CN101800704B - P2P streaming media system data request scheduling method based on mixed dynamic priority queue - Google Patents
P2P streaming media system data request scheduling method based on mixed dynamic priority queue Download PDFInfo
- Publication number
- CN101800704B CN101800704B CN2010101260421A CN201010126042A CN101800704B CN 101800704 B CN101800704 B CN 101800704B CN 2010101260421 A CN2010101260421 A CN 2010101260421A CN 201010126042 A CN201010126042 A CN 201010126042A CN 101800704 B CN101800704 B CN 101800704B
- Authority
- CN
- China
- Prior art keywords
- data
- request
- scheduling
- time limit
- node
- 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.)
- Expired - Fee Related
Links
Images
Landscapes
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
Abstract
The invention discloses a P2P streaming media system data request scheduling method based on a mixed dynamic priority queue, comprising the following steps: respectively create a scheduling time limit priority queue and a scheduling scarcity degree priority queue at a data sending node; playing time limit information and scarcity degree information are included in a data request which is sent by a data receiving node; when each data request is arrived at the data sending node, respectively insert the data request into the corresponding positions of the scheduling time limit priority queue and the scheduling scarcity degree priority queue according to the scheduling time limit and the scarcity degree; when the data is scheduled, prior schedule a request of which the scheduling time limit is out of date in next scheduling cycle, secondly, prior schedule according to the scarcity degree, when each data scheduling is finished, delete a scheduled data request from two queues, and adjust the scheduling time limit of each data request in the scheduling time limit priority queue. Higher average data block arrive on time rate and node uploading bandwidth utilization ratio can be obtained by the method in the invention, thereby having better media playback quality.
Description
Technical field
The present invention relates to a kind of content distribution service, particularly P2P streaming media service, relate in particular to a kind of request of data dispatching method of P2P stream media system based on the P2P technology.
Background technology
Streaming Media is meant on data network in chronological sequence order transmission and continuant, the video data stream play.Streaming media data stream has 3 characteristics: continuity, real-time, sequential, promptly its data flow has strict front and back sequential relationship.Because these characteristics of Streaming Media, it has become the main mode of real-time Transmission sound, video on the internet.The P2P technology is incorporated in the Streaming Media transmission just formed the P2P stream media technology.
According to the organizational form of node, the P2P stream media system can be divided into two big classes: tree and network structure.Adopt the mode of data-driven at cancellated P2P stream media system.In order to allow the download that can walk abreast of the various piece of media file, file division need be become a plurality of fritters, blocks of files represents that with the sequence number of order numbering is usually since 0, until last piece.Owing to there is not definite upstream and downstream relation between the node of network structure P2P stream media system, generally adopts buffer memory figure (Buffer Map) to represent the store status of media data block in the current cache and between node, exchange.In buffer memory figure, the store status of content is come record with bi-values, and 1 expression exists, and 0 expression does not exist.Buffer memory figure has represented the availability situation of data in the current node buffer memory, the reference frame of data block selection when it is content exchange.
The performance of P2P stream media system depends on two aspects: peer-to-peer network makes up and the node data dispatching method.Peer-to-peer network makes up and has determined the Internet resources that each node may use, and data dispatch has determined how node uses these available resources.In the P2P stream media system, node receives the data block store state information that its neighbours' node is periodically sent, and determines which node to obtain the desired data block that obtains from, and this process promptly is a data dispatch.Adopt local rare preferential data block selection in the CoolStreaming system and, be a kind of more representational data dispatch mode based on the node selection strategy of maximum available bandwidth.Data dispatch has determined the resource occupation mode of P2P system, and systematic function is had crucial influence.In the P2P Streaming Media is used, need the intelligentized dispatching algorithm of design could satisfy the real-time broadcast request of media content better.Especially, dispatching algorithm need satisfy the playback time limit of each data block and the bandwidth constraint of neighbours' node.
