Intelligent control of temperature with dynamic voltage-frequency scaling (DVFS) in embedded processors

Abstract

The increment in computing power of embedded processors has fueled a revolution in many application domains such as mobile computing or robotics. Dissipating the energy consumed by those processors on a very small area has made power management a first-order constraint. On one hand, it is impossible to directly apply active dissipation techniques. On the other hand, design requirements prevent the correct behaviour of known passive detection techniques. To alleviate this problem, we present a new control approach to keep the temperature of the system controlled through the Dynamic Voltage and Frequency Scaling (DVFS) system. The solution includes a feedback control scheme together with a supervisor that adjusts the control parameters based on the system load. To ease experimentation without compromising real use, the code can run in user space and as a Linux kernel driver. The experiments in a real platform prove that, compared to the current control methodology, our approach handles the processor’s temperature with more precision, keeping similar performance levels in the execution of well known benchmarks.

Keywords

• control inteligente de temperatura
• arquitectura de computadores
• dvfs