Highly efficient photovoltaic parameter estimation using parallel particle swarm optimization on a GPU

Accurate modeling of solar photovoltaic (PV) systems is crucial to their control and performance optimization. We focus on the two most widely used PV models, i.e., the single- and double-diode model, and try to estimate their parameters from current-voltage data. This task is usually formulated as a nonlinear least squares problem and tackled by various metaheuristic algorithms. Despite the abundance of sophisticated metaheuristics in the literature, we employ an (almost) standard particle swarm optimization (PSO) algorithm and, somewhat unexpectedly, find that such primitive PSO is adequate to solve the problem to high accuracy, though it may take more fitness evaluations. Moreover, given the population-based nature of PSO, we take full advantage of modern graphics processing units (GPUs) and develop a highly efficient PV parameter identification method by effectively parallelizing PSO on a GPU. Numerical results on two benchmark datasets show that our approach can achieve high estimation accuracy on par with state-of-the-art methods while enjoying approximately a hundred-times speedup. Our code is publicly available at https://github.com/ShuhuaGao/PV-PPSO.