Your article is protected by copyright and all rights are held exclusively by Springer Science +Business Media New York. This e-offprint is for personal use only and shall not be self-archived in electronic repositories. If you wish to self-archive your article, please use the accepted manuscript version for posting on your own website. You may further deposit the accepted manuscript version in any repository, provided it is only made publicly available 12 months after official publication or later and provided acknowledgement is given to the original source of publication and a link is inserted to the published article on Springer's website. The link must be accompanied by the following text: "The final publication is available at link.springer.com”.

Foremost I would like to thank my advisor professor Spyros Denazis for his continuous support, motivation and guidance during the research and writing of this thesis. Besides my advisor, I would like to thank the rest of my thesis committee: Prof. Antonios Tzes and Prof. Evaggelos Dermatas for their encouragement, insightful comments, and their help whenever I needed. I would like to express my sincere gratitude to Prof. George Bitsoris for his contribution of time, immense knowledge and being an excellent example of teacher. My sincere thanks also goes to Dr. Andreas Kind and Dr. Xenofontas Dimitropoulos for offering the internship opportunity in the IBM Research Laboratory of Zurich and leading me working on exciting research topics. I feel grateful that most time of my research I work together with my close friend Nikolaos Leontiou, who is also PhD student in the same lab. Our collaboration helps me to be more productive and improve the quality of my research. I thank my close friend Nikolaos Athanasopoulos for his patience, advices and ideas which help me a lot to complete this thesis. I thank my close friends and fellow labmates Nikolaos Efthymiopoulos, Athanasios Christakidis and Maria Efthymiopoulou for their support, advices, productive discussions and fun we have had all these years.

Abstract: In this paper, considering the transitions among different power states such as active, idle, and standby, we define the transition probability mathematically from active mode to idle mode, and propose a novel analytical approach to evaluate energy consumption and performance metrics, i.e., queue length, throughput, and response time. Simulation results indicate that our proposed model might motivate storage researchers to exploit a quick analysis toolkit and give some insights for the design of power-aware storage systems.

Abstract There is a lack of thermal models for storage clusters; most existing thermal models do not take into account the utilization of hard drives (HDDs) and solid state disks (SSDs). To address this problem, we build a ther-mal model for hybrid storage clusters that are comprised of HDDs and SSDs. We start this study by generating the thermal profiles of hard drives and solid state disks. The profiling results show that both HDDs and SSDs have pro-found impacts on temperatures of storage nodes in a cluster. Next, we build two types of hybrid storage clusters, namely,

Abstract—Recognizing that power and cooling cost for data centers are increasing, we address in this study the thermal impact of storage systems. In the first phase of this work, we generate the thermal profile of a storage server containing three hard disks. The profiling results show that disks have comparable thermal impacts as processing and networking elements to overall storage node temperature. We develop a thermal model to estimate the outlet temperature of a storage server based on processor and disk utilizations. The thermal model is validated against data acquired by an infrared thermometer as well as build-in temperature sensors on disks. Next, we apply the thermal model to investigate the thermal impact of workload management on storage systems. Our study suggests that disk-aware thermal management techniques have significant impacts on reducing cooling cost of storage systems. We further show that this work can be extended to analysis the cooling cost of data centers with massive storage capacity. Keywords-Thermal; Model; Storage System; I.