Prediction of Significant Wave Heights Based on CS-BP Model in the South China Sea

Abstract

Forecasting the significant wave heights (Hs) is indispensable in HS-related engineering studies and is exceedingly important in the assessment of wave energy in future. As a technique essential for the future of clean energy systems, reducing the forecasting errors related to Hs has always been a vital research subject. In this paper, an optimized hybrid method based on the back propagation neural network (BP) and the cuckoo search algorithm (CS) is proposed to forecast the Hs in the South China Sea. This approach employs the CS as an intelligent optimization algorithm to optimize the parameters of the BP model, which develop a hybrid model that is suit for the data set, reducing the forecasting errors. The proposed method is subsequently tested based on nine prediction points selected in the South China Sea, where the proposed hybrid model is proved to perform effectively and steadily.