近幾年來雲端儲存服務一直是熱門的雲端服務項目之一，為了讓用戶群有著低延
遲的檔案存取，資料中心級的雲端儲存供應商開始針對了地理區域的特性來做改
善。Content Delivery Network(CDN) 在過去幾年被廣泛使用在基於地理用戶的網
頁內容儲存，CDN 確保了快速的網頁回應時間以及下載時間，此項技術也開始
被應用在雲端儲存服務上。另一種解決辦法則是複製多個檔案在每一個區域上，
Geo-Replication 即是這種概念，將檔案從較遠的資料中心緩存在較近的資料中
心，能夠達到同樣效果。隨著資料量的大幅成長，分散式雲端儲存的架構也開始
崛起，善用每個儲存裝置的計算能力以及儲存空間將是未來的趨勢。目前的分散
式雲端儲存大多分散節點在世界各地，利用點對點的方式傳檔，但在這樣的方式
下還沒有一個緩存的架構出現。
考量到行動裝置的快速崛起，啟發了我們在分散式的架構下對檔案的緩存，
我們提出了一個新的檔案存取策略，適用於行動裝置以及用戶的移動性。讓使用
者能在手持行動裝置的異地條件下，一樣能快速的取得雲端儲存上的檔案。新系
統的緩存策略是基於行動裝置的地區性來產生3 層的緩存，系統結合行動裝置的
位置資訊以及檔案區塊的管理來達到closet 的效果，在區塊分布儲存的方式下，
單一儲存節點並沒有辦法取得所有檔案區塊，因此也保有資料的隱私性。
最後，我們利用模擬的方式，在貼近現實網路條件的設定中，藉由下載檔案
的速度來評估我們的新系統。

Cloud storage service has been one of the popular cloud services in recent years.To provide low latency file access and high quality service for customers, cloud storage providers focus on improving the characteristic of geographical location. Content delivery network has come of age. CDN delivers webpages and Web content to users based on their geographic locations. It ensures a faster response and shorter download time. The concept of closest cache has been applied in cloud storage service.

An alternate approach is replicating all objects to all data centers like georeplication. To cache replicas in closet region from remote region have the same effect as CDN.As the amount of data grows, the architecture of decentralized cloud storage system has expanded rapidly. By using the computing and idle storage space in each storage device will become a trend in the future. These peers in decentralized system are distributed around the world. However, good P2P technique still can be developed.The rapid rise of mobile devices inspired us to file caching in decentralized architecture, so we propose a new file access strategy for mobile devices and user mobility. Users access their files faster from cloud storage even if they use mobile device in remote location. The new cache strategy in our system is based on the region of mobile device to generate a three-tier cache system. The system combines location of mobile devices and file chunk management to achieve the closet goal. In chunk storage, no one can get whole chunks, so we ensure file privacy. Finally, we evaluated our system by download speed in a realistic network
simulation model.

