On the effectiveness of energy-aware real-time scheduling algorithms on single-core platforms

Energy-aware scheduling is a challenging problem that has been studied for decades, investigating the trade-off between performance and energy consumption. In early CMOS circuits, Dynamic Voltage and Frequency Scaling (DVFS) techniques allowed drastically reducing the power consumption. Recent technological advancements have decreased the portion of dissipation which is affected by speed scaling, making Dynamic Power Management (DPM) algorithms more effective. However, the adoption of simplistic power models often biased the decision on which technique to adopt, decreasing the effectiveness of the selected implementation. This paper discusses the factors to consider when deciding which technique to implement on a given single-core architecture, highlight the limitations of the current mainstream.