Auto-Optimization with Active Learning in Uncertain Environment: A Predictive Control Approach

TL;DR

This paper introduces an auto-optimization framework combining model predictive control and active learning to adaptively identify parameters and track optimal conditions in uncertain, dynamic environments.

Contribution

It develops a novel EO-MPC with virtual excitation signals and an AL-MPC that balances tracking and parameter estimation, with proven recursive feasibility and convergence.

Findings

Effective parameter identification in uncertain environments.

Successful integration of virtual excitation signals into MPC.

Validated approach through practical examples.

Abstract

This paper presents an auto-optimal model predictive control (MPC) framework enhanced with active learning, designed to autonomously track optimal operational conditions in an unknown environment,where the conditions may dynamically adjust to environmental changes. First, an exploitation-oriented MPC (EO-MPC) is proposed, integrating real-time sampling data with robust set-based parameter estimation techniques to address the critical challenge of parameter identification. By introducing virtual excitation signals into the terminal constraint and establishing a validation mechanism for persistent excitation condition, the EO-MPC effectively resolves the issue of insufficient persistent excitation in parameter identification. Building upon this foundation, an active learning MPC (AL-MPC) approach is developed to integrate both available and virtual future data to resolve the fundamental conflict between tracking an unknown optimal operational condition and parameter identification. The recursive feasibility and convergence of the proposed methods are rigorously established, and numerous examples substantiate the reliability and effectiveness of the approach in practical applications.