CN107295358A - A kind of 3D Streaming Media storage methods under cloud environment - Google Patents
A kind of 3D Streaming Media storage methods under cloud environment Download PDFInfo
- Publication number
- CN107295358A CN107295358A CN201610786057.8A CN201610786057A CN107295358A CN 107295358 A CN107295358 A CN 107295358A CN 201610786057 A CN201610786057 A CN 201610786057A CN 107295358 A CN107295358 A CN 107295358A
- Authority
- CN
- China
- Prior art keywords
- files
- stream media
- video
- server
- popularity
- 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
- 238000003860 storage Methods 0.000 title claims abstract description 44
- 238000000034 method Methods 0.000 title claims abstract description 27
- 238000009826 distribution Methods 0.000 claims description 15
- 230000005540 biological transmission Effects 0.000 claims description 13
- 238000009825 accumulation Methods 0.000 claims description 7
- 238000001514 detection method Methods 0.000 claims description 6
- 230000000717 retained effect Effects 0.000 claims 1
- 238000012544 monitoring process Methods 0.000 description 16
- 238000005516 engineering process Methods 0.000 description 7
- 238000007726 management method Methods 0.000 description 7
- 238000012546 transfer Methods 0.000 description 7
- 230000004044 response Effects 0.000 description 6
- 238000002474 experimental method Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- PEDCQBHIVMGVHV-UHFFFAOYSA-N Glycerine Chemical compound OCC(O)CO PEDCQBHIVMGVHV-UHFFFAOYSA-N 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 230000007812 deficiency Effects 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000000630 rising effect Effects 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- 238000007619 statistical method Methods 0.000 description 2
- 238000005303 weighing Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013144 data compression Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000032798 delamination Effects 0.000 description 1
- 238000000151 deposition Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 239000010985 leather Substances 0.000 description 1
- 230000035800 maturation Effects 0.000 description 1
- 230000000116 mitigating effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000010076 replication Effects 0.000 description 1
- 230000004043 responsiveness Effects 0.000 description 1
- 238000005728 strengthening Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/23—Processing of content or additional data; Elementary server operations; Server middleware
- H04N21/231—Content storage operation, e.g. caching movies for short term storage, replicating data over plural servers, prioritizing data for deletion
- H04N21/23103—Content storage operation, e.g. caching movies for short term storage, replicating data over plural servers, prioritizing data for deletion using load balancing strategies, e.g. by placing or distributing content on different disks, different memories or different servers
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/23—Processing of content or additional data; Elementary server operations; Server middleware
- H04N21/231—Content storage operation, e.g. caching movies for short term storage, replicating data over plural servers, prioritizing data for deletion
- H04N21/23113—Content storage operation, e.g. caching movies for short term storage, replicating data over plural servers, prioritizing data for deletion involving housekeeping operations for stored content, e.g. prioritizing content for deletion because of storage space restrictions
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/23—Processing of content or additional data; Elementary server operations; Server middleware
- H04N21/239—Interfacing the upstream path of the transmission network, e.g. prioritizing client content requests
- H04N21/2393—Interfacing the upstream path of the transmission network, e.g. prioritizing client content requests involving handling client requests
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/23—Processing of content or additional data; Elementary server operations; Server middleware
- H04N21/24—Monitoring of processes or resources, e.g. monitoring of server load, available bandwidth, upstream requests
- H04N21/2405—Monitoring of the internal components or processes of the server, e.g. server load
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
- H04N21/258—Client or end-user data management, e.g. managing client capabilities, user preferences or demographics, processing of multiple end-users preferences to derive collaborative data
- H04N21/25866—Management of end-user data
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
- H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
- H04N21/262—Content or additional data distribution scheduling, e.g. sending additional data at off-peak times, updating software modules, calculating the carousel transmission frequency, delaying a video stream transmission, generating play-lists
- H04N21/26291—Content or additional data distribution scheduling, e.g. sending additional data at off-peak times, updating software modules, calculating the carousel transmission frequency, delaying a video stream transmission, generating play-lists for providing content or additional data updates, e.g. updating software modules, stored at the client
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
- H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
- H04N21/43—Processing of content or additional data, e.g. demultiplexing additional data from a digital video stream; Elementary client operations, e.g. monitoring of home network or synchronising decoder's clock; Client middleware
- H04N21/442—Monitoring of processes or resources, e.g. detecting the failure of a recording device, monitoring the downstream bandwidth, the number of times a movie has been viewed, the storage space available from the internal hard disk
- H04N21/44204—Monitoring of content usage, e.g. the number of times a movie has been viewed, copied or the amount which has been watched
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Databases & Information Systems (AREA)
- Computer Graphics (AREA)
- General Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Two-Way Televisions, Distribution Of Moving Picture Or The Like (AREA)
- Information Transfer Between Computers (AREA)
Abstract
The invention discloses the 3D Streaming Media storage methods under a kind of cloud environment.This method is:1) for a files in stream media, server is the videogram node of files in stream media application one;2) using the preceding M% of the files in stream media as the copy storage of the files in stream media to server, and a video link is set up, by video link storage to the videogram node;3) the video popularity of the files in stream media is updated with playing duration according to the video-on-demand times of the files in stream media in the period of setting length;If the video popularity of the video file exceedes the popularity threshold value of setting, then judge the files in stream media as high popularity video file, the complete copy of the files in stream media is stored onto the server, and the complete copy of the files in stream media is respectively stored on current online multiple user nodes for meeting setting rank.Present invention section space-efficient efficiency, which has, significantly to be increased, while user's request can be responded quickly and efficiently.
