ZTE Communications ›› 2017, Vol. 15 ›› Issue (2): 35-41.DOI: 10.3969/j.issn.1673-5188.2017.02.005
-
收稿日期:2017-02-09出版日期:2017-04-25发布日期:2019-12-24
Scheduling Heuristics for Live Video Transcoding on Cloud Edges
Panagiotis Oikonomou1, Maria G. Koziri1, Nikos Tziritas2, Thanasis Loukopoulos1, XU Cheng-Zhong2
- 1 University of Thessaly, Lamia 35100, Greece
2 Research Center for Cloud Computing, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen 518055, China
-
Received:2017-02-09Online:2017-04-25Published:2019-12-24 -
About author:Panagiotis Oikonomou (paikonom@uth.gr) received his Diploma degree (2008) and M.Sc. degree (2010) from the Department of Electrical and Computer Engineering, University of Thessaly, Greece. He is currently a Ph.D. candidate at the same Department. His research interests include optimization algorithms and fuzzy logic methods.|Maria G. Koziri (mkoziri@uth.gr) received her Diploma degree in computer engineering from the Technical University of Crete, Greece in 2003 and Ph.D. degree in computer science from the University of Thessaly, Greece in 2007. She is currently a visiting lecturer in the Computer Science Department of the University of Thessaly. Her research interests include video compression, scalable video coding, rate-distortion optimization and computer architecture.|Nikos Tziritas (nikolaos@siat.ac.cn) received his B.Sc. degree from the Technological Educational Institute of Serres, Greece in 2004, and M.Sc. and Ph.D. degrees from the University of Thessaly, Greece in 2006 and 2011, respectively. He is currently an associate professor in Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, China. His work has appeared in over 35 publications. He is the recipient of the Award for Excellence for Early Career Researchers in Scalable Computing from IEEE Technical Committee in Scalable Computing in 2016.|Thanasis Loukopoulos (luke@dib.uth.gr) received his Ph.D. degree in computer science from the Hong Kong University of Science and Technology, China. He is currently a lecturer at the Department of Computer Science and Biomedical Informatics of the University of Thessaly, Greece. His research interests are in green computing, cloud computing, WSNs, scheduling, load balancing and video coding parallelization. His work appeared in over 50 publications. He had the best paper award in ICPP 2001.|XU Cheng-Zhong (cz.xu@siat.ac.cn) received the Ph.D. degree in computer science from the University of Hong Kong, China in 1993. He is currently a professor in the Department of Electrical and Computer Engineering of Wayne State University, China and the director of Cloud and Internet Computing Laboratory (CIC) and Sun’s Center of Excellence in Open Source Computing and Applications (OSCA). His research interest is mainly in scalable distributed and parallel systems and wireless embedded computing devices. He has published two books and more than 160 articles in peer-reviewed journals and conferences in these areas.
引用本文
. [J]. ZTE Communications, 2017, 15(2): 35-41.
Panagiotis Oikonomou, Maria G. Koziri, Nikos Tziritas, Thanasis Loukopoulos, XU Cheng-Zhong. Scheduling Heuristics for Live Video Transcoding on Cloud Edges[J]. ZTE Communications, 2017, 15(2): 35-41.
Figure 1. Example system model with edge transcoding.
Figure 1. Example system model with edge transcoding.
Table 1 Dataset for broadcasters (general characteristics)
| Name | Value |
|---|---|
| Dataset duration | 75,079 s |
| Average broadcast duration | 23,263.4 s |
| Max broadcast duration | 1.05E6 s |
| Number of broadcasts | 786,100 |
| Total transcoding tasks | 1,244,450 |
| Percentage of braodcasts at 1080p | 26.21% |
| Percentage of braodcasts at 720p | 53.24% |
| Percentage of braodcasts at 480p | 11.18% |
| Percentage of braodcasts at 360p | 7.49% |
| Percentage of braodcasts at 240p | 1.86% |
Table 1 Dataset for broadcasters (general characteristics)
| Name | Value |
|---|---|
| Dataset duration | 75,079 s |
| Average broadcast duration | 23,263.4 s |
| Max broadcast duration | 1.05E6 s |
| Number of broadcasts | 786,100 |
| Total transcoding tasks | 1,244,450 |
| Percentage of braodcasts at 1080p | 26.21% |
| Percentage of braodcasts at 720p | 53.24% |
| Percentage of braodcasts at 480p | 11.18% |
| Percentage of braodcasts at 360p | 7.49% |
| Percentage of braodcasts at 240p | 1.86% |
Figure 2. Histogram for broadcasting arrival rates.
