CN103297431A - Streaming media video-on-demand duplicate hybrid buffer strategy based on cloud server cluster - Google Patents
Streaming media video-on-demand duplicate hybrid buffer strategy based on cloud server cluster Download PDFInfo
- Publication number
- CN103297431A CN103297431A CN2013101985913A CN201310198591A CN103297431A CN 103297431 A CN103297431 A CN 103297431A CN 2013101985913 A CN2013101985913 A CN 2013101985913A CN 201310198591 A CN201310198591 A CN 201310198591A CN 103297431 A CN103297431 A CN 103297431A
- Authority
- CN
- China
- Prior art keywords
- video
- copy
- prefix
- server
- program request
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 claims abstract description 19
- 238000012217 deletion Methods 0.000 claims description 34
- 230000037430 deletion Effects 0.000 claims description 34
- 230000015654 memory Effects 0.000 claims description 30
- 230000001174 ascending effect Effects 0.000 claims description 4
- 230000006870 function Effects 0.000 claims description 3
- 230000007812 deficiency Effects 0.000 claims description 2
- 230000000903 blocking effect Effects 0.000 abstract 1
- 230000003139 buffering effect Effects 0.000 abstract 1
- 230000008901 benefit Effects 0.000 description 3
- 238000000151 deposition Methods 0.000 description 3
- 239000012634 fragment Substances 0.000 description 3
- 230000011218 segmentation Effects 0.000 description 3
- 239000002699 waste material Substances 0.000 description 2
- 208000037656 Respiratory Sounds Diseases 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000003542 behavioural effect Effects 0.000 description 1
- 238000000205 computational method Methods 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 206010037833 rales Diseases 0.000 description 1
- 230000010076 replication Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
Images
Abstract
The invention discloses a method for effectively buffering streaming media video-on-demand duplicate hybrid buffer strategy based on a cloud server cluster. The method includes performing prefix dynamic blocking on the video duplicates based on video duration, and utilizing a dynamic prefix and complete duplicate hybrid storage strategy to improve system efficiency and experience quality of users; confirming number of needed duplicates according to factors such as video hot degree and confirming two types of the duplicates (complete duplicates and prefix duplicates) on the basis of demanding rate, and dynamically segmenting prefixes of the prefix duplicates on the basis of video duration so as to generate the prefix duplicates; and when storage space is enough, utilizing a hot balance and load balance combining method to store the duplicates, and when storage space is not enough, smoothly deleting hot-degree-decreasing video duplicates based on time window threshold values. By the method, users can obtain good video-on-demand experience.
Description
Technical field
The present invention relates on the Cloud Server group hybrid cache strategy that copy to the streaming media video source file carries out dynamic prefix piecemeal and dynamically carries out prefix copy and complete copy, belong to the field of cloud storage.
Background technology
Streaming Media (particularly HD video) has that data volume is big, the demanding characteristics of real-time.The video copy storage policy has direct influence to the performance of system in the streaming media video VOD system.Utilize the Cloud Server group that video copy is carried out cache management, can improve systematic function.
User's program request behavior is relevant with network performance, if period of reservation of number is long, will abandon this video request program.Studies show that the streaming media video program request meets long tail effect, namely in all video frequency programs, the user is tending towards watching wherein 20% video frequency program, and these programs belong to popular video (higher popularity is arranged), and all the other 80% then belong to the unexpected winner video.How the inhomogeneous video of buffer memory temperature in Cloud Server is one of key factor that improves the user video Quality of experience.
At present, in order to solve that the focus video is concentrated and the problem that causes the server bottleneck, video is stored in Cloud Server and generally is divided into two kinds: based on the complete copy strategy with based on the storage policy of stick.
For the higher video of popularity, if the user that certain moment point is broadcast is too much, provide the server of this video can reach the bottleneck of handling up, make period of reservation of number lengthen, influence viewing experience.Storage based on copy is exactly that popular video is copied in other server of server cluster fully, and user's order request can all be given other server like this, reduces the load of individual server.
Based on stick storage video is carried out piecemeal according to certain mode, the different video piece of same video frequency program is pressed certain rale store in different servers, during the different fragments of user's program request video, load will be assigned in the different servers like this.