Description
Technical field
The invention belongs to network technology and field of multimedia communication, it is related to the 3D Streaming Medias storage side under a kind of cloud environment
Method.
Background technology
With the prosperity deeply with digital equipment Market of IT application process, the data volume that the whole world is produced is just with every about two
The speed that year doubles increases, and information data is as more and more important modern assets.The further investigation of cloud computing simultaneously with it is fast
Speed development, becomes a kind of new infrastructure service facility, can charging is taken on demand whenever and wherever possible just as water power.
Efficient green data and computing capability, and the large-scale distributed storage of different internets and E-business applications can be supported
And computing capability, become the important Floor layer Technology for building Next Generation Internet and e-commerce services platform.
In the late two decades, as developing rapidly for network infrastructure there occurs great change with maturation, technique for video broadcasting
Leather, the appearance of 3D videos makes the transmission of video in future to be not only limited to 2D videos.However, because 3D videos need multiple viewpoints
Video content, therefore be compared to 2D Streaming Medias, 3D Streaming Medias need to play multiple frames in synchronization, while also to include
Colour information and depth information, so as to cause the huge redundant data of 3D Streaming Media needs.Simultaneously as the limitation of bandwidth to regarding
The storage transmission of frequency and play quality problem cause very big inconvenience, and people have to face under so slow network speed
The problem of plenty of time and 3D video pictures that download occupies needed for the 3D video file transfers of big internal memory in itself play fuzzy.
However, the characteristic of stream determines that when taking stream transmission the media such as sound, video or animation are by video and audio service
Device is finished to the uninterrupted transmission of subscriber computer so user need not all download when whole file, and need to only be passed through several
Second or less start-up study can be watched.
At present, mainly there are two kinds of methods of service in terms of transmission of video:C/S modes and P2P modes.But, according to C/S
Pattern, i.e., individually provide order program service by server, because server load is heavy caused by the performance bottleneck of system, exist
The common problems such as server performance is not enough, bandwidth is inadequate, resource repeated construction, resource insufficient memory, cause Streaming Media to take
Business ability is reduced, so that user can be made to submit request response slow or even response failure;If being carried by the user node in P2P networks
For service, then unstable user node is difficult to ensure that the stability and availability of information resources, so as to cause user please
Response is asked to interrupt, meanwhile, the occupancy client resource that the technology can be excessive, it is desirable to which client terminal has higher performance, not
The problem of having effective settlement server bottleneck and magnanimity seascape data storage.Therefore for the QoS security problems of system, two kinds
Mode all has deficiency.
The content of the invention
In order to overcome the shortcomings of existing transmission of video method of service, the present invention combines Cloud-P2P system storage models
There is provided a kind of storage method of 3D Streaming Medias, including 3DVSCP (3D video storage based on Cloud-
P2P, the Streaming Media storage algorithm based on Cloud-P2P systems) and UDCP (User on demand based on Cloud-
P2P, user's program request algorithm based on Cloud-P2P systems), define the popularity and user gradation of new 3D Streaming Medias.This
By combining the advantage of existing two kinds of methods of service, there is provided the thought that cloud storage is combined with stream media technology for invention.Due to
3D videos need the video content of multiple viewpoints, therefore are compared to 2D Streaming Medias, and 3D Streaming Medias need to play in synchronization
Multiple frames, while colour information and depth information are also included, so that cause the huge redundant data of 3D Streaming Media needs, because
Data volume, is carried out data compression than larger streaming media resource, server and user node is then stored in a distributed manner by this
On, each back end is allocated using load-balancing technique, alleviates the pressure of server and network.It can so optimize
Stream Media Application many deficiencies, while system cost and administration fee can also be saved, simplify managing, further for resource
Realize the fully shared of educational resource.Simultaneously, it is contemplated that network bandwidth transmission bottleneck, 3D Streaming Medias need progress to be divided into size
The block of the network bandwidth is met, by the method for Delamination Transmission, and on hardware device, the transmission service of 3D Streaming Medias needs more
Big and more stable bandwidth.In summary, i.e., stored, be transmitted by piecemeal with layering by compressing.
