AUTHOR=Alhussan Amel Ali , M. El-Kenawy El-Sayed , Abdelhamid Abdelaziz A. , Ibrahim Abdelhameed , Eid Marwa M. , Khafaga Doaa Sami 

TITLE=Wind speed forecasting using optimized bidirectional LSTM based on dipper throated and genetic optimization algorithms

JOURNAL=Frontiers in Energy Research

VOLUME=Volume 11 - 2023

YEAR=2023

URL=https://www.frontiersin.org/journals/energy-research/articles/10.3389/fenrg.2023.1172176

DOI=10.3389/fenrg.2023.1172176

ISSN=2296-598X

ABSTRACT=Accurate forecasting of wind speed is crucial for power systems' stability. Many machine learning
models have been developed for forecasting wind speed with reasonable accuracy. However, the
accuracy of these models still needs more improvements to achieve more accurate results. In
 this paper, an optimized model is proposed for boosting the accuracy of the prediction accuracy
of wind speed. The optimization is performed in terms of a new optimization algorithm based on
dipper-throated optimization (DTO) and genetic algorithm (GA), which is referred to as (GADTO).
The proposed optimization algorithm is used to optimize the long short-term memory (LSTM)
 forecasting model parameters. To verify the effectiveness of the proposed methodology, a
benchmark dataset freely available on Kaggle is employed in the conducted experiments. The
dataset is first preprocessed to be prepared for further processing. In addition, feature selection is
applied to select the significant features in the dataset using a new feature selection method based
on the proposed GADTO algorithm. The selected features are used to learn the optimization
algorithm to select the best configuration of the LSTM forecasting model. The optimized LSTM
 is used to predict the future values of the wind speed, and the results are analyzed using a set
of evaluation criteria. In addition, a statistical test is performed to study the difference of the
proposed approach compared to other approaches. The results of these tests confirmed the
 proposed approach’s statistical difference and its robustness in forecasting the wind speed with
a root mean square error (RMSE) value of 0.012 that outperforms the performance of other
 methods included in the conducted experiments.