一种促进稀疏性的自适应调节方法用于并网太阳能光伏系统的数据驱动建模与控制

This paper introduces a new statistical learning technique based on sparsity promotion 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. The ARSR adaptively regulates the hyperparameter weights of candidate functions to best represent the dynamics of PV systems. This method allows for the application of different sparsity-promoting hyperparameters for each state variable, whereas the conventional approach uses the same hyperparameter for all state variables, which may result in not excluding all the unrelated terms from the dynamics. Consequently, the proposed method can identify more complex dynamics with greater accuracy. 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 be successfully employed for fault analysis studies, which distinguishes its capabilities from other data-driven techniques. Finally, the proposed approach is validated through real-time simulations.