Figure 2. Histogram for broadcasting arrival rates.
Table 2 Video sequences used for weight calculation
| Name | Resolution | Frames | Time 240p (fps) | Time 360p (fps) | Time 480p (fps) | Time 720p (fps) |
|---|---|---|---|---|---|---|
| BasketballDrive | 1920×1080 | 500 | 15.78 | 5.37 | 3.78 | 1.47 |
| BQTerrace | 1920×1080 | 600 | 29.10 | 9.11 | 6.42 | 2.37 |
| Cactus | 1920×1080 | 500 | 25.48 | 8.77 | 5.09 | 1.96 |
| Kimono | 1920×1080 | 240 | 18.54 | 6.05 | 4.33 | 1.62 |
| ParkScene | 1920×1080 | 240 | 24.95 | 7.62 | 5.28 | 1.94 |
| PeopleOnStreet | 2560×1600 | 150 | 10.01 | 2.82 | 2.00 | 0.74 |
| Traffic | 2560×1600 | 150 | 27.36 | 8.06 | 5.77 | 2.17 |
| Average | - | - | 21.60 | 6.82 | 4.66 | 1.75 |
| Weights | - | - | 1.00 | 3.16 | 4.63 | 12.34 |
Table 2 Video sequences used for weight calculation
| Name | Resolution | Frames | Time 240p (fps) | Time 360p (fps) | Time 480p (fps) | Time 720p (fps) |
|---|---|---|---|---|---|---|
| BasketballDrive | 1920×1080 | 500 | 15.78 | 5.37 | 3.78 | 1.47 |
| BQTerrace | 1920×1080 | 600 | 29.10 | 9.11 | 6.42 | 2.37 |
| Cactus | 1920×1080 | 500 | 25.48 | 8.77 | 5.09 | 1.96 |
| Kimono | 1920×1080 | 240 | 18.54 | 6.05 | 4.33 | 1.62 |
| ParkScene | 1920×1080 | 240 | 24.95 | 7.62 | 5.28 | 1.94 |
| PeopleOnStreet | 2560×1600 | 150 | 10.01 | 2.82 | 2.00 | 0.74 |
| Traffic | 2560×1600 | 150 | 27.36 | 8.06 | 5.77 | 2.17 |
| Average | - | - | 21.60 | 6.82 | 4.66 | 1.75 |
| Weights | - | - | 1.00 | 3.16 | 4.63 | 12.34 |
Figure 3. Percentage of broadcasts processed by the edge (1000 servers, full dataset). Two different cases: homogeneous and heterogeneous.
Figure 3. Percentage of broadcasts processed by the edge (1000 servers, full dataset). Two different cases: homogeneous and heterogeneous.
Figure 4. Percentage of broadcasts processed by the edge for decreasing arrival rate (1000 servers).
Figure 4. Percentage of broadcasts processed by the edge for decreasing arrival rate (1000 servers).
Figure 5. Percentage of broadcasts processed by the edge for varying QoS reduction percentages (full dataset, heterogeneous servers).
Figure 5. Percentage of broadcasts processed by the edge for varying QoS reduction percentages (full dataset, heterogeneous servers).
Figure 6. Average QoS of viewers as the allowable reduction in QoS for edge transcoding jobs is increased (full dataset, heterogeneous servers).
