Adjoint-based predictor-corrector sequential convex programming for parametric nonlinear optimization

TL;DR

This paper introduces an adjoint-based predictor-corrector sequential convex programming framework for parametric nonlinear optimization, providing convergence guarantees and demonstrating effectiveness on a large-scale hydro power plant control problem.

Contribution

It presents a novel algorithmic framework with proven convergence for solving parametric nonlinear optimization problems, including variants for online applications.

Findings

Proven contraction estimate guarantees tracking performance.

Local convergence of both algorithm variants established.

Successful application to a large-scale hydro power plant control problem.

Abstract

This paper proposes an algorithmic framework for solving parametric optimization problems which we call adjoint-based predictor-corrector sequential convex programming. After presenting the algorithm, we prove a contraction estimate that guarantees the tracking performance of the algorithm. Two variants of this algorithm are investigated. The first one can be used to solve nonlinear programming problems while the second variant is aimed to treat online parametric nonlinear programming problems. The local convergence of these variants is proved. An application to a large-scale benchmark problem that originates from nonlinear model predictive control of a hydro power plant is implemented to examine the performance of the algorithms.