Energy-Efficient Safety-Aware Scheduling of Real-Time Control Systems with Burst Tasks
Ting Cheng, Yonghui Liang, Qimin Xu, Shanying Zhu · 2024
In industrial sites, multiple real-time control systems often share computing resources. However, burst computing tasks may lead to the random dropping of control computing subtasks, resulting in control failures and potential hazards. To address this issue, we propose an energy-efficient safety-aware task scheduling scheme based on mixed-integer programming. When burst computing tasks are triggered, this scheduling scheme adaptively releases resources from low-criticality control computing sub tasks and adjusts the processor speed based on the dynamic voltage and frequency scaling technology (DVFS), ensuring the timely completion of burst computing tasks and keeping the control system state deviation within a safe threshold. To achieve the scheduling scheme, we propose an efficient algorithm called EESASA. Simulation results show that EESASA can minimize the overall cost of control and processor energy while ensuring the safety of the control system and the timely completion of burst computing tasks.