CN100568957C - A kind of video frequency request program caching method based on the p2p technology - Google Patents
A kind of video frequency request program caching method based on the p2p technology Download PDFInfo
- Publication number
- CN100568957C CN100568957C CNB2007100535764A CN200710053576A CN100568957C CN 100568957 C CN100568957 C CN 100568957C CN B2007100535764 A CNB2007100535764 A CN B2007100535764A CN 200710053576 A CN200710053576 A CN 200710053576A CN 100568957 C CN100568957 C CN 100568957C
- Authority
- CN
- China
- Prior art keywords
- program
- data
- request
- institute
- hard disk
- 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
Abstract
The object of the present invention is to provide a kind of caching method of video frequency request program, the method is characterized in that, comprising: obtain the step of program request person's quantity of institute's request program, this step is used to obtain the program request number of nodes of institute's request program; Judge whether institute's request program is the step of hot programs, this step is used for judging according to program request person's quantity of institute's request program whether the program of institute's program request is hot programs; Non-hot programs is write the step of hard disk, this step be used for minimum use and the earliest data in buffer write hard disk.Because the present invention so can significantly reduce the read-write number of times of hard disk, obtains better user satisfaction for the scheme that non-hot programs adopts internal memory and hard disk cache to combine; For hot programs, directly adopt rare resource in the memory cache net, improved the efficient of buffer memory on the one hand, there is not hard disk cache on the other hand, do not need to read continually hard disk.
Description
Technical field
The present invention relates to the caching method of the video frequency request program in the P2P technology.
Background technology
In recent years, along with information autobahn, the fast development of compression of digital video and mass storage, video request program (Video-on-Demand, abbreviation VOD) service becomes a reality, and this makes that we can be quick, obtains the information that we need from streaming media server exactly.It allows information demander to select required information at any time, can be widely used in fields such as video request program, video monitoring, long-distance education.
What demand stream media system was handled mainly is multi-medium data, and that multi-medium data takies disk space usually is big, the transmission bandwidth height, and also the processor resource that takies when handling is bigger.Existing C/S pattern has been difficult to satisfy and has supported large-scale program request to use.
P-2-P technology (peer-to-peer is called for short P2P) has proposed solution for the problems referred to above.It allows the user can be directly connected to other user's computer, carries out file-sharing and exchange.The characteristics of the parallel Data transmission of its multiple spot have effectively utilized the network bandwidth, when improving transfer speed of data, have effectively utilized Internet resources, have lowered the load of server effectively.The main thought of distributed (P2P) buffer memory is exactly at each node deploy buffer memory, allows ordinary node also can provide data, services as server.
The design of cache replacement algorithm generally need be paid close attention to two problems, and promptly which content needs buffer memory; Which content need be eliminated from buffer memory.At first problem, general processing method is that the Streaming Media piece of each downloading and playing is all wanted buffer memory, its shortcoming is to cause easily in the not high and system of this node convection current row degree to be cached with the buffer memory of the Streaming Media of abundant copy, and replaces out the Streaming Media of the copy amount deficiency of popularity height and buffer memory.At second problem, general processing method is to adopt simply least often to use algorithm, this algorithm is eliminated the Streaming Media piece of nearest accessed least number of times on this node, and it only pays close attention to the Streaming Media popularity situation of this node statistics, the not situation of other nodes in the taking into account system.Replace the popularity that algorithm should be considered Streaming Media preferably for one, also should be concerned about the caching situation of this Streaming Media piece at other nodes.
Live broadcast system CoolStreaming system adopts the mode of program segments, segmentation is as the least unit of scheduling of resource and broadcast, each segmentation has comprised the video information in a second, sliding window with 120 section lengths just can constitute a buffer memory effectively, and the segmentation beyond the sliding window is not then within the limit of consideration of node.So, in practice, just can use 120 bits to represent a buffer memory mapping.If certain position is wherein put one, show that then the segmentation of this bit correspondence is effective, i.e. this segmentation has been stored in the buffer memory; Otherwise, if certain bit by zero setting, shows that then the segmentation of this bit correspondence is invalid.The sequence number of first segmentation is stored in two extra bytes in the sliding window.
CoolStreaming belongs to live broadcast system, and all node play position are more close, and data user rate is very high like this, and two minutes video segment of all each nodal caches just can satisfy the demand data of other nodes.
