RL-TIME: Reinforcement Learning-based Task Replication in Multicore Embedded Systems
This addresses reliability and efficiency challenges for embedded systems with strict real-time and thermal requirements, offering a dynamic improvement over static design-time methods.
The paper tackles the problem of task replication in multicore embedded systems, which can improve reliability but often causes excessive overhead and overheating, by proposing RL-TIME, a reinforcement learning-based approach that dynamically adjusts replicas based on system conditions. The results show that RL-TIME reduces power consumption by 63%, increases schedulability by 53%, and respects thermal constraints 72% more often compared to state-of-the-art methods.
Embedded systems power many modern applications and must often meet strict reliability, real-time, thermal, and power requirements. Task replication can improve reliability by duplicating a task's execution to handle transient and permanent faults, but blindly applying replication often leads to excessive overhead and higher temperatures. Existing design-time methods typically choose the number of replicas based on worst-case conditions, which can waste resources under normal operation. In this paper, we present RL-TIME, a reinforcement learning-based approach that dynamically decides the number of replicas according to actual system conditions. By considering both the reliability target and a core-level Thermal Safe Power (TSP) constraint at run-time, RL-TIME adapts the replication strategy to avoid unnecessary overhead and overheating. Experimental results show that, compared to state-of-the-art methods, RL-TIME reduces power consumption by 63%, increases schedulability by 53%, and respects TSP 72% more often.