Because node quantity is a lot of in the system, and each node independently makes the node selection strategy according to local information, so may appear at the situation that the lot of data request appears in certain node.Lose for fear of request, need rank request.Similarly, periodically response data request of node sends corresponding data block.Because each request of data needs the regular hour (relevant with the service station upstream bandwidth with the data block size), when the request of data arrival rate exceeds request during the processing time, then asks queuing to occur.For a long time request is waited for and will be produced many-sided problem: one, use for Streaming Media, and might occur when asking to have exceeded its broadcast time limit can be serviced the time, thereby transmit hash; Its two, request is waited for and have been reduced the speed that data transmit; Its three, during request queue, this connection will keep always, because number of connection is limited, take for a long time and will connect and do not carry out data and transmit and reduced resource utilization ratio.
At present, data sending node adopts the mode (request is kept in the fifo queue) of First Come First Served usually to the request of data of receiving.Because the First Come First Served scheduling mode is not considered the time limit of data playback, therefore, when the request of data of playing the time limit vicinity comes the back of formation, may exceed it when dispatching this request and play the time limit, even if the data block of dispatching previously is to time limit arrivals to be played such as receiving terminal also need later on.Therefore, traditional first in first out (FIFO) queue management mechanism may become the performance bottleneck of system when queue length is longer, is necessary to design the request of data dispatching method of intelligence.
At present, the data dispatch of P2P stream media system is studied main intensive data request transmitting terminal, promptly inquires into node and how to select data block and destination node request msg according to the demand data of oneself.The implicit hypothesis of these researchs, i.e. data sending terminal response data request in time.According to top analysis, the phenomenon of request queue may appear in data sending node, also do not cause widely and pay attention to yet how carry out rational data dispatching request at data sending terminal.
In the P2P shared file system, data sending node is equivalent to the server side of data delivery service, and their performance has material impact to the overall performance of P2P system.The shortest residue processing time, (Shortest Remaining Processing Time was a kind of optimization method for scheduling task of classics SRPT), can prove the average response time that the SRPT request of can minimizing is required.In order to shorten the average service time of request of data in the P2P shared file system, people such as Qiao propose to adopt the SRPT mode to dispatch the request of data of receiving at data sending terminal.The target application of this method is the P2P shared file system, and the request scheduling foundation is the residue processing time, thereby does not consider the broadcast time limit of data block.In addition, this method does not have data block diversity requirement in the taking into account system yet.
Therefore, need make up special request of data dispatching method according to the specific (special) requirements of Streaming Media.
Summary of the invention
The purpose of this invention is to provide a kind of request of data dispatching method of the P2P of being used for stream media system, can adapt to the requirement of media stream in real time, sequential, the scheduling that improves system utilizes performance.
For achieving the above object, the technical solution used in the present invention is: a kind of P2P streaming media system data request scheduling method based on mixed dynamic priority queue, set up scheduling time limit Priority Queues and the rare degree Priority Queues of scheduling respectively in data sending node; In the request of data of sending by the Data Receiving node, include limit information and rare degree information when playing; When each request of data arrives data sending node, according to playing the scheduling time limit of time limit information calculations in data sending node, according to the rare degree of rare degree information calculations, and according to dispatching the relevant position that time limit and rare degree insert request of data respectively scheduling time limit Priority Queues and the rare degree Priority Queues of scheduling; In the data sending node configuration scheduling cycle, when begin each dispatching cycle, carry out data dispatch; Described data dispatch is, at first check scheduling time limit Priority Queues, if there is the scheduling time limit of request will be expired in next dispatching cycle, then dispatch this request of data, otherwise, check the rare degree Priority Queues of scheduling, if there is request of data, then request of data is the preceding arranged in scheduling, when each data dispatch is finished, and the modulated degrees of data request of deletion from two formations, and the scheduling time limit of each request of data in the time limit Priority Queues is dispatched in adjustment, if two formations are empty queue, then stop data dispatch, wait for the beginning of next dispatching cycle.
In the technique scheme, data sending node is considered the broadcast time limit and the rare degree of data block simultaneously when the response data request.According to broadcast time limit and the processing of data and the scheduling time limit of delivery time computation requests of node, for satisfying the broadcast time limit of data block, request of data should be dispatched before the scheduling time limit.The priority scheduling broadcast time limit is about to arrive data block in dispatching cycle, if the free of data piece arrives its scheduling time limit, the request of data that the rare degree of priority scheduling is low.The data structure of scheduling time limit Priority Queues and the rare degree Priority Queues of scheduling can be provided with two queue structures respectively, and request of data is copied to respectively in two formations; A formation also can be set, and another adopts the data directory structure, and scheduling time limit Priority Queues for example is set, and sets the data directory of rare degree again; Can also formation be set according to the arrival time limit of request of data, the index of scheduling time limit and rare degree is set respectively simultaneously.The set-up mode of these queue structures all can be realized two Priority Queues requirements of technique scheme, thereby all belongs to protection scope of the present invention.
