A software-based calibration approach to increase the robustness of embedded systems

Embedded systems often interact with dynamic environments requiring not only to meet deadlines but also to achieve a certain level of accuracy. Since the inaccuracy of a task output produces a similar adverse effect like timing violation, we propose a software-based calibration approach to increase the robustness of embedded systems by monitoring and comparing system component's output accuracy with a calibration standard to take actions for addressing any inaccuracy. The calibration standard is derived from a representative component's output with known high accuracy. As an example, we analyse the accuracy of a component that performs dynamic voltage and frequency scaling (DVFS) and explains the associated timing effects in terms of task schedulability. We also perform experiments on LITMUSRT kernel to demonstrate the need and applicability of our calibration approach in the domain of embedded systems. © 2020 Inderscience Enterprises Ltd.