There are some problems in above-mentioned storage policy.(1) be that the memory space that takies is excessive based on the subject matter of complete copy buffer memory.Behavioural analysis to user's order video studies show that, 70% user sees can intactly not finish watching whole video, just wherein the sub-fraction that a lot of users watch, so complete copy is more many, the memory space of waste is just more many.In addition, because the copy buffer memory must dynamically carry out generation and the deletion of copy, make user's experience fluctuation occur.(2) because the different piecemeals of bar block cache video are placed in the different servers, make that the degree of coupling between the server increases, be unfavorable for the expansion of server cluster.If certain Cloud Server is out of order suddenly, the video segment that leaves in this server just can not be watched by the user.
In order to reduce user's program request time delay, commonly adopt the mode of proxy caching.General three kinds of proxy caching is based on total caching with based on the prefix buffer memory with based on the segmentation buffer memory.
The operation principle of acting server is, earlier a part of data of video flowing front are cached in the acting server that closes on the user, when user's order video, can respond the user fast, the pluses and minuses of three kinds of different buffer memorys are as follows: ⑴ is for total caching, its advantage is for shooting straight, and shortcoming is that to take memory space big.⑵ prefix buffer memory is commonly used is fixing prefix buffer memory, and employing is that the prefix of fixed proportion is carried out buffer memory exactly, is 30% prefix such as fixed value.Fixedly the shortcoming of prefix buffer memory is to adopt identical ratio without exception for all videos that will carry out buffer memory, can cause the hit rate difference of different video big like this.For example fixedly during prefix 30%, some video watch the integrity degree height, the hit rate of buffer memory is just low like this, and some video watch integrity degree low, 30% has just caused the space waste.Buffer memory for 50%, for watching the higher video of integrity degree, its hit rate is still not high, and watches the lower video of integrity degree, and wasting space is more.Low can the making of the hit rate of prefix obtained remaining video from the video source memory device in user's program request, all adopt prefix just to strengthen the I/O of video source server, causes bottleneck, can cause time delay to strengthen.⑶ segmentation buffer memory is divided into different fragments to video and carries out buffer memory.Advantage has been considered the program request rate difference of different fragments.Shortcoming, segmentation is too much, has increased the administration overhead of system.Be not easy to large-scale use.
The staff of Columbia University and Bell Laboratory follows the trail of the program request track of 1,300 ten thousand videos, found that the duration of video and the integrity degree of watching of video have tight association.When the duration of video own hour, the interruption rate that the user drops by the wayside is very low, when the video duration was longer, the value that the video that the user watches accounts for the total duration of video obviously reduced.This phenomenon is not applied in the copy cache policy at present.
Existing replication policy all is based on user's program request rate, and video temperature height just produces a plurality of copies, and the video temperature is low, just deletes copy.Copy is replaced the fluctuation that algorithm is not considered video request program yet, directly deletes copy, experience lf being influenced quality when causing the video temperature to fluctuate up and down easily.
Summary of the invention
Goal of the invention: the low problem of spatial cache utilance when the present invention mainly solves many copies and places, improve the program request hit rate, accelerated the program request response, and the problem of the influence of the variation of adaptive smooth video temperature.
Technical scheme: the present invention propose a kind of be suitable for the streaming media video program request based on dynamic prefix and complete copy hybrid cache method.This method is carried out effectively dynamically prefix at the characteristic of video request program and video duration and is cut apart, and prefix copy and complete copy hybrid cache are dynamically deleted copy when the video temperature changes.
This method comprises following content:
1. based on the dynamic prefix piecemeal of video duration
Be provided with the video frequency program V={V of n portion
1, V
2, V
3..., V
n, its video duration set is T, T={T
1, T
2, T
3..., T
n, the dynamic prefix block collection of each video copy is P among the video V, P={ P
1, P
2, P
3..., P
n.The dynamic division function is Dynamic_Prefix (), and dynamically the prefix method is following (annotates: video duration T in the algorithm
kUnit be second):
Dynamic_Prefix()
FOR?k=1?TO?k=n
IF?0＜T
k≤1000
P
k＝V
k；
ELSE?IF?1000＜T
k≤2000
P
k＝0.8V
k；
ELSE?IF?2000＜T
k≤4000
P
k＝0.6V
k；
ELSE?IF?4000＜T
k≤8000
ELSE?P
k＝0.3V
k；
END?IF
END FOR//traversal whole video sequence dynamically divides prefix
END//dynamically the prefix block algorithm finishes
2. mix copy and place strategy, comprise two parts content herein altogether, copy is placed and level and smooth deletion.
