Task aware hybrid DVFS for multi-core real-time systems using machine learning

There have been renewed interest in embedded battery powered devices due to their widespread applications in sectors such as automotive, industrial, and health care. In order to reduce energy consumption and enhance battery life, dynamic voltage and frequency scaling (DVFS) techniques have been applied to processors (one of the most energy consuming components). In order to keep pace with advancements in fabrication technologies, it is important to scale voltage and frequency intelligently; otherwise, DVFS techniques could result in a higher energy consumption. In our previous work, depending on the execution characteristics of real-time tasks, DVFS decisions were made using machine learning method in unicore processors. We also used learning-based approach to select the best real-time DVFS technique for the situation from a set of techniques and proposed a framework that integrates the selection of various scheduling policies and the optimization of existing real-time DVFS techniques in multi-core processors. In this paper, we describe the design of the framework to make an effective learning-based DVFS system, and demonstrate the utility of the generalized learning-based framework using experiments on multi-core real-time systems for both synthetic tasks and benchmark tasks from real applications. Our findings show that the framework is computationally lightweight and effective in reducing energy consumption.