CN109450815B - Peer-to-peer network streaming media system data scheduling method based on utility value - Google Patents

Peer-to-peer network streaming media system data scheduling method based on utility value Download PDF

Info

Publication number
CN109450815B
CN109450815B CN201811137678.9A CN201811137678A CN109450815B CN 109450815 B CN109450815 B CN 109450815B CN 201811137678 A CN201811137678 A CN 201811137678A CN 109450815 B CN109450815 B CN 109450815B
Authority
CN
China
Prior art keywords
video
node
segment
utility value
neighbor
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN201811137678.9A
Other languages
Chinese (zh)
Other versions
CN109450815A (en
Inventor
刘平山
范雅晴
熊肖一
黄桂敏
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Qingdao Sailfish Technology Co ltd
Original Assignee
Guilin University of Electronic Technology
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Guilin University of Electronic Technology filed Critical Guilin University of Electronic Technology
Priority to CN201811137678.9A priority Critical patent/CN109450815B/en
Publication of CN109450815A publication Critical patent/CN109450815A/en
Application granted granted Critical
Publication of CN109450815B publication Critical patent/CN109450815B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L47/00—Traffic control in data switching networks
    • H04L47/50—Queue scheduling
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L47/00—Traffic control in data switching networks
    • H04L47/50—Queue scheduling
    • H04L47/62—Queue scheduling characterised by scheduling criteria
    • H04L47/625—Queue scheduling characterised by scheduling criteria for service slots or service orders
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00—Network arrangements or protocols for supporting network services or applications
    • H04L67/01—Protocols
    • H04L67/10—Protocols in which an application is distributed across nodes in the network
    • H04L67/104—Peer-to-peer [P2P] networks
    • 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
    • H04N21/435—Processing of additional data, e.g. decrypting of additional data, reconstructing software from modules extracted from the transport stream
    • 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
    • H04N21/44—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream or rendering scenes according to encoded video stream scene graphs
    • H04N21/44004—Processing of video elementary streams, e.g. splicing a video clip retrieved from local storage with an incoming video stream or rendering scenes according to encoded video stream scene graphs involving video buffer management, e.g. video decoder buffer or video display buffer
    • 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
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/80—Generation or processing of content or additional data by content creator independently of the distribution process; Content per se
    • H04N21/83—Generation or processing of protective or descriptive data associated with content; Content structuring
    • H04N21/845—Structuring of content, e.g. decomposing content into time segments
    • H04N21/8456—Structuring of content, e.g. decomposing content into time segments by decomposing the content in the time domain, e.g. in time segments

Landscapes

  • Engineering & Computer Science (AREA)
  • Signal Processing (AREA)
  • Multimedia (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Databases & Information Systems (AREA)
  • Data Exchanges In Wide-Area Networks (AREA)
  • Information Transfer Between Computers (AREA)

Abstract

The invention discloses a data scheduling method of a peer-to-peer network streaming media system based on a utility value, which comprises the steps of designing a utility value calculation method comprehensively considering video playing quality and network throughput, obtaining a maximized video fragment utility value by taking the maximized video fragment utility value of a node as a target, and scheduling and planning video fragments by using the maximized video fragment utility value and adopting a data scheduling greedy algorithm and taking the maximized video fragment utility values of all requests in a node cache window as a target based on available bandwidth of a sending node, namely completing data scheduling in the peer-to-peer network streaming media playing system; the algorithm approximately achieves two optimization targets of maximizing video playing quality and maximizing network throughput, effectively improves the video playing quality and the network throughput in the peer-to-peer network streaming media playing system, improves the system service quality and reduces the server bandwidth overhead.

