Adaptive Regulated Sparsity Promoting Approach for Data-Driven Modeling and Control of Grid-Connected Solar Photovoltaic Generation

TL;DR

This work tackles the challenge of data-driven modeling for grid-connected PV systems by introducing Adaptive Regulated Sparse Regression (ARSR), which per-state tunes sparsity hyperparameters to accurately identify dynamic models from measurements. By constructing a library of candidate nonlinear functions and solving per-state sparse regression with RMSE-guided hyperparameter optimization, ARSR yields reliable open-loop and closed-loop models for both single-stage and two-stage PV configurations, enabling data-driven control design and fault analysis. The method is validated through case studies and real-time simulations, demonstrating close agreement with physical models and robust fault analysis capabilities, while reducing dependency on precise physics-based models. The results suggest ARSR as a practical, scalable tool for data-driven PV modeling and control with potential for real-time grid applications.

Abstract

This paper aims to introduce a new statistical learning technique based on sparsity promoting for data-driven modeling and control of solar photovoltaic (PV) systems. Compared with conventional sparse regression techniques that might introduce computational complexities when the number of candidate functions increases, an innovative algorithm, named adaptive regulated sparse regression (ARSR) is proposed that adaptively regulates the hyperparameter weights of candidate functions to best represent the dynamics of PV systems. Utilizing this algorithm, open-loop and closed-loop models of single-stage and two-stage PV systems are obtained from measurements and are utilized for control design purposes. Moreover, it is demonstrated that the proposed data-driven approach can successfully be employed for fault analysis studies, which distinguishes its capabilities compared with other data-driven techniques. Finally, the proposed approach is validated through real-time simulations.

Figures (15)

• Figure 1: Proposed adaptive regulated sparse regression for modeling identification and control of PV systems.
• Figure 2: Schematic of a single-stage and two-stage PV systems.
• Figure 3: The controllers for single-stage PV system.
• Figure 4: Two-stage PV system controller.
• Figure 5: Controllers of the PV system.