The copy laying method is as follows:
Timer triggers, and regularly adds up each video in total program request rate of server zone;
FOR?k=1?TO?k=n
The program request rate S of k video on each server zone of // accumulative total
k
IF S
k＜TH
1// judge whether to produce copy, TH
1Be threshold value 1
Directly jump to next circulation;
ELSE
Calculate required copy number; // the k video file program request rate is greater than TH
1, create a Copy
IF(complete copy program request rate/prefix copy program request rate)〉Th
2
The required copy type of // judgement, TH
2Be threshold value 2
Calculate the complete copy requisite space; The type of // copy is complete copy
ELSE
Calculate prefix copy requisite space; The type of // copy is the prefix copy
END?IF
Never deposit in the server set of video k and choose optimal service device S set ER;
While(m server ∈ SER) // and travel through the server of SER, whether the space is sufficient
IF m server space deficiency
Level and smooth deletion copy;
END?IF
Get the copy data of video k, be placed on the m server;
New directory more;
END While//SER server set has all been placed the copy of video k
END IF//k video of end judged the situation of copy
END FOR//end k=1TO k=n circulation travels through all video files that is over
END//copy is placed strategy and is finished
The level and smooth delet method of copy is as follows:
Removal request arrives;
The video sequence of storing on this server of While(video j ∈) // traversal this server in all videos
Program request rate＜Th of IF video j
3And total number of copies＞1 of video j in the server zone
Video j adds set V
c//V
cRecord video copy to be deleted
ELSE
J is the next video in the video sequence;
END?IF
END While//traveled through the video sequence on this server has found out video set V to be deleted
c
FOR c ∈ waits to delete video set V
c
IF c video copy creation-time〉time window threshold value TH
4//TH
4Can avoid repeating deleting and copying
The copy of deletion video c, and new directory more;
ELSE
Video c sequence number adds file set S
Cache// avoid the short time to delete the fluctuation S that brings
CacheIn video by the descending of program request rate, during identical program request rate by measure ascending order arrange;
// preferentially to delete temperature low, video capacious
END?IF
END FOR//end V
cV has been deleted in circulation
cThe middle copy time is greater than TH
4All video copy While(memory space inadequates)
R gets S set
CacheIn first element; //r sequence number is that the mapping IF r of certain video is the total complete copy number of r among complete copy and the Cloud Server group〉1
Deletion complete copy, and new directory more; A complete copy ELSE of the minimum reservation of // Cloud Server group IF r is the prefix copy;
Deletion prefix copy, and new directory more;
END?IF
Upgrade S
Cache, deletion S
CacheIn the r element;
END WHILE//this moment, this server stores space was sufficient
END//level and smooth deletion strategy finishes, and changes the placement step of copy over to
The program request rate account form of the dynamic prefix of single video and complete copy is:
The A on-demand content belongs in this video prefix scope, prefix program request number=prefix program request number+1,
The B on-demand content surpasses the prefix ranges of this video, complete video program request number=complete video program request number+1,
The summation of the program request number of this video among the C record Cloud Server group,
C=A+B。
Introduce copy rise time judgment threshold, prevent in the short time fluctuation of program request rate and make system's erroneous judgement and the deletion video of focus originally, avoided repeatedly carry out copying and deleting of copy.
Introduced two kinds of different deletion strategies, temperature is less than threshold value 3 and the copy rise time video sequence V greater than threshold value 4
c, the video of this sequence the inside all will directly be deleted.Temperature less than threshold value 3 but the copy rise time less than the video sequence S of threshold value 4
Cache, adopt a video of once only deleting in this sequence, whether decision space is sufficient then, and this method can reduce mistake and delete.