Description

Peer-to-peer network streaming media system data scheduling method based on utility value
Technical Field
The invention relates to the technical field of computer networks, peer-to-peer network technologies and streaming media, in particular to a data scheduling method of a peer-to-peer network streaming media system based on a utility value.
Background
With the development and popularization of broadband networks, the demand of users to watch videos through the internet is increasing. Internet video is mainly transmitted by using a streaming media technology, and when streaming media video is transmitted from a Server to a large number of clients, early streaming media playing systems successively adopt a Client/Server (C/S) mode and a Content Delivery Network (CDN) mode. Due to the sharp increase of the user scale, the C/S mode or the CDN mode has the bottleneck of the performance of the server and cannot meet the requirement of expansibility. Peer-to-Peer (P2P) technology can use the resources provided by each node to improve the service capability of the system for free. Therefore, the streaming media playing system based on the peer-to-peer network technology is widely deployed and applied. The streaming media playing system based on the peer-to-peer network technology comprises two core modules: one is an overlay network structure, which establishes transmission paths between nodes; one is data scheduling, which determines between which nodes video data is transmitted. The invention mainly aims at a data scheduling module of a streaming media playing system based on a peer-to-peer network technology.
In the P2P streaming media playing system, the streaming media video clip required by each node comes from a neighbor node or a server. When the neighbor nodes of one node do not have corresponding streaming media video segments, the neighbor nodes of one node request the server. This saves server bandwidth and utilizes the resources of each node. At present, some data scheduling algorithms are constructed with the goal of maximizing network throughput, so as to maximize the utilization of resources of nodes and reduce server bandwidth overhead. The rarity of video clips is an important contributor when maximizing network throughput. Still other data scheduling algorithms aim at maximizing video playback quality, and the urgency of video segments and video segment quality attributes are important considerations.
However, maximizing network throughput often conflicts with maximizing video playback quality. If a video clip is rare, the video clip has a high impact on network throughput and requires preferential transmission. However, the video clip may have a lower urgency or its impact on the playback quality, and need not be transmitted preferentially. This creates a conflict. Therefore, maximizing network throughput does not necessarily guarantee maximizing video playback quality, and vice versa. Thus, in the data scheduling process, only a single optimization objective (maximizing network throughput or maximizing video playback quality) is met, and the best performance cannot be achieved. Therefore, a data scheduling algorithm which can simultaneously meet two optimization targets of the maximum video playing quality and the maximum network throughput as far as possible needs to be designed, so that the video playing quality and the network throughput of the system are close to the optimal, the service quality of the system is improved, and the bandwidth overhead of a server is reduced.
Disclosure of Invention
The invention mainly aims to provide a utility value-based peer-to-peer network streaming media system data scheduling method so as to approximately achieve two optimization goals of maximizing video playing quality and maximizing network throughput, improve system service quality and reduce server bandwidth overhead.
The technical scheme for realizing the purpose of the invention is as follows:
a data scheduling method of a peer-to-peer network streaming media system based on utility values comprises the steps of designing a utility value calculation method comprehensively considering video playing quality and network throughput, obtaining the maximized video fragment utility value by taking the maximized video fragment utility value of a node as a target, scheduling and planning video fragments by using the maximized video fragment utility value and adopting a data scheduling greedy algorithm and taking the maximization of all the requested video fragment utility values in a node cache window as a target based on the available bandwidth of a sending node, namely finishing data scheduling in the peer-to-peer network streaming media playing system.
The utility value calculation method comprehensively considers the urgency, rarity and video quality of the video segments, carries out weighted summation on three attributes of the video segments according to the quantity and different contents of the video segments requested by the neighbor node cache of one video segment node, and leads the utility value of the video segment j to be defined as:
Figure GDA0002657343240000021
in the formula (1), rq、reAnd rrCoefficients representing video quality, urgency and rareness of the video segment, respectively, and rq+re+rr＝1。
The urgency is to measure the distance between the requested video clip and the playing deadline, and the calculation mode is as follows:
Figure GDA0002657343240000022
