Energy and Pre-emption Savings through Real-Time Race-To-Halt Algorithms
Ref: CISTER-TR-130507 Publication Date: 30, May, 2013
Energy and Pre-emption Savings through Real-Time Race-To-Halt AlgorithmsRef: CISTER-TR-130507 Publication Date: 30, May, 2013
Energy consumption has become one of the major issues for modern embedded systems. Initially, power saving approaches mainly focused on dynamic power dissipation, while neglecting the static (leakage) power consumption. However, technology improvements resulted in a case where static power dissipation increasingly dominates. Addressing this issue, hardware vendors have equipped modern processors with several sleep states. We propose a set of leakage-aware energy management approaches that reduce the energy consumption of embedded real-time systems while respecting the real-time constraints. Our algorithms are based on the race-to-halt strategy that tends to run the system at top speed with an aim to create long idle intervals, which are used to initiate a sleep state. The effectiveness of our algorithms is illustrated with an exhaustive simulations that show an improvement of up to 8% reduction in energy consumption over an existing work at high utilization. The complexity of our algorithms is smaller when compared to state-of-the-art algorithms. We also eliminate assumptions made in the related work that restrict the practical implications of their algorithms. Moreover, a novel study about the sleep states relation with the number of pre-emptions is also presented with an extensive set of simulation results, where our algorithms reduce the experienced number of pre-emptions in all cases. Our results show that sleep states in general can save up to 30% of the overall number of pre-emptions when compared to the sleep-agnostic earliest-deadline-first algorithm.
Notes: Technical report