(644c) Deep Learning-Based Approximate Economic Model Predictive Control with Offset-Free Asymptotic Performance Guarantees Using a Modifier-Adaptation Scheme
AIChE Annual Meeting
2021
2021 Annual Meeting
Computing and Systems Technology Division
Predictive Control and Optimization
Thursday, November 11, 2021 - 4:08pm to 4:27pm
To overcome the challenges with online optimization and explicit MPC, there is increasing interest in âapproximateâ MPC policies that learn an explicit representation using any of the readily available function approximation techniques such as polynomials [5], radial basis functions [6], and neural networks [7-11]. The basic idea behind approximate MPC is as follows. First, the optimal control problem is solved offline for a large number of state realizations to obtain the corresponding optimal control input. Then, using this as training data, a parametric function is trained, which can then be used online to cheaply evaluate the control action. This process can be interpreted as a form of expert-based supervised learning or imitation learning [12]. Although good performance has been obtained with approximate MPC in several applications [13,14], errors in the approximation are inevitable due to the choice of âhyperparametersâ that specify the functional form of the policy and insufficient training data in certain regions of the state space leading to poor generalization. These approximation errors lead to asymptotic losses in closed-loop performance.
In this presentation, we first propose a closed-loop training procedure for approximating economic MPC using deep neural networks (DNNs) in which the training samples are generated from a control-oriented representation of the state-space that is defined in terms of a tube of closed-loop trajectories. To account for the closed-loop asymptotic performance losses using the approximate policy, we then propose a Karush-Kuhn-Tucker (KKT)-derived online adaptive correction scheme, where the main idea is to add a corrective term to the approximate policy that ensures that the limit point of closed-loop system satisfies the KKT conditions of the corresponding steady-state optimization problem. Finally, to ensure convergence of the online adaptive correction scheme that is not guaranteed in the design of the DNN, we propose an offline performance verification method. The scenario-based performance verification scheme provides probabilistic guarantees that the closed-loop control system converges to a stable equilibrium point. The performance of the proposed approach is demonstrated using a benchmark Williams-Otto reactor example.
References
[1] D.Q. Mayne, âModel predictive control: Recent developments and future promise,â Automatica, vol. 50, no. 12, pp. 2967â2986, 2014.
[2] M. Diehl, H. G. Bock, J. P. Schloder, R. Findeisen, Z. Nagy, and F. Allgower, âReal-time optimization and nonlinear model predictive control of processes governed by differential-algebraic equations,â Journal of Process Control, vol. 12, pp. 577â585, 2002.
[3] A. Bemporad, M. Morari, V. Dua, and E. N. Pistikopoulos, âThe explicit linear quadratic regulator for constrained systems,â Automatica, vol. 38, no. 1, pp. 3â20, 2002.
[4] A. Alessio, and A. Bemporad. "A survey on explicit model predictive control." Nonlinear model predictive control. Springer, Berlin, Heidelberg, 2009. 345-369.
[5] A. Chakrabarty, V. Dinh, M. J. Corless, A. E. Rundell, S. H. Z Ìak, and G. T. Buzzard, âSupport vector machine informed explicit nonlinear model predictive control using low-discrepancy sequences,â IEEE Transactions on Automatic Control, vol. 62, pp. 135â148, 2017.
[6] L. H. Cseko Ì, M. Kvasnica, and B. Lantos, âExplicit MPC-based RBF neural network controller design with discrete-time actual Kalman filter for semiactive suspension,â IEEE Transactions on Control Systems Technology, vol. 23, no. 5, pp. 1736â1753, 2015.
[7] S. Chen, K. Saulnier, N. Atanasov, D. D. Lee, V. Kumar, G. J. Pappas, and M. Morari, âApproximating explicit model predictive control using constrained neural networks,â in Proceedings of the American Control Conference, (Milwaukee), pp. 1520â1527, 2018.
[8] B. Karg, and S. Lucia. âEfficient representation and approximation of model predictive control laws via deep learning.â IEEE Transactions on Cybernetics, vol. 50, no. 9, pp. 3866-3878, 2020.
[9] J. A. Paulson and A. Mesbah. âApproximate closed-loop robust model predictive control with guaranteed stability and constraint satisfaction,â IEEE Control Systems Letters, vol. 4, no. 3, pp. 719â724, 2020.
[10] A.D. Bonzanini, J. A. Paulson, G. Makrygiorgos, and A. Mesbah. âFast approximate learning-based multistage nonlinear model predictive control using Gaussian processes and deep neural networks,â Computers & Chemical Engineering, vol. 145, pp. 107174.
[11] R.J. Lovelett, F. Dietrich, S. Lee, and I.G. Kevrekidis. âSome manifold learning considerations toward explicit model predictive control,â AIChE Journal, vol. 66, pp. e16881.
[12] D.P. Bertsekas, âReinforcement learning and optimal control,â Athena Scientific Belmont, MA., 2019
[13] A.D. Bonzanini, J. A. Paulson, D.B. Graves, and A. Mesbah. âToward safe dose delivery in plasma medicine using projected neural network-based fast approximate NMPC,â In Proceedings of the IFAC World Congress, 5353-5359, 2020, Berlin, Germany.
[14] J. Drgona, D. Picard, M. Kvasnica, and L. Helsen. âApproximate model predictive building control via machine learning,â Applied Energy, vol. 218, pp. 199â216, 2018.