The technical scheme is that:
A kind of 3D Streaming Media storage methods under cloud environment, its step is:
1. on transmitting file:
1) whenever having a 3D video distribution or being uploaded by user, carry out copy by server end and set up to deposit with copy
Storage distribution and management.Simultaneously for one videogram node of video application, because be the video resource newly added, therefore by video
Popularity threshold value initial value be set to peak.
2) it is 3 to set high popularity Streaming Media number of copies.Encoded program test, can be minimum when number of copies is 3
It is required that lower basic guarantee ensures must there is a complete copy in server node.It has been investigated that, when number of copies H is less,
With copy number H increase, user data requests by user node service to probability increase, node accumulation layer transfer rate β c
It is in rising trend.When copy amount increases to certain value, with copy amount H continuation increase, node accumulation layer transfer rate β
The trend of c increases slows down, and gradually levels off to 100%.Streaming media files carry out piecemeal, and the two-way of each 3D video is regarded
Preceding the 20% of frequency sets up copy storage to server end respectively, and sets up a video link, and link storage is arrived into the video
Directory node on.
3) by system-monitoring module statistics within certain period the video-on-demand times of the video and playing duration (using day for singly
Position), more new video stream row degree, while being resequenced according to popularity to video storage catalogue, high popularity is regarded accordingly
Frequency is placed into catalogue leading portion.Whether the 3D videos popularity that monitoring module detection simultaneously have modified exceedes popularity threshold value, if
More than the threshold value, then judge that the video, as high popularity video file, the complete copy storage of the two-way video of the video is arrived
In a certain amount of physical memory of server, while the complete copy of the video is respectively stored into current online multiple meet
On the user node for setting rank, advanced level user's node is typically chosen for.
2. user sends order request:
1) user obtains and browses video storage catalogue of the backup in server, selectes video and carries out program request.
2) server obtains the popularity of user gradation and order video, with reference to current server service centre performance threshold
Value, the order request to the user is allocated and handles, choose whether to provide server service and user node service and
Which user node service is provided by.
3) due to simply storing its preceding 20% copy on the server for the low 3D Streaming Medias of popularity, therefore, when
When there are the relatively low 3D Streaming Medias of user's program request popularity, the complete copy of 3D Streaming Medias is temporarily stored to a certain node of server
On, after finishing, according to its popularity and popularity threshold value relatively decide whether retain complete copy.
4) server data administrative center obtains the grade of current online user node and line duration carries out a team
Row sequence (last node of queue is server node), the replica node first before queue provides service, if currently
There is provided service replica node offline, then service is provided by queue next node, to ensure reliability.
5) when logging in system by user, timing is carried out by monitoring modular, while whether monitoring active user uploads text in real time
Part, sends corresponding data to control data corporation, and carry out corresponding space distribution if upper transmitting file;When user exits
During system, user gradation is updated according to the accumulation line duration of user.User gradation determines the ranking replacement of User Catalog (with the moon
For unit).
Further, popularity is used for weighing some files in stream media pouplarity within certain a period of time, from certain
It can be regarded as the probability that files in stream media is requested by a user at the following a certain moment, therefore the stream of some Streaming Media in meaning
Row degree is to be difficult to predict.At present, the prediction algorithm for Streaming Media popularity is carried out by the historical record of Streaming Media mostly
Statistical analysis.Universal 3D Streaming Medias popularity is determined jointly by the playing duration of the number of times and the Streaming Media of user's program request media
Fixed.The concept of a video weight will be proposed herein, and it is determined by the time difference of video distribution time and current time.
Meanwhile, the popularity of 3D Streaming Medias is continually changing with the time, therefore it one day is a period to choose.So
If it is to open after 3D files in stream media that can ignore user when doing, do not go to watch for a long time, then so will
The popularity of 3D files in stream media is had influence on.The popularity of files in stream media has been arrived in embodiment well in certain limit for this
Size, so as to more conform to the experience of the process of user, so can more be concerned about the files in stream media that user is really liked, carry
High service request rate.
