeforeAnd
if yes, it indicates that the overall performance of the system is not improved by the flow scheduling operation, if no, it indicates that the overall performance of the system is improved by the flow scheduling operation,
wherein SIDhighestIndicating the highest bit rate level that the player eventually reaches, L indicating the serverThe level of maximum bit rate that can be provided is 0 < p < 1.
5. The stream connection scheduling method for the multi-server adaptive streaming media system according to claim 1, wherein: the content slice has a size of 2-10 seconds.
6. The stream connection scheduling method for the multi-server adaptive streaming media system according to claim 1, wherein: the step 3 of downloading the media description file from the server by the streaming media client is performed before data transmission, and the storage location of the media content is obtained by analyzing the media description file.
7. The stream connection scheduling method for the multi-server adaptive streaming media system according to claim 1, wherein: and 4, when the client side performs initial caching of the media content, firstly selecting the media content slice with the lowest bit rate for caching.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810904114.7A CN109040854B (en) | 2018-08-09 | 2018-08-09 | Stream connection scheduling method suitable for multi-server self-adaptive stream media system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810904114.7A CN109040854B (en) | 2018-08-09 | 2018-08-09 | Stream connection scheduling method suitable for multi-server self-adaptive stream media system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109040854A CN109040854A (en) | 2018-12-18 |
| CN109040854B true CN109040854B (en) | 2021-02-02 |
Family
ID=64632521
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810904114.7A Active CN109040854B (en) | 2018-08-09 | 2018-08-09 | Stream connection scheduling method suitable for multi-server self-adaptive stream media system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109040854B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2001092731A (en) * | 1999-09-22 | 2001-04-06 | Hitachi Information Systems Ltd | Method for distributing data |
| CN104040989A (en) * | 2011-10-12 | 2014-09-10 | 布若德匹克公司 | Gateway, and method, computer program and storage means corresponding thereto |
| CN104349176A (en) * | 2013-07-30 | 2015-02-11 | 中国电信股份有限公司 | Self-adaptive stream media system, downloading method and stream media server, user terminal |
| CN104365074A (en) * | 2012-06-12 | 2015-02-18 | 思科技术公司 | Preventing overestimation of available bandwidth in adaptive bitrate streaming clients |
| CN105684390A (en) * | 2013-10-29 | 2016-06-15 | 汤姆逊许可公司 | Method and device for reserving bandwidth for an adaptive streaming client |
| CN106453270A (en) * | 2016-09-20 | 2017-02-22 | 天津大学 | Adaptive transmission algorithm based on PI control streaming media |
| CN106899894A (en) * | 2015-12-18 | 2017-06-27 | 中国电信股份有限公司 | The adaptive stream media method of dynamic optimization, device and server |
-
2018
- 2018-08-09 CN CN201810904114.7A patent/CN109040854B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2001092731A (en) * | 1999-09-22 | 2001-04-06 | Hitachi Information Systems Ltd | Method for distributing data |
| CN104040989A (en) * | 2011-10-12 | 2014-09-10 | 布若德匹克公司 | Gateway, and method, computer program and storage means corresponding thereto |
| CN104365074A (en) * | 2012-06-12 | 2015-02-18 | 思科技术公司 | Preventing overestimation of available bandwidth in adaptive bitrate streaming clients |
| CN104349176A (en) * | 2013-07-30 | 2015-02-11 | 中国电信股份有限公司 | Self-adaptive stream media system, downloading method and stream media server, user terminal |
| CN105684390A (en) * | 2013-10-29 | 2016-06-15 | 汤姆逊许可公司 | Method and device for reserving bandwidth for an adaptive streaming client |
| CN106899894A (en) * | 2015-12-18 | 2017-06-27 | 中国电信股份有限公司 | The adaptive stream media method of dynamic optimization, device and server |
| CN106453270A (en) * | 2016-09-20 | 2017-02-22 | 天津大学 | Adaptive transmission algorithm based on PI control streaming media |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109040854A (en) | 2018-12-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Spiteri et al. | From theory to practice: Improving bitrate adaptation in the DASH reference player | |
| US8838823B2 (en) | Performance aware peer-to-peer content-on-demand | |
| US9332051B2 (en) | Media manifest file generation for adaptive streaming cost management | |
| EP2730072B1 (en) | Network-capacity optimized adaptive streaming | |
| US8578042B2 (en) | Method, system and device for playing streaming media | |
| KR102472155B1 (en) | How to Broadcast Streaming Content in a Peer to Peer (P2P) Network | |
| US20020091840A1 (en) | Real-time optimization of streaming media from a plurality of media sources | |
| Chen et al. | Smart streaming for online video services | |
| CN108833350B (en) | Data transmission method suitable for multi-server self-adaptive streaming media system | |
| US20120143986A1 (en) | Systems and methods for downloading by different processes | |
| EP2404431A1 (en) | Methods and arrangements for prioritization in a peer-to-peer network | |
| WO2017084277A1 (en) | Code stream self-adaption method and system for online media service | |
| Yousef et al. | Enabling adaptive bitrate algorithms in hybrid CDN/P2P networks | |
| Yarnagula et al. | QoE for mobile clients with segment-aware rate adaptation algorithm (SARA) for DASH video streaming | |
| US20220191260A1 (en) | Method for playing on a player of a client device a content streamed in a network | |
| CN102439935A (en) | Media adaptation method and apparatus | |
| KR102304476B1 (en) | Multipath-based block transmission system and streaming method for adaptive streaming service | |
| US20190238390A1 (en) | Method for streaming an audio video content | |
| KR101252947B1 (en) | Method and apparatus for push-pull hybrid streaming adaptive to video chunk distribution | |
| CN109040854B (en) | Stream connection scheduling method suitable for multi-server self-adaptive stream media system | |
| CN1812566A (en) | Apparatus and method for realizing P2P stream broadcasting in information family appliances | |
| US9154552B2 (en) | Method and apparatus for cooperative file distribution with receiver determined quality of services | |
| Kim et al. | Content-aware rate adaptation scheme to improve stability in HTTP Adaptive Streaming | |
| CN109995824B (en) | Task scheduling method and device in peer-to-peer network | |
| Ozcelik et al. | Chunk Duration--Aware SDN-Assisted DASH |
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 |