Learning-Based Distributed Model Predictive Control Approximation Scheme With Guarantees

doi:10.1109/TII.2023.3331160

Learning-Based Distributed Model Predictive Control Approximation Scheme With Guarantees

2024-04-01

1

PRE

AI

DOI：10.1109/TII.2023.3331160

Original

Original request for help

Save

Abstract

En 中文

This work presents a learning-based approximation scheme to improve the computational burden of general distributed model predictive control (DMPC). Under the framework of dual decomposition, an independent neural network approximator with rectified linear unit is designed for each subsystem. The primal and Lagrangian dual analysis indicates that this error-containing approximation is a suboptimal solution of the global DMPC optimization problem. In addition, the distributed conditions designed to guarantee the feasibility and stability of global system, which inspired by an explicit-implicit procedure to approximate an MPC law, are derived from an decoupling process using dual decomposition. In cases with infeasible approximator output or the distributed conditions are violated, an backup controller will used to promote the implementation of approximation. The proposed learning-based DMPC approximator with feasibility and stability guarantees is finally employed to a reactor-separator process, and simulation results demonstrate the efficiency and superior performance of proposed strategy.

Keywords:

Approximation

distributed model predictive control (DMPC)

machine learning-based model predictive control (MPC)

neural network (NN)

Learning-Based Distributed Model Predictive Control Approximation Scheme With Guarantees

Abstract

Journal

Organization