In the technique scheme, the computational methods in the scheduling time limit of request of data are,
Numeration is CS according to block size, and media play speed is R, then individual data piece reproduction time: t=CS/R;
Note requested data block sequence number is SN
r, current just at played data block sequence number SN
p, then play time limit t
d=(SN
r-SN
p) * t;
Request sends node request transmission time stamp and is ts
s, the request time of reception stabs and is ts
r, request transmission time t
Rs=ts
r-ts
s
Request response node data block transmitting time td
s=max (CS/BW
s, CS/BW
r)+d
Ul, BW wherein
sExpression sends node bandwidth, BW
rExpression receives node bandwidth, d
UlBe up link time delay (network intermediate node queuing time);
Be limited to t when then dispatching
s=t
d-t
Rs-td
s
Therefore, normally, described broadcast time limit information comprises plays time limit and request transmission time stamp.Certainly, limit information also can comprise and currently just stabbing in played data block sequence number and request transmission time during described broadcast, at this moment, because the requested data block sequence number is known, individual data piece reproduction time is known, therefore can calculate by data sending node and play the time limit, and then calculate the scheduling time limit, but correspondingly increase the load of data sending node.
Described rare degree information is, at the copy amount of the requested data block of Data Receiving node record.
The copy amount ÷ data block total number of rare degree=requested data block, in the rare degree Priority Queues of scheduling, request of data is according to rare degree sequence arrangement from small to large.
In the corresponding request of data, can comprise copy amount, the title that also can comprise through normalized lacks the degree value.
Because node is difficult to the data block block message of all other node in the acquisition system, the statistics of data block copy amount only has local sense.
Because the technique scheme utilization, the present invention compared with prior art has following advantage:
1. method of the present invention is when being used for the P2P stream media system, in data sending node the request of data in other node in from system has been carried out rational scheduling, can satisfy the broadcast time limit of requested date piece, therefore can reduce data block and miss the chance of playing the time limit, thereby improve the quality of media playback; Taken into account the diversity requirement of data in system simultaneously, under the prerequisite that time-constrain is met, the data block request that the rare degree of priority scheduling is lower, the diversity of data block in can the raising system, thereby help to allow more node download to the data of wanting, and then improve the utilance of system.
2. emulation experiment shows, adopts method of the present invention, can obtain higher average data piece arrival rate and node uploading bandwidth utilization ratio on time than the method for prior art, thereby have better media playback quality.
Description of drawings
Fig. 1 is the P2P streaming media system data request scheduling flow chart of the embodiment of the invention one based on mixed dynamic priority queue;
Fig. 2 is an average data piece arrival rate situation of change schematic diagram in time on time among the embodiment one;
Fig. 3 is a node uploading bandwidth utilization ratio situation of change schematic diagram in time among the embodiment one;
Fig. 4 is an average data piece arrival rate schematic diagram relatively on time under the different system scale condition among the embodiment one;
Fig. 5 is a node uploading bandwidth utilization ratio schematic diagram relatively under the different system scale condition among the embodiment one.
Embodiment
Below in conjunction with drawings and Examples the present invention is further described:
Embodiment one: shown in accompanying drawing 1, a kind of P2P streaming media system data request scheduling method based on mixed dynamic priority queue is set up scheduling time limit Priority Queues and the rare degree Priority Queues of scheduling respectively in data sending node; In the request of data of sending by the Data Receiving node, include limit information and rare degree information when playing; When each request of data arrives data sending node, according to playing the scheduling time limit of time limit information calculations in data sending node, according to the rare degree of rare degree information calculations, and according to dispatching the relevant position that time limit and rare degree insert request of data respectively scheduling time limit Priority Queues and the rare degree Priority Queues of scheduling; In the data sending node configuration scheduling cycle, when begin each dispatching cycle, carry out data dispatch; Described data dispatch is, at first check scheduling time limit Priority Queues, if there is the scheduling time limit of request will be expired in next dispatching cycle, then dispatch this request of data, otherwise, check the rare degree Priority Queues of scheduling, if there is request of data, then request of data is the preceding arranged in scheduling, when each data dispatch is finished, and the modulated degrees of data request of deletion from two formations, and the scheduling time limit of each request of data in the time limit Priority Queues is dispatched in adjustment, if two formations are empty queue, then stop data dispatch, wait for the beginning of next dispatching cycle.
