Grey-box identification for photovoltaic power systems via particle-swarm algorithm

Abstract

-Amongst renewable generators, photovoltaics (PV) are becoming more popular as the appropriate low cost solution to meet increasing energy demands. However, the integration of renewable energy sources to the electricity grid possesses many challenges. The intermittency of these non-conventional sources often requires accurate forecast, planning and optimal management. Many attempts have been made to tackle these challenges; nonetheless, existing methods fail to accurately capture the underlying characteristics of the system. There exists scope to improve present PV yield forecasting models and methods. This paper explores the use of apriori knowledge of PV systems to build clear box models and identify uncertain parameters via heuristic algorithms. The model is further enhanced by incorporating black box models to account for unmodeled uncertainties in a novel grey-box forecasting and modeling of PV systems.

Grey-Box Modeling for Photo-Voltaic Power Systems Using Dynamic Neural-Networks

“…Details of the atmospheric transmittances b, d, and r calculations and formulas can be found in [4][17] [18].…”

Modeling of photovoltaic modules using a gray-box neural network approach

“…An alternative approach is using a functional approximator artificial neural networks (ANN) [2,[10][11][12][13][14][15], genetic algorithm [16], neuro-fuzzy inference system [13], and particle swarm optimization [17,18]) to simulate PV module. The input and output layer of functional approximator consists of weather data (historically recorded) and measured output power of PV module, respectively.…”

“…One of the pioneer works in the application of grey-box modeling concept to engineering problems was reported in [19]. The use of grey-box approach for modeling PV power system via particle swarm optimization has been only recently proposed by [17,18]. Particle swarm optimization was chosen to optimize the parameters in the clear-box model and to find the best coefficients in the grey-box model.…”