Stability and performance in MPC using a finite-tail cost

TL;DR

This paper analyzes the stability and performance of a finite-tail cost MPC scheme, showing it allows simpler design and less restrictive horizons, with practical validation on a four tank system.

Contribution

It provides a stability and performance analysis for finite-tail cost MPC, extending existing methods with new stability conditions and practical benefits.

Findings

Stability conditions depend on prediction and extended horizons.

Finite-tail cost MPC simplifies offline design.

Validated benefits on a four tank system.

Abstract

In this paper, we provide a stability and performance analysis of model predictive control (MPC) schemes based on finite-tail costs. We study the MPC formulation originally proposed by Magni et al. (2001) wherein the standard terminal penalty is replaced by a finite-horizon cost of some stabilizing control law. In order to analyse the closed loop, we leverage the more recent technical machinery developed for MPC without terminal ingredients. For a specified set of initial conditions, we obtain sufficient conditions for stability and a performance bound in dependence of the prediction horizon and the extended horizon used for the terminal penalty. The main practical benefit of the considered finite-tail cost MPC formulation is the simpler offline design in combination with typically significantly less restrictive bounds on the prediction horizon to ensure stability. We demonstrate the benefits of the considered MPC formulation using the classical example of a four tank system.