行動裝置在世界各地快速的增加包含開發中國家 ， 在那裡行動
裝置使用者很難得到網際網路存取 。 本論文提出挑戰性內容遞送網
路(Challenged Content Delivery Network, CCDN)討論如何在斷續的網路存取下 ， 對於行動裝置使用者機遇性散佈新聞 。 我們建構一個最佳化的問題以計算每位使用者的散布規劃 。 在資源限制下散佈規劃可以幫助使用者改善他們的使用者體驗 。 我們的數學模型同時考慮新聞 、 行動裝置使用者以及斷續網路的特性 。 我們提出基於多維度背包問題的散佈規劃演算法 。 另外 ， 我們也發展線上啟發式策略以適應動態的系統與網路情況 。 我們的模擬結果顯示我們所提出的散佈規劃演算法相較於根據簡單策略的基準線演算法 ， 可以達到 55% 至 10 倍的使用者體驗改善 、 37% 至 20倍的系統效率 。 我們更能夠在12分鐘內針對中型的使用者網路提供散佈規劃 。 我們預想在將來挑戰性內容遞送網路可以讓新聞提供者接觸到更多的行動裝置使用者 ， 而行動裝置使用者也可以在網際網路存取的情況下沒有觀看更多的新聞

Mobile devices are getting increasingly popular all over the world, including
developing countries, where mobile users rarely have the Internet access. In
this paper, we propose a Challenged Content Delivery Network (CCDN) to
opportunistically distribute news reports to mobile users with intermittent
Internet access. In particular, we formulate an optimization problem to
compute the distribution plans for individual mobile users, so as to maximize
the overall user experience under various resource constraints. Our formulation jointly considers the characteristics of
news reports, mobile users, and intermittent networks.
We present a
distribution planning algorithm based on the multidimensional knapsack problem,
and we develop several online heuristics to adapt to the system and network dynamics.
We conduct extensive trace-driven simulations to evaluate our
proposed CCDN, which demonstrate that our algorithm: (i)
outperforms the baseline algorithms by 55% to 10 times in terms of user
experience, (ii) achieves higher system efficiency than the
baseline algorithm--by 37% to 20 times, and (iii) terminates in
12 minutes for a medium-size network of 150 users. We envision that our CCDN will allow
news providers to reach out to more mobile users, and mobile users to watch news
reports without always-on Internet access.

中文摘要 i
Abstract ii
1 Introduction 1
1.1 Introduction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1
2 Related Work 5
2.1 Opportunistic Networks . . . . . . . . . . . . . . . . . . . . . . . . . . . 5
2.2 Caching . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6
2.3 Intermittent Clouds . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7
3 News Video Distribution System 8
3.1 System Architecture . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8
3.1.1 Proposed Network Model: Challenged CDNs . . . . . . . . . . . 8
3.1.2 News Report Model . . . . . . . . . . . . . . . . . . . . . . . . 8
3.1.3 Mobile User Model . . . . . . . . . . . . . . . . . . . . . . . . . 9
3.2 Distribution Planning Problem and Solution . . . . . . . . . . . . . . . . 10
3.2.1 Notations . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10
3.2.2 Problem Formulation . . . . . . . . . . . . . . . . . . . . . . . . 12
3.2.3 Distribution Planning Algorithm . . . . . . . . . . . . . . . . . . 13
3.3 Practical Concerns . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14
3.3.1 Adaptive Communication Strategies . . . . . . . . . . . . . . . . 14
3.3.2 Machine Learning on Distribution Servers . . . . . . . . . . . . . 14
3.3.3 Segmenting Video Layers . . . . . . . . . . . . . . . . . . . . . 15
4 Trace-driven Simulations 17
4.1 Datasets . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 17
4.2 Simulator Implementation . . . . . . . . . . . . . . . . . . . . . . . . . 18
4.3 Simulation Scenarios . . . . . . . . . . . . . . . . . . . . . . . . . . . . 19
4.4 Results . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 19
5 System Prototype 25
6 Conclusion and Future Work 29
6.1 Conclusion . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 29
Bibliography 30

[1] IBM CPLEX optimizer. http://www-01.ibm.com/software/
commerce/optimization/cplex-optimizer/.
[2] Letor 4.0 dataset. http://research.microsoft.com/en-us/um/
beijing/projects/letor/letor4dataset.aspx, 2009.
