(1 + ε)-approximate sparse recovery
Eric Price, David P. Woodruff
FOCS 2011
In this article we describe the application of physical analytics to manage optimally energy consumption of a data center (DC). In its core the solution leverages the intelligent co-management of IT workloads and the physical infrastructure of the DC. Specifically, we demonstrate workload dependent control using real-time data such as temperature, pressure, humidity and power consumption. The data is used to build specific and comprehensive models, which enables operators to either control the cooling resources or alternatively to place the IT workloads for optimum energy usage.
Eric Price, David P. Woodruff
FOCS 2011
Leo Liberti, James Ostrowski
Journal of Global Optimization
Chidanand Apté, Fred Damerau, et al.
ACM Transactions on Information Systems (TOIS)
Rolf Clauberg
IBM J. Res. Dev