Introduced taking all factors into consideration of temperature and load, to these video S to be deleted
Cache, adopt based on the temperature descending, during identical temperature, according to the video big or small ascending order arrangement that takes up space.Based on the deletion that puts in order.
Useful result of the present invention is:
(1) dynamically carries out the prefix piecemeal based on the video duration, increased the video request program hit rate, with respect to the complete copy video, improved the utilance of spatial cache.
(2) adopt hybrid cache to place strategy, each server temperature equilibrium, simultaneously balance the load of server, increased the throughput of system.
(3) based on the level and smooth deletion strategy of time window, owing to introduced time window threshold value TH
4, avoided the deletion repeatedly that the fluctuation of video request program rate causes and copied, reduced the extra expense of system, improved user's program request Quality of experience.
(4) in the level and smooth deletion strategy, two kinds of different deletion strategies for a server, have been defined as the video sequence of non-temperature, and the video of this sequence is all deleted.For the video sequence that similar fluctuation temperature reduces, take preferentially to delete lower grade video, when temperature is identical, the preferential big video of delete capability.This deletion strategy can be quick, effectively deletion.
Description of drawings
The statistical chart of duration is watched by Fig. 1 Columbia University at 1,300 ten thousand video request program trajectory analysis video durations and user.
Fig. 2 is based on the copy hybrid cache strategy of prefix copy and complete copy
The level and smooth deletion strategy of Fig. 3 copy
Embodiment
A kind of copy hybrid cache strategy of the streaming media video program request based on the Cloud Server group comprises following content:
Content 1 according to Fig. 1 data, proposes a kind of new dynamic prefix method of partition based on the video duration.Can be seen that by Fig. 1 the duration of video is more short, it is more big by the ratio that the user watches, and on the contrary, the video duration is more long, and interrupt probability is more big midway for it.
Carry out the dynamic prefix piecemeal of video copy based on the video duration.Be provided with the video frequency program V={V of n portion
1, V
2, V
3..., V
n, its video duration set is T, T={T
1, T
2, T
3..., T
n, the dynamic prefix block collection of each video copy is P among the video V, P={P
1, P
2, P
3..., P
n.
For the video copy of wanting piecemeal, obtain the duration of its video.When the video duration belongs to 0-1000(sec), then the video copy prefix is complete video.
When the video duration belongs to 1000-2000(sec), then the video copy prefix is got video duration 80% and is carried out copy prefix buffer memory.
When the video duration belongs to 2000-4000(sec), then the video copy prefix is got video duration 60% and is carried out copy prefix buffer memory.
When the video duration belongs to 4000-8000(sec), then the video copy prefix is got video duration (90-3* video duration/400) % and is carried out copy prefix buffer memory.
When the video duration greater than 8000(sec) time, then the video copy prefix is got video duration 30% and is carried out copy prefix buffer memory.Content 2 is mixed copy and is placed strategy (seeing accompanying drawing 2).Comprise two parts content herein altogether, copy is placed, level and smooth deletion.
Copy placement flow process is as follows:
Step 201 adopts the timer mode, regularly monitors the program request rate of different video.
The program request rate account form of the dynamic prefix of video and complete copy:
(A) on-demand content belongs in this video prefix scope, prefix program request number=prefix program request number+1
(B) on-demand content surpasses the prefix ranges of this video, complete video program request number=complete video program request number+1
(C) certain video total program request number in server zone
（C）=（A）+（B）
Step 202 is judged the program request rate S of k video
kWhether greater than threshold value 1, if greater than threshold value 1, then forward step 203 to, otherwise just forward step 212 to.
Step 208 because server m memory space is inadequate, forwards level and smooth deletion strategy to, i.e. step 301.
Step 210 is upgraded the directory management among the Cloud Server group, records the server of the placement of this video, copy type, and the zero-time of placing.The program request rate of this copy is initialized as 0.
Step 211 judges whether the server of SER all travels through, if travel through, forwards 206 to, finishes if travel through, and the copy that shows the current video that will copy has been placed and finished, and turns to 212.