Wherein, the Data Receiving node just asks to send node, request of data is except comprising the data block sequence number of request, the source node of request, also need to be carried at data sending node and carry out the required relevant information of request scheduling, comprise and play time limit, request transmission time, data block copy amount (or rare degree).Available C Plus Plus structure is expressed as follows:
struct?ChunkReq{
unsigned?int?seq_num；
unsigned?iht?src_id；
double?playback_deadline；
time_t?req_sending_time；
double rarity_degree；
}；
Data sending node is carried out data dispatch:
Set up two Priority Queues respectively, be respectively applied for scheduling time limit and the rare degree of preserving data block, in data sending node, data block request can be expressed as:
struct?ChunkReq_Recv{
unsigned?int?seq_num；
unsigned?int?src_id；
double?sched_deadline；
double?rarity_degree；
}；
A) when data sending node is received certain request of data,
According to playing the time limit and asking time of reception to calculate the scheduling time limit, if the scheduling time limit less than the current time, then sends the request of node transmission NACK refusal to request.Otherwise, be inserted into respectively in the corresponding Priority Queues according to from small to large order according to the data block calculated scheduling time limit and rare degree.
B) when time started dispatching cycle arrives,
From two Priority Queues, select the request that need respond this dispatching cycle according to the following rules:
S1: check scheduling time limit Priority Queues, if any scheduling time limit of request will be in next dispatching cycle expired (T
i＜=t
s＜T
I+1), then dispatch this request of data (more than one of possibility), otherwise dispatch head of the queue request in the rare degree Priority Queues (rare degree minimum), and send data by up link.
S2: the modulated degree request of deletion from two formations
S3: need to adjust the scheduling time limit (deducting a data block transmitting time) in the scheduling time limit Priority Queues after request scheduling is finished, as scheduling time limit of data block less than the current time, then send node and send NACK message to it.
As in a dispatching cycle, dispatching a plurality of requests simultaneously, then repeat said process.
Wherein, the computational methods in the scheduling time limit of request of data are,
Numeration is CS according to block size, and media play speed is R, then individual data piece reproduction time: t=CS/R;
Note requested data block sequence number is SN
r, current just at played data block sequence number SN
p, then play time limit t
d=(SN
r-SN
p) * t;
Request sends node request transmission time stamp and is ts
s, the request time of reception stabs and is ts
r, request transmission time t
Rs=ts
r-ts
s
Request response node data block transmitting time td
s=max (CS/BW
s, CS/BW
r)+d
Ul, BW wherein
sExpression sends node bandwidth, BW
rExpression receives node bandwidth, d
UlBe up link time delay (network intermediate node queuing time);
Be limited to t when then dispatching
s=t
d-t
Rs-td
s
Method according to present embodiment, by emulation experiment this method and First Come First Served are contrasted with nearest time limit priority scheduling method, emphasis is two Key Performance Indicators of three kinds of methods relatively: the average data piece is arrival rate and average node uploading bandwidth utilization ratio on time.Obviously, the data dispatching method of request transmitting terminal is influential equally to above-mentioned performance, keeps the data dispatching method of request transmitting terminal constant when the contrast experiment.
Figure 2 shows that in the system adopt different request scheduling method system in data sending node the average data piece on time arrival rate with the situation of change in sampling time.FIFO represents First Come First Served scheduling mode (employing fifo queue), and EDF represents nearest deadline scheduling, and HPS represents mixing priority scheduling method disclosed by the invention.As seen from the figure, adopt the inventive method can obtain higher average data piece arrival rate on time, thereby have better media playback quality than other method.First Come First Served mode performance commonly used at present is the poorest relatively.