But VOD system is different, and user's the program request time is different, the video location of watching also differs greatly, add the VCR operation, user's play position is just disperseed more, so existing VOD system all is the shared rate that increases data between node by the buffer memory that increases program.But the memory size of personal computer is often limited, can not satisfy large-scale buffer memory demand, and existing system is mostly taked the hard disk cache strategy, after the data slot reception is complete, the hard disk that just writes direct, when receiving request of data, directly reading of data provides service from the hard disk.But simple hard disk cache strategy has following shortcoming: frequent disk read-write has brought damage to hard disk; Disk read-write is more much lower than memory read-write efficient.
Summary of the invention
The object of the present invention is to provide a kind of caching method of video frequency request program, this method can overcome the limited deficiency that can not satisfy large-scale buffer memory demand of memory size of above-mentioned personal computer, improves the efficient of buffer memory greatly.
The caching method of video frequency request program of the present invention is characterised in that, comprising: obtain the step of the program request number of nodes of institute's request program, this step is used to obtain the program request number of nodes of institute's request program; Judge whether institute's request program is the step of hot programs, this step is used for judging according to the program request number of nodes of institute's request program whether the program of institute's program request is hot programs; Non-hot programs is write the step of hard disk, this step be used for minimum use and the earliest data in buffer write hard disk; Check the step of memory cache total amount, this step is used to judge whether the memory cache sum surpasses the threshold value of regulation, if the memory cache sum surpasses the threshold value of regulation, then, deleting its mirror image in internal memory with minimum use and when data in buffer writes hard disk the earliest for non-hot programs for the junior segmentation of hot programs deletion buffer memory; Judge whether demand staging is buffered in the step of internal memory, this step is used for judging that whether the data of being asked are at internal memory when the valid data request that has from other node, if in internal memory, provide the data download service by internal memory, if the data of being asked not at internal memory, are then read the reflection of segment data on hard disk in the internal memory and by internal memory the data download service are provided.
The feature of the caching method of video frequency request program of the present invention also is, in the step of the program request number of nodes that obtains institute's request program, periodically obtains the program request number of nodes of institute's request program, and the scope of obtaining the cycle was set in 5～30 minutes.
The feature of the caching method of video frequency request program of the present invention also is, also comprises: the step of initialization sliding window, this step are used for log-on data service thread, data dispatch thread and play thread.
The feature of the caching method of video frequency request program of the present invention also is, also comprises: with the step that complete segmentation is registered in sliding window, this step is used for latest data is added buffer memory; Move the step of sliding window according to play position, this step is used for the buffer memory latest data.
Idea behind the present invention:,, need increase the buffer storage length of node greatly with respect to live broadcast system in order to improve internodal data sharing rate in the video on-demand system.And the cold and hot degree of program also affects internodal data sharing rate to a great extent, and for hot programs, the node of program request is many, and the buffer memory of buffer memory is also abundanter in the net, can suitably reduce the buffer storage length of each node; For non-hot programs, should suitably increase buffer storage length, increase the buffer memory quantity in the net, increase internodal data sharing rate.If adopt pure memory cache scheme, take too many memory source; If adopt pure hard disk cache scheme, frequent disk read-write also can cause very big damage to hard disk, and this is that the user is unacceptable.
Because the scheme for non-hot programs adopts internal memory and hard disk cache to combine so can significantly reduce the read-write number of times of hard disk, obtains better user satisfaction; For hot programs, directly adopt rare resource in the memory cache net, improved the efficient of buffer memory on the one hand, there is not hard disk cache on the other hand, do not need the frequent hard disk that reads.
Description of drawings
Fig. 1 is the flow chart of the caching method of video frequency request program of the present invention in the metadata cache stage.
Fig. 2 is the flow chart of caching method when service is provided for other node of video frequency request program of the present invention.
Fig. 3 is in the caching method of video frequency request program of the present invention, and node is from the schematic diagram of other node data download segmentation.
Fig. 4 is the sliding window schematic diagram in the caching method of video frequency request program of the present invention.
Embodiment
Followingly be elaborated with reference to the caching method of accompanying drawing to video frequency request program of the present invention.
