Integrating artificial intelligence techniques to enhance the performance of hybrid floating breakwater – wave energy converter analysis

Abstract

Abstract This study presents an integrated experimental and computational analysis of hybrid floating breakwaters and Wave Energy Converters (WECs). Laboratory experiments were carried out at the Hydraulic Laboratory at Port Said University using floating breakwaters with different rear-wall designs. Based on the experimental data, a novel Ensemble Floating Breakwaters Prediction (EFBP) model was created by combining three Artificial Intelligence (AI) techniques: Artificial Neural Networks (ANN), Support Vector Machines (SVM), and Gene Expression Programming (GEP). The ensemble method leverages the complementary strengths of these algorithms by averaging to improve prediction reliability and accuracy. The EFBP model showed exceptional performance (R 2 = 0.9928, MSE = 1.4543 × 10⁻ 4 ), surpassing all individual models. This research establishes the EFBP as a robust predictive tool for optimizing hybrid floating breakwater-WEC systems, aiding the development of sustainable marine energy technologies.