Figure 3 shows that in the system in data sending node and adopt the situation of change of the node uploading bandwidth utilization ratio of different request scheduling method system with the sampling time.Same Fig. 2 of picture in picture example (down together).The high more actual capacity that means that system has of node uploading bandwidth utilization ratio.Show among the figure that node uploading bandwidth utilization ratio is a little more than other two kinds of methods in the open method system of employing the present invention.
The average data piece of the system that Figure 4 shows that three kinds of methods under different scales condition arrival rate on time compares.As seen from the figure, along with system scale (node quantity) increases, arrival rate is on a declining curve on time for the average data piece in the system, but when node quantity is identical, the open method of the present invention in three kinds of methods, have a highest average data piece arrival rate on time.Be similar to Fig. 2 result, First Come First Served mode performance commonly used at present is the poorest relatively.
Figure 5 shows that node uploading bandwidth utilization ratio relatively in the system of system's three kinds of methods under the different scales condition.This figure clearly demonstrates under this experiment condition the open method of the present invention and can obtain obviously higher node bandwidth and upload utilance, and particularly when system scale was big, performance advantage of the present invention was more obvious.This is because rare degree priority scheduling has increased the diversity of data block in the system, thereby can improve the chance that each node obtains desired data.In three kinds of methods, node uploading bandwidth utilization ratio is minimum under the time limit priority scheduling method condition recently, because under this condition, data block sequence number distributes concentrated relatively, is unfavorable for improving node uploading bandwidth utilization ratio.
From above-mentioned experimental result as seen, disclosed by the invention based on mixing average data piece that Priority Queues request of data dispatching method can improve the P2P stream media system effectively than current First Come First Served request scheduling method commonly used and simple priority scheduling method arrival rate and node uploading bandwidth utilization ratio on time, thus the media playback quality of system improved.
Claims (2)
1. the P2P streaming media system data request scheduling method based on mixed dynamic priority queue is characterized in that: set up scheduling time limit Priority Queues and the rare degree Priority Queues of scheduling respectively in data sending node; In the request of data of sending by the Data Receiving node, include limit information and rare degree information when playing; When each request of data arrives data sending node, according to playing the scheduling time limit of time limit information calculations in data sending node, according to the rare degree of rare degree information calculations, and according to dispatching the relevant position that time limit and rare degree insert request of data respectively scheduling time limit Priority Queues and the rare degree Priority Queues of scheduling; In the data sending node configuration scheduling cycle, when begin each dispatching cycle, carry out data dispatch; Described data dispatch is, at first check scheduling time limit Priority Queues, if there is the scheduling time limit of request will be expired in next dispatching cycle, then dispatch this request of data, otherwise, check the rare degree Priority Queues of scheduling, if there is request of data, then request of data is the preceding arranged in scheduling, when each data dispatch is finished, and the modulated degrees of data request of deletion from two formations, and the scheduling time limit of each request of data in the time limit Priority Queues is dispatched in adjustment, if two formations are empty queue, then stop data dispatch, wait for the beginning of next dispatching cycle;
Wherein, the computational methods in the scheduling time limit of request of data are,
Numeration is CS according to block size, and media play speed is R, then individual data piece reproduction time: t=CS/R;
Note requested data block sequence number is SN
r, current just at played data block sequence number SN
p, then play time limit t
d=(SN
r-SN
p) * t;
Request sends node request transmission time stamp and is ts
s, the request time of reception stabs and is ts
r, request transmission time t
Rs=ts
r-ts
s
Request response node data block transmitting time td
s=max (CS/BW
s, CS/BW
r)+d
Ul, BW wherein
sExpression sends node bandwidth, BW
rExpression receives node bandwidth, d
UlIt is the up link time delay;
Be limited to t when then dispatching
s=t
d-t
Rs-td
s
Described broadcast time limit information comprises current just in the played data block sequence number with ask transmitting time for instructions and stab;
Described rare degree information is, at the copy amount of the requested data block of Data Receiving node record; The copy amount ÷ data block total number of rare degree=requested data block, in the rare degree Priority Queues of scheduling, request of data is according to rare degree sequence arrangement from small to large.