Fig. 3 is in the caching method of video frequency request program of the present invention, and node is from the schematic diagram of other node data download segmentation.As shown in Figure 3, in video on-demand system based on p2p, program source generally all will adopt the way of segmentation, video data is divided into isometric or elongated data block, with the least unit of segmentation, so just can realize from the point-to-point scheme of a plurality of node foradownloaded video data as data dispatch and broadcast.Among the figure, 4 indicate downloads the node of segment data, 1,2,3 other nodes of being connected with node 4 of expression respectively.Node 4 has been downloaded different segment datas from different nodes respectively.Node has the characteristics of selfishness, node often more is ready can provide data, services to the node that data are provided oneself to those, so data that nodal cache is play recently, this is adopted the thought of sliding window, be used to manage data cached, the different nodes that play position is close can be by the distribution situation of mutual sliding window information acquisition resource segmentation like this, and then finishes the mutual download service between data.
Fig. 4 is the sliding window schematic diagram in the caching method of video frequency request program of the present invention.Suppose that each segmentation has comprised the video information of t1 time span (t1 generally got 10～20 seconds), the sliding window with n section length just can constitute a buffer memory effectively, and the segmentation beyond the sliding window is not then within the limit of consideration of node.Sliding window is responsible for the segment number Min of tag cache minimum, maximum segment number Max, play position Play, four initial segment numbers of byte records in front wherein, as shown in Figure 4.
Fig. 1 is the flow chart of the caching method of video frequency request program of the present invention in the metadata cache stage.Fig. 2 is the flow chart of caching method when service is provided for other node of video frequency request program of the present invention.Followingly the specific embodiment of the present invention is elaborated with reference to accompanying drawing.
In step 10, initialization sliding window, log-on data service thread, data dispatch thread and broadcast thread.The purpose of initialization sliding window is initialization buffer structure and some related linear programs.Sliding window is the control structure of buffer memory, download and broadcast; The data, services flow process is responsible for providing the data download service to other nodes; The data dispatch thread is responsible for the request scheduling and the reception of data, submits data to sliding window after the complete arrival of segment data; Play thread and be responsible for the decoding broadcast of media data, moving of sliding window moved according to play position in this flow process.
Whether in step 20, step 25, checking has complete segment data to arrive, if having then data are registered in sliding window.The main purpose in this step is that the latest data segmentation is added buffer memory.Segmentation is the least unit of data dispatch and broadcast, so just submit to after having only the segmentation reception complete, the data after the registration just can be play for this locality, the data download service is provided also can for other nodes.
In step 30, node periodically obtains the program request number of nodes P of institute's request program.Program request number of nodes P judges whether program is the foundation of hot programs.By an index server is set in system, the node of request program all must be registered on index server, the content of registration comprises the identifier, address, the identifier of institute's request program, the play position and the available bandwidth of node of node, index server just can be classified according to program like this, node to each program of program request carries out the statistic of classification index, and initiate like this node just can obtain the program request number of nodes of program from index server.In addition, want the access index server owing to obtain program request person's number needs of program, visit and too frequently can bring very big burden to index server, index obtains the period T of program request person's quantity (being temperature) can not be too small, T generally get 5～30 minutes proper.
In step 40, check the memory cache sum M, judge whether the memory cache sum surpasses prescribed threshold, when the memory cache sum M does not surpass the threshold value H2 of regulation, directly advances to step 70, moves sliding window according to play position and plays.When the memory cache sum M surpasses the threshold value H2 of regulation, advance to step 45, judge whether the program of institute's program request is hot programs, if be non-hot programs, advance to step 50, with minimum use and the earliest data in buffer write hard disk, and delete its mirror image (step 55) in internal memory; If hot programs then advances to step 60, the junior segmentation of buffer memory is deleted from internal memory.
H2 is the threshold values at the memory cache sum of non-hot programs, when memory cache quantity surpasses this threshold values, memory cache is write hard disk, deletes the Image Data on the corresponding internal memory then.Personal computer at the difference configuration can be provided with different threshold values H2, is traditionally arranged to be 50～100M, and the system bigger for internal memory can be set to bigger value, and the buffer memory more data can obtain better result of broadcast.
