OATAO is an open access repository that collects the work of Toulouse researchers and makes it freely available over the web where possible.

OATAO is an open access repository that collects the work of Toulouse researchers and makes it freely available over the web where possible. This is an author-deposited version published in : http://oatao.univ-toulouse.fr/ Eprints ID : 13199 Abstract Data centers play an important role on worldwide electrical energy consumption. Understanding their power dissipation is a key aspect to achieve energy efficiency. Some application specific models were proposed, while other generic ones lack accuracy. The contributions of this paper are threefold. First we expose the importance of modelling alternating to direct current conversion losses. Second, a weakness of CPU proportional models is evidenced. Finally, a methodology to estimate the power consumed by applications with machine learning techniques is proposed. Since the results of such techniques are deeply data dependent, a study on devices' power profiles was executed to generate a small set of synthetic benchmarks able to emulate generic applications' behaviour. Our approach is then compared with two other models, showing that the percentage error of energy estimation of an application can be less than 1 %.

Using power meters and performance counters to get insight on system's behavior in terms of power consumption is common nowadays. The values coming from these external or internal meters are usually used directly by the research community, for instance to derive higher-level power models with learning techniques or to use them in decision tools such as schedulers in HPC and Cloud Computing. While it is reasonable when one wants only to have a broad view on the power consumption, they can not be used directly in most cases: We prove in this article that the problems of distributed measure and hardware limits are way more complex and create bias, and we give the keys to understand and chose the proper methodology to handle these bias to obtain relevant values for enhanced usage. A generic methodology is analyzed and its main lessons extracted for a direct usage by the research community to master system and power measures for servers in datacenter.

Abstract. The energy consumption of a computing system depends not only on its architecture, but also on its usage. This paper describes the Energy Consumption Library (libec), a modular library of sensors and power estimators, which do not depend on wattmeter to measure the power dissipated by a machine and/or the applications that it executes, etc. In addition, four use cases are used to demonstrate some of the library's capabilities.

No abstract

Composite materials have changed the way of using polymers, as the strength was favored by the incorporation of fibers and particles. This new class of materials allowed a larger number of applications. The insertion of nanometric sized particles has enhanced the variation of properties with a smaller load of fillers. In this paper, we attempt to a better understanding of nanocomposites by using an artificial intelligence's technique, known as artificial neural networks. This technique allowed the modeling of Young's modulus of nanocomposites. A good approximation was obtained, as the correlation between the data and the response of the network was high, and the error percentage was low.

No abstract

No abstract