Artificial Neural Network (ANN) Trained by a Novel Arithmetic Optimization Algorithm (AOA) for Short Term Forecasting of Wind Power

• Published in: Intelligent Technologies and Applications Vol. 1616; pp. 197 - 209
• Main Authors: Zafar, Muhammad Hamza, Khan, Noman Mujeeb, Moosavi, Syed Kumayl Raza, Mansoor, Majad, Mirza, Adeel Feroz, Akhtar, Naureen
• Format: Book Chapter
• Language: English
• Published: Switzerland Springer International Publishing AG 2022; Springer International Publishing
• Series: Communications in Computer and Information Science
• Subjects: Arithmetic optimization algorithm; Bio-inspired neural network; Intelligent control system; Regression; Wind power
• ISBN: 9783031105241; 3031105249
• ISSN: 1865-0929; 1865-0937
• DOI: 10.1007/978-3-031-10525-8_16

Stochastic nature of wind power with a high amount of non-linearity makes it very difficult to predict wind power production in real time which has a high impact in the renewable energy industry. The uncertainty of wind power makes it challenging to integrate it with the power grid. As a solution, an early short term forecasting of the wind flow significantly improves the wind power generation. For this purpose, a novel arithmetic optimization algorithm is used to train an artificial neural network for short term wind power prediction. Effective exploration and exploitation behavior of the algorithm due to embedded arithmetic operators for updating the weights and biases train the neural network. To validate the performance of the proposed technique, well-known techniques are compared using a case study on wind power in Turkey for the winter and summer season as a benchmark. The proposed method has shown better prediction performance as compared to the existing techniques. AOANN achieves up to 94.87% and 97.18% less training error and up to 96.42% and 83.64% less testing error in winter and summer seasons respectively.