Judge that whether this program is that hot programs is to carry out according to the play-on-demand program person quantity P that obtains in step 30,, be judged to be hot programs, otherwise be non-hot programs when P surpasses when being used to distinguish the threshold value H1 of the cold and hot degree of program.H1 is a threshold values of distinguishing the cold and hot degree of program, and this threshold values is subjected to the restriction of internodal data transfer bandwidth and efficient.If VOD system is deployed in provinces and cities' scope, internodal like this physical connection is relatively reliable, and data transmission efficiency is more guaranteed, and H1 gets 100～200 like this; If the deployment nationwide, because the node data efficiency of transmission between zones of different is not high, so H1 gets more than 1000.The purpose of this step is according to the different buffering scheme of program temperature design.The interlude that obtains temperature at twice adopts previous temperature to carry out buffer memory.When program temperature situation may change twice visit the time in front and back, the scheme of storage was just at nearest data downloaded, to the not influence of former data.In the extensive video on-demand system of reality operation, the change of program temperature is fewer, and the program temperature is relatively all more stable.
At each segment data (no matter being that hot programs also is non-hot programs), need his historical operating position of statistics, this also is the main foundation that media data is write hard disk from internal memory.Less and the buffer memory segment data early for access times, the probability that they use afterwards is also relatively low, so temporarily these data are write hard disk, reduces the quantity of memory cache.And those frequencies of utilization are higher and up-to-date data in buffer, and the probability of Shi Yonging is higher from now on, and they are buffered in the internal memory, can accelerate the speed of data, services, avoid the data read to hard disk.
For hot programs, because the some broadcasting user is many, the metadata cache redundancy ratio is more, so we can suitably reduce buffer memory quantity, we adopt redundant buffer memory in view of the above.We are provided with a buffer memory grade to each segment data in redundant buffer memory,
If it is higher that the buffer memory grade compares, illustrate that this fragment data is rarer in the buffer memory of all nodes, and segmentation is newer, thus must priority cache, reduce the redundancy of metadata cache.Variable in the wherein top formula is to obtain by the periodic mutual cache information of the node that connects.
In step 70, move sliding window according to play position, for the segmentation of shifting out sliding window,, then data are registered in the ephemeral data formation if data are providing service, after data, services is finished, delete its data in the ephemeral data formation; If service is not provided, direct deleted data.The purpose in this step is mobile sliding window, the data that buffer memory is up-to-date.The data that shift out sliding window are the data that will eliminate, for hot programs, only adopt memory cache, need superseded buffer memory so only need delete the internal memory the inside; For non-hot programs, employing be the buffering scheme that internal memory and hard disk combine, so the buffer memory that the need of internal memory and hard disk the inside are eliminated all will be deleted.The data download service is provided for other nodes if just shifted out the data sementation of sliding window at that time, so these data is being put into the ephemeral data formation and continues to provide service, deleting these data automatically after the service known is finished.And the new segment data that moves into sliding window is given the request of data thread, and new media data is downloaded in request.
In step 80, check to play whether stop, if stop, finishing; Otherwise turn back to step 20.
Below the mode of data, services that provides of the present invention is described.
Provide the step of data download service as follows:
Whether in step 110, checking has the valid data request to arrive, and the main purpose in this step is to judge whether to need to give other nodes that the data download service is provided, if there is not the valid data request to arrive, advances to step 140, judges to play whether stop; If there is the valid data request to arrive, execution in step 115 judges whether the segmentation of being asked is buffered in the internal memory.In the buffer memory of data sementation in this locality of request (demand staging in sliding window time be called hit), request of data just is considered as effectively.If the segmentation of being asked not in internal memory, is read (step 120) in the internal memory with the hard disk image data of segmentation correspondence; If the segmentation of being asked is in internal memory, execution in step 130 provides the data download service by internal memory.
Node provides data, services can only pass through internal memory for other nodes, if data must be read data in the internal memory earlier on hard disk.The buffer memorys all for hot programs all (do not have hard disk cache) in internal memory, directly execution in step 130 provides the data download service by internal memory.What the buffer memory of non-hot programs adopted is the scheme that internal memory and hard disk combine, so if must read in the internal memory earlier less than buffer memory in internal memory.
In step 140, check to play whether stop, if stop, then finishing; Otherwise turn back to step 110.
More than explanation only is one embodiment of the present invention, can not limit the present invention, and any change that does not exceed theme of the present invention that those of ordinary skills made is as long as in the scope that the present invention asked, all in protection scope of the present invention.
