Due to the continuous growth of customer population, the spreading of broadband access, the increase in energy price, and the expanding number of services being offered by telecoms and providers, energy efficiency issue has become a high-priority objective for wired networks and services infrastructures. Current network devices are well-known to be over-dimensioned for rush-hour traffic loads, and to have Oat energy requirements with respect to their real utilization. Recent studies suggested to reduce the energy consumption of networks and networked devices through the introduction of adaptive capabilities, which allow to modulate energy requirements according to networkaware performance (i.e., delays, packet losses, etc.). However, at the today's state of the art, the real impact of these power management techniques is not clear, and requires further studies and researches. Based on this context, we focus on development of a new simulator called "GreenSim", that aims at analyzing and evaluating the impact of adaptive energy saving techniques both on network- and energy-sides in the presence of real traffic traces and data. The results achieved with the proposed simulator demonstrate that these green technologies, when applied to packet processing engines inside network devices, can save up more that 40% of energy consumption in the presence of real Internet traffic profiles, while maintaining an acceptable network performance level.
GreenSim: An Open Source Tool for Evaluating the Energy Savings through Dynamic Adaptation
BOLLA, RAFFAELE;BRUSCHI, ROBERTO;A. Carrega
2010-01-01
Abstract
Due to the continuous growth of customer population, the spreading of broadband access, the increase in energy price, and the expanding number of services being offered by telecoms and providers, energy efficiency issue has become a high-priority objective for wired networks and services infrastructures. Current network devices are well-known to be over-dimensioned for rush-hour traffic loads, and to have Oat energy requirements with respect to their real utilization. Recent studies suggested to reduce the energy consumption of networks and networked devices through the introduction of adaptive capabilities, which allow to modulate energy requirements according to networkaware performance (i.e., delays, packet losses, etc.). However, at the today's state of the art, the real impact of these power management techniques is not clear, and requires further studies and researches. Based on this context, we focus on development of a new simulator called "GreenSim", that aims at analyzing and evaluating the impact of adaptive energy saving techniques both on network- and energy-sides in the presence of real traffic traces and data. The results achieved with the proposed simulator demonstrate that these green technologies, when applied to packet processing engines inside network devices, can save up more that 40% of energy consumption in the presence of real Internet traffic profiles, while maintaining an acceptable network performance level.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.