in the above formula (2), j is the sequence number of each video segment; the size of a cache window is represented, namely a video clip with the length of seconds that a receiving node requests missing in each scheduling period; t is tcurrIs the current playing time; djThe playing deadline of the video clip j is calculated by the following formula:
Figure GDA0002657343240000023
in the above formula (3), vfIs the frame rate of the video, NGOPThe number of frames per video segment.
The rarity represents how much a segment requested by one receiving node is owned by a neighbor node, and a video segment requested by one receiving node may be owned by a plurality of neighbor nodes at the same time, may be owned by only one neighbor node, and may not be owned by any neighbor node; a video segment requested by a receiving node is owned by fewer neighbor nodes, and the rarity of the video segment is higher; the rarity is inversely related to the number of neighbor nodes that own the requested video segment; setting the negative correlation function with the number of the neighbor nodes of the video clip, wherein the calculation formula of rarity is as follows:
Figure GDA0002657343240000031
in the above formula (4), M represents the total number of neighbor nodes owned by one receiving node,
Figure GDA0002657343240000032
representing the number of neighbor nodes that own segment j,
Figure GDA0002657343240000033
the calculation formula of (2) is as follows:
Figure GDA0002657343240000034
in the above formula (5), i represents the number of the neighbor node, j is the number of each video segment, Q is the user set formed by the node i and the neighbor nodes thereof, ai,jIndicating whether the neighbor node has the video segment j, ai,j1 means that the neighboring node i owns a video segment j, ai,jThe opposite is true if 0.
The video quality attribute is the picture quality of a video segment measured based on a PSNR value, the attribute is defined as an average value of peak signal-to-noise ratios (PSNR) of all video frames of a requested video segment, each video segment is composed of a specific number of video frames, different video frames have different PSNR values, when streaming media data scheduling is carried out, a segment with a higher priority request PSNR value can bring better viewing experience to a user, and the video quality of a video segment j is defined as:
Figure GDA0002657343240000035
in the above formula (6), PSNRjRepresenting the video quality, PSNR, of a video segment jminRepresents the minimum value of peak signal-to-noise ratio, PSNR, of all video segments in the buffer windowmaxRepresenting the maximum value of the peak signal-to-noise ratio of all video segments in the buffer window.
The coefficients of the video quality, the urgency and the rarity of the video clip are different according to the number of neighbor nodes which have a receiving node to request the video clip, the coefficients of all attributes in the utility value calculation method are changed, the corresponding calculation formulas are also different, and if no neighbor node has the congestion conditionWith the segment j, the coefficients r of video quality, urgency and rarityq、reAnd rrAll are zero, then the utility value w of video segment jj0; if the number of neighbor nodes with the segment j is more than 0 and not more than 3, the coefficients r of video quality, urgency and rarenessq、reAnd rrRespectively 0.1 and (0.9-r)r) And rrThen the utility value of video segment j
Figure GDA0002657343240000041
If the number of neighbor nodes with the segment j is more than 3, the coefficients r of video quality, urgency and rarityq、reAnd rr0.4, 0.5, 0.1, respectively, the utility value of video segment j
Figure GDA0002657343240000042
The maximized utility value of the video clip is abstracted into a mathematical model according to the calculation method of the utility value of the video clip and the constraint conditions to be considered in the streaming media playing system, and the mathematical model obtains better playing quality and network throughput by maximizing the utility value of the video clip of the streaming media received in each sending period.
The mathematical model is formed by integrating the utility value of the video clip and four constraint conditions, and the expression of the mathematical model is as follows:
Figure GDA0002657343240000043
the four constraint conditions are as follows:
constraint 1:
Figure GDA0002657343240000044
ensuring that no more than 1 sending node sends each fragment;
constraint 2:
Figure GDA0002657343240000045
ensuring that the transmitting node is not overloaded during each transmission cycle, whereinsjIs the length of the video segment j, τ is the transmission period, biIs the upstream bandwidth of the sending node;
constraint 3:
Figure GDA0002657343240000046
each sending node is limited to send the own fragments only;
constraint 4:
Figure GDA0002657343240000047
the solution used to define the mathematical model is discrete.
The data scheduling greedy algorithm comprises the following steps:
1) calculating utility value w of each video segment in cache windowj；
2) According to the utility value wjArranging the video clips in a descending order to obtain an ordered video clip list order _ list _ video;
3) executing the fourth step to the ninth step for each video clip j of the ordered video clip list order _ list _ video;
4) for each neighbor node i of a video segment j, calculating the time t required by the neighbor node to transmit the existing video segmentsendi；
5) According to tsendiPerforming ascending arrangement on the neighbor nodes to obtain an ordered neighbor node list order _ list _ peer;
6) performing steps 7) -9) for each neighbor node i in order _ list _ peer);
