Performance prediction of PV modules based on artificial neural network and explicit analytical model

Abstract

The accurate characterization and prediction of current-voltage characteristics of photovoltaic (PV) modules under different operating conditions is essential for solar power forecasting and ensuring grid stability. The traditional method based on the single-diode model is inconvenient and complex because the current-voltage equation is implicit. In this paper, a novel method combining an artificial neural network (ANN) with an explicit analytical model (EAM) is proposed for predicting the I-V characteristics of PV modules under different operating conditions. The EAM makes it efficient to obtain the I-V curves from the estimated model parameters due to its simplicity and explicit expression. The ANN based on the EAM is composed of a three-layer feedforward neural network, in which the inputs are solar irradiation and module temperature and the outputs are the four parameters in EAM. Once the ANN is built and trained by using the measured I-V curves, the shape parameters and I-V curve are predicted by only reading solar irradiation and temperature without solving any nonlinear implicit equations. The accuracy and capability of the proposed method are verified by the experimental data for different types of PV modules. Moreover, the dependence of shape parameters in the EAM on solar irradiation and temperature is investigated first.

A systematic review on predicting PV system parameters using machine learning

“…It is more prominent in solar experiments since researchers can postulate solar panels' performance and durability using computational tools in either simulation or practical experiments. During our screening, we found that some authors performed their studies practically in real time [35] , [36] , [58] , and many authors adopted simulation tools with curated data sets to obtain their findings [5] , [67] , [4] . In another situation, simulation and practical approaches have been applied in the same experiments for a better comparative analysis [50] , [61] , [41] .…”

On the parameters domain of the single-diode model

“…Examples of these algorithms are presented by Wang et at. [40] and Zhang et al [41]. These algorithms determine directly the optimal models used to describe the I-V curve, however, no further information can be extracted regarding the boundaries of the parameters.…”

An accurate analytical model for predicting the maximum power of photovoltaic module operating outdoor under varying conditions

“…However, the maximum power prediction based on the SDM requires firstly extraction of five parameters at reference conditions from an implicit equation that relies on current and voltage and then determine the model parameters under various temperature and irradiance conditions using set transformation equations 6‐12 . Recently, many methods have been presented based on artificial neural networks (ANNs) to predict the maximum power of PV modules 13‐15 . However, these technics have some computational problems such as higher computational complexity and cost.…”

“…[6][7][8][9][10][11][12] Recently, many methods have been presented based on artificial neural networks (ANNs) to predict the maximum power of PV modules. [13][14][15] However, these technics have some computational problems such as higher computational complexity and cost.…”