Optimización de energía en sistemas de Cloud Computing
Archivos
Fecha
2017-10-06
Autores
Título de la revista
ISSN de la revista
Título del volumen
Editor
Resumen
[ES]En el presente Trabajo Fin de Máster, se han desarrollado diversas técnicas de optimización de potencia y energía en sistemas de Cloud Computing. Se ha comenzado por la unión de dos simuladores para obtener un entorno de simulación capaz de estimar consumo energético, así como la posibilidad de ejecución de flujos de trabajo (Workflows) para poder el control dinámico de la tensión y frecuencia del procesador para ahorrar energía. En la segunda fase, se han desarrollado dos sistemas expertos basados en reglas borrosas para obtener dos planificadores de máquinas virtuales y tareas, y se muestran y analizan los resultados obtenidos, comprobando el ahorro de energía conseguido con la técnica DVFS, y concluyendo que el uso conjunto de los dos sistemas expertos consigue el mejor resultado.
[EN] In this Master's End Work, various techniques of power and power optimization have been developed in Cloud Computing systems. It has been started by the union of two simulators to obtain a simulation environment capable of estimating energy consumption, as well as the possibility of execution of workflows for dynamic control of the voltage and frequency of the processor to save energy. In the second phase, two expert systems based on fuzzy rules have been developed to obtain two virtual machine planners and tasks, and they show and analyze the results obtained, verifying the energy savings achieved with the DVFS technique, and concluding that the use set of the two expert systems get the best result.
[EN] In this Master's End Work, various techniques of power and power optimization have been developed in Cloud Computing systems. It has been started by the union of two simulators to obtain a simulation environment capable of estimating energy consumption, as well as the possibility of execution of workflows for dynamic control of the voltage and frequency of the processor to save energy. In the second phase, two expert systems based on fuzzy rules have been developed to obtain two virtual machine planners and tasks, and they show and analyze the results obtained, verifying the energy savings achieved with the DVFS technique, and concluding that the use set of the two expert systems get the best result.