It is well known that being shown initial stage in video, scattered version of trying to be the first occurs in network, and the temperature of user is not high, with
Appearance of the legal video on network, the popularity of video reaches a peak, and then video popularity will have one
Huge landing, over time, video popularity tend towards stability finally substantially.Therefore, it can be said that video weight is obeyed
The Poisson distribution of time difference.
Further, according to the popularity size of each Streaming Media of Zip-f distribution simulations;Pass through random number simulation user point
Broadcast situation, including user's program request moment and point broadcasting flow-medium ID;By numerical experiment it can be found that Duplicate user node it is online
Time obeys the exponential distribution that parameter is 0.5, with this online situation of analog subscriber node.
Further, whether replica node always reached the standard grade with its line duration, user gradation and current time away from last time online
The time interval at moment is related, and higher grade is and longer away from last time on-line time distance, then the online probability of the user is bigger.It is logical
Cross numerical experiment and can be found that the line duration of Duplicate user node obeys the exponential distribution that parameter is 0.5, therefore we can be with
Say, line duration sorts from long to short according to user gradation from high to low, the more preceding user of ranking its online possibility is more
It is high.
Further, it has been investigated that, when copy H is less, with copy number H increase, user data requests by
The probability increase that user node service is arrived, node accumulation layer transfer rate β c are in rising trend.When copy amount increases to certain value
When, with copy amount H continuation increase, the trend of node accumulation layer transfer rate β c increases slows down, and gradually levels off to
100%.
Further, node amount of storage and server end amount of storage.I.e. server node flows matchmaker with user node because storing
Memory capacity shared by body file.In this experiment, cloud environment system be from physical machine by virtualization technology fictionalize come
A cloud being constituted of node.The management of node in systems is by being monitored by monitoring system, and to data
Carry out statistics and the analysis of the amount of storage of server node and user node.Worked as by statistics with analyzing the data, real-time update
The performance threshold of preceding server end.
Further, user's request speed of response is to issue the time delay that the request is realized in request to user from user,
Mainly include data transfer delay and data processing delay;User's request responsiveness be system meet the number of user's request with it is same
User in one period asks the ratio of number.
The beneficial effects of the invention are as follows:
The present invention provide based on Cloud-P2P storage models under cloud environment, can be true by the contrast of table 1, table 2
It is fixed not only to mitigate server node with UDCP algorithms using Streaming Media popularity and user gradation as the 3DVSCP algorithms of core
Workload, and substantial amounts of server storage can be saved, and with the increase of video resource number, memory space
Saving will be apparent from.Simultaneously when video resource number is less, with the reduction of popularity threshold value, space-efficient efficiency is saved
Have and significantly increase, and when video resource number increases, different popularity threshold values will tend to same efficiency value, that is, take
The size that business device space is saved is more or less the same, while user's request can be responded quickly and efficiently.
Table 1 is the server copy amount of storage of inventive algorithm
50 videos | 100 videos | 200 videos | 300 videos | 400 videos | 500 videos | |
Popularity is 0.05 | 446.8 | 553.8 | 806 | 1021.8 | 1314.2 | 1548.4 |
Popularity is 0.1 | 355.32 | 456.88 | 689.88 | 964.32 | 1183.96 | 1395.64 |
Popularity is 0.15 | 245.32 | 375.28 | 602.52 | 844.8 | 1077.5.6 | 1317.2 |
Popularity is 0.2 | 207.28 | 321.48 | 558.84 | 802.96 | 1034.52 | 1286.44 |
Table 2 is the server copy amount of storage of other algorithms
50 videos | 100 videos | 200 videos | 300 videos | 400 videos | 500 videos | |
Popularity is 0.05 | 474 | 953 | 1550 | 2409 | 3283 | 4126 |
Popularity is 0.1 | 506.2 | 988.4 | 1460.6 | 2452.8 | 3287.8 | 4262.2 |
Popularity is 0.15 | 509.8 | 990.4 | 1511.8 | 2408.4 | 3269.8 | 4377.2 |
Popularity is 0.2 | 497.2 | 900.2 | 1584.6 | 2388.4 | 3279 | 4415.4 |
Brief description of the drawings
Fig. 1 is the Cloud-P2P Fusion Model system assumption diagrams of the present invention.
Fig. 2 is to judge 3D Streaming Media popularity size flow charts.
Fig. 3 is that server is set up and reproduction replica flow chart.
Fig. 4 is user's program request flow chart.
Embodiment
In order to make the purpose , technical scheme and advantage of the present invention be clearer, it is right below in conjunction with drawings and Examples
The present invention is further elaborated.It should be appreciated that specific embodiment described herein is only used for explaining of the invention, and without
It is of the invention in limiting.
