Learning Approximate Semi-Explicit Hybrid MPC with an Application to Microgrids

Reference

D. Masti, T. Pippia, A. Bemporad, and B. De Schutter, "Learning approximate semi-explicit hybrid MPC with an application to microgrids," Proceedings of the 21st IFAC World Congress, Virtual conference, pp. 5207-5212, July 2020.

Abstract

We present a semi-explicit formulation of model predictive controllers for hybrid systems with feasibility guarantees. The key idea is to use a machine-learning approach to learn a compact predictor of the integer/binary components of optimal solutions of the multiparametric mixed-integer linear optimization problem associated with the controller, so that, on-line, only a linear programming problem must be solved. In this scheme, feasibility is ensured by a simple rule-based engine that corrects the binary configuration only when necessary. The performance of the approach is assessed on a well known benchmark for which explicit controllers based on domain-specific knowledge are already available. Simulation results show how our proposed method considerably lowers computation time without deteriorating closed-loop performance.

Publisher page

• Access full text  

Downloads

• PDF of corresponding technical report (482 KB)

BibTeX

@inproceedings{MasPip:20-011,
   author    = {Masti, Daniele and Pippia, Tomas and Bemporad, Alberto and De
                Schutter, Bart},
   title     = {Learning Approximate Semi-Explicit Hybrid {MPC} with an
                Application to Microgrids},
   booktitle = {Proceedings of the 21st IFAC World Congress},
   address   = {Virtual conference},
   pages     = {5207--5212},
   month     = jul,
   year      = {2020}
   }

• Download BibTeX entry