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

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.

• Publication year

  2025

• Venue

  arXiv.org

• Publication date

  2025-12-04

• Fields of study

  Computer Science, Engineering

• Identifiers
  DOI 10.48550/arXiv.2512.04647arXiv 2512.04647
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Set-Point Tracking MPC with Avoidance Features

  2023cited by this paper
• Dual Control of Exploration and Exploitation for Auto-Optimization Control With Active Learning

  2023influential reference
• Assessment of industrial-scale green hydrogen production using renewable energy

  2023cited by this paper
• Dynamic interdependence of comfortable thermal conditions and energy efficiency increase in a nursery school building for heating and cooling period

  2023cited by this paper
• Adaptive robust predictive control with sample-based persistent excitation

  2022influential reference
• Perspective view of autonomous control in unknown environment: Dual control for exploitation and exploration vs reinforcement learning

  2022cited by this paper
• Robust adaptive model predictive control with persistent excitation conditions

  2022influential reference
• Multistep Dual Control for Exploration and Exploitation in Autonomous Search With Convergence Guarantee

  2022cited by this paper
• Dual Control for Exploitation and Exploration (DCEE) in Autonomous Search

  2020cited by this paper
• Complex Track Maneuvering using Real-Time MPC Control for Autonomous Driving

  2020cited by this paper
• Active exploration in adaptive model predictive control *

  2020cited by this paper
• Learning to Seek: Autonomous Source Seeking with Deep Reinforcement Learning Onboard a Nano Drone Microcontroller

  2019cited by this paper
• Robust adaptive model predictive control: Performance and parameter estimation

  2019cited by this paper
• Deep Visual MPC-Policy Learning for Navigation

  2019cited by this paper
• Model Predictive Control of Linear Systems With Preview Information: Feasibility, Stability, and Inherent Robustness

  2018cited by this paper
• Stochastic model predictive control with active uncertainty learning: A Survey on dual control

  2017cited by this paper
• A reinforcement learning approach for MPPT control method of photovoltaic sources

  2017cited by this paper
• Dual adaptive model predictive control

  2017cited by this paper
• MPC for Tracking Periodic References

  2016cited by this paper
• A proportional integral extremum-seeking control approach for discrete-time nonlinear systems

  2015cited by this paper
• Persistently exciting model predictive control

  2014cited by this paper
• Reference Tracking MPC Using Dynamic Terminal Set Transformation

  2014cited by this paper
• Model predictive control: Recent developments and future promise

  2014cited by this paper
• Classification and comparison of maximum power point tracking techniques for photovoltaic system: A review

  2013cited by this paper
• Maximum power point tracking control techniques: State-of-the-art in photovoltaic applications

  2013cited by this paper
• MPC for tracking zone regions

  2010cited by this paper
• MPC for tracking piecewise constant references for constrained linear systems

  2008cited by this paper
• Numerical Optimization-Based Extremum Seeking Control With Application to ABS Design

  2007cited by this paper
• Improved perturbation and observation method (IP&O) of MPPT control for photovoltaic power systems

  2005cited by this paper
• Stability of extremum seeking feedback for general nonlinear dynamic systems

  2000cited by this paper
• Plantwide control: the search for the self-optimizing control structure

  2000cited by this paper
• Steady states and constraints in model predictive control

  1999cited by this paper
• Set invariance in control

  1999cited by this paper
• New approach to constrained predictive control with simultaneous model identification

  1996cited by this paper
• Persistent excitation in adaptive systems

  1987cited by this paper

• No citing papers are available for this paper.