Self-organizing sensing infrastructure for autonomic management of green datacenters

The scale and complexity of modern datacenters are growing at an alarming rate due to the rising popularity of the cloud computing paradigm as an effective means to cater to the ever increasing demand for computing and storage. The management of modern datacenters is rapidly exceeding human ability, making autonomic approaches essential. In this article, methods for acquiring thermal awareness using real-time measurements and heat and air circulation models as well as solutions for proactive autonomic datacenter management that exploit this awareness are discussed. Novel communication and coordination schemes that enable self-organization of a network of external heterogeneous sensors (e.g., thermal cameras, scalar temperature and humidity sensors, airflow meters) into a multitier sensing infrastructure capable of real-time datacenter monitoring are also presented.

[1]  Dario Pompili,et al.  SILENCE: distributed adaptive sampling for sensor-based autonomic systems , 2011, ICAC '11.

[2]  Chandrakant D. Patel,et al.  Thermo-Fluids Provisioning of a High Performance High Density Data Center , 2007, Distributed and Parallel Databases.

[3]  Chin-Chen Chang,et al.  Intelligent systems for future generation communications , 2010, The Journal of Supercomputing.

[4]  Richard E. Brown,et al.  Report to Congress on Server and Data Center Energy Efficiency: Public Law 109-431 , 2008 .

[5]  Dario Pompili,et al.  Proactive thermal management in green datacenters , 2012, The Journal of Supercomputing.

[6]  Sarita V. Adve,et al.  The impact of technology scaling on lifetime reliability , 2004, International Conference on Dependable Systems and Networks, 2004.

[7]  Álvaro Herrero,et al.  Intrusion Detection at Packet Level by Unsupervised Architectures , 2007, IDEAL.

[8]  Erol Gelenbe,et al.  Energy-Efficient Cloud Computing , 2010, Comput. J..

[9]  Alberto Caprara,et al.  Improved approximation algorithms for multidimensional bin packing problems , 2006, 2006 47th Annual IEEE Symposium on Foundations of Computer Science (FOCS'06).