Hybrid Modeling, Sim-to-Real Reinforcement Learning, and Large Language Model Driven Control for Digital Twins

TL;DR

This paper explores digital twin modeling and control using hybrid, AI-driven, and physics-based methods, comparing their performance in a greenhouse setting with various control strategies including LLMs.

Contribution

It introduces a hybrid modeling approach and evaluates LLM-based control within digital twins, highlighting their advantages and trade-offs in dynamical system management.

Findings

HAM offers balanced accuracy and efficiency

LSTM achieves high precision but is resource-intensive

MPC provides robustness and predictability

Abstract

This work investigates the use of digital twins for dynamical system modeling and control, integrating physics-based, data-driven, and hybrid approaches with both traditional and AI-driven controllers. Using a miniature greenhouse as a test platform, four predictive models Linear, Physics-Based Modeling (PBM), Long Short Term Memory (LSTM), and Hybrid Analysis and Modeling (HAM) are developed and compared under interpolation and extrapolation scenarios. Three control strategies Model Predictive Control (MPC), Reinforcement Learning (RL), and Large Language Model (LLM) based control are also implemented to assess trade-offs in precision, adaptability, and implementation effort. Results show that in modeling HAM provides the most balanced performance across accuracy, generalization, and computational efficiency, while LSTM achieves high precision at greater resource cost. Among controllers, MPC delivers robust and predictable performance, RL demonstrates strong adaptability, and LLM-based controllers offer flexible human-AI interaction when coupled with predictive tools.