[1] P. Mell and T. Grance, “The nist definition of cloud computing, nist special
publication 800-145.” http://csrc.nist.gov/publications/nistpubs/
pp.800-145/SP800-145.pdf, 2011.
[2] W. Zeng, Y. Zhao, K. Ou, and W. Song, “Research on cloud storage architecture and
key technologies,” in Proceedings of the 2Nd International Conference on Interaction
Sciences: Information Technology, Culture and Human, ICIS ’09, (New York,
NY, USA), pp. 1044–1048, ACM, 2009.
[3] M. Pathan, R. Buyya, and A. Vakali, “Content delivery networks: State of the art,
insights, and imperatives,” in Content Delivery Networks (R. Buyya, M. Pathan, and
A. Vakali, eds.), vol. 9 of Lecture Notes Electrical Engineering, pp. 3–32, Springer
Berlin Heidelberg, 2008.
[4] J. Byers, J. Considine, M. Mitzenmacher, and S. Rost, “Informed content delivery
across adaptive overlay networks,” IEEE/ACM Transactions on Networking, vol. 12,
pp. 767–780, Oct 2004.
[5] B. Hess, A. Z. Farahani, F. Tschirschnitz, and F. von Reischach, “Evaluation of finegranular
gps tracking on smartphones,” in Proceedings of the First ACM SIGSPATIAL
International Workshop on Mobile Geographic Information Systems, MobiGIS
’12, (New York, NY, USA), pp. 33–40, ACM, 2012.
[6] S. Patterson, “Personal cloud storage hit 685 petabytes this year. webpronews, 2013.”
http:// www.webpronews.com/ personal-cloud-storage-hit-685-petabytes-this-year-
2013-12, 2013.
[7] H. Weatherspoon and J. Kubiatowicz, “Erasure coding vs. replication: A quantitative
comparison,” in Revised Papers from the First International Workshop on Peer-to-
Peer Systems, IPTPS ’01, (London, UK, UK), pp. 328–338, Springer-Verlag, 2002.
[8] LACIE Inc. https://www.wuala.com, 2007.
[9] Quantum Inc. http://www.symform.com, 2014.
[10] M. Scanlon, J. Farina, and M.-T. Kechadi, “Bittorrent sync: Network investigation
methodology,” in 2014 Ninth International Conference on Availability, Reliability
and Security (ARES), pp. 21–29, Sept 2014.
[11] aeroFs Inc. https://www.aerofs.com, 2013.
[12] G. Liang and U. C. Kozat, “Fast cloud: Pushing the envelope on delay performance
of cloud storage with coding,” IEEE/ACM Transactions on Networking, vol. 22,
pp. 2012–2025, Dec. 2014.
[13] X. Tang and J. Xu, “Qos-aware replica placement for content distribution,” IEEE
Transactions on Parallel and Distributed Systems, vol. 16, pp. 921–932, Oct. 2005.
[14] K. Rzadca, A. Datta, and S. Buchegger, “Replica placement in p2p storage: Complexity
and game theoretic analyses,” in IEEE 30th International Conference on Distributed
Computing Systems (ICDCS), pp. 599–609, June 2010.
[15] Z. Wu, M. Butkiewicz, D. Perkins, E. Katz-Bassett, and H. V. Madhyastha,
“Spanstore: Cost-effective geo-replicated storage spanning multiple cloud services,”
in Proceedings of the Twenty-Fourth ACM Symposium on Operating Systems Principles,
SOSP ’13, (New York, NY, USA), pp. 292–308, ACM, 2013.
[16] Z. Ye, S. Li, and X. Zhou, “Gcplace: Geo-cloud based correlation aware data replica
placement,” in Proceedings of the 28th Annual ACM Symposium on Applied Computing,
SAC ’13, (New York, NY, USA), pp. 371–376, ACM, 2013.
[17] R. Gracia-Tinedo, M. Sanchez Artigas, A. Moreno-Martinez, C. Cotes, and P. Garcia
Lopez, “Actively measuring personal cloud storage,” in 2013 IEEE Sixth International
Conference on Cloud Computing (CLOUD), pp. 301–308, June 2013.
[18] S. Traverso, K. Huguenin, I. Trestian, V. Erramilli, N. Laoutaris, and K. Papagiannaki,
“Social-aware replication in geo-diverse online systems,” IEEE Transactions
on Parallel and Distributed Systems, vol. 26, pp. 584–593, Feb 2015.
[19] Level 3 Communications, Inc., “Solutions.” http://www.level3.com/en/
solutions/, 2014.
[20] S. Tragopoulou, I. Varlamis, and M. Eirinaki, ?Classification of movement data
concerning users activity recognition via mobile phones, ?in Proceedings of the
4th International Conference on Web Intelligence, Mining and Semantics (WIMS14).
ACM, 2014.
[21] M. Garmehi, M. Analoui, M. Pathan, and R. Buyya, “An economic replica placement
mechanism for streaming content distribution in hybrid cdn-p2p networks,”
Computer Communications, vol. 52, pp. 60 – 70, 2014.
[22] L. Zhong, X. Wang, and M. Kihl, “Topological model and analysis of the p2p bittorrent
protocol,” International Journal of System Control and Information Processing,
vol. 1, no. 1, 2012.
[23] OoKLA Inc, OOKLA RAW DATA. http://www.ookla.com/speedtest-intelligence,
2013.