Journal
IEEE SYSTEMS JOURNAL
Volume 11, Issue 2, Pages 931-940Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/JSYST.2015.2446205
Keywords
Dynamic voltage and frequency scaling (DVFS); energy efficiency; power-aware system; real-time systems; reinforcement learning (RL)
Categories
Funding
- Natural Sciences and Engineering Research Council of Canada
Ask authors/readers for more resources
Power consumption is one of the most challenging issues in the design of modern computing systems. In any computational device, processor consumes significant amount of power compared with other components. In order to reduce power consumption, dynamic voltage and frequency scaling (DVFS) has been commonly used in modern processors. In recent years, there has been much research on real-time DVFS techniques. These techniques work with different strategies and perform well under different conditions. However, a single algorithm is not always optimal under different workloads, dynamic slacks, and power settings. Furthermore, the variation in device configuration also affects the suitability of a given DVFS algorithm. Aiming for adaptability, in this paper, we propose a novel reinforcement learning-based approach, which takes a set of existing techniques, specialized to handle different conditions, and switches to the most suitable one in various situations. Experimental results show that the proposed hybrid approach saves more energy than any single policy executing individually.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available