In Cloud-P2P system models, such as Fig. 1, server group terminal replica management module is provided to 3D Streaming Media copies
Replicate and management, it is main to be responsible for identification Streaming Media, the foundation of Streaming Media copy and copy replication, while determining depositing for Streaming Media copy
Which node Streaming Media copy, i.e., be stored on by storage;User node management module provides management of the server to user node,
It is main to be responsible for that the user recorded in User Catalog is made a distinction and recognized, and current online user is counted and managed
Reason;Scheduler module is responsible for active user adjacent available being associated property of user node being asked to be connected, and according to user
Dispose to request dynamic, configure multi-line, multi-level ground transfer resource;Monitoring module is responsible for the use feelings of monitoring system resource
Condition, processing is abnormal, realizes server node and user node configuration, load balancing and monitoring resource, it is ensured that can be smooth by service
User is supplied to, meanwhile, data statistics and monitoring are carried out in transmitting procedure;Virtualization mechanism passes through system virtualization, resource
The computer resource that will be dispersed in server end and node side with the technology such as network virtualization is virtualized to be managed and invent
Resource pool is for being managed collectively and distributing, while coordinating Security Assurance Mechanism to be authenticated, authorize to the identity of node and role
And management, so that the credibility of strengthening system, stability and ease for use.
3DVSCP algorithms:
It is different from 2D Streaming Medias, 3D Streaming Medias in order to ensure user viewing film third dimension, it is necessary to while obtain to a left side
The stereo-picture that right eye is perceived, and need to be compressed storage to the two-way video that right and left eyes are perceived simultaneously.
Whenever having a 3D video distribution or being uploaded by user, copy foundation and the storage of copy are carried out by server end
Allocation manager.It is simultaneously one videogram node of video application, and each initial parameter value is set.Herein, in order to distinguish
High popularity file and low popularity file, make server efficiency more efficient, set variable parameter:Popularity threshold value.It is popular
Degree is high popularity file more than the files in stream media of the threshold value, otherwise is ground popularity file.The threshold value can be according to different
Server is changed with environment.High popularity Streaming Media number of copies is set simultaneously for 3 to ensure to have one in server node
Individual complete copy, and streaming media transmission queue each file progress piecemeal.
Because user probably obeys Zip-f distributions when files in stream media is watched, that is, the user for having 80% goes to see
See preceding 20% files in stream media, and Most users can decide whether after seeing again before viewing after 20% files in stream media
80% file, before 20% file be able to will be accessed repeatedly.Stability when therefore, to ensure lookup with order video
With accuracy, while further mitigating the load of server node, before the two-way video of each 3D video 20% is distinguished
Copy storage is set up to server node.
Then by system-monitoring module statistics within certain period the video-on-demand times of the video and playing duration (using day for singly
Position), more new video stream row degree and video storage catalogue content accordingly.The 3D video popularities that monitoring module detection simultaneously have modified
Whether popularity threshold value is exceeded, if more than the threshold value, then judging the video as high popularity video file, by the double of the video
Server end is arrived in the complete copy storage of road video, while by the storage of multiple complete copies of the video to current online senior
On user node.
Symbol and formula explanation:
i:Represent i-th of 3D video file
N:Represent the video file sum in current video catalogue
Ti:Represent i-th of intraday playing duration of 3D videos
Hi:Represent i-th of 3D video in intraday video-on-demand times
Pi:Represent the popularity of i-th of 3D video
Ii:Represent the issuing date of i-th of 3D video
Qi:Represent the same day weight of i-th each node
λ:The expectation of Poisson distribution and variance
Popularity is used for weighing some files in stream media pouplarity within certain a period of time, in a sense can be with
Regarded as the probability that files in stream media is requested by a user at the following a certain moment, therefore the popularity of some Streaming Media is to be difficult to
Prediction.At present, the prediction algorithm for Streaming Media popularity is to carry out statistical analysis by the historical record of Streaming Media mostly.It is general
Time 3D Streaming Medias popularity together decided on the playing duration of the Streaming Media by the number of times of user's program request media.Herein
The middle concept that will propose a video weight, it is determined by the time difference of video distribution time and current time.
Meanwhile, the popularity of 3D Streaming Medias is continually changing with the time, therefore it one day is a period to choose.So
If it is to open after 3D files in stream media that can ignore user when doing, do not go to watch for a long time, then so will
The popularity of 3D files in stream media is had influence on.The popularity of files in stream media has been arrived in embodiment well in certain limit for this
Size, so as to more conform to the experience of the process of user, so can more be concerned about the files in stream media that user is really liked, carry
High service request rate.
