Making scheduling "cool": temperature-aware workload placement in data centers
ATEC '05 Proceedings of the annual conference on USENIX Annual Technical Conference
IEEE Transactions on Parallel and Distributed Systems
Performance model driven QoS guarantees and optimization in clouds
CLOUD '09 Proceedings of the 2009 ICSE Workshop on Software Engineering Challenges of Cloud Computing
Security and Privacy Challenges in Cloud Computing Environments
IEEE Security and Privacy
Dynamic Resource Allocation for Spot Markets in Cloud Computing Environments
UCC '11 Proceedings of the 2011 Fourth IEEE International Conference on Utility and Cloud Computing
CloudOpt: multi-goal optimization of application deployments across a cloud
Proceedings of the 7th International Conference on Network and Services Management
Increasing Cloud power efficiency through consolidation techniques
ISCC '11 Proceedings of the 2011 IEEE Symposium on Computers and Communications
Feedback-based optimization of a private cloud
Future Generation Computer Systems
| Hi-index | 0.00 |
With the advent of cloud computing, storage and computing functions are migrating to remote resources such as virtual servers and storage systems which are mostly hosted in the data centers. This migration can ensure significant energy savings as utilization of local resources contribute to 40% of the Greenhouse Gas emissions of the Information and Communication Technologies (ICTs). On the other hand, provisioning of the cloud services needs to be handled carefully since energy consumption of the transport network, as well as the energy consumed by the data centers, is expected to increase. We revisit our previously proposed Mixed Integer Linear Programming (MILP) models that are used to reconfigure the cloud network design with look-ahead demand profile. Due to long runtimes of the MILP models in large-scale scenarios, in this paper, we propose two heuristics to reconfigure the cloud network for provisioning the cloud and Internet computing demands. The first heuristic aims to minimize the propagation delay while the second one targets minimizing the power consumption of the data centers and the transport network. We verify the heuristics through simulations where MILP models are used as the benchmarks. Numerical results show that power minimized provisioning can guarantee significant energy savings in the cloud network with less resource consumption. We also present the energy versus delay trade-off and point out possible solutions.