A new ANN model for hourly solar radiation and wind speed prediction: A case study over the north & south of the Arabian Peninsula

Prediction models for renewable energy sources are frequently used to manage stand-alone micro grid systems. Such prediction models are important due to the high cost or even the unavailability of real-world data in many regions. Herein, a new technique based on the Feed-forward Back-propagation Artificial Neural Network (FBANN) model has been developed and used to predict both the hourly solar radiation and the wind speed simultaneously. The new model has been tested over the Northern and Southern regions of the Arabian Peninsula. The novelty of the model lies in the following characteristics: (i) a new integration between two different FBANN configurations has been established, (ii) only three input parameters are required for the model to run and (iii) solar radiation and wind speed are predicted simultaneously. The correlation coefficient (R) and the mean absolute percentage error (MAPE) have been selected as an accuracy evaluation index between inputs and targets. To ensure reliability, the input meteorological data is immense and covers a wide time span. Results reveal that the proposed FBANN model achieves high levels of accuracy. The R value of the hybrid model for all the investigated locations is more than 0.96 while the MAPE does not exceed 3%.

Automated summary

A new technique based on FBANN model was developed to predict both hourly solar radiation and wind speed simultaneously, achieving high levels of accuracy with R values exceeding 0.96 and MAPE not exceeding 3% across all investigated locations in the Northern and Southern regions of the Arabian Peninsula.