Level and smooth deletion algorithm step is as follows:
Step 302 is searched the video of depositing on this server, finds out the video that satisfies following two conditions simultaneously: among the ⑴ Cloud Server group total copy number greater than 1, ⑵ video temperature less than threshold value 3.This class video is mapped to V
cTabulation (depositing video sequence number to be deleted).
Step 303 is chosen V
cIn the video c that does not traverse
Step 304 is if the creation-time of c copy is greater than time window threshold value TH
4, represent that this video has belonged to the not high video of temperature really, forwards step 305 to.If creation-time is less than TH
4, represent that this video may be the fluctuation of the temperature in the short time, forwards step 306 to.
Step 305 is directly deleted its copy, and more new directory (step 314) forwards step 307 then to.
Step 307 is judged video sequence V
cWhether traversal is intact, if do not traveled through, forwards step 303 to, if traversal is finished, turns to step 308.
Step 308 judges whether the memory space of this server is sufficient, if sufficient, finishes level and smooth deletion strategy, forwards step 209 to and carries out the copy placement.Otherwise forward step 309 to.
Step 309 is got first element in the Scache set, and that define this element map is video r
More than show and described basic principle of the present invention and principal character and advantage of the present invention.The technical staff of the industry should be appreciated that; the present invention is not restricted to the described embodiments; that describes in above-described embodiment and the specification just illustrates principle of the present invention; without departing from the spirit and scope of the present invention; the present invention also has various changes and modifications; these changes and improvements all fall in the claimed scope of the invention, and the claimed scope of the present invention is defined by its equivalent of appending claims.
Claims (6)
1. the hybrid cache strategy of the video copy of a streaming media video VOD system is characterized in that:
Dynamic prefix piecemeal based on the video duration; Copy hybrid cache strategy in the Cloud Server cluster.
2. the hybrid cache strategy of the video copy of streaming media video VOD system according to claim 1 is characterized in that, based on the dynamic prefix piecemeal of video duration copy, its method is as follows:
Be provided with the video frequency program V={V of n portion
1, V
2, V
3..., V
n, its video duration set is T, T={T
1, T
2, T
3..., T
n, the dynamic prefix block collection of each video copy is P among the video V, P={P
1, P
2, P
3..., P
n; The dynamic division function is Dynamic_Prefix (), and dynamically the prefix method is as follows:
Dynamic_Prefix()
FOR?k=1?TO?k=n
IF?0＜T
k≤1000
P
k＝Ｖ
k；
ELSE?IF?1000＜T
k≤2000
P
k＝0.8V
k；
ELSE?IF?2000＜T
k≤4000
P
k＝0.6V
k；
ELSE?IF?4000＜T
k≤8000
ELSE?P
k＝0.3V
k；
END?IF
END FOR//traversal whole video sequence dynamically divides prefix
END//dynamically the prefix block algorithm finishes.
3. the hybrid cache strategy of the video copy of streaming media video VOD system according to claim 1 is characterized in that, copy hybrid cache strategy comprises that copy is placed and level and smooth deletion in the Cloud Server cluster,
The copy laying method is as follows:
Timer starts, and regularly adds up each video in total program request rate of server zone;
FOR?k=1?TO?k=n
The program request rate S of k video on each server zone of // accumulative total
k
IF S
k＜TH
1// judge whether to produce copy, TH
1Be threshold value 1
Directly jump to next circulation;
ELSE
Calculate required copy number; // the k video file program request rate is greater than TH
1, create a Copy
IF is complete copy program request rate/prefix copy program request rate〉TH
2
The required copy type of // judgement, TH
2Be threshold value 2
Calculate the complete copy requisite space; The type of // copy is complete copy
ELSE
Calculate prefix copy requisite space; The type of // copy is the prefix copy
END?IF
Never deposit in the server set of video k and choose optimal service device S set ER;
While(m server ∈ SER) // and travel through the server of SER, whether the space is sufficient
IF m server space deficiency
Level and smooth deletion copy;
END?IF
Get the copy data of video k, be placed on the m server;
New directory more;
END While//SER server set has all been placed the copy of video k
END IF//k video of end judged the situation of copy
END FOR//end k=1TO k=n circulation travels through all video files among the Cloud Server group that is over
END//copy is placed strategy and is finished.
