Efficient model predictive control for nonlinear systems modelled by deep neural networks
This paper presents a model predictive control (MPC) for dynamic systems whose nonlinearity and uncertainty are modelled by deep neural networks (NNs), under input and state constraints. Since the NN output contains a high-order complex nonlinearity of the system state and control input, the MPC problem is nonlinear and challenging to solve for real-time control. This paper proposes two types of methods for solving the MPC problem: the mixed integer programming (MIP) method which produces an exact solution to the nonlinear MPC, and linear relaxation (LR) methods which generally give suboptimal solutions but are much computationally cheaper. Extensive numerical simulation for an inverted pendulum system modelled by ReLU NNs of various sizes is used to demonstrate and compare performance of the MIP and LR methods.
Code (0)
등록된 구현이 없습니다.
Tasks
Model Predictive ControlSimilar Papers 제목 키워드 기반
Approximate Robust NMPC using Reinforcement Learning
We present a Reinforcement Learning-based Robust Nonlinear Model Predictive Control (RL-RNMPC) framework for controlling nonlinear systems in the presence of disturbances and uncertainties. An approximate Robust Nonlinea…
Model Predictive Controlreinforcement-learningReinforcement LearningReinforcement Learning (RL)Robust Output-Lifted Learning Model Predictive Control
We propose an iterative approach for designing Robust Learning Model Predictive Control (LMPC) policies for a class of nonlinear systems with additive, unmodelled dynamics. The nominal dynamics are assumed to be differen…
modelModel Predictive ControlModel Predictive Control of Wind Turbines with Piecewise-Affine Power Coefficient Approximation
In this paper, an offset-free bilinear model predictive control approach for wind turbines is presented. State-of-the-art controllers employ different control loops for pitch angle and generator torque which switch depen…
Model Predictive ControlSteady-state nonlinearity of open-loop reset systems
In this paper, we introduce a new representation for open-loop reset systems. We show that at steady-state a reset integrator can be modelled as a parallel interconnection of the base-linear system and piece-wise constan…
Robust and Kernelized Data-Enabled Predictive Control for Nonlinear Systems
This paper presents a robust and kernelized data-enabled predictive control (RoKDeePC) algorithm to perform model-free optimal control for nonlinear systems using only input and output data. The algorithm combines robust…