[3] Ranklib. http://sourceforge.net/p/lemur/wiki/RankLib/, 2009.
[4] Dtn2. http://sourceforge.net/projects/dtn/files/DTN2/
dtn-2.9.0/, 2012.
[5] FireChat shows the triumph of technology over repression. http://tinyurl.
com/p8eblx7, 2012.
[6] Ibr-dtn. http://trac.ibr.cs.tu-bs.de/
project-cm-2012-ibrdtn, 2012.
[7] How do we accelerate Internet access in Africa? http://ventureburn.com/
2014/01/how-do-we-accelerate-internet-access-in-africa/,
2013.
[8] It’s time to take a closer look at China’s mobile in-
dustry. http://www.businessinsider.com/
the-key-china-mobile-industry-statistics-2013-12?op=1,
2014.
[9] Social, digital and mobile in India 2014. http://wearesocial.net/blog/
2014/07/social-digital-mobile-india-2014/, 2014.
[10] D. Blei, A. Ng, and M. Jordan. Latent dirichlet allocation. Journal of machine
Learning research, 3:993–1022, 2003.
[11] C. Burges. From ranknet to lambdarank to lambdamart: An overview. Technical
report, Microsoft Research, 2010
[12] B. Burns, O. Brock, and B. Levine. Mv routing and capacity building in disruption
tolerant networks. In Proc. of IEEE INFOCOM, 2005.
[13] P. Cheng, K. Lee, M. Gerla, and J. H¨arri. GeoDTN+Nav: Geographic DTN routing
with navigator prediction for urban vehicular environments. Mobile Networks and
Applications, 15(1):61–82, 2010.
[14] E. Cho, S. M. A., and J. Leskovec. Friendship and mobility: User movement in
location-based social networks. In Proc. of ACM KDD, 2011.
[15] S. Cong, P. Pranesh, N. Kangqi, Y. Juyuan, A. Mostafa, N. Mayur, and Z. Ellen.
Ic-cloud: Computation offloading to an intermittently-connected cloud. Technical
report, January 2013.
[16] E. Daly and M. Haahr. Social network analysis for routing in disconnected delay-
tolerant manets. In Proc. of ACM MobiHoc, 2007.
[17] S. Deerwester, S. Dumais, T. Landauer, G. Furnas, and R. Harshman. Indexing by
latent semantic analysis. Journal of the American Society for Information Science,
41(6):391–407, 1990.
[18] N. Do, C. Hsu, and N. Venkatasubramanian. Hybcast: Rich content dissemination
in hybrid cellular and 802.11 ad hoc networks. In Proc. of IEEE SRDS, 2012.
[19] K. Fall. A delay-tolerant network architecture for challenged Internets. In Proc. of
ACM SIGCOMM, 2003.
[20] W. Gao, Q. Li, B. Zhao, and G. Cao. Multicasting in delay tolerant networks: A
social network perspective. In Proc. of ACM MobiHoc, 2009.
[21] M. Gonzalez, C. Hidalgo, and A. Barabasi. Understanding individual human mobil-
ity patterns. Nature, 453:779–782, 2008.
[22] K. Harras and K. Almeroth. Controlled flooding in disconnected sparse mobile
networks. Wireless Communication Mobile Computing, 9(1):21–33, 2009.
[23] P. Hui, J. Crowcroft, and E. Yoneki. Bubble rap: Social-based forwarding in delay-
tolerant networks. IEEE Transactions on Mobile Computing, 10(11):1576–1589,
2011.
[24] S. Isaacman and M. Martonosi. Low-infrastructure methods to improve Internet
access for mobile users in emerging regions. In Proc. of ACM WWW, 2011.
[25] T. Joachims. Optimizing search engines using clickthrough data. In Proc. of ACM
KDD, 2002.
[26] L. Keller, A. Lec, B. Cici, H. Seferoglu, C.Fragouli, and A. Markopoulou. Mi-
crocast: Cooperative video streaming on smartphones. In Proc. of ACM MobiSys,
2012.
[27] J. Leguay, T. Friedman, and V. Conan. DTN routing in a mobility pattern space. In
Proc. of ACM SIGCOMM WDTN, 2005.
[28] Z. Li, B. Ding, J. Han, R. Kays, and P. Nye. Mining periodic behaviors for moving
objects. In Proc. of ACM KDD, 2010.
