article · Computers, materials & continua/Computers, materials & continua (Print)
Renewable energy from wind power plays a vital role in meeting future energy demands and lowering emissions. Accurately forecasting power output is crucial for effective energy management. To predict wind power generation, multiple machine learning and deep learning regression models were evaluated, including deep neural networks, k-nearest neighbours, long short-term memory networks, random forests, bagging regressors, gradient boosting, and an averaging model. The models were trained and tested on a preprocessed dataset comprising four features and 50530 instances. To enhance forecasting accuracy, a hybrid optimisation method combining stochastic fractal search and particle swarm optimisation was applied to fine-tune the parameters of the long short-term memory network. Across five statistical evaluation metrics, this hybrid optimised neural network achieved the highest predictive performance, attaining a coefficient of determination of 99.99 percent.
As countries turn to renewable sources like wind to curb emissions and secure energy supply, dependable power generation forecasting becomes critical. Highly variable weather conditions make wind generation difficult to anticipate. Accurate predictive models help grid operators understand future power availability, supporting better management and more stable integration of clean energy into national electricity networks.
This technique could be relevant to power grid operators and wind farm management companies seeking to forecast power generation accurately. Evaluated computationally on a single dataset of 50530 instances, the approach appears to be early-stage research. Real-world commercialisation would require integration into energy management platforms and testing across operational environments and diverse geographical conditions.
AI-generated from the published abstract. Always read the original work before citing.
Wind power is one of the sustainable ways to generate renewable energy. In recent years, some countries have set renewables to meet future energy needs, with the primary goal of reducing emissions and promoting sustainable growth, primarily the use of wind and solar power. To achieve the prediction of wind power generation, several deep and machine learning models are constructed in this article as base models. These regression models are Deep neural network (DNN), k-nearest neighbor (KNN) regressor, long short-term memory (LSTM), averaging model, random forest (RF) regressor, bagging regressor, and gradient boosting (GB) regressor. In addition, data cleaning and data preprocessing were performed to the data. The dataset used in this study includes 4 features and 50530 instances. To accurately predict the wind power values, we propose in this paper a new optimization technique based on stochastic fractal search and particle swarm optimization (SFS-PSO) to optimize the parameters of LSTM network. Five evaluation criteria were utilized to estimate the efficiency of the regression models, namely, mean absolute error (MAE), Nash Sutcliffe Efficiency (NSE), mean square error (MSE), coefficient of determination (R2), root mean squared error (RMSE). The experimental results illustrated that the proposed optimization of LSTM using SFS-PSO model achieved the best results with R2 equals 99.99% in predicting the wind power values.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.32604/cmc.2023.032533
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.
