Discrete and Continuous Optimal Control for Energy Minimization in Real-Time Systems

Bruno Gaujal (1) , Alain Girault (2) , Stéphan Plassart (3)

1 POLARIS - Performance analysis and optimization of LARge Infrastructures and Systems
2 SPADES - Sound Programming of Adaptive Dependable Embedded Systems
3 EPFL - Ecole Polytechnique Fédérale de Lausanne

This paper presents a discrete time Markov Decision Process (MDP) to compute the optimal speed scaling policy to minimize the energy consumption of a single processor executing a finite set of jobs with real-time constraints. We further show that the optimal solution is the same when speed change decisions are taken at arrival times of the jobs as well as when decisions are taken in continuous time.

Mots clés: Optimal Control; Real-Time Systems; Markov Decision Process; Dynamic Voltage and Frequency Scaling

Domaines: Informatique [cs]

Bruno Gaujal, Alain Girault, Stéphan Plassart. Discrete and Continuous Optimal Control for Energy Minimization in Real-Time Systems. EBCCSP 2020 - 6th International Conference on Event-Based Control, Communication, and Signal Processing, Sep 2020, Krakow, Poland. pp.1-8, ⟨10.1109/EBCCSP51266.2020.9291353⟩. ⟨hal-03020330⟩