Real-Time Embedded Systems Scheduling Optimization

Abstract

The embedded real-time scheduling problem is qualified as a hard multi-objective optimization problem under constraints since it should compromise between three key conflictual objectives that are tasks deadlines guarantee, energy consumption reduction, and reliability enhancement. On this fact, conventional approaches can easily fail to find a good tradeoff in particular when the design space is too vast. On the other side, bio-inspired meta-heuristics have proved their efficiency even if the design space is very large. In this framework, the authors review the most pertinent works of literature targeting the application of bio-inspired methods to resolve the real-time scheduling problem for embedded systems, notably artificial immune systems, machine learning, cellular automata, evolutionary algorithms, and swarm intelligence. A deep discussion is conducted putting the light on the main challenges of using bio-inspired methods in the context of embedded systems. At the end of this review, the authors highlight some of the future directions.