7) judging whether the neighbor node i has the video clip j, if so, executing the step 8), otherwise, executing the step 6);
8) determining the time t required to transmit an existing video segmentsendiWhether the time is less than the size of the buffer window or not and the time t required for transmitting the existing video clip is judged simultaneouslysendiWhether the sum of the current playing time and the current playing time is less than the playing time of the video clip j, if so, executing the step 9), otherwise, executing the step 6);
9) sending a request of a video clip j to a neighbor node i, and updating a sending queue S of the neighbor node iqueuei。
In step 4), the time t required for transmitting the existing video clipsendiThe time t required for transmitting the existing video clip is defined as the time t required for transmitting the existing video clip by the sending queue in the cache window of the nodesendiSending the length sum S of the existing video clips in the queue by the neighbor node iqueueiWith the length S of the video segment jjThe sum is larger than the uplink bandwidth b of the neighbor node iiThe calculation formula is as follows:
Figure GDA0002657343240000051
in the above formula (7), SqueueiIndicates the sum of the lengths of the existing video segments in the sending queue of the neighbor node i, SjIs the length of video segment j, biIs the uplink bandwidth of the neighbor node i.
The invention provides a data scheduling method of a peer-to-peer network streaming media system based on a utility value. Then, with the aim of maximizing the utility value of all the requested video fragments of a node as a target, a data scheduling greedy algorithm based on the maximization of the utility value is realized, so that the aims of simultaneously improving the video playing quality and the network throughput in the peer-to-peer network streaming media playing system are effectively fulfilled, the service quality of the system is improved, and the bandwidth overhead of a server is reduced.
Drawings
Fig. 1 is a flowchart of a method for calculating utility values of streaming media video segments.
Detailed Description
The invention is further illustrated but not limited by the following figures and examples.
Example (b):
a data scheduling method of a peer-to-peer network streaming media system based on utility values comprises the steps of firstly designing a utility value calculation method comprehensively considering video playing quality and network throughput, then obtaining the maximized video fragment utility value by taking the maximized video fragment utility value of a node as a target, finally utilizing the maximized video fragment utility value, adopting a data scheduling greedy algorithm, taking the maximization of all the requested video fragment utility values in a node cache window as a target, and scheduling and planning the video fragments based on the available bandwidth of a sending node, namely completing data scheduling in the peer-to-peer network streaming media playing system; the video playing quality and the network throughput in the peer-to-peer network streaming media playing system are effectively improved.
As shown in fig. 1, the utility value calculation method comprehensively considers the urgency, rarity, and video quality of a video segment, performs weighted summation on three attributes of the video segment according to the number and content of the requested video segments cached by the neighbor node of a video segment node, and defines the utility value of a video segment j as:
Figure GDA0002657343240000061
in the formula (1), rq、reAnd rrCoefficients representing video quality, urgency and rareness of the video segment, respectively, and rq+re+rr＝1。
The urgency is to measure the distance between the requested video clip and the playing deadline, and the calculation mode is as follows:
Figure GDA0002657343240000062
in the above formula (2), j is the sequence number of each video segment; the size of a cache window is represented, namely a video clip with the length of seconds that a receiving node requests missing in each scheduling period; t is tcurrIs the current playing time; djThe playing deadline of the video clip j is calculated by the following formula:
Figure GDA0002657343240000063
in the above-mentioned formula (3),vfis the frame rate of the video, NGOPThe number of frames per video segment.
The rarity represents how much a segment requested by one receiving node is owned by a neighbor node, and a video segment requested by one receiving node may be owned by a plurality of neighbor nodes at the same time, may be owned by only one neighbor node, and may not be owned by any neighbor node; a video segment requested by a receiving node is owned by fewer neighbor nodes, and the rarity of the video segment is higher; the rarity is inversely related to the number of neighbor nodes that own the requested video segment; setting the negative correlation function with the number of the neighbor nodes of the video clip, wherein the calculation formula of rarity is as follows:
Figure GDA0002657343240000071
in the above formula (4), M represents the total number of neighbor nodes owned by one receiving node,
Figure GDA0002657343240000072
representing the number of neighbor nodes that own segment j,
Figure GDA0002657343240000073
the calculation formula of (2) is as follows:
Figure GDA0002657343240000074
in the above formula (5), i represents the number of the neighbor node, j is the number of each video segment, Q is the user set formed by the node i and the neighbor nodes thereof, ai,jIndicating whether the neighbor node has the video segment j, ai,j1 means that the neighboring node i owns a video segment j, ai,jThe opposite is true if 0.
