Multi-Objective Bayesian Optimisation Over Sparse Subspaces for Model Predictive Control of Wind Farms

作     者：Hoang, Kiet Tuan Boersma, Sjoerd Mesbah, Ali Imsland, Lars Struen 

作者机构：Department of Engineering Cybernetics Norwegian University of Science and Technology Trondheim7034 Norway Biometris Group Wageningen University & Research Wageningen6708 Netherlands Department of Chemical and Biomolecular Engineering University of California BerkeleyCA94720 United States 

出 版 物：《SSRN》 

年 卷 期：2024年

核心收录：

主　　题：Model predictive control 

摘      要：As model mismatch is inevitable, fine-tuning advanced control strategies like model predictive control (MPC) using closed-loop performance data is critical for increased closed-loop control of wind farms (WFs). However, challenges such as conflicting WF control objectives, limited closed-loop data due to expensive experiments, and the high-dimensional design spaces of these MPC formulations make tuning non-trivial. Inspired by the notion of performance-oriented learning, we propose a multi-objective (MO) Bayesian optimisation (BO) framework over sparse subspaces to address these challenges systematically for increased closed-loop MPC performance. To show the efficacy of the BO approach, a simulation case study with a 3x3 WF is investigated where the control objective is to provide secondary frequency regulation while minimising dynamic loading for an MPC with 28 design parameters to auto-tune. Simulation results show that the proposed framework achieves a good balance between the two conflicting WF control objectives, where dynamic loading is reduced by 51.59% compared to a nominal MPC whose performance is not tuned using closed-loop data while still achieving similar tracking performance. The proposed method is general and can be applied regardless of a closed-loop control goal, WF specifications (complexity, topology, location, size), or controller formulation for multi-objective constrained control of WFs. © 2024, The Authors. All rights reserved.