This is an interim version of our Electronic Legal Deposit Catalogue-eJournals and eBooks while we continue to recover from a cyber-attack.
An Adaptive Correction Scheme for Offset-Free Asymptotic Performance in Deep Learning-based Economic MPC⁎DK gratefully acknowledges the financial support from the IK-TPLUSS project from the Research Council of Norway, and Peder Sather Grant. DK and JP contributed equally to this work. Issue 3 (2021)
Record Type:
Journal Article
Title:
An Adaptive Correction Scheme for Offset-Free Asymptotic Performance in Deep Learning-based Economic MPC⁎DK gratefully acknowledges the financial support from the IK-TPLUSS project from the Research Council of Norway, and Peder Sather Grant. DK and JP contributed equally to this work. Issue 3 (2021)
Main Title:
An Adaptive Correction Scheme for Offset-Free Asymptotic Performance in Deep Learning-based Economic MPC⁎DK gratefully acknowledges the financial support from the IK-TPLUSS project from the Research Council of Norway, and Peder Sather Grant. DK and JP contributed equally to this work.
Abstract: There has been an increasing interest in explicit and cheap-to-evaluate control policies that approximate (computationally expensive) control laws such as model predictive control (MPC). However, approximate control policies are subject to approximation errors, leading to asymptotic performance losses. The contribution of this paper is three-fold: (i) a closed-loop training scheme is presented for deep neural network approximation of economic MPC; (ii) an online adaptive correction scheme is presented to account for the performance losses induced by approximation errors; and (iii) an offline performance verification scheme is presented to ensure that the approximate control policy converges to an equilibrium point of the system. The proposed approach is illustrated using a Williams-Otto reactor problem.