The video quality attribute is the picture quality of a video segment measured based on a PSNR value, the attribute is defined as an average value of peak signal-to-noise ratios (PSNR) of all video frames of a requested video segment, each video segment is composed of a specific number of video frames, different video frames have different PSNR values, when streaming media data scheduling is carried out, a segment with a higher priority request PSNR value can bring better viewing experience to a user, and the video quality of a video segment j is defined as:
Figure GDA0002657343240000075
in the above formula (6), PSNRjRepresenting the video quality, PSNR, of a video segment jminRepresents the minimum value of peak signal-to-noise ratio, PSNR, of all video segments in the buffer windowmaxRepresenting the maximum value of the peak signal-to-noise ratio of all video segments in the buffer window.
The coefficients of the video quality, the urgency and the rarity of the video clip are also different according to the number of neighbor nodes which have a receiving node to request the video clip, the coefficients of all attributes in the utility value calculation method are changed, the corresponding calculation formulas are also different, and if no neighbor node has the clip j, the coefficients r of the video quality, the urgency and the rarity are differentq、reAnd rrAll are zero, then the utility value w of video segment jj0; if the number of neighbor nodes with the segment j is more than 0 and not more than 3, the coefficients r of video quality, urgency and rarenessq、reAnd rrRespectively 0.1 and (0.9-r)r) And rrThen the utility value of video segment j
Figure GDA0002657343240000081
If the number of neighbor nodes with the segment j is more than 3, the coefficients r of video quality, urgency and rarityq、reAnd rr0.4, 0.5, 0.1, respectively, the utility value of video segment j
Figure GDA0002657343240000082
The maximized utility value of the video clip is abstracted into a mathematical model according to the calculation method of the utility value of the video clip and the constraint conditions to be considered in the streaming media playing system, and the mathematical model obtains better playing quality and network throughput by maximizing the utility value of the video clip of the streaming media received in each sending period.
The mathematical model is formed by integrating the utility value of the video clip and four constraint conditions, and the expression of the mathematical model is as follows:
Figure GDA0002657343240000083
the four constraint conditions are as follows:
constraint 1:
Figure GDA0002657343240000084
ensuring that no more than 1 sending node sends each fragment;
constraint 2:
Figure GDA0002657343240000085
ensuring that the transmitting node is not overloaded during each transmission period, where sjIs the length of the video segment j, τ is the transmission period, biIs the upstream bandwidth of the sending node;
constraint 3:
Figure GDA0002657343240000086
each sending node is limited to send the own fragments only;
constraint 4:
Figure GDA0002657343240000087
the solution used to define the mathematical model is discrete.
As shown in table 1, the data scheduling greedy algorithm includes the following steps:
1) calculating utility value w of each video segment in cache windowj；
2) According to the utility value wjArranging the video clips in a descending order to obtain an ordered video clip list order _ list _ video;
3) executing the fourth step to the ninth step for each video clip j of the ordered video clip list order _ list _ video;
4) for each neighbor node i of a video segment j, calculating the time t required by the neighbor node to transmit the existing video segmentsendi；
5) According to tsendiPerforming ascending arrangement on the neighbor nodes to obtain an ordered neighbor node list order _ list _ peer;
6) performing steps 7) -9) for each neighbor node i in order _ list _ peer);
7) judging whether the neighbor node i has the video clip j, if so, executing the step 8), otherwise, executing the step 6);
8) determining the time t required to transmit an existing video segmentsendiWhether the time is less than the size of the buffer window or not and the time t required for transmitting the existing video clip is judged simultaneouslysendiWhether the sum of the current playing time and the current playing time is less than the playing time of the video clip j, if so, executing the step 9), otherwise, executing the step 6);
9) sending a request of a video clip j to a neighbor node i, and updating a sending queue S of the neighbor node iqueuei。
In step 4), the time t required for transmitting the existing video clipsendiThe time t required for transmitting the existing video clip is defined as the time t required for transmitting the existing video clip by the sending queue in the cache window of the nodesendiSending the length sum S of the existing video clips in the queue by the neighbor node iqueueiWith the length S of the video segment jjThe sum is larger than the uplink bandwidth b of the neighbor node iiThe calculation formula is as follows:
Figure GDA0002657343240000091
in the above formula (7), SqueueiIndicates the sum of the lengths of the existing video segments in the sending queue of the neighbor node i, SjIs the length of video segment j, biIs the uplink bandwidth of the neighbor node i.
TABLE 1 Utility value-based pseudo code table for data scheduling greedy algorithm
Figure GDA0002657343240000092
Figure GDA0002657343240000101

