When Machine Learning Meets Media Cloud: Architecture, Application and Outlook

doi:10.19729/j.cnki.1673-5188.2018.03.006

Abstract

Abstract:

Nowadays, media cloud and machine learning have become two hot research domains. On the one hand, the increasing user demand on multimedia services has triggered the emergence of media cloud, which uses cloud computing to better host media services. On the other hand, machine learning techniques have been successfully applied in a variety of multimedia applications as well as a list of infrastructure and platform services. In this article, we present a tutorial survey on the way of using machine learning techniques to address the emerging challenges in the infrastructure and platform layer of media cloud. Specifically, we begin with a review on the basic concepts of various machine learning techniques. Then, we examine the system architecture of media cloud, focusing on the functionalities in the infrastructure and platform layer. For each of these function and its corresponding challenge, we further illustrate the adoptable machine learning based approaches. Finally, we present an outlook on the open issues in this intersectional domain. The objective of this article is to provide a quick reference to inspire the researchers from either machine learning or media cloud area.

Key words: machine learning, media cloud

JIN Yichao, WEN Yonggang. When Machine Learning Meets Media Cloud: Architecture, Application and Outlook[J]. ZTE Communications, 2018, 16(3): 30-39.

Figures/Tables 5

References 64

[1]	Cisco. ( 2017). Cisco visual networking index: Forecast and methodology, 2016-2021 [Online] . Available:
[2]	W. Zhu, C. Luo, J. Wang, S. Li , “Multimedia cloud computing,” IEEE Signal Processing Magazine, vol. 28, no.3,pp. 59-69, May 2011. doi: 10.1109/MSP.2011.940269.
[3]	M. Tan and X. Su , “Media cloud: when media revolution meets rise of cloud computing,” in IEEE 6th International Symposium on Service Oriented System Engineering (SOSE), Irvine, USA, 2011, pp. 251-261. doi: 10.1109/SOSE.2011.6139114.
[4]	Y. Xu and S. Mao , “A survey of mobile cloud computing for rich media applications,” IEEE Wireless Communications, vol. 20, no.3,pp. 46-53, Jun. 2013. doi: 10.1109/MWC.2013.6549282.
[5]	Y. Wen, X. Zhu, J. Rodrigues, C. Chen , “Cloud mobile media: Reflections and outlook,” IEEE Transactions on Multimedia, vol. 16, no.4,pp. 885-902, Jun. 2014. doi: 10.1109/TMM.2014.2315596.
[6]	S. Marsland , Machine Learning:An Algorithmic Perspective. Boca Raton, USA: CRC Press, 2015.
[7]	W. Zhao, R. Chellappa, P. J. Phillips, A. Rosenfeld , “Face recogni- tion: A literature survey,” ACM computing surveys, vol. 35, no. 4, pp. 399-458, 2003.
[8]	R. Poppe , “A survey on vision-based human action recognition,” Image and vision computing, vol.28, no. 6, pp. 976-990, 2010.
[9]	M. Wang and X.-S. Hua,, “Active learning in multimedia annotation and retrieval: a survey,” ACM Transactions on Intelligent Systems and Technology, vol. 2, no. 2 article no. 10, Feb. 2011. doi: 10.1145/1899412.1899414.
[10]	W. Hu, N. Xie, L. Li, X. Zeng, S. Maybank , “A survey on visual content-based video indexing and retrieval,” IEEE Transactions on Systems, Man, and Cybernetics, vol. 41, no.6,pp. 797-819, Nov. 2011. doi: 10.1109/TSMCC.2011.2109710.
[11]	L. Deng and X. Li,, “Machine learning paradigms for speech recognition: an overview,” IEEE Transactions on Audio, Speech, and Language Processing, vol. 21, no.5,pp. 1060-1089, May 2013. doi: 10.1109/TASL.2013.2244083.
[12]	L. A. Barroso, J. Clidaras, U. Holzle , “The datacenter as a computer: an introduction to the design of warehouse-scale machines,” Synthesis Lectures on Computer Architecture, vol. 8, no. 3, pp. 1-154, 2013.
[13]	W. Zhang, Y. Wen, Y. Wong, K. Toh , C.-H. Chen, “Towards joint optimization over ict and cooling systems in data centre: a survey,” IEEE Communica tions Surveys and Tutorials , vol. 18, no . 3, pp. 1596-1616, 2016. doi: 10.1109/COMST.2016.2545109.
