Task-optimal data-driven surrogate models for eNMPC via differentiable simulation and optimization

IFAC-PapersOnLine, vol. 59, pp. 43–48

Abstract

We present a method for end-to-end learning of Koopman surrogate models for optimal performance in a specific control task. In contrast to previous contributions that employ standard reinforcement learning (RL) algorithms, we use a training algorithm that exploits the potential differentiability of environments based on mechanistic simulation models to aid the policy optimization. We evaluate the performance of our method by comparing it to that of other training algorithms on an existing economic nonlinear model predictive control (eNMPC) case study of a continuous stirred-tank reactor (CSTR) model. Compared to the benchmark methods, our method produces similar economic performance while eliminating constraint violations. Thus, for this case study, our method outperforms the others and offers a promising path toward more performant controllers that employ dynamic surrogate models.

Authors 3

1. Daniel Mayfrank Aachen

   RWTH Aachen University · Forschungszentrum Jülich

   Affiliation as printed

   Forschungszentrum Jülich GmbH, Institute of Climate and Energy Systems, Energy Systems Engineering (ICE-1), Jülich 52425, Germany

   RWTH Aachen University, Aachen 52062, Germany

2. Alexander Mitsos Aachen

   RWTH Aachen University · Forschungszentrum Jülich · Jülich Aachen Research Alliance

   Affiliation as printed

   Forschungszentrum Jülich GmbH, Institute of Climate and Energy Systems, Energy Systems Engineering (ICE-1), Jülich 52425, Germany

   JARA-ENERGY, Jülich 52425, Germany

   RWTH Aachen University, Process Systems Engineering (AVT.SVT), Aachen 52074, Germany

3. Manuel Dahmen corresponding

   Forschungszentrum Jülich

   Affiliation as printed

   Forschungszentrum Jülich GmbH, Institute of Climate and Energy Systems, Energy Systems Engineering (ICE-1), Jülich 52425, Germany