Claims (1)

1. A data scheduling method of a peer-to-peer network streaming media system based on utility values is characterized by firstly designing a utility value calculation method comprehensively considering video playing quality and network throughput, then obtaining the maximized video fragment utility value by taking the maximized video fragment utility value of a node as a target, finally utilizing the maximized video fragment utility value, adopting a data scheduling greedy algorithm, taking the maximization of all the requested video fragment utility values in a node cache window as a target, and scheduling and planning the video fragments based on the available bandwidth of a sending node, namely completing data scheduling in the peer-to-peer network streaming media playing system;
the utility value calculation method comprehensively considers the urgency, rarity and video quality of the video segments, carries out weighted summation on three attributes of the video segments according to the quantity and different contents of the video segments requested by the neighbor node cache of one video segment node, and leads the utility value of the video segment j to be defined as:
Figure FDA0002657343230000011
in the formula (1), rq、reAnd rrCoefficients representing video quality, urgency and rareness of the video segment, respectively, and rq+re+rr＝1；
The urgency is to measure the distance between the requested video clip and the playing deadline, and the calculation mode is as follows:
Figure FDA0002657343230000012
in the above formula (2), j is the sequence number of each video segment; watch (A)Showing the size of a cache window, namely requesting missing video segments with the length of seconds by one receiving node in each scheduling period; t is tcurrIs the current playing time; djThe playing deadline of the video clip j is calculated by the following formula:
Figure FDA0002657343230000013
in the above formula (3), vfIs the frame rate of the video, NGOPThe frame number of each video is;
the rarity represents how much a segment requested by one receiving node is owned by a neighbor node, and a video segment requested by one receiving node may be owned by a plurality of neighbor nodes at the same time, may be owned by only one neighbor node, and may not be owned by any neighbor node; a video segment requested by a receiving node is owned by fewer neighbor nodes, and the rarity of the video segment is higher; the rarity is inversely related to the number of neighbor nodes that own the requested video segment; setting the negative correlation function with the number of the neighbor nodes of the video clip, wherein the calculation formula of rarity is as follows:
Figure FDA0002657343230000021
in the above formula (4), M represents the total number of neighbor nodes owned by one receiving node,
Figure FDA0002657343230000022
representing the number of neighbor nodes that own segment j,
Figure FDA0002657343230000023
the calculation formula of (2) is as follows:
Figure FDA0002657343230000024
in the above formula (5), i represents the number of the neighbor node, and j is the code of each video segmentNumber Q is a user set formed by the node i and the neighbor nodes thereof, ai,jIndicating whether the neighbor node has the video segment j, ai,j1 means that the neighboring node i owns a video segment j, ai,jThe opposite is true when the value is 0;
the video quality attribute is the picture quality of a video segment measured based on a PSNR value, the attribute is defined as the average value of peak signal-to-noise ratios (PSNR) of all video frames of a requested video segment, each video segment is composed of a specific number of video frames, different video frames have different PSNR values, when streaming media data scheduling is carried out, a segment with a higher PSNR value is preferentially requested to bring better viewing experience to a user, and the video quality of a video segment j is defined as:
Figure FDA0002657343230000025
in the above formula (6), PSNRjRepresenting the video quality, PSNR, of a video segment jminRepresents the minimum value of peak signal-to-noise ratio, PSNR, of all video segments in the buffer windowmaxRepresenting the maximum value of the peak signal-to-noise ratio of all the video segments in the buffer window;
the coefficients of the video quality, the urgency and the rarity of the video clip are also different according to the number of neighbor nodes which have a receiving node to request the video clip, the coefficients of all attributes in the utility value calculation method are changed, the corresponding calculation formulas are also different, and if no neighbor node has the clip j, the coefficients r of the video quality, the urgency and the rarity are differentq、reAnd rrAll are zero, then the utility value w of video segment jj0; if the number of neighbor nodes with the segment j is more than 0 and not more than 3, the coefficients r of video quality, urgency and rarenessq、reAnd rrRespectively 0.1 and (0.9-r)r) And rrThen the utility value of video segment j
Figure FDA0002657343230000031
If the number of neighbor nodes of the segment j is ownedGreater than 3, coefficients of video quality, urgency and rarity rq、reAnd rr0.4, 0.5, 0.1, respectively, the utility value of video segment j
Figure FDA0002657343230000032
The maximized utility value of the video clip is abstracted into a mathematical model according to a calculation method of the utility value of the video clip and constraint conditions to be considered in the streaming media playing system, and the mathematical model obtains better playing quality and network throughput by maximizing the utility value of the video clip of the streaming media received in each sending period;
the mathematical model is formed by integrating the utility value of the video clip and four constraint conditions, and the expression of the mathematical model is as follows:
Figure FDA0002657343230000033
the four constraint conditions are as follows:
constraint 1:
Figure FDA0002657343230000034
ensuring that no more than 1 sending node sends each fragment;
constraint 2:
Figure FDA0002657343230000035
ensuring that the transmitting node is not overloaded during each transmission period, where sjIs the length of the video segment j, τ is the transmission period, biIs the upstream bandwidth of the sending node;
constraint 3:
Figure FDA0002657343230000036
each sending node is limited to send the own fragments only;
constraint 4:
Figure FDA0002657343230000037
the solution used to define the mathematical model is discrete;
the data scheduling greedy algorithm comprises the following steps:
1) calculating utility value w of each video segment in cache windowj；
2) According to the utility value wjArranging the video clips in a descending order to obtain an ordered video clip list order _ list _ video;
3) executing the fourth step to the ninth step for each video clip j of the ordered video clip list order _ list _ video;
4) for each neighbor node i of a video segment j, calculating the time t required by the neighbor node to transmit the existing video segmentsendi；
5) According to tsendiPerforming ascending arrangement on the neighbor nodes to obtain an ordered neighbor node list order _ list _ peer;
6) performing steps 7) -9) for each neighbor node i in order _ list _ peer);
7) judging whether the neighbor node i has the video clip j, if so, executing the step 8), otherwise, executing the step 6);
8) determining the time t required to transmit an existing video segmentsendiWhether the time is less than the size of the buffer window or not and the time t required for transmitting the existing video clip is judged simultaneouslysendiWhether the sum of the current playing time and the current playing time is less than the playing time of the video clip j, if so, executing the step 9), otherwise, executing the step 6);
9) sending a request of a video clip j to a neighbor node i, and updating a sending queue S of the neighbor node iqueuei；
In step 4), the time t required for transmitting the existing video clipsendiThe time t required for transmitting the existing video clip is defined as the time t required for transmitting the existing video clip by the sending queue in the cache window of the nodesendiSending the length sum S of the existing video clips in the queue by the neighbor node iqueueiWith the length S of the video segment jjThe sum is larger than the uplink bandwidth b of the neighbor node iiThe calculation formula is as follows:
Figure FDA0002657343230000041
in the above formula (7), SqueueiIndicates the sum of the lengths of the existing video segments in the sending queue of the neighbor node i, SjIs the length of video segment j, biIs the uplink bandwidth of the neighbor node i.
CN201811137678.9A 2018-09-28 2018-09-28 Peer-to-peer network streaming media system data scheduling method based on utility value Active CN109450815B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201811137678.9A CN109450815B (en) 2018-09-28 2018-09-28 Peer-to-peer network streaming media system data scheduling method based on utility value