4. the hybrid cache strategy of the video copy of streaming media video VOD system according to claim 3 is characterized in that, the level and smooth deletion strategy method of copy is as follows:
The video removal request arrives;
The video sequence of storing on this server of While(video j ∈) // traversal this server in all videos
Program request rate＜TH of IF video j
3And total number of copies＞1 of video j in the server zone
Video j adds set V
c//V
cRecord video copy to be deleted
ELSE
J is the next video in the video sequence;
END?IF
END While//traveled through the video sequence of storing on this server has found out the video set that will delete
FOR c ∈ waits to delete video set V
c
IF c video copy creation-time〉time window threshold value TH
4//TH
4Can avoid repeating deleting and copying
The copy of deletion video c, and new directory more;
ELSE
Video c sequence number adds file set S
Cache// avoid the short time to delete the fluctuation that brings
S
CacheIn video by the descending of program request rate, during identical program request rate by measure ascending order arrange;
// preferentially to delete temperature low, video capacious
END?IF
END FOR//end V
cV has been deleted in circulation
cThe middle copy time is greater than TH
4All video copy While(memory space inadequates)
R gets S set
CacheIn first element; //r refers to the sequence number of video, is the total complete copy number of r among complete copy and the Cloud Server group corresponding to certain video IF r〉1
Deletion complete copy, and new directory more; A complete copy ELSE of the minimum reservation of // Cloud Server group IF r is the prefix copy;
Deletion prefix copy, and new directory more;
END?IF
Upgrade S
Cache, deletion S
CacheIn the r element;
END WHILE//this moment, this server stores space was sufficient
END//level and smooth deletion strategy finishes, and changes the placement step of copy over to.
5. according to the hybrid cache strategy of the video copy of the described streaming media video VOD system of claim 3, it is characterized in that the program request rate account form of prefix copy and complete copy is:
The A on-demand content belongs in this video prefix scope, prefix program request number=prefix program request number+1,
The B on-demand content surpasses the prefix ranges of this video, complete video program request number=complete video program request number+1,
The summation of the program request number of this video among the C record Cloud Server group,
C=A+B。
6. the hybrid cache strategy of the video copy of streaming media video VOD system according to claim 4 is characterized in that, the level and smooth deletion strategy method of copy has two kinds:
A, temperature are less than threshold value 3 and the copy rise time video sequence V greater than threshold value 4
c, the video of this sequence the inside all will directly be deleted.
B, temperature less than threshold value 3 but the copy rise time less than the video sequence S of threshold value 4
Cache, adopt a video of once only deleting in this sequence, whether decision space is sufficient then.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310198591.3A CN103297431B (en) | 2013-05-24 | 2013-05-24 | A kind of streaming media video video-on-demand duplicate hybrid buffer method based on Cloud Server group |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310198591.3A CN103297431B (en) | 2013-05-24 | 2013-05-24 | A kind of streaming media video video-on-demand duplicate hybrid buffer method based on Cloud Server group |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103297431A true CN103297431A (en) | 2013-09-11 |
| CN103297431B CN103297431B (en) | 2016-07-13 |
Family
ID=49097751
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310198591.3A Expired - Fee Related CN103297431B (en) | 2013-05-24 | 2013-05-24 | A kind of streaming media video video-on-demand duplicate hybrid buffer method based on Cloud Server group |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103297431B (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103973780A (en) * | 2014-04-25 | 2014-08-06 | 华中科技大学 | Resource allocation and overhead optimization method for cloud video |
| CN104219534A (en) * | 2014-08-27 | 2014-12-17 | 烽火通信科技股份有限公司 | System and method for implementing cloud storage agency by using Linux set top box |
