Analysis of the Effects of Cell Temperature on the Predictability of the Solar Photovoltaic Power Production

Abstract

The use of intermittent power supplies, such as solar energy, has posed a complex conundrum when it comes to the prediction of the next days' supply. There have been several approaches developed to predict the power production using Machine Learning methods, such as Artificial Neural Networks (ANNs). In this work, we propose the use of weather variables, such as ambient temperature, solar irradiation, and wind speed, collected from a weather station of a Photovoltaic (PV) system located in Amman, Jordan. The objective is to substitute the aforementioned ambient temperature with the more realistic PV cell temperature with a desire of achieving better prediction results. To this aim, ten physics-based models have been investigated to determine the cell temperature, and those models have been validated using measured PV cell temperatures by computing the Root Mean Square Error (RMSE). Then, the model with the lowest RMSE has been adopted in training a data-driven prediction model. The proposed prediction model is to use an ANN compared to the well-known benchmark model from the literature, i.e., Multiple Linear Regression (MLR). The results obtained, using standard performance metrics, have displayed the importance of considering the cell temperature when predicting the PV power output.

Modelling, simulation, and measurement of solar power generation: New developments in design and operational models

“…The dynamic viscosity, is stated in Eq. (24) Nnamchi et al [ 36 , 40 ] where is the average air temperature.…”

“…Moreover, triple linear correlation (Nguyen et al [ 19 ], Araneo et al [ 31 ], Skoplaki et al [ 32 ], Kichou et al [ 33 ], Scarabelot et al [ 34 ], Zouine et al [ 27 ], Muneeshwaran et al [ 28 ], Dong et al [ 35 ], Al-Dahidi [ 36 ], Ndegwa et al [ 37 ]) to displace a single linear correlation in the implicit model. Significantly, Nguyen et al [ 19 ] modified the SPGMBCT model with wind speed, thermal inertia (thermal diffusivity) and irradiance resulting in an outstanding result.…”

“…Obviously, Dong et al [ 35 ] developed a neural network to accurately predict PV cell temperature and solar power generation. Similarly, Al-Dahidi [ 36 ] developed an explicit (triple) SPGMBCT model using multiple linear regression (MLR) and artificial neural network (ANN) models for better prediction of PV cell temperature and solar power generation. Remarkably, Ndegwa et al [ 37 ] used the explicit (triple) SPGMBCT models to achieve precision in predicting the cell temperature and solar power generation of PV systems.…”

A Scalable Solution for Running Ensemble Simulations for Photovoltaic Energy

“…Among the statistical and computational methods, Artificial Neural Network (ANN) have been used to predict both the behavior of panels, and in some cases also the weather conditions. A plethora of literature [16,18,19,20,21,22,23,24,25,26] have emerged to study the application of ANN on solar power forecasting because they can be trained to focus on a geographically confined region and optimize local solar power forecasting. The general idea is to train an ANN to learn the statistical pattern between weather variables and the observed power production.…”

“…The efficiency of power generation varies based, in addition to irradiance, also on cell temperature [13,14], which itself is related to ambient temperature. Wind speed affects air temperature, and thus must be taken into account to make accurate predictions [15,16]. Once irradiance and temperature are forecasted, the conversion to power generation can be made through a PV panel simulator.…”