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201811137678.9A CN109450815B (en) 2018-09-28 2018-09-28 Peer-to-peer network streaming media system data scheduling method based on utility value

Publications (2)

Publication Number Publication Date
CN109450815A CN109450815A (en) 2019-03-08
CN109450815B true CN109450815B (en) 2020-10-30

Family

ID=65544341

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201811137678.9A Active CN109450815B (en) 2018-09-28 2018-09-28 Peer-to-peer network streaming media system data scheduling method based on utility value

Country Status (1)

Country Link
CN (1) CN109450815B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111556344A (en) * 2020-04-04 2020-08-18 网宿科技股份有限公司 Method, device, equipment and system for downloading video stream

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101697554A (en) * 2009-09-27 2010-04-21 华中科技大学 Method for scheduling P2P streaming media video data transmission
CN104506929A (en) * 2014-12-26 2015-04-08 电子科技大学 Hybrid data scheduling method for P2P (peer to peer) systems
CN106462861A (en) * 2014-03-28 2017-02-22 邻客音公司 Scheduling algorithms for online promotional campaigns

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20160069919A1 (en) * 2011-09-25 2016-03-10 Theranos, Inc. Systems and methods for multi-analysis
US9497682B2 (en) * 2013-06-07 2016-11-15 Intel Corporation Central processing unit and methods for supporting coordinated multipoint transmission in an LTE network

