Home > Research > Publications & Outputs > Real-time power cycling in video on demand data...

Research

Associated organisational units

Electronic data

  • bare_conf

    Accepted author manuscript, 441 KB, PDF document

    Available under license: CC BY-NC: Creative Commons Attribution-NonCommercial 4.0 International License

Links

Text available via DOI:

View graph of relations

Real-time power cycling in video on demand data centres using online Bayesian prediction

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review

Published

Standard

Real-time power cycling in video on demand data centres using online Bayesian prediction. / Sanz Marco, Vicent; Wang, Zheng; Porter, Barry Francis.
2017 IEEE 37th International Conference on Distributed Computing Systems. IEEE, 2017. p. 2125-2130.

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review

Harvard

Sanz Marco, V, Wang, Z & Porter, BF 2017, Real-time power cycling in video on demand data centres using online Bayesian prediction. in 2017 IEEE 37th International Conference on Distributed Computing Systems. IEEE, pp. 2125-2130. https://doi.org/10.1109/ICDCS.2017.167

APA

Sanz Marco, V., Wang, Z., & Porter, B. F. (2017). Real-time power cycling in video on demand data centres using online Bayesian prediction. In 2017 IEEE 37th International Conference on Distributed Computing Systems (pp. 2125-2130). IEEE. https://doi.org/10.1109/ICDCS.2017.167

Vancouver

Sanz Marco V, Wang Z, Porter BF. Real-time power cycling in video on demand data centres using online Bayesian prediction. In 2017 IEEE 37th International Conference on Distributed Computing Systems. IEEE. 2017. p. 2125-2130 doi: 10.1109/ICDCS.2017.167

Author

Sanz Marco, Vicent ; Wang, Zheng ; Porter, Barry Francis. / Real-time power cycling in video on demand data centres using online Bayesian prediction. 2017 IEEE 37th International Conference on Distributed Computing Systems. IEEE, 2017. pp. 2125-2130

Bibtex

@inproceedings{80d658dd01b4422eb9914a17aa546c1e,
title = "Real-time power cycling in video on demand data centres using online Bayesian prediction",
abstract = "Energy usage in data centres continues to be a major and growing concern as an increasing number of everyday services depend on these facilities. Research in this area has examined topics including power smoothing using batteries and deep learning to control cooling systems, in addition to optimisation techniques for the software running inside data centres. We present a novel real-time power-cycling architecture, supported by a media distribution approach and online prediction model, to automatically determine when servers are needed based on demand. We demonstrate with experimental evaluation that this approach can save up to 31% of server energy in a cluster. Our evaluation is conducted on typical rack mount servers in a data centre testbed and uses a recent real-world workload trace from the BBC iPlayer, an extremely popular video on demand service in the UK.",
author = "{Sanz Marco}, Vicent and Zheng Wang and Porter, {Barry Francis}",
year = "2017",
month = jun,
day = "5",
doi = "10.1109/ICDCS.2017.167",
language = "English",
isbn = "9781538617939",
pages = "2125--2130",
booktitle = "2017 IEEE 37th International Conference on Distributed Computing Systems",
publisher = "IEEE",

}

RIS

TY - GEN

T1 - Real-time power cycling in video on demand data centres using online Bayesian prediction

AU - Sanz Marco, Vicent

AU - Wang, Zheng

AU - Porter, Barry Francis

PY - 2017/6/5

Y1 - 2017/6/5

N2 - Energy usage in data centres continues to be a major and growing concern as an increasing number of everyday services depend on these facilities. Research in this area has examined topics including power smoothing using batteries and deep learning to control cooling systems, in addition to optimisation techniques for the software running inside data centres. We present a novel real-time power-cycling architecture, supported by a media distribution approach and online prediction model, to automatically determine when servers are needed based on demand. We demonstrate with experimental evaluation that this approach can save up to 31% of server energy in a cluster. Our evaluation is conducted on typical rack mount servers in a data centre testbed and uses a recent real-world workload trace from the BBC iPlayer, an extremely popular video on demand service in the UK.

AB - Energy usage in data centres continues to be a major and growing concern as an increasing number of everyday services depend on these facilities. Research in this area has examined topics including power smoothing using batteries and deep learning to control cooling systems, in addition to optimisation techniques for the software running inside data centres. We present a novel real-time power-cycling architecture, supported by a media distribution approach and online prediction model, to automatically determine when servers are needed based on demand. We demonstrate with experimental evaluation that this approach can save up to 31% of server energy in a cluster. Our evaluation is conducted on typical rack mount servers in a data centre testbed and uses a recent real-world workload trace from the BBC iPlayer, an extremely popular video on demand service in the UK.

U2 - 10.1109/ICDCS.2017.167

DO - 10.1109/ICDCS.2017.167

M3 - Conference contribution/Paper

SN - 9781538617939

SP - 2125

EP - 2130

BT - 2017 IEEE 37th International Conference on Distributed Computing Systems

PB - IEEE

ER -