[29] A. Lindgren, A. Doria, and O. Schel´en. Probabilistic routing in intermittently con-
nected networks. ACM SIGMOBILE mobile computing and communications review,
7(3):19–20, 2003.
[30] D. Lymberopoulos, O. Riva, K. Strauss, A. Mittal, and A. Ntoulas. Pocketweb:
Instant web browsing for mobile devices. In Proc. of ACM ASPLOS, 2012.
[31] A. Monreale, F. Pinelli, R. Trasarti, and F. Giannotti. Wherenext: A location predic-
tor on trajectory pattern mining. In Proc. of ACM KDD, 2009.
[32] V. Mota, F. Cunha, D. Macedo, J. Nogueira, and A. Loureiro. Protocols, mobility
models and tools in opportunistic networks: A survey. Computer Communications,
48(0):5 – 19, 2014.
[33] A. Mtibaa, M. May, C. Diot, and M. Ammar. Peoplerank: Social opportunistic
forwarding. In Proc. of IEEE INFOCOM, 2010.
[34] H. Ntareme, M. Zennaro, and B. Pehrson. Delay tolerant network on smartphones:
Applications for communication challenged areas. In Proc. of ExtremeCom, 2011.
[35] A. Pietilainen, E. Oliver, J. Lebrun, G. Varghese, and C. Diot. MobiClique: Middle-
ware for mobile social networking. In Proc. of ACM WOSN, 2009.
[36] F. Qian, K. Quah, J. Huang, J. Erman, A. Gerber, Z. Mao, S. Sen, and O. Spatscheck.
Web caching on smartphones: Ideal vs. reality. In Proc. of ACM MobiSys, 2012.
[37] H. Schwarz, D. Marpe, and T. Wiegand. Overview of the scalable video coding
extension of the H.264/AVC standard. IEEE Transactions on Circuits and Systems
for Video Technology, 17(9):1103–1120, 2007.
[38] C. Shi, M. Ammar, E. Zegura, and M. Naik. Computing in cirrus clouds: The
challenge of intermittent connectivity. In Proc. of ACM SIGCOMM MCC, 2012.
[39] C. Shi, V. Lakafosis, M. Ammar, and E. Zegura. Serendipity: Enabling remote com-
puting among intermittently connected mobile devices. In Proc. of ACM MobiHoc,
2012.
[40] C. Song, Z. Qu, N. Blumm, and A. Barab´asi. Limits of predictability in human
mobility. Science, 327:1018–1021, 2010.
[41] T. Spyropoulos, K. Psounis, and C. Raghavendra. Spray and wait: an efficient rout-
ing scheme for intermittently connected mobile networks. In Proc. of ACM SIG-
COMM WDTN, 2005.
[42] A. Vahdat and D. Becker. Epidemic routing for partially connected ad hoc networks.
Technical report, Duke University, 2000.
[43] M. Varnamkhasti. Overview of the algorithms for solving the multidimensional
knapsack problems. Advanced Studies in Biology, 4(1):37–47, 2012.
[44] S. Wang, C. Fan, Y. Huang, and C. Hsu. Toward optimal crowdsensing video quality
for wearable cameras in smart cities. In Proc. of SmartCity, 2015.
[45] T. Wang, P. Hui, S. Kulkarni, and P. Cuff. Cooperative caching based on file popu-
larity ranking in delay tolerant networks. In Proc. of ExtremeCom, 2012.
[46] G. Wei, C. Guohong, A. Iyengar, and M. Srivatsa. Cooperative caching for efficient
data access in disruption tolerant networks. IEEE Transactions on Mobile Comput-
ing, 13(3):611–625, 2014.
[47] H. Wirtz, T. Zimmermann, M. Ceriotti, and K. Wehrle. Ca-fi: Ubiquitous mobile
wireless networking without 802.11 overhead and restrictions. In Proc. of WoW-
MoM, 2014.
[48] Y. Zhang, C. Tan, and L. Qun. Cachekeeper: A system-wide web caching service
for smartphones. In Proc. of ACM UbiComp, 2013.
[49] W. Zhao, M. Ammar, and E. Zegura. A message ferrying approach for data delivery
in sparse mobile ad hoc networks. In Proc. of ACM MobiHoc, 2004.
[50] Y. Zheng, Q. Li, Y. Chen, X. Xie, and W. Ma. Understanding mobility based on gps
data. In Proc. of the UbiComp, 2008.