Figure 6. Average QoS of viewers as the allowable reduction in QoS for edge transcoding jobs is increased (full dataset, heterogeneous servers).
| [1] | J. Gubbi, R Buyya, S. Marusic, and M. Palaniswami, “Internet of things (IoT): a vision, architectural elements, and future directions,” Future Generation Computer Systems, vol. 29, no. 7, pp. 1645-1660, Sept. 2013. doi: 10.1016/j.future.2013.01. 010. |
| [2] | S. K. Khaitan and J. D. McCalley, “Design techniques and applications of cyber physical systems: a survey,” IEEE Systems Journal, vol. 9, no. 2, pp. 350-365, Jun. 2015. doi: 10.1109/JSYST.2014.2322503. |
| [3] | Cisco Systems Inc. (2017, Jan. 30). Cisco Visual Networking Index: Global Mobile Data Traffic Forecast Update, 2015-2020 [Online White Paper]. Available: |
| [4] | T. Wiegand, G. J. Sullivan, G. Bjøntegaard, A. Luthra , “Overview of the H.264/AVC video coding standard,” IEEE Transactions on Circuits and Systems for Video Technology, vol. 13, no. 7, pp.. 560-576, Jul. 2003. doi: 10.1109/TCSVT.2003.815165. |
| [5] | G. J. Sullivan, J.-R. Ohm, W.-J. Han, and T. Wiegand, “Overview of the high efficiency video coding (HEVC) standard,” IEEE Transactions on Circuits and Systems for Video Technology, vol. 22, no. 12, pp.. 1649-1668, Dec. 2012. doi: 10.1109/TCSVT.2012.2221191. |
| [6] | D. Grois, D. Marpe, A. Mulayoff , et al., “Performance comparison of H.265/MPEG-HEVC, VP9, and H.264/MPEG-AVC encoders,” in Picture Coding Symposium (PCS), San Jose, USA, Dec. 2013, pp. 394-397. doi: 10.1109/PCS. 2013.6737766. |
| [7] | R. A. Pardo, K. Pires, A. Blanc, G. Simon , “Transcoding live adaptive video streams at a massive scale in the cloud,” in ACM SIGMM Conference on Multimedia Systems (MMSys), Portland, USA, Mar. 2015, pp. 49-60. doi: 10.1145/2713168.2713177. |
| [8] | VideoLAN. ( 2017, Jan. 30). x264 home page [Online]. Available: |
| [9] | F. Bossen , “Common test conditions and software reference configurations,” JCT-VC, San Jose, USA, Document: JCTVC-H1100, Feb. 2012. |
| [10] | M. G. Koziri, P. Papadopoulos, N. Tziritas , et al., “Slice-based parallelization in HEVC encoding: realizing the potential through efficient load balancing,” in IEEE International Workshop on Multimedia Signal Processing (MMSP), Montreal, Canada, Sept. 2016, pp. 1-6. doi: 10.1109/MMSP.2016.7813354. |
| [11] | M. Shafique, M. U. K. Khan, and J. Henkel, “Power efficient and workload balanced tiling for parallelized high efficiency video coding,” in IEEE International Conference on Image Processing (ICIP), Paris, France, Oct. 2014, pp. 1253-1257. doi: 10.1109/ICIP.2014.7025250. |
| [12] | C. C. Chi, M. A. Mesa, B. Juurlink , et al., “Parallel scalability and efficiency of HEVC parallelization approaches,” IEEE Transactions on Circuits and Systems for Video Technology, vol. 22, no. 12, pp.. 1827-1838, Dec. 2012. doi: 10.1109/TCSVT.2012.2223056. |
| [13] | Y.-J. Ahn, T.-J. Hwang, D.-G. Sim, and W.-J. Han, “Implementation of fast HEVC encoder based on SIMD and data-level parallelism,” EURASIP Journal Image and Video Processing, vol. 16, Dec. 2014. doi: 10.1186/1687-5281-2014-16. |