It is well known that being shown initial stage in video, scattered version of trying to be the first occurs in network, and the temperature of user is not high, with
Appearance of the legal video on network, the popularity of video reaches a peak, and then video popularity will have one
Huge landing, over time, video popularity tend towards stability finally substantially.Therefore, it can be said that video weight is obeyed
The Poisson distribution of time difference, it can thus be concluded that video weighted line regress formula is:
Qi=(λIi)*(e-λ)/(Ii!) (1)
The playing duration and video-on-demand times of some files in stream media are counted by monitoring modular, and calculates user in one day
It is total by program request in total time of system viewing Streaming Media and the intraday files in stream media of the system, with reference to (1) formula
The popularity that video i can be obtained is:
Formula (2) shows to represent that user's streaming media files i attention rate is higher when Pi is bigger, i.e. files in stream media
I has more people and accessed for a long time, and number of clicks is also more.
Arthmetic statement:
1. system is issued or user uploads 3D videos;
2. being the empty video storage catalogue node of the video application one, and before the two-way video of the video 20% is built
Service end is arrived in vertical copy storage;
3. the monitoring module of system counts the video request program number of times and playing duration;
4. calculate popularity, more new video storage catalogue;
5. the monitoring module of system detects whether the video popularity exceedes popularity threshold value, if so, going to step 6;It is no
Then, step 3 is gone to;
6. the copy of complete two-way video is stored into a certain amount of physical memory of server, and detect online user
Grade, if the left-eye video of advanced level user and the 3D videos is not stored also, goes to step 7;If the advanced level user and 3D is regarded
The right eye video of frequency is not stored also, goes to step 8;Otherwise continue waiting for and detect other online user's grades;
7. by left-eye video copy storage to advanced level user's node, go to step 6;
8. by right eye video copy storage to advanced level user's node.
UDCP algorithms:
Before each user sends order request, it can first obtain and browse video storage mesh of the backup in server
Record, including video name (vedioName) and mark (vedioID), then select video and carry out program request.Server is obtained simultaneously
The popularity of user gradation and order video, (property of directory is not carried out with reference to current server performance threshold including user
Can load), the order request to the user is allocated and handled, and chooses whether to provide server service and replica node service
And which replica node service is provided by.
For the huge redundancy of 3D Streaming Medias, and must be in user client in order to ensure the effect of three-dimensional video-frequency
Several frames are played, it is necessary to solve Heterogeneity in end simultaneously, i.e., multiple transmitting terminals are likely to be at different positions, there is different bands
Width connection and disposal ability, and they need to send the data of a video source at the same time.In this case it is desirable to as far as possible many
User node it is online, and for the concrete ability of user node, be respectively transmitted the stream medium data with certain mass;At this
The solution proposed in text is to reduce the load of bandwidth by piecemeal, it is ensured that stream medium data can quickly reach user
End;While the efficiency requirements in order to be further ensured that network transmission, by being layered by multiple multi-case data passages while entering line number
According to transmission.
Due to simply storing its preceding 20% copy on a memory for the low 3D Streaming Medias of popularity, therefore, when having
During the relatively low 3D Streaming Medias of user's program request popularity, the complete copy of 3D Streaming Medias is temporarily stored on server, played
Bi Hou, according to its popularity and popularity threshold value relatively decide whether retain complete copy.
Server data administrative center obtains online Duplicate user node level and carries out a queue order with line duration
(last node of queue is server node), the replica node first before queue provides service, if currently providing clothes
Replica node of being engaged in is offline, then service is provided by queue next node, to ensure reliability.
When logging in system by user, timing is carried out by monitoring modular, while the whether upper transmitting file of monitoring active user in real time,
And send corresponding data to control data corporation;When user log off, according to the accumulation line duration of user and contribution
Degree updates user gradation.User gradation determines the ranking replacement of User Catalog (in units of the moon)
Symbol description:
α:The point of safes of server load is represented, 0.2~0.5 can be set to
β:The dangerous spot of server load is represented, 0.7~0.8 can be set to
x:Represent current server loading condition
Arthmetic statement:
1. user obtains and inquires about server video storage catalogue;
2. user's selecting video content simultaneously sends order request;
3. server detecting system inquires about server current load situation:If server current load degree x be in (0,
α] it is interval when, the service request directly is added into application service queue, and (queue is had been filed on by user, but is also not carried out
Service request is constituted), go to 6;If server current load degree x be in (α, β] it is interval when, go to 4;If server is worked as
When preceding loading level x is in (β ,+∞) interval, 5 are gone to;
4. further detection user gradation, if user is senior and intermediate users, server is added to by the service request
Service queue, goes to 6;Otherwise the popularity of user's order video is further detected, if for the relatively low 3D videos of popularity
Program request, the service request is added to server service queue, 6 are gone to;Otherwise the service request is added to replica node
Service queue, goes to 7;
5. further the grade of detection user, if user is advanced level user, server service is added to by the service request
Queue, goes to 6;Otherwise the popularity of user's order video is further detected, if for the point of the relatively low 3D videos of popularity
Broadcast, the service request is added to server service queue, 6 are gone to;Otherwise the service request is added to replica node service
Queue, goes to 7;
6. service request is deployed to corresponding server node, follow-up service request response work is completed;
7. service request is deployed to corresponding replica node, follow-up service request response work is completed.
