Assessment of Artificial Neural Networks Learning Algorithms and Training Datasets for Solar Photovoltaic Power Production Prediction

Sameer Al-Dahidi,Osama Ayadi,Jehad Adeeb,Mohamed Louzazni

doi:10.3389/fenrg.2019.00130

Abstract

The capability of accurately predicting the Solar Photovoltaic (PV) power productions is crucial to effectively control and manage the electrical grid. In this regard, the objective of this work is to propose an efficient Artificial Neural Network (ANN) model in which 10 different learning algorithms (i.e., different in the way in which the adjustment on the ANN internal parameters is formulated to effectively map the inputs to the outputs) and 23 different training datasets (i.e., different combinations of the real-time weather variables and the PV power production data) are investigated for accurate one day-ahead power production predictions with short computational time. In particular, the correlations between different combinations of the historical wind speed, ambient temperature, global solar radiation, PV power productions, and the time stamp of the year are examined for developing an efficient solar PV power production prediction model. The investigation is carried out on a 231 kWac grid-connected solar PV system located in Jordan. An ANN that receives in input the whole historical weather variables and PV power productions, and the time stamp of the year accompanied with Levenberg-Marquardt (LM) learning algorithm is found to provide the most accurate predictions with less computational efforts. Specifically, an enhancement reaches up to 15%, 1%, and 5% for the Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and Coefficient of Determination (R2) performance metrics, respectively, compared to the Persistence prediction model of literature.

Highlights

The share of Renewable Energy (RE) in the total installed capacity worldwide has been rapidly growing in the recent years, with 181 Gigawatts of RE capacity added in 2018, which accounts for more than 50% of the net annual additions of power generating capacity during the same year (REN21 Members, 2019)
The results of the two best learning algorithms (BR and LM in diamond and circle green markers, respectively), the three worse learning algorithms (GDX, RP, and OSS in cross, plus, upward-pointing triangle red markers, respectively), and the other remaining learning algorithms of each set of features are shown in the figure
We have developed an efficient Artificial Neural Network (ANN) model for providing accurate 1 day-ahead hourly predictions of the Photovoltaics (PV) system power productions with short computational efforts

Summary

Introduction

The share of Renewable Energy (RE) in the total installed capacity worldwide has been rapidly growing in the recent years, with 181 Gigawatts of RE capacity added in 2018, which accounts for more than 50% of the net annual additions of power generating capacity during the same year (REN21 Members, 2019) This growth has introduced an increasing general interest in high. Implementing high accuracy prediction model in the grid management system can reduce the cost of this balancing power (Yang et al, 2014; Antonanzas et al, 2016; Al-Dahidi et al, 2019). Despite the fact that these approaches can lead to accurate prediction results, but simplifications and assumptions in the adopted models impose uncertainty that might pose limitations on their practical implementation (AlDahidi et al, 2019)

Objectives

Results

Conclusion