| [14] | M. G. Koziri, D. Zacharis, I. Katsavounidis, N. Bellas , “Implementation of the AVS video decoder on a heterogeneous dual-core SIMD processor,” IEEE Transactions on Consumer Electronics, vol. 57, no. 2, pp.. 673-681, May 2011. doi: 10.1109/TCE.2011.5955207. |
| [15] | J. F. Franche, and S. Coulombe, “Fast H.264 to HEVC transcoder based on post-order traversal of quadtree structure,” in IEEE International Conference on Image Processing (ICIP), Quebec, Canada, Sept. 2015, pp. 477-481. doi: 10.1109/ICIP.2015.7350844. |
| [16] | I. Ahmad, X. Wei, Y. Sun, Y.-Q. Zhang, “Video transcoding: an overview of various techniques and research issues,” IEEE Transactions on Multimedia, vol. 7, no. 5, pp.. 793-804, Oct. 2005. doi: 10.1109/TMM.2005.854472. |
| [17] | W. Zhang, Y. Wen, J. Cai, D. O. Wu , “Toward transcoding as a service in a multimedia cloud: energy-efficient job-dispatching algorithm,” IEEE Transactions on Vehicular Technology, vol. 63, no. 5, pp.. 2002-2012, Jun. 2014. doi: 10.1109/TVT.2014.2310394. |
| [18] | S. Lin, X. Zhang, Q. Yu , et al., “Parallelizing video transcoding with load balancing on cloud computing,” in IEEE International Symposium on Circuits and Systems (ISCAS), Beijing, China, May 2013, pp. 2864-2867. doi: 10.1109/ISCAS.2013.6572476. |
| [19] | A. Ashraf, F. Jokhio, T. Deneke , et al., “Stream-based admission control and scheduling for video transcoding in cloud computing,” in IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGrid), Delft, Netherlands, May 2013, pp. 482-489. doi: 10.1109/CCGrid.2013.21. |
| [20] | G. Gao, W. Zhang, Y. Wen , et al., “Towards cost-efficient video transcoding in media cloud: insights learned from user viewing patterns,” IEEE Transactions on Multimedia, vol. 17, no. 8, pp.. 1286-1296, Aug. 2015. doi: 10.1109/TMM.2015.2438713. |
| [21] | S. U. R. Malik, S. U. Khan, S. J. Ewen, et al., “Performance analysis of data Intensive cloud systems based on data management and replication: a survey,” Distributed and Parallel Databases, vol. 34, no. 2, pp.. 179-215, Jun. 2016. doi: 10.1007/s10619-015-7173-2. |
| [22] | W. Ji, Z. Li, Y. Chen , “Joint source-channel coding and optimization for layered video broadcasting to heterogeneous devices,” IEEE Transactions on Multimedia, vol. 14, no. 2, pp.. 443-455, Apr. 2012. doi: 10.1109/TMM.2011.2177645. |
| [23] | W. Ji, Z. Li, Y. Chen , “Content-aware utility-fair video streaming in wireless broadcasting networks,” in IEEE International Conference on Image Processing (ICIP), Brussels, Belgium, Sept. 2011, pp. 145-148. doi: 10.1109/ICIP.2011.6115717. |
| [24] | M. T. Beck, S. Feld, A. Fichtner , et al., “ME-VoLTE: network functions for energy-efficient video transcoding at the mobile edge,” in International Conference on Intelligence in Next Generation Networks (ICIN), Paris, France, Feb. 2015, pp. 38-44. doi: 10.1109/ICIN.2015.7073804. |
| [25] | J. De Cock, A. Mavlankar, A. Moorthy, A. Aaron , “A large-scale video codec comparison of x264, x265 and libvpx for practical VOD applications,” SPIE Applications of Digital Image Processing XXXIX, vol. 9971, 997116. Sept. 2016. doi: 10.1117/12.2238495. |
| [26] | Amazon Web Services . ( 2017, Jan. 30). Amazon EC2 Instance Types [Online]. Available: |
| No related articles found! |
| 阅读次数 | ||||||
|
全文 |
|
|||||
|
摘要 |
|
|||||