| CN109981532A (en) * | 2017-12-27 | 2019-07-05 | 中移（杭州）信息技术有限公司 | A kind of transmission method and server of media file |
| CN110531939A (en) * | 2019-09-10 | 2019-12-03 | 南京焦点领动云计算技术有限公司 | A kind of video on-demand system disk space optimization method |
| CN111198729A (en) * | 2020-01-10 | 2020-05-26 | 腾讯科技（深圳）有限公司 | Static resource loading method and device, computer equipment and storage medium |
| CN112312162A (en) * | 2020-10-16 | 2021-02-02 | 安擎(天津)计算机有限公司 | Video server for transmitting video stream |
| CN113825015A (en) * | 2021-09-17 | 2021-12-21 | 吴修文 | Large-scale concurrent video plug flow acceleration and management method |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050033856A1 (en) * | 2000-08-01 | 2005-02-10 | Fulu Li | Method and apparatus for broadcasting media objects with guaranteed quality of service |
| CN1996996A (en) * | 2006-12-19 | 2007-07-11 | 北京邮电大学 | The method for stream media file buffer for the mobile stream media proxy server |
| US20100095331A1 (en) * | 2008-10-14 | 2010-04-15 | Volker Friedrich Hilt | Method and apparatus for performing template-based prefix caching for use in video-on-demand applications |
| CN102333126A (en) * | 2011-10-15 | 2012-01-25 | 西安交通大学 | Streaming media on demand method based on Hadoop and virtual streaming media server cluster |
-
2013
- 2013-05-24 CN CN201310198591.3A patent/CN103297431B/en not_active Expired - Fee Related
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050033856A1 (en) * | 2000-08-01 | 2005-02-10 | Fulu Li | Method and apparatus for broadcasting media objects with guaranteed quality of service |
| CN1996996A (en) * | 2006-12-19 | 2007-07-11 | 北京邮电大学 | The method for stream media file buffer for the mobile stream media proxy server |
| US20100095331A1 (en) * | 2008-10-14 | 2010-04-15 | Volker Friedrich Hilt | Method and apparatus for performing template-based prefix caching for use in video-on-demand applications |
| CN102333126A (en) * | 2011-10-15 | 2012-01-25 | 西安交通大学 | Streaming media on demand method based on Hadoop and virtual streaming media server cluster |
Non-Patent Citations (2)
| Title |
|---|
| HWANG K W，ET AL: ""Leveraging video viewing patterns for optimal content placement"", 《NETWORKING 2012. SPRINGER BERLIN HEIDELBERG》, 25 May 2012 (2012-05-25), pages 44 - 58 * |
| 吴小明: ""基于P2P技术的混合流媒体代理缓存研究"", 《中国优秀硕士学位论文全文数据库 信息科技辑》, 15 February 2008 (2008-02-15), pages 16 - 19 * |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103973780A (en) * | 2014-04-25 | 2014-08-06 | 华中科技大学 | Resource allocation and overhead optimization method for cloud video |
| CN103973780B (en) * | 2014-04-25 | 2018-05-22 | 华中科技大学 | A kind of resource allocation of cloud video and expense optimization method |
| CN104219534A (en) * | 2014-08-27 | 2014-12-17 | 烽火通信科技股份有限公司 | System and method for implementing cloud storage agency by using Linux set top box |
| CN109981532A (en) * | 2017-12-27 | 2019-07-05 | 中移（杭州）信息技术有限公司 | A kind of transmission method and server of media file |
| CN110531939A (en) * | 2019-09-10 | 2019-12-03 | 南京焦点领动云计算技术有限公司 | A kind of video on-demand system disk space optimization method |
| CN110531939B (en) * | 2019-09-10 | 2022-09-02 | 南京焦点领动云计算技术有限公司 | Disk space optimization method for video-on-demand system |
| CN111198729A (en) * | 2020-01-10 | 2020-05-26 | 腾讯科技（深圳）有限公司 | Static resource loading method and device, computer equipment and storage medium |
| CN111198729B (en) * | 2020-01-10 | 2021-07-20 | 腾讯科技（深圳）有限公司 | Static resource loading method and device, computer equipment and storage medium |
| CN112312162A (en) * | 2020-10-16 | 2021-02-02 | 安擎(天津)计算机有限公司 | Video server for transmitting video stream |
| CN113825015A (en) * | 2021-09-17 | 2021-12-21 | 吴修文 | Large-scale concurrent video plug flow acceleration and management method |
| CN113825015B (en) * | 2021-09-17 | 2024-02-13 | 吴修文 | Large-scale concurrent video push accelerating and managing method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103297431B (en) | 2016-07-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103297431A (en) | Streaming media video-on-demand duplicate hybrid buffer strategy based on cloud server cluster | |
| CN102447973B (en) | Method, device and system for cache regulation | |