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101697554A (en) * 2009-09-27 2010-04-21 华中科技大学 Method for scheduling P2P streaming media video data transmission
CN106462861A (en) * 2014-03-28 2017-02-22 邻客音公司 Scheduling algorithms for online promotional campaigns
CN104506929A (en) * 2014-12-26 2015-04-08 电子科技大学 Hybrid data scheduling method for P2P (peer to peer) systems

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
A Multi-objective Particle Swarm Optimization Data Scheduling Algorithm for Peer-to-Peer Video Streaming;Liu, Pingshan 等;《2017 13th international conference on natural computation, fuzzy system and knowledge discovery(ICNC-FSKD 2017)》;20180625;第278-285页 *
Data Scheduling Algorithm for Layered P2P VoD Streaming Networks;WEN,Zheng等;《Globecom 2013-communications software, services and multimedia symposium》;20131231;第1730-1735页 *

Also Published As

Publication number Publication date
CN109450815A (en) 2019-03-08

Similar Documents

Publication Publication Date Title
US9838459B2 (en) Enhancing dash-like content streaming for content-centric networks
CN104350755B (en) The method and apparatus of the stabilization of the self adaptation stream videoconference client of through-rate limitation
Liu et al. Rate adaptation for dynamic adaptive streaming over HTTP in content distribution network
US20080022005A1 (en) Glitch-Free Media Streaming
US20120203923A1 (en) Adaptive variable fidelity media distribution system and method
KR20060115216A (en) Apparatus and method for transmitting multimedia streaming
CN107637046B (en) Method and apparatus for controlling multiple connections to increase data transfer rate
CN113453038B (en) Effectiveness optimal collaborative cache management method under CDN-P2P hybrid architecture
US20110082943A1 (en) P2p network system and data transmitting and receiving method thereof
Guo et al. Deep-Q-network-based multimedia multi-service QoS optimization for mobile edge computing systems
van der Hooft et al. An HTTP/2 push-based approach for SVC adaptive streaming
CN109450815B (en) Peer-to-peer network streaming media system data scheduling method based on utility value
US20240137585A1 (en) Multiple protocol prediction and in-session adaptation in video streaming
Nguyen et al. An adaptive streaming method of 360 videos over HTTP/2 protocol
Cui et al. DASH+: Download multiple video segments with stream multiplexing of QUIC
CN111478977B (en) Working method of multimedia network flow analysis system
Dubin et al. A fair server adaptation algorithm for HTTP adaptive streaming using video complexity
US11627358B2 (en) Communication entity and a method for transmitting a video data stream
CN112106335B (en) Method and system for streaming media data over a content distribution network
Dakshayini et al. Client-to-client streaming scheme for vod applications
Khan et al. Bandwidth Estimation Techniques for Relative'Fair'Sharing in DASH
Khan et al. Ultra-HD Video Streaming in 5G Fixed Wireless Access Bottlenecks.
Wu et al. ASRSR: Adaptive Sending Resolution and Super-resolution for Real-time Video Streaming
CN101924793A (en) P2P streaming media-based secondary coding play method and system
CN114245225B (en) Method and system for streaming media data via a content distribution network

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
TR01 Transfer of patent right
TR01 Transfer of patent right

Effective date of registration: 20240126

Address after: 230000 B-1015, wo Yuan Garden, 81 Ganquan Road, Shushan District, Hefei, Anhui.

Patentee after: HEFEI MINGLONG ELECTRONIC TECHNOLOGY Co.,Ltd.

Country or region after: China

Address before: 541004 1 Jinji Road, Qixing District, Guilin, the Guangxi Zhuang Autonomous Region

Patentee before: GUILIN University OF ELECTRONIC TECHNOLOGY

Country or region before: China

TR01 Transfer of patent right
TR01 Transfer of patent right

Effective date of registration: 20240412

Address after: Room 01-11, 11th Floor, Qingdao International Shipping Center, No. 66 Lianyungang Road, Shibei District, Qingdao City, Shandong Province, 266000

Patentee after: Qingdao Sailfish Technology Co.,Ltd.

Country or region after: China

Address before: 230000 B-1015, wo Yuan Garden, 81 Ganquan Road, Shushan District, Hefei, Anhui.

Patentee before: HEFEI MINGLONG ELECTRONIC TECHNOLOGY Co.,Ltd.

Country or region before: China