Claims (10)
1. the 3D Streaming Media storage methods under a kind of cloud environment, its step is:
1) for a files in stream media, server is the videogram node of files in stream media application one;
2) copy of the preceding M% of the files in stream media as the files in stream media is stored onto server, and sets up one and regarded
Frequency is linked, by video link storage to the videogram node;
3) files in stream media is updated with playing duration according to the video-on-demand times of the files in stream media in the period of setting length
Video popularity;If the video popularity of the video file exceedes the popularity threshold value of setting, Streaming Media text is judged
Part is high popularity video file, by the complete copy of files in stream media storage to the server, and by the Streaming Media
The complete copy of file is respectively stored on current online multiple user nodes for meeting setting rank, and the user node is referred to as
The replica node of the files in stream media.
2. the method as described in claim 1, it is characterised in that according to formula
Calculate video popularity Pi;Wherein, the weight Qi=(λ of the files in stream mediaIi)*(e-λ)/(Ii!), λ is Poisson distribution
Expect and variance, Ii is the issuing date of the files in stream media, N represents that the video file in server end current video catalogue is total
Number, Ti represents the playing duration of the period for the setting length interior files in stream media, and Hi represents to set should in the period of length
The video-on-demand times of files in stream media.
3. the method as described in claim 1, it is characterised in that block transmission is carried out to the files in stream media, by the Streaming Media
The preceding M% of file is stored onto server as the copy of the files in stream media.
4. the method as described in claim 1 or 3, it is characterised in that the M values are determined according to Zip-f distributions.
5. method as claimed in claim 4, it is characterised in that M≤20.
6. the method as described in claim 1 or 2 or 3, it is characterised in that the user is calculated according to the accumulation line duration of user
User class.
Exist 7. the method as described in claim 1, it is characterised in that when a files in stream media is by program request, first basis are current
The grade and line duration of the replica node of the files in stream media of line, are ranked up to the replica node, constitute a team
Arrange and the service node for preserving the files in stream media complete copy is placed on the last of the queue;Then first by the queue foremost
Replica node provide play service.
8. the method as described in claim 1 or 7, it is characterised in that when a files in stream media is by program request, if the Streaming Media
The video popularity of file is less than setting popularity threshold value, then the complete copy of the files in stream media is temporarily stored into one first
On service node;After finishing, determined according to the video popularity of the files in stream media and the comparison of setting popularity threshold value
Whether the complete copy of the files in stream media is retained.
9. the method as described in claim 1 or 7, it is characterised in that when server receives the service of first-class media file order program
During request, the current load degree x of detection service device first;If server current load degree x be in (0, α] it is interval when,
Then distribute corresponding server and provide broadcasting service for the service request;If server current load degree x be in (α, β] area
Between or (β ,+∞) it is interval constantly, then detection sends the user gradation of the service request, if user gradation is more than setting rank
Distribute corresponding server and provide broadcasting service for the service request, otherwise further detect the files in stream media of the service request
Video popularity, if the video popularity of the files in stream media is less than given threshold, distribute corresponding server for the clothes
Business request provides the service of broadcasting, otherwise distributes corresponding replica node and provides broadcasting service for the service request;Wherein, α is represented
The point of safes of server load, β represents the dangerous spot of server load.
