Non-Markovian optimal switching control for hybrid renewable energy systems
Abstract
In this paper, we consider an optimal stochastic switching problem arising in the operation of hybrid renewable energy systems with battery storage when the dynamics are not necessarily Markovian. Relying on probabilistic tools such as reflected backward stochastic differential equations (RBSDEs) and Dynkin games, we provide a characterization of the value processes and establish the existence of optimal switching strategies. To demonstrate the practical relevance of our framework, we propose a model for microgrid dynamics and perform numerical experiments. Computations rely on a deep learning–driven approach for doubly reflected BSDEs and the associated Dynkin games.
Fields of Study & Subjects
Stochastic processes and financial applications
Integrated Energy Systems Optimization
Adaptive Dynamic Programming Control
Publication details
- Journal / source
- Discrete and Continuous Dynamical Systems - S
- Volume
- 31
- Issue
- 0
- Pages
- 164–186
- Publication date
- 27 February 2026
- Language
- EN