System-Level Power Management Using Online Learning

• Published in: IEEE transactions on computer-aided design of integrated circuits and systems 2009-05, Vol.28 (5), p.676-689
• Main Authors: Dhiman, G., Rosing, T.S.
• Format: Article
• Language: English
• Subjects: Algorithms; Batteries; Central processing units; Convergence; Devices; Disk drives; Dynamic voltage frequency scaling; Dynamic voltage scaling; Dynamical systems; Dynamics; Energy consumption; Energy management; energy-performance trade-off; Frequency; Hard disks; Learning; Management; online learning; Performance evaluation; Policies; Power management; Power system management; Stochastic processes; Workload
• ISSN: 0278-0070; 1937-4151
• DOI: 10.1109/TCAD.2009.2015740

In this paper, we propose a novel online-learning algorithm for system-level power management. We formulate both dynamic power management (DPM) and dynamic voltage-frequency scaling problems as one of workload characterization and selection and solve them using our algorithm. The selection is done among a set of experts, which refers to a set of DPM policies and voltage-frequency settings, leveraging the fact that different experts outperform each other under different workloads and device leakage characteristics. The online-learning algorithm adapts to changes in the characteristics and guarantees fast convergence to the best-performing expert. In our evaluation, we perform experiments on a hard disk drive (HDD) and Intel PXA27x core (CPU) with real-life workloads. Our results show that our algorithm adapts really well and achieves an overall performance comparable to the best-performing expert at any point in time, with energy savings as high as 61% and 49% for HDD and CPU, respectively. Moreover, it is extremely lightweight and has negligible overhead.