10. the method as described in claim 1, it is characterised in that the files in stream media is 3D files in stream media.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610786057.8A CN107295358B (en) | 2016-08-31 | 2016-08-31 | A kind of 3D Streaming Media storage method under cloud environment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610786057.8A CN107295358B (en) | 2016-08-31 | 2016-08-31 | A kind of 3D Streaming Media storage method under cloud environment |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107295358A true CN107295358A (en) | 2017-10-24 |
CN107295358B CN107295358B (en) | 2019-11-05 |
Family
ID=60095588
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610786057.8A Active CN107295358B (en) | 2016-08-31 | 2016-08-31 | A kind of 3D Streaming Media storage method under cloud environment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107295358B (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108965909A (en) * | 2018-08-01 | 2018-12-07 | 中国联合网络通信集团有限公司 | A kind of unexpected winner video evaluations method and system |
CN109040844A (en) * | 2018-09-25 | 2018-12-18 | 有米科技股份有限公司 | A kind of method, apparatus and electronic equipment obtaining video temperature |
CN110222043A (en) * | 2019-06-12 | 2019-09-10 | 青岛大学 | Data monitoring method, device and the equipment of cloud storage service device |
CN113312329A (en) * | 2020-02-26 | 2021-08-27 | 阿里巴巴集团控股有限公司 | Data file scheduling method, device and equipment |
CN115408358A (en) * | 2022-10-31 | 2022-11-29 | 天津联想协同科技有限公司 | Network disk online file management method and device, network disk and storage medium |
-
2016
- 2016-08-31 CN CN201610786057.8A patent/CN107295358B/en active Active
Non-Patent Citations (1)
Title |
---|
吴小明: "基于P2P技术的混合流媒体代理缓存研究", 《硕士论文》 * |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108965909A (en) * | 2018-08-01 | 2018-12-07 | 中国联合网络通信集团有限公司 | A kind of unexpected winner video evaluations method and system |
CN108965909B (en) * | 2018-08-01 | 2021-02-02 | 中国联合网络通信集团有限公司 | Cold door video evaluation method and system |
CN109040844A (en) * | 2018-09-25 | 2018-12-18 | 有米科技股份有限公司 | A kind of method, apparatus and electronic equipment obtaining video temperature |
CN110222043A (en) * | 2019-06-12 | 2019-09-10 | 青岛大学 | Data monitoring method, device and the equipment of cloud storage service device |
CN113312329A (en) * | 2020-02-26 | 2021-08-27 | 阿里巴巴集团控股有限公司 | Data file scheduling method, device and equipment |
CN113312329B (en) * | 2020-02-26 | 2024-03-01 | 阿里巴巴集团控股有限公司 | Scheduling method, device and equipment for data files |
CN115408358A (en) * | 2022-10-31 | 2022-11-29 | 天津联想协同科技有限公司 | Network disk online file management method and device, network disk and storage medium |
CN115408358B (en) * | 2022-10-31 | 2023-04-11 | 天津联想协同科技有限公司 | Network disk online file management method and device, network disk and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN107295358B (en) | 2019-11-05 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107295358B (en) | A kind of 3D Streaming Media storage method under cloud environment | |
JP5143957B2 (en) | Topology-aware cache collaboration | |
US7788380B2 (en) | Load balancing method and apparatus, and software streaming system using the same | |
Hu et al. | Flod: A framework for peer-to-peer 3d streaming | |
Doyle et al. | The trickle-down effect: Web caching and server request distribution | |
US7441261B2 (en) | Video system varying overall capacity of network of video servers for serving specific video | |
CN102137133B (en) | Method and system for distributing contents and scheduling server | |
CN101080001B (en) | Device for realizing balance of media content in network TV system and its method | |
CN113315978B (en) | Collaborative online video edge caching method based on federal learning | |
CN102316097B (en) | Streaming media scheduling and distribution method capable of reducing wait time of user | |
CN101626389B (en) | Network node management method | |
CN106375395A (en) | Load balancing method and system for node servers | |
CN107948004A (en) | A kind of video CD N transfers optimization method and device | |
CN101072160B (en) | Distributed virtual environment management method, system and node | |
CN109600624A (en) | A kind of distributed load equalizing method and device based on Streaming Media | |
CN101247206B (en) | Layered transmission method and control system of peer-to-peer network | |
CN104333816B (en) | The determination method and device of downloading mode in a kind of P2P networks | |
CN103916328A (en) | Flow control method and system for content distribution network and peer-to-peer network | |
US11632588B2 (en) | Measuring the performance of a peer-managed content distribution network | |
Tan et al. | QoE-driven DASH multicast scheme for 5G mobile edge network | |
CN108449374B (en) | Web3D virtual scene peer-to-peer transmission data scheduling method and platform | |
CN107609039B (en) | CDN-based space distribution method for hot films at near-end cache server | |
CN112689166A (en) | Method and system for flexibly increasing and decreasing CDN hot content in real time | |
CN113778692B (en) | Data processing method and device, computer equipment and storage medium | |
CN112073223A (en) | System and method for managing and controlling operation of cloud computing terminal and cloud server |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |