基于半马尔科夫决策过程的视频传输拥塞控制算法

doi:10.3969/j.issn.1000-436x.2014.08.019

摘要/Abstract

摘要：

针对传输控制协议(TCP, transmission control protocol)的拥塞控制算法未能满足视频传输质量要求的问题，提出了一种基于半马尔科夫决策过程的视频传输拥塞控制算法。首先，为克服目前基于峰值信噪比的视频质量评估方法实时性低的缺点，设计了一种可在线运行的无参考视频质量评估方法。其次，根据接收端视频质量的反馈，采用半马尔科夫决策过程对拥塞控制进行建模，并通过求解此模型得到拥塞控制参数的调整策略。仿真实验结果表明，与目前典型的拥塞控制算法相比，该算法不但具备更好的TCP友好性，而且有效地提高了解码后视频序列的主观和客观质量。

关键词: 拥塞控制, 视频传输, 视频质量评估, 半马尔科夫决策过程

Abstract:

Due to the problem that the congestion control algorithm of transmission control protocol (TCP) cannot meet the requirements of quality of experience for Internet video transmission, a semi-Markov decision process based conges-tion control algorithm for video transmission was proposed. First, in order to improve the accuracy of video quality as-sessment, an online operation no-reference video quality assessment was presented. Then, the congestion control problem was formulated as a semi-Markov decision process according to the feedback of video quality assessment, and the opti-mal parameters of congestion control were obtained by solving the semi-Markov decision process. Simulation results re-veal that proposed algorithm achieves better subjective and objective video quality, and obtains well TCP-friendliness ra-tio, compared with the conventional congestion control algorithms.

Key words: congestion control, video transmission, video quality assessment, semi-Markov decision process

田波,杨宜民,蔡述庭. 基于半马尔科夫决策过程的视频传输拥塞控制算法[J]. 通信学报, 2014, 35(8): 154-161.

Bo TIAN,Yi-min YANG,Shu-ting CAI. Semi-Markov decision process based congestion control algorithm for video transmission[J]. Journal on Communications, 2014, 35(8): 154-161.

图/表 12

图1

图2

图3

图4

图5

图6

图7

图8

图9

表1

表2

表3

参考文献 18

[1]	YOUNG H J , YOONSIK C . Resource-aware and quality-fair video-streaming using multiple adaptive TCP connections[J]. Com-puters and Electrical Engineering, 2010, 36(2): 702-716.
[2]	KYUNG H K , KWANG M J , CHUL H K , et al. A transmission con-trol SCTP for real-time multimedia streaming[J]. Computer Networks, 2010, 54(4): 1418-1425.
[3]	HSIEN P S , MIHAELA V D S . A quality-centric TCP-friendly con-gestion control for multimedia transmission[J]. IEEE Transactions on Multimedia, 2012, 14(3): 896-905.
[4]	OUSSAMA H , HSIEN P S , MIHAELA V D S , et al. Online learning based congestion control for adaptive multimedia transmission[J]. IEEE Transactions on Signal Processing, 2013, 61(6): 1460-1468.
[5]	EMMANUEL J , MARTIN F , GHANBARI M . Fuzzy-logic congestion control of transcoded video streaming without packet loss feedback[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2008, 18(3): 387-393.
[6]	EMMANUEL A J , MARTIN F , CHRISTIAN W , et al. Interval type-2 fuzzy logic congestion control for video streaming across IP net-works[J]. IEEE Transactions on Fuzzy Systems, 2009, 17(5): 1123-1138.
[7]	JENG C V C , FU C C , MICHAEL J T , et al. Improving network congestion: a RED-based fuzzy PID approach[J]. Computer Standards and Interfaces, 2012, 34(5): 426-438.
[8]	JOY R , SAJEEB S , SYED F H . A new congestion control algorithm for datagram congestion control protocol (DCCP) based real-time multimedia applications[A]. 7th International Conference on Electrical and Computer Engineering[C] Dhaka, Bangladesh, 2012. 533-536.
[9]	FU F W , MIHAELA V D S . Structural solutions for dynamic schedul-ing in wireless multimedia transmission[J]. IEEE Transactions on Cir-cuits and Systems for Video Technology, 2012, 22(5): 727-737.
[10]	ZHOU C , HE J W , CHEN Q W . A robust active queue management scheme for network congestion control[J]. Computers and Electrical Engineering, 2013, 39(1): 285-293.
[11]	AYRACHENKOV K , AYESTA U , DONCEL J , et al. Congestion control of TCP flows in Internet routers by means of index policy[J]. Computer Networks, 2013, 57(17): 3463-3478.
[12]	秦晓芳，杨大成，张欣 . 新的基于 SR-SW-HARQ 的低时延视频传输方案[J]. 通信学报， 2009,30(1):19-24.
[13]	WANG B , JIM K , PRASHANT S , et al. Multimedia streaming via TCP:an analytic performance study[J]. ACM Transactions on Multimedia Computing, Communications, and Applications, 2008, 4(2): 1602-1621.
[14]	CAI L , SHEN X M , PAN J P , et al. Performance analysis of TCP-friendly AIMD algorithm for multimedia applications[J]. IEEE Transactions on Multimedia, 2005, 7(2): 339-355.
[15]	刘河潮，常义林，元辉 . 一种网络分组丢失的无参考视频质量评估方法[J]. 西安电子科技大学学报(自然科学版)， 2012,39(2):37-43. LIU H C , CHANG Y L , YUAN H , et al. No-reference video quality assessment over IP network based on packet loss[J]. Journal of Xi Dian University, 2012,39(2):37-43.
[16]	ZHU L , YU F R , NING B , et al. Cross-layer design for video trans-missions in metro passenger information systems[J]. IEEE Transac-tions on Vehicular Technology, 2011, 60(3): 1171-1181.
[17]	MICHELE C W , LI C , JASLEEN K , et al. Generalized stochastic performance models for loss-based congestion control[J]. Computer Communications, 2010, 33(4): 513-525.
[18]	MARGARET H P , STEPHEN W . An objective method for combining multiple subjective data sets[A]. SPIE Visual Communications andImage Processing Conference[C] Lugarno, Switzerland, 2003. 583-587.

视频序列	SMDPCC	MTCC	TCP
BUS	4.582	4.471	4.398
AKIYO	4.551	4.429	4.375
CONTAINER	4.542	4.410	4.293
FOREMAN	4.527	4.387	4.316
SALESMAN	4.513	4.409	4.261
CARPHONE	4.477	4.321	3.894
FOOTBALL	4.463	4.327	3.933
平均值	4.522	4.393	4.210

视频序列	SMDPCC	MTCC	TCP
BUS	35.134 9	35.039 1	34.284 4
AKIYO	34.941 6	34.483 4	33.405 5
CONTAINER	33.781 9	33.549 2	32.573 8
FOREMAN	34.498 1	34.536 1	33.872 9
SALESMAN	33.762 2	32.7128	32.419 4
CARPHONE	34.439 0	33.461 9	33.321 1
FOOTBALL	34.291 2	33.683 1	33.628 6
平均值	34.407 0	33.923 7	33.358 0

视频序列	SMDPCC	MTCC
BUS	2.31	2.43
AKIYO	2.26	2.49
CONTAINER	2.29	2.41
FOREMAN	2.14	2.47
SALESMAN	2.19	2.51
CARPHONE	2.07	2.48
FOOTBALL	1.97	2.32
平均值	2.18	2.44