Learner Phase of Partial Reinforcement Optimizer with Nelder-Mead Simplex for Parameter Extraction of Photovoltaic Models

Abstract

This paper proposes an improved version of the Partial Reinforcement Optimizer (PRO), termed LNPRO. The LNPRO has undergone a learner phase, which allows for further communication of information among the PRO population, changing the state of the PRO in terms of self-strengthening. Furthermore, the Nelder-Mead simplex is used to optimize the best agent in the population, accelerating the convergence speed and improving the accuracy of the PRO population. By comparing LNPRO with nine advanced algorithms in the IEEE CEC 2022 benchmark function, the convergence accuracy of the LNPRO has been verified. The accuracy and stability of simulated data and real data in the parameter extraction of PV systems are crucial. Compared to the PRO, the precision and stability of LNPRO have indeed been enhanced in four types of photovoltaic components, and it is also superior to other excellent algorithms. To further verify the parameter extraction problem of LNPRO in complex environments, LNPRO has been applied to three types of manufacturer data, demonstrating excellent results under varying irradiation and temperatures. In summary, LNPRO holds immense potential in solving the parameter extraction problems in PV systems.