Regresar

Empirical modeling and simulation of an heterogeneous Cloud computing environment

Abstract:

Cloud computing offers users a convenient scalable and flexible scenario for developing, running, and testing different applications in a pay-as-you-go model. However, the increasing demand of computational resources have resulted in more power consumption. In order to address this issue, the use of energy efficient resources such as FPGAs within a Cloud computing environment is nowadays a hot research topic, driven both from industry and academy. The efficient use of this type of resources can lead to increase the profit obtained by Cloud providers by serving more client requests while fulfilling their requirements with the minimum set of resources. In this paper, we survey an architectural framework and algorithms for managing heterogeneous resources, focusing on FPGAs. Based on this architecture, a simulation tool for studying the impact on performance and energy consumption of scaling the number of FPGAs in the system is presented. This tool is based on statistical models of processing time and energy consumption. The scalability study demonstrates that increasing the number of FPGAs can improve energy consumption up to 40%, while also admitting up to 35% more requests into the system.