article · Frontiers in Energy Research
Accurate wind speed forecasting is essential for maintaining power system stability, yet existing machine learning models require improvements in predictive accuracy. A new forecasting model addresses this challenge by combining a bidirectional long short-term memory neural network with an optimisation algorithm named GADTO, which merges dipper-throated optimisation with a genetic algorithm. The optimisation approach tunes model parameters and incorporates a binary version of the algorithm to select the most significant dataset features. Tested on a publicly available Kaggle benchmark dataset, the optimised forecasting framework demonstrated robust performance. Statistical validation using analysis of variance and Wilcoxon signed-rank tests confirmed that the model differs significantly from alternative methods. It achieved an average root mean square error of 0.00046, outperforming other recent predictive techniques.
Wind energy production varies with changing atmospheric conditions, making precise wind speed prediction essential for grid operators managing power system stability. By achieving higher forecasting precision and reducing predictive errors, advanced algorithmic models can assist energy planners in integrating renewable power more reliably, preventing grid instability, and improving general electrical power management.
This forecasting framework could enable power grid operators, wind farm developers, and energy traders to anticipate wind generation more reliably. Evaluated on a publicly available Kaggle benchmark dataset, the research sits at an early, algorithmic development stage. Moving towards real-world commercial use would require validation on live operational telemetry from commercial wind farms, integration into utility supervisory control and data acquisition systems, and testing across diverse geographic regions.
AI-generated from the published abstract. Always read the original work before citing.
Accurate forecasting of wind speed is crucial for power systems stability. Many machine learning models have been developed to forecast wind speed accurately. 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 bidrectional long short-term memory (BiLSTM) 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 the binary version of the proposed GADTO algorithm. The selected features are utilized to learn the optimization algorithm to select the best configuration of the BiLSTM forecasting model. The optimized BiLSTM is used to predict the future values of the wind speed, and the resulting predictions are analyzed using a set of evaluation criteria. Moreover, a statistical test is performed to study the statistical difference of the proposed approach compared to other approaches in terms of the analysis of variance (ANOVA) and Wilcoxon signed-rank tests. The results of these tests confirmed the proposed approach’s statistical difference and its robustness in forecasting the wind speed with an average root mean square error (RMSE) of 0.00046, which outperforms the performance of the other recent methods.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.3389/fenrg.2023.1172176
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