Claims (4)
1, a kind of caching method of video frequency request program is characterized in that, comprising: obtain the step of the program request number of nodes of institute's request program, this step is used to obtain the program request number of nodes of institute's request program; Judge whether institute's request program is the step of hot programs, this step is used for judging according to the program request number of nodes of institute's request program whether the program of institute's program request is hot programs; Non-hot programs is write the step of hard disk, this step be used for minimum use and the earliest data in buffer write hard disk; Check the step of memory cache total amount, this step is used to judge whether the memory cache sum surpasses the threshold value of regulation, if the memory cache sum surpasses the threshold value of regulation, then, deleting its mirror image in internal memory with minimum use and when data in buffer writes hard disk the earliest for non-hot programs for the junior segmentation of hot programs deletion buffer memory; Judge whether demand staging is buffered in the step of internal memory, this step is used for judging that whether the data of being asked are at internal memory when the valid data request that has from other node, if the data sementation of being asked is in internal memory, then provide the data download service by internal memory, if the data sementation of being asked not in internal memory, is then read the reflection of segment data on hard disk in the internal memory and by internal memory the data download service is provided.
2, the caching method of video frequency request program as claimed in claim 1, it is characterized in that, in the step of the program request number of nodes that obtains institute's request program, periodically obtain the program request number of nodes of institute's request program, the scope of obtaining the cycle was set in 5～30 minutes.
3, the caching method of video frequency request program as claimed in claim 1 is characterized in that, also comprises: the step of initialization sliding window, this step are used for log-on data service thread, data dispatch thread and play thread.
4, the caching method of video frequency request program as claimed in claim 1 is characterized in that, also comprises: with the step that complete segmentation is registered in sliding window, this step is used for latest data is added buffer memory; Move the step of sliding window according to play position, this step is used for the buffer memory latest data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNB2007100535764A CN100568957C (en) | 2007-10-17 | 2007-10-17 | A kind of video frequency request program caching method based on the p2p technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNB2007100535764A CN100568957C (en) | 2007-10-17 | 2007-10-17 | A kind of video frequency request program caching method based on the p2p technology |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN101141623A CN101141623A (en) | 2008-03-12 |
| CN100568957C true CN100568957C (en) | 2009-12-09 |
Family
ID=39193322
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CNB2007100535764A Expired - Fee Related CN100568957C (en) | 2007-10-17 | 2007-10-17 | A kind of video frequency request program caching method based on the p2p technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN100568957C (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106970832A (en) * | 2017-03-14 | 2017-07-21 | 广东欧珀移动通信有限公司 | Information processing method, device and computer equipment |
Families Citing this family (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101551781B (en) * | 2009-05-22 | 2011-03-30 | 中国科学院计算技术研究所 | Method of magnetic disc cache replacement in P2P video on demand system |
| CN101707625B (en) * | 2009-11-27 | 2013-07-17 | 中国电信股份有限公司 | Method and system for caching P2P object |
| CN102263803B (en) * | 2010-05-24 | 2014-08-06 | 英华达(上海)电子有限公司 | Method, device and system for updating electronic book data |
| CN101944377A (en) * | 2010-08-17 | 2011-01-12 | 深圳市同洲电子股份有限公司 | Storage method and storage device for streaming media file and streaming media server |
| CN101951395B (en) * | 2010-08-30 | 2013-08-21 | 中国科学院声学研究所 | Access prediction-based data cache strategy for P2P Video-on-Demand (VoD) system server |
| CN102568525B (en) * | 2010-12-31 | 2015-02-18 | 新奥特（北京）视频技术有限公 | Intelligent buffer method on flow chart and time line |
| CN102404608A (en) * | 2011-11-30 | 2012-04-04 | 苏州奇可思信息科技有限公司 | Video on demand method based on point-to-point transmission of local area network |
| CN103747043A (en) * | 2013-12-24 | 2014-04-23 | 乐视网信息技术（北京）股份有限公司 | CDN server dispatching method, CDN control center and system |
| CN104243600A (en) * | 2014-09-26 | 2014-12-24 | 华南理工大学 | Three-section type quick buffering method for P2P (peer-to-peer) streaming media |
| CN104408164B (en) * | 2014-12-05 | 2018-05-18 | 北京国双科技有限公司 | Based on SSAS Tabular data analysis processing methods and device |
