A Review on Artificial Intelligence Based Wind Energy Forecasting Techniques

Effective use of renewable energy is a key element of sustainable development for not only human society but also in low carbon energy environments. Wind forecasting helps to predict the behaviour and availability of wind energy resources at specific locations. Most of the previous research has focused on the general issues surrounding wind energy, and none have taken a systematic approach of evaluating the problem on a data‐driven basis. The presented study synthesises a vast amount of research on the topic and indicates the problematic spheres of inquiry in the future by using bibliometric methods and scientific mapping tools from 2020 to 2025. The results indicated that the supervisory control and data acquisition (SCADA) dataset, meteorological dataset, and sparse dataset have been applied to make wind speed and power potential predictions using the physical, statistical, machine learning, deep learning, and hybrid models. Moreover, this research offered an appropriate road map to wind forecasting process in order to determine the most appropriate predictive strategies with respect to various time horizons, important features of inputs, computing time, and measurement error. It is analysed that the deep learning algorithms such as artificial neural network (ANN), convolutional neural network (CNN), recurrent neural network (RNN), and long‐short term memory (LSTM) have been best in predicting wind power using feature engineering analysis. The research is not only beneficial to the increased share of renewable energy but also meets the requirements of the Sustainable Development Goals, such as climate action (SDG 13), affordable and clean energy (SDG 7).