![](bg6.png)
an environment where a vast number of data are
continuously uploaded. The basis of our proposed
technique was to improve a technique introduced by
(Hasebe et al., 2010), which uses virtual nodes and
migrates them dynamically. Our improvement was a
modification of the data migration strategy so that the
destination of the virtual nodes can be chosen from
multiple options according to the current state of the
system. Finally, the performance of our systems was
evaluated in simulations. The results showed that
our technique improves the technique in the previous
study and effectively skews the workload during a
constant massive influx of data.
In future work, we will develop a prototype im-
plementation and evaluate its performance on real sy-
stems.
REFERENCES
Colarelli, D. and Grunwald, D. (2002). Massive arrays of
idle disks for storage archives. In ACM/IEEE Confe-
rence on Supercomputing, pages 1–11.
Harnik, D., Naor, D., and Segall., I. (2009). Low power
mode in cloud storage systems. In IEEE Internati-
onal Symposium on Parallel and Distributed Proces-
sing, pages 23–29.
Hasebe, K., Niwa, T., Sugiki, A., and Kato., K. (2010).
Power-saving in large-scale storage systems with data
migration. In IEEE International Conference on
Cloud Computing Technology and Science (Cloud-
Com’10), pages 266–273.
Hasebe, K., Okoshi, J., and Kato., K. (2015). Power-
saving in storage systems for cloud data sharing servi-
ces with data access prediction. IEICE Transactions,
E98-D(10):1744–1754.
Hasebe, K., Sawada, T., and Kato., K. (2016). A game
theoretic approach to power reduction in distributed
storage systems. Journal of Information Processing,
24(1):173–181.
Kaushik, R. T. and Bhandarkar., M. (2010). Greenhdfs: to-
wards an energy-conserving, storage-efficient, hybrid
hadoop compute cluster. In 2010 international confe-
rence on Power aware computing and systems (Hot-
Power’10), pages 1–9.
Pinheiro, E. and Bianchini, R. (2004). Energy conservation
techniques for disk array-based servers. In Internatio-
nal Conference on Supercomputing, pages 68–78.
Pinheiro, E., Bianchini, R., and Dubnicki, C. (2006). Ex-
ploiting redundancy to conserve energy in storage sys-
tems. In ACM SIGMETRICS Conference on Measure-
ment and modeling of computer systems, pages 15–26.
statistics, F. (2013a). https://newsroom.fb.com/News.
statistics, Y. (2013b). http://www.youtube.com/yt/press/
statistics.
Stoica, I., Morris, R., Karger, D., Kaashoek, M. F., and Ba-
lakrishnan, H. (2001). Chord: a scalable peer-to-peer
lookup service for internet applications. In ACM SIG-
COMM, pages 149–160.
Tatar, A., de Amorim, M. D., Fdida, S., and Antoniadis, P.
(2014). A survey on predicting the popularity of web
content,. Journal of Internet Services and Applicati-
ons, 5(8).
Telegraph (2013). http://www.telegraph.co.uk/technology/
twitter/9945505/Twitter-in-numbers.html.
Verma, A., Koller, R., Useche, L., and Rangaswami, R.
(2010). Srcmap: energy proportional storage using
dynamic consolidation. In 8th USENIX Conference on
File and Storage Technologies (FAST’10), pages 154–
168.
Vrbsky, S. V., Lei, M., Smith, K., and Byrd, J. (2010). Data
replication and power consumption in data grids. In
2010 IEEE Second International Conference on Cloud
Computing Technology and Science (CloudCom’10),
pages 288–295.
Weddle, C., Oldham, M., Qian, J., Wang, A., Reiher, P.,
and Kuenning, G. (2007). Paraid: a gear-shifting
power-aware raid. In USENIX Conference on File and
Storage Technologies (FAST’07), pages 245–260.
Zhu, Q., Chen, Z., Tan, L., Zhou, Y., Keeton, K., and Wil-
kes, J. (2005). Hibernator: helping disk arrays sleep
through the winter. In ACM symposium on Operating
systems principles, pages 177–190.
A Flexible Data Migration Strategy for Power Savings in Distributed Storage Systems
357