| CN105657442A (en) * | 2015-12-30 | 2016-06-08 | 北京奇艺世纪科技有限公司 | Video file generation method and system |
| CN106454396A (en) * | 2016-10-26 | 2017-02-22 | 山东浪潮商用系统有限公司 | Method for improving concurrency of live broadcast time shifted TV |
| CN108668142B (en) * | 2017-03-27 | 2021-02-12 | 华为技术有限公司 | Video playing method and device |
| CN108549525B (en) * | 2018-04-04 | 2022-07-15 | 北京蓝杞数据科技有限公司天津分公司 | Data storage and access method and device, electronic equipment and storage medium |
| CN109327710B (en) * | 2018-12-10 | 2021-08-03 | 网宿科技股份有限公司 | Method and device for determining cold and hot conditions of video stream of live broadcast system |
| CN109800181B (en) * | 2018-12-12 | 2021-05-04 | 深圳市景阳科技股份有限公司 | Disk-based data writing method, data writing device and terminal equipment |
| CN112449248A (en) * | 2019-08-28 | 2021-03-05 | 杭州海康威视系统技术有限公司 | Video data on demand method and device and video on demand node |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1643716A1 (en) * | 2004-09-03 | 2006-04-05 | Microsoft Corporation | A system and method for receiver driven streaming in a peer-to-peer network |
| CN1874490A (en) * | 2006-06-30 | 2006-12-06 | 华中科技大学 | Disk buffering method in use for video on demand system of peer-to-peer network |
| EP1811780A1 (en) * | 2006-01-24 | 2007-07-25 | Alcatel Lucent | Access node with caching function for video channels |
-
2007
- 2007-10-17 CN CNB2007100535764A patent/CN100568957C/en not_active Expired - Fee Related
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1643716A1 (en) * | 2004-09-03 | 2006-04-05 | Microsoft Corporation | A system and method for receiver driven streaming in a peer-to-peer network |
| EP1811780A1 (en) * | 2006-01-24 | 2007-07-25 | Alcatel Lucent | Access node with caching function for video channels |
| CN1874490A (en) * | 2006-06-30 | 2006-12-06 | 华中科技大学 | Disk buffering method in use for video on demand system of peer-to-peer network |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106970832A (en) * | 2017-03-14 | 2017-07-21 | 广东欧珀移动通信有限公司 | Information processing method, device and computer equipment |
| CN106970832B (en) * | 2017-03-14 | 2020-01-10 | Oppo广东移动通信有限公司 | Information processing method and device and computer equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN101141623A (en) | 2008-03-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN100568957C (en) | A kind of video frequency request program caching method based on the p2p technology | |
| CN105630423B (en) | A kind of correcting and eleting codes cluster-based storage expansion method based on data buffer storage | |
| KR101228230B1 (en) | Methods and apparatus for self-organized caching in a content delivery network | |
| US8612668B2 (en) | Storage optimization system based on object size | |
| CN104243425B (en) | A kind of method, apparatus and system carrying out Content Management in content distributing network | |
| CN100477787C (en) | Disk buffering method in use for video on demand system of peer-to-peer network | |
| CN103096126B (en) | Towards the cooperative caching method and system of video-on-demand service in cooperative caching cluster | |
| CN101060418B (en) | Special disk reading and writing system suitable for IPTV direct broadcast server with time shift | |
| CN104935648A (en) | High-cost-performance CDN system, and file pre-push and fragment buffer memory methods | |
| CN106649349A (en) | Method, device and system for data caching, applicable to game application | |
| WO2006012418A9 (en) | Distributed storage architecture based on block map caching and vfs stackable file system modules | |
| CN101207799A (en) | System and method for storing program and program ordering system | |
| CN109982104A (en) | The video of mobile awareness prefetches and caching Replacement Decision method in a kind of mobile edge calculations | |
| CN101330594B (en) | Method for storing VOD medium of equity network and media demanding system thereof | |
| CN101110844B (en) | Program fragment prefetching method and peer-to-peer network node | |
| CN101312522A (en) | Video play-on-demand system | |
| Uddin et al. | 360 degree video caching with LRU & LFU | |
| CN109451344A (en) | Based on the buffer replacing method of correlation rule in P2P stream media system | |
| CN103581051B (en) | A kind of file caching method, device and system | |
| CN109168023B (en) | Method for caching scalable video stream | |
| Ling et al. | An adaptive caching algorithm suitable for time-varying user accesses in VOD systems | |
| CN104837029A (en) | Method for storing and accessing resource hard disk of high-definition video-on-demand system | |
| Akhtar et al. | Hifi: A hierarchical filtering algorithm for caching of online video | |
| CN103365897A (en) | Fragment caching method supporting Bigtable data model | |
| JP6529577B2 (en) | Information Oriented Networking (ICN) Router |
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: 20091209 Termination date: 20121017 |