2. the P2P streaming media system data request scheduling method based on mixed dynamic priority queue according to claim 1 is characterized in that: described broadcast time limit information comprises plays time limit and request transmission time stamp.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2010101260421A CN101800704B (en) | 2010-03-17 | 2010-03-17 | P2P streaming media system data request scheduling method based on mixed dynamic priority queue |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2010101260421A CN101800704B (en) | 2010-03-17 | 2010-03-17 | P2P streaming media system data request scheduling method based on mixed dynamic priority queue |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN101800704A CN101800704A (en) | 2010-08-11 |
| CN101800704B true CN101800704B (en) | 2011-12-14 |
Family
ID=42596206
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2010101260421A Expired - Fee Related CN101800704B (en) | 2010-03-17 | 2010-03-17 | P2P streaming media system data request scheduling method based on mixed dynamic priority queue |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN101800704B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102158906B (en) * | 2011-05-19 | 2014-02-26 | 北京工业大学 | Service quality sensory system and task scheduling method thereof |
| CN102904833B (en) * | 2011-07-27 | 2015-07-08 | 中国科学院声学研究所 | Self-adaptive P2P (Peer-to-Peer) steam media data piece selection method and node |
| CN104731975A (en) * | 2015-04-13 | 2015-06-24 | 成都汇智远景科技有限公司 | Big data processing method |
| CN111416779B (en) * | 2020-03-27 | 2022-04-19 | 西安电子科技大学 | Internet service queue scheduling method based on time limit |
| CN112865934B (en) * | 2020-12-31 | 2022-11-01 | 京信网络系统股份有限公司 | Data transmission method, device, base station and storage medium |
| CN113315619B (en) * | 2021-06-02 | 2022-08-26 | 清华大学 | Data block deadline oriented multipath transmission control method and device |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101436946B (en) * | 2008-12-15 | 2011-06-15 | 香港应用科技研究院有限公司 | Method for scheduling data request in peer-to-peer sharing network |
-
2010
- 2010-03-17 CN CN2010101260421A patent/CN101800704B/en not_active Expired - Fee Related
Also Published As
| Publication number | Publication date |
|---|---|
| CN101800704A (en) | 2010-08-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101800704B (en) | P2P streaming media system data request scheduling method based on mixed dynamic priority queue | |
| CN104079501B (en) | Queue scheduling method based on multiple priorities | |
| EP2783490B1 (en) | Time-sensitive data delivery | |
| JP4951706B2 (en) | Queue-based adaptive chunk scheduling for peer-to-peer live streaming | |
| CN104734989B (en) | Data transfer throughput dispatching method based on token bucket and its system | |
| US7730238B1 (en) | Buffer management method and system with two thresholds | |
| US20090254659A1 (en) | Delayed Downloading Video Service Using Peer-to-Peer (P2P) Content Distribution Network | |
| Aggarwal et al. | Optimizing cloud resources for delivering IPTV services through virtualization | |
| US20090172157A1 (en) | Method and Device for Content Transmission on P2P Network | |
| US20100058406A1 (en) | System and method for content communication | |
| CN102307153A (en) | Virtual desktop transmission device and method | |
| CN104320672A (en) | Method for scheduling resources of live streaming media system under CDN-P2P hybrid architecture | |
| CN108462654B (en) | Enhanced GJB289A bus communication management and scheduling method | |
| CN109150756B (en) | Queue scheduling weight quantification method based on SDN power communication network | |
| CN105379212A (en) | Weighted ingest policy management in a content distribution network | |
| US20140195612A1 (en) | Queue-based adaptive chunk scheduling for peer-to-peer live streaming | |
| CN102158906A (en) | Service quality sensory system and task scheduling method thereof | |
| CN102138336B (en) | Moving-picture image data-distribution method | |
| CN101459585A (en) | P2P stream media data request method | |
| CN102882809A (en) | Network speed-limiting method and device based on message buffering | |
| CN102158767A (en) | Scalable-coding-based peer to peer live media streaming system | |
| Cui et al. | Dash+: Download multiple video segments with stream multiplexing of quic | |
| Yahia et al. | When HTTP/2 rescues DASH: Video frame multiplexing | |
| Guo et al. | Smooth workload adaptive broadcast | |
| CN109246487B (en) | Intelligent scheduling system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| C17 | Cessation of patent right | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20111214 Termination date: 20140317 |