Lifetime-Aware Cloud Data Centers: Models and Performance Evaluation
Luca Chiaraviglio,
Antonio Cianfrani,
Marco Listanti,
William Liu,
Marco Polverini
Affiliations
Luca Chiaraviglio
Department of Information, Electronics and Telecommunications, University of Rome Sapienza, Rome 00185, Italy
Antonio Cianfrani
Department of Information, Electronics and Telecommunications, University of Rome Sapienza, Rome 00185, Italy
Marco Listanti
Department of Information, Electronics and Telecommunications, University of Rome Sapienza, Rome 00185, Italy
William Liu
Department of Information Technology and Software Engineering, School of Engineering, Computer and Mathematical Sciences, Auckland University of Technology, 55 Wellesley Street East, Auckland 1010, New Zealand
Marco Polverini
Department of Information, Electronics and Telecommunications, University of Rome Sapienza, Rome 00185, Italy
We present a model to evaluate the server lifetime in cloud data centers (DCs). In particular, when the server power level is decreased, the failure rate tends to be reduced as a consequence of the limited number of components powered on. However, the variation between the different power states triggers a failure rate increase. We therefore consider these two effects in a server lifetime model, subject to an energy-aware management policy. We then evaluate our model in a realistic case study. Our results show that the impact on the server lifetime is far from negligible. As a consequence, we argue that a lifetime-aware approach should be pursued to decide how and when to apply a power state change to a server.
