The demand for data center (DC) has been increasing significantly due to the rapid growth in ICT technology. This brings along the “green” issues in data center such as energy consumption, heat generation and cooling requirements. These issues can be addressed by “Green of/by IT” approach in the context of operating costs as well as the environmental impacts. To install temperature monitoring system in every corner of data center is certainly cost inefficient. Optimizing the number of sensors deployed in DC is thus important for reducing the monitoring cost. This project aims to create a wireless temperature monitoring system with an optimizing technique to optimize the number of temperature sensors deployed in a DC. The real-time temperature data collected by this system can also be used to predict the next state of the temperature in DC to detect potential anomaly in heat generation. Quick preventive response can thus be invoked to manage this potential hot spots in DC. This could be a promising green by IT approach.
[1]
Yixin Chen,et al.
Intelligent Sensor Placement for Hot Server Detection in Data Centers
,
2013,
IEEE Transactions on Parallel and Distributed Systems.
[2]
Andreas Krause,et al.
Optimizing Sensing: From Water to the Web
,
2009,
Computer.
[3]
Yixin Chen,et al.
Transactions on Parallel and Distributed Systems 1 1 2 3 4 5 6 7 8
,
2022
.
[4]
Andreas Terzis,et al.
RACNet: a high-fidelity data center sensing network
,
2009,
SenSys '09.
[5]
Andreas Krause,et al.
Optimizing sensing: theory and applications
,
2008
.
[6]
Roman Garnett,et al.
Bayesian optimization for sensor set selection
,
2010,
IPSN '10.
[7]
Yixin Chen,et al.
Towards Optimal Sensor Placement for Hot Server Detection in Data Centers
,
2011,
2011 31st International Conference on Distributed Computing Systems.