Please use this identifier to cite or link to this item:
https://hdl.handle.net/2440/107293
Citations | ||
Scopus | Web of Science® | Altmetric |
---|---|---|
?
|
?
|
Type: | Conference paper |
Title: | Green-aware online resource allocation for geo-distributed cloud data centers on multi-source energy |
Author: | He, H. Shen, H. |
Citation: | Proceedings of the 17th International Conference on Parallel and Distributed Computing, Applications and Technologies (PDCAT 2016), 2016 / Shen, H., Sang, Y., Tian, H. (ed./s), vol.0, pp.113-118 |
Publisher: | IEEE |
Issue Date: | 2016 |
ISBN: | 9781509050819 |
Conference Name: | 17th International Conference on Parallel and Distributed Computing, Applications and Technologies (PDCAT 2016) (16 Dec 2016 - 18 Dec 2016 : Guangzhou, China) |
Editor: | Shen, H. Sang, Y. Tian, H. |
Statement of Responsibility: | Huaiwen He and Hong Shen |
Abstract: | Huge energy consumption of large-scale cloud data centers damages the environment with excessive carbon emission. More and more data center operators are seeking to reduce carbon footprint via various types of renewable energy sources. However, the intermittent availability of renewable energy source makes it quite challenging to cooperate the dynamic workload arrivals. In this paper, we investigate how to coordinate multitype renewable energy (e.g. wind power and solar power) in order to reduce the long-term energy cost with spatio-temporal diversity of electricity price for geo-distributed cloud data centers under the constraints of service level agreement (SLA) and carbon footprints. To tackle the randomness of workload arrival, dynamic electricity price change and renewable energy generation, we first formulate the minimizing energy cost problem into a constrained stochastic optimization problem. Then, based on Lyapunov optimization technique, we design an online control algorithm which can work without long-term future system information for solving the problem. Finally, we evaluate the effectiveness of the algorithm with extensive simulations based on real-world workload traces, electricity price and historic climate data. |
Rights: | © 2016 IEEE |
DOI: | 10.1109/PDCAT.2016.037 |
Grant ID: | http://purl.org/au-research/grants/arc/DP150104871 |
Appears in Collections: | Aurora harvest 3 Computer Science publications |
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.