Analysis of On/Off servers with Dynamic Voltage Scaling

Abstract

With rapid adoption of cloud solutions across industries, energy consumed by server farms continues to rise. There are numerous approaches to reduce energy consumption in data centres, and one of the approaches is to use energy-aware policies, which focus on how servers should be operated in order to achieve energy saving and meet service level agreements (SLA). In this thesis, we focus on studying a single server model with dynamic voltage scaling (DVS), presenting a framework with explicit solutions to solve for performance metrics and energy consumption. Our framework is convenient and in- tuitive, one can easily identify expected response time and expected energy consumption for a given policy. In addition, we also provide insights on how the value of the faster service rate and the choice of when to use speed scaling impact energy consumption and performance metrics.