Wind Power Prediction Based on Machine Learning and Deep Learning Models

Abstract

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 (R 2 ), root mean squared error (RMSE). The experimental results illustrated that the proposed optimization of LSTM using SFS-PSO model achieved the best results with R 2 equals 99.99% in predicting the wind power values.

TSxtend: A Tool for Batch Analysis of Temporal Sensor Data

“…Several works address energy-related problems using data science techniques to identify opportunities for energy-efficiency improvements [33][34][35]. However, only a few can automate the entire experimentation process.…”

“…A decision tree [27] is a prediction model that has been used in countless fields, especially in the energy field [34,60,61], and is one of the most widely used algorithms in this field.…”

A Review of Modern Wind Power Generation Forecasting Technologies

“…We wonder if it is possible to directly sample power generation and effectively find its own characteristics for prediction, which requires further development; in addition, according to the characteristics of different wind fields, more suitable functions for identification and even other artificial intelligence methods such as neural networks or deep learning methods may be applied for prediction [83][84][85][86]. Whether adaptability can improve prediction accuracy is also a very important issue.…”

Performance enhancement of wind power forecast model using novel pre‐processing strategy and hybrid optimization approach

“…In 2023, Zahraa Tarek, et al 24 established a novel optimization method based on stochastic fractal search and particle swarm optimization (SFS‐PSO) in which the parameters of the LSTM network were optimized. Thereby, the results show that the suggested strategy is preferable since it produces better outcomes by forecasting the values of wind power.…”

“…For better forecasting, the LSTM parameters must be applied to a variety of time series issues. In addition, LSTM via the SFS‐PSO model was presented in reference 24, which helps to increase both the system's solution quality and the accuracy of wind power forecasts. Additionally, CNN provides better results and enhances the exploration and exploitation capabilities.…”