[14]	M. Isard , “Autopilot: automatic data center management,” ACM SIGOPS Operating Systems Review, vol. 41, no.2,pp. 60-67, Apr. 2007. doi: 10.1145/1243418.1243426.
[15]	P. Barham, B. Dragovic, K. Fraser , et al., “Xen and the art of virtualization,” in ACM Symposium on Operating Systems Principles , New York, USA, 2003.
[16]	S. Soltesz, H. Pötzl, M. E. Fiuczynski, A. Bavier, L. Peterson , “Container-based operating system virtualization: a scalable, high- performance alternative to hypervisors,” ACM SIGOPS Operating Systems Review, vol. 41, no. 3, pp. 275-287, 2007. doi: 10.1145/1272996.1273025.
[17]	A. Tatar ,M. D. de Amorim, S. Fdida, and P. Antoniadis, “A survey on predicting the popularity of web content,” Journal of Internet Services and Applications, vol. 5, no. 1, pp. 1-20, 2014. doi: 10.1186/s13174-014-0008-y.
[18]	F. Xia, N. Y. Asabere, A. M. Ahmed, J. Li, X. Kong , “Mobile multimedia recommendation in smart communities: a survey,” IEEE Access, vol. 1, pp. 606-624, Sept. 2013. doi: 10.1109/ACCESS.2013.2281156.
[19]	S. Podlipnig and L. Böszörmenyi, “A survey of web cache replacement strategies,” ACM Computing Surveys, vol. 35, no. 4, pp. 374-398, 2003.
[20]	J. Famaey, F. Iterbeke, T. Wauters, F. De Turck , “Towards a predictive cache replacement strategy for multimedia content,” Journal of Network and Computer Applications, vol. 36, no. 1, pp. 219-227, 2013. doi: 10.1016/j.jnca.2012.08.014.
[21]	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.
[22]	Y. Chen, K. Wu, Q. Zhang , “From QoS to QoE: a tutorial on video quality assessment,” IEEE Communications Surveys & Tutorials, vol. 17, no. 2, pp. 1126-1165, 2015. doi: 10.1109/COMST.2014.2363139.
[23]	M. K. Saini, R. Gadde, S. Yan, W. T. Ooi , “Movimash: online mobile video mashup,” in Proc. 20th ACM International Conference on Multimedia, Nara, Japan, 2012, pp. 139-148.
[24]	M. Avgerinou, P. Bertoldi, L. Castellazzi , “Trends in data centre energy consumption under the european code of conduct for data centre energy efficiency,” Energies , vol. 10, no.10, p. 1470, 2017.
[25]	J. Choi, S. Govindan, B. Urgaonkar, A. Sivasubramaniam , “Pro- filing, prediction, and capping of power consumption in consolidated environments,” in IEEE International Symposium on Modeling, Analysis and Simulation of Computers and Telecommunication Systems, Baltimore, USA, 2008, pp. 1-10. doi: 10.1109/MASCOT.2008.4770558.
[26]	A. W. Lewis, S. Ghosh ,N.-F. Tzeng, “Run-time energy consumption estimation based on workload in server systems,” HotPower, vol. 8, pp. 17-21, 2008.
[27]	G. Dhiman, K. Mihic, T. Rosing , “A system for online power prediction in virtualized environments using gaussian mixture models,” in ACM/IEEE 47th Design Automation Conference (DAC), Anaheim, USA, 2010, pp. 807-812. doi: 10.1145/1837274.1837478.
[28]	J. Gao , “Machine learning applications for data center optimization, ” Google White Paper, 2014.
[29]	Y. Li, H. Hu, Y. Wen, J. Zhang , “Learning-based power prediction for data centre operations via deep neural networks,” in Proc. 5th International Workshop on Energy Efficient Data Centres, Waterloo, Canada, 2016, pp. 1-10. doi: 10.1145/2940679.2940685.
[30]	D. Pelleg, M. Ben-Yehuda, R. Harper, L. Spainhower, T. Adeshiyan , “Vigilant: out-of-band detection of failures in virtual machines,” ACM SIGOPS Operating Systems Review, vol. 42, no.1,pp. 26-31, Jan. 2008.
[31]	S. Fu , “Performance metric selection for autonomic anomaly detection on cloud computing systems,” in IEEE Global Telecommunications Conference (GLOBECOM 2011), Kathmandu, Nepal, 2011, pp. 1-5. doi: 10.1109/GLOCOM.2011.6134532.
[32]	Q. Guan, Z. Zhang, S. Fu , “Ensemble of bayesian predictors and decision trees for proactive failure management in cloud computing systems,” Journal of Communications, vol. 7, no. 1, pp. 52-61, 2012. doi: 10.4304/jcm.7.1.52-61.
[33]	J. J. Prevost, K. Nagothu, B. Kelley, M. Jamshidi , “Prediction of cloud data center networks loads using stochastic and neural models,” in IEEE International Conference on System of Systems Engineering (SoSE), Albuquerque, USA, 2011, pp. 276-281. doi: 10.1109/SYSOSE.2011.5966610.