| CN104243425B (en) | A kind of method, apparatus and system carrying out Content Management in content distributing network | |
| CN104967861B (en) | Video caching system and method in CDN network | |
| US8745262B2 (en) | Adaptive network content delivery system | |
| US8612668B2 (en) | Storage optimization system based on object size | |
| CN105049254B (en) | Data buffer storage replacement method based on content rating and popularity in a kind of NDN/CCN | |
| CN101472166B (en) | Method for caching and enquiring content as well as point-to-point medium transmission system | |
| US9767033B2 (en) | Method and apparatus for managing cache memory in communication system | |
| CN101179494B (en) | Resource distribution method facing to network multimedia transmission service | |
| CN103260050A (en) | Video-on-demand system based on Google App Engine Cloud platform | |
| CN101068341B (en) | Stream media dispatching system and medium file scheduling method thereof | |
| CN101304514A (en) | VOD system as well as data caching method and scheduling server thereof | |
| CN101741884A (en) | Distributed storage method and device | |
| CN112788139A (en) | Block chain storage capacity optimization method and system | |
| Li et al. | A cost-effective resource allocation and management scheme for content networks supporting IPTV services | |
| CN103414747A (en) | Adaptive streaming media caching method | |
| Akhtar et al. | Avic: a cache for adaptive bitrate video | |
| CN107273310A (en) | A kind of read method of multi-medium data, device, medium and equipment | |
| CN108881943B (en) | Node cache replacement method based on elimination index in P2P streaming media on-demand system | |
| JP3999004B2 (en) | Content management method | |
| CN103581051A (en) | File buffering storage method and device and system | |
| CN110740374B (en) | Multimedia data processing method and device, computer equipment and storage medium | |
| CN116193170A (en) | Video cartoon scheduling method, device, medium and equipment | |
| Ling et al. | An adaptive caching algorithm suitable for time-varying user accesses in VOD systems |
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 | ||
| EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20130911 Assignee: Jiangsu Nanyou IOT Technology Park Ltd. Assignor: NANJING University OF POSTS AND TELECOMMUNICATIONS Contract record no.: 2016320000207 Denomination of invention: Streaming media video-on-demand duplicate hybrid buffer method based on cloud server cluster Granted publication date: 20160713 License type: Common License Record date: 20161109 |
|
| LICC | Enforcement, change and cancellation of record of contracts on the licence for exploitation of a patent or utility model | ||
| EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20130911 Assignee: NANJING GMINNOVATION TECHNOLOGY Co.,Ltd. Assignor: NANJING University OF POSTS AND TELECOMMUNICATIONS Contract record no.: 2017320000157 Denomination of invention: Streaming media video-on-demand duplicate hybrid buffer method based on cloud server cluster Granted publication date: 20160713 License type: Common License Record date: 20170628 |
|
| EC01 | Cancellation of recordation of patent licensing contract |
Assignee: Jiangsu Nanyou IOT Technology Park Ltd. Assignor: NANJING University OF POSTS AND TELECOMMUNICATIONS Contract record no.: 2016320000207 Date of cancellation: 20180116 |
|
| EC01 | Cancellation of recordation of patent licensing contract | ||
| EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20130911 Assignee: Nanjing jinxuetang Information Technology Co.,Ltd. Assignor: NANJING University OF POSTS AND TELECOMMUNICATIONS Contract record no.: X2020980006913 Denomination of invention: A hybrid caching method for VOD copies of streaming media based on Cloud Server Cluster Granted publication date: 20160713 License type: Common License Record date: 20201020 |
|
| EE01 | Entry into force of recordation of patent licensing contract | ||
| EC01 | Cancellation of recordation of patent licensing contract |
Assignee: Nanjing jinxuetang Information Technology Co.,Ltd. Assignor: NANJING University OF POSTS AND TELECOMMUNICATIONS Contract record no.: X2020980006913 Date of cancellation: 20220304 |
|
| EC01 | Cancellation of recordation of patent licensing contract | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20160713 |