Thermal influence indices: Causality metrics for efficient exploration of data center cooling

Bhagwat, Harshad; Singh, Amarendra K.; Vasan, Arunchandar; Sivasubramaniam, Anand

doi:10.1109/igcc.2012.6322254

Cited by 7 publications

(1 citation statement)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Authors in [30] proposed a two stage approach, which finalizes the number of servers required based on workload characteristics and prediction routine and revalidates the server counts using a second stage integer linear programming (ILP) approach which minimizes power consumption accounting for heat recirculation and temperature constraints. Authors in [31] proposed a simple set of thermal influence metrics that quantify causal heat relationships between sources (cool air inlet and thermal heat-recirculation factor THR) and sinks (outlet). This relationship helps understand possible hotspots, occurrences, possibility of servers hitting its red-temperature threshold and overloading of CRAC scenarios.…”

Section: Integrated Compute and Cooling Power Consumption Considerationsmentioning

confidence: 99%

Heterogeneity and thermal aware adaptive heuristics for energy efficient consolidation of virtual machines in infrastructure clouds

Kumar¹,

Raghunathan

2016

Journal of Computer and System Sciences

View full text Add to dashboard Cite

Please cite this article in press as: M.R. Velayudhan Kumar, S. Raghunathan, Heterogeneity and thermal aware adaptive heuristics for energy efficient consolidation of virtual machines in Infrastructure clouds, J. Comput. Syst. Sci. (2015), http://dx. Highlights• Metrics to classify servers in a heterogeneous cloud environment based on server's power consumption and performance characteristics.• Adaptive heterogeneous and thermal aware heuristic approaches for the problem of energy and performance efficient dynamic consolidation of VMs. • Accounted for server processor sleep states and state transition time latencies in a heterogeneous cloud environment.• Hybrid heuristics approach, which works with both homogeneous and heterogeneous server cloud environment and improves cloud datacenters' energy efficiency. • Extensive simulation-based evaluation and analysis of the proposed algorithms. AbstractHolistic da specific us consumptio operationa improve en state, state proposed h

show abstract

Section: Integrated Compute and Cooling Power Consumption Considerationsmentioning

confidence: 99%