[34]	X. Chen ,C.-D. Lu, and K. Pattabiraman, “Failure prediction of jobs in compute clouds: A google cluster case study,” in IEEE International Symposium on Software Reliability Engineering Workshops (ISSREW), Naples, Italy, 2014, pp. 341-346. doi: 10.1109/ISSREW.2014.105.
[35]	B. Zhu, G. Wang, X. Liu , et al., “Proactive drive failure prediction for large scale storage systems,” in IEEE 29th Symposium on Mass Storage Systems and Technologies (MSST), Long Beach, USA, 2013, pp. 1-5. doi: 10.1109/MSST.2013.6558427.
[36]	S. Sohrabi, A. Tang, I. Moser, A. Aleti , “Adaptive virtual machine migration mechanism for energy efficiency,” in Proc. 5th International Workshop on Green and Sustainable Software, Austin, USA, 2016, pp. 8-14. doi: 10.1145/2896967.2896969.
[37]	Z. Li, C. Yan, X. Yu, N. Yu , “Bayesian network-based virtual machines consolidation method,” Future Generation Computer Systems, vol. 69, pp. 75-87, 2017. doi: 10.1016/j.jnca.2016.03.002
[38]	G.K. Shyam .and S. S. Manvi, “Virtual resource prediction in cloud environment: a bayesian approach,” Journal of Network and Computer Applications, vol. 65, pp. 144-154, Apr. 2016.
[39]	S.S. .Masoumzadeh and H. Hlavacs, “Integrating VM selection criteria in distributed dynamic VM consolidation using fuzzy q-learning,” in IEEE International Conference on Network and Service Management (CNSM), Zurich, Switzerland, 2013, pp. 332-338. doi: 10.1109/CNSM.2013.6727854.
[40]	Y. Jin, Y. Wen, H. Hu , “Minimizing monetary cost via cloud clone migration in multi-screen cloud social tv system,” in IEEE Global Communications Conference (GLOBECOM), Atlanta, USA, 2013, pp. 1747-1752. doi: 10.1109/GLOCOM.2013.6831326.
[41]	Y. Jin, Y. Wen, H. Hu, M. Montpetit , “Reducing operational costs in cloud social TV: an opportunity for cloud cloning,” IEEE Transactions on Multimedia, vol. 16, no.6,pp. 1739-1751, Oct. 2014. doi: 10.1109/TMM.2014.2329370.
[42]	N. Liu, Z. Li, J. Xu , et al. ( 2017, Mar.13). A hierarchical framework of cloud resource allocation and power management using deep reinforcement learning [Online]. Available:
[43]	M. Cha, H. Kwak, P. Rodriguez ,Y.-Y. Ahn, and S. Moon , “I tube, you tube, everybody tubes: analyzing the world’s largest user generated content video system,” in Proc. 7th ACM SIGCOMM Conference on Internet Measurement, San Diego, USA, 2007, pp. 1-14. doi: 10.1145/1298306.1298309.
[44]	G. Szabo and B. A. Huberman, “Predicting the popularity of online content,” Communications of the ACM, vol. 53, no. 8, pp. 80-88, 2010.
[45]	Y. Borghol, S. Ardon, N. Carlsson, D. Eager, A. Mahanti , “The untold story of the clones: content-agnostic factors that impact youtube video popularity,” in Proc. 18th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Beijing, China, 2012, pp. 1186-1194. doi: 10.1145/2339530.2339717.
[46]	W. Chuand S.-T. Park, “Personalized recommendation on dynamic content using predictive bilinear models,” in Proc. 18th International Conference on World Wide Web, Madrid, Spain, 2009, pp. 691-700. doi: 10.1145/1526709.1526802.
[47]	M. Ahmed, S. Spagna, F. Huici, S. Niccolini , “A peek into the future: Predicting the evolution of popularity in user generated content,” in Proc. Sixth ACM International Conference on Web search and Data Mining, Rome, Italy, 2013, pp. 607-616. doi: 10.1145/2433396.2433473.
[48]	X. Ma, H. Wang, H. Li, J. Liu, H. Jiang , “Exploring sharing patterns for video recommendation on youtube-like social media,” Multimedia Systems, vol. 20, no. 6, pp. 675-691, 2014. doi: 10.1007/s00530-013-0309-1.
[49]	P. Covington, J. Adams, E. Sargin , “Deep neural networks for youtube recommendations,” in Proc. 10th ACM Conference on Recommender Systems, Boston, USA, 2016, pp. 191-198. doi: 10.1145/2959100.2959190.
[50]	G. Pallis and A. Vakali, “Insight and perspectives for content delivery networks,” Communications of the ACM, vol. 49, no. 1, pp. 101-106, 2006.
[51]	P. Venketesh, R. Venkatesan, L. Arunprakash , “Semantic web prefetching scheme using naïve bayes classifier,” International Journal of Computer Science and Applications, vol. 7, no. 1, pp. 66-78, 2010.
