Stretch: exploiting service level degradation for energy management in mixed-criticality systems

Abstract

Mixed-criticality systems are introduced due to industrial interest to integrate different types of functionalities with varying importance into a common and shared computing platform. Low-energy consumption is vital in mixed-criticality systems due to their ever-increasing computation requirements and the fact that they are mostly supplied with batteries. In case when high-criticality tasks overrun in such systems, low-criticality tasks can be whether ignored or degraded to assure high-criticality tasks timeliness. We propose a novel energy management method (called Stretch), which lowers the energy consumption of mixed-criticality systems with the cost of degrading service level of low-criticality tasks. Our Stretch method extends both execution time and period of tasks while preserving their utilization. This leads to degrading the task's service level due to a period extension that is exploited by Stretch for energy management. Experiments show that Stretch provides 14% energy savings compared to the state-of-the-art with only 5% service level degradation in low-criticality tasks. The energy savings can be increased to 74% with the cost of 100% service level degradation in low-criticality tasks.