[52]	W. Ali, S. M. Shamsuddin, A. S. Ismail , “Intelligent naıve bayes- based approaches for web proxy caching,” Knowledge-Based Systems, vol. 31, pp. 162-175, 2012.
[53]	T. Yan, D. Chu, D. Ganesan, A. Kansal, J. Liu , “Fast app launching for mobile devices using predictive user context,” in Proc. 10th International Conference on Mobile Systems, Applications, and Services, Low Wood Bay, UK, 2012, pp. 113-126. doi: 10.1145/2307636.2307648.
[54]	H. Hu, Y. Wen , T.-S. Chua, et al.,“Joint content replication and request routing for social video distribution over cloud CDN: a community clustering method,” IEEE Transactions on Circuits and Systems for Video Technology, vol. 26, no.7,pp. 1320-1333, Jul. 2016. doi: 10.1109/TCSVT.2015.2455712.
[55]	W. Hu, Y. Jin, Y. Wen, Z. Wang, L. Sun , “Towards wi-fi AP-assisted content prefetching for on-demand TV series: a learning-based approach,” IEEE Transactions on Circuits and Systems for Video Tech- nology, vol.28, no. 7, pp.1665-1676 , Jul. 2017. doi: 10.1109/TCSVT.2017.2684302.
[56]	M. Covell, M. Arjovsky, Y.-C. Lin, A. Kokaram, “Optimizing transcoder quality targets using a neural network with an embedded bitrate model,” Electronic Imaging , vol. 2016, no. 2, pp. 1-7, 2016. doi: 10.2352/ISSN.2470-1173.2016.2.VIPC-237.
[57]	P. P. Dash, A. Mishra, A. Wong . (2016, Sept. 22). Deep quality: a deep no-reference quality assessment system [Online]. Available:
[58]	H. Zhang, H. Hu, G. Gao, Y. Wen, K. Guan . ( 2018,Apr.10). Deepqoe: a unified framework for learning to predict QoE [Online]. Available:
[59]	V. D’Alessandro, B. Park, L. Romano , et al., “Scalable network traffic classification using distributed support vector machines,” in IEEE 8th International Conference on Cloud Computing (CLOUD), New York, USA, 2015, pp. 1008-1012. doi: 10.1109/CLOUD.2015.138.
[60]	L. Vu, C. T. Bui, Q. U. Nguyen , “A deep learning based method for handling imbalanced problem in network traffic classification,” in Proc. Eighth International Symposium on Information and Communication Technology, Nha Trang, Vietnam, 2017, pp. 333-339.
[61]	J. Ran, X. Kong, G. Lin, D. Yuan, H. Hu , “A self-adaptive network traffic classification system with unknown flow detection,” in 3rd IEEE International Conference on Computer and Communications (ICCC), Chengdu, China, 2017, pp. 1215-1220.
[62]	J. Hochst, L. Baumgartner, M. Hollick, B. Freisleben , “Unsupervised traffic flow classification using a neural autoencoder,” in IEEE 42nd Conference on Local Computer Networks (LCN), Singapore, Singapore, 2017, pp. 523-526. doi: 10.1109/LCN.2017.57.
[63]	Y. Jin and Y. Wen, “When cloud media meets network function virtualization: challenges and applications,” IEEE MultiMedia, vol. 24, no. 3, pp. 72-82, 2017. doi: 10.1109/MMUL.2017.3051519.
[64]	H. Jagadish, J. Gehrke, A. Labrinidis , et al., “Big data and its technical challenges,” Communications of the ACM, vol. 57, no. 7, pp. 86-94, 2014. doi: 10.1145/2611567.

	Regression	Decision tree	Bayesian network	PCA	Q-learning	Deep learning
Power predict and control	[25], [26], [27]					[28], [29]
Failure predict and operate		[30], [31], [32]		[31], [32]		[33], [34], [35]
VM configure and consolidate			[36], [37], [38]		[39], [40], [41], [42]

	Regression	Decision tree	Bayesian network	PCA	Q-learning	Deep learning
Power predict and control	[25], [26], [27]					[28], [29]
Failure predict and operate		[30], [31], [32]		[31], [32]		[33], [34], [35]
VM configure and consolidate			[36], [37], [38]		[39], [40], [41], [42]

	Regression	Bayesian network	K-means	PCA	Affinity propagation	Q-learning	Deep learning
Content recommendation	[44], [45], [46]		[44]	[45]	[47]		[48], [49]
Content prefetching		[50], [51], [52]	[53]		[54]	[55]
Media data adaptation							[56], [57], [58]

	Regression	Bayesian network	K-means	PCA	Affinity propagation	Q-learning	Deep learning
Content recommendation	[44], [45], [46]		[44]	[45]	[47]		[48], [49]
Content prefetching		[50], [51], [52]	[53]		[54]	[55]
Media data adaptation							[56], [57], [58]