Wave energy forecasting: A state-of-the-art survey and a comprehensive evaluation

Abstract

Wave energy, a promising renewable energy source, has the potential to diversify the global energy mix significantly. Accurate forecasting of significant wave height (SWH) is crucial for enhancing the efficiency and reliability of wave energy conversion systems. As interest in this field grows, research into SWH forecasting has expanded dramatically. This comprehensive survey evaluates sixteen SWH forecasting methods, including Persistence, decision trees, deep neural networks, random neural networks, and random forests. The paper begins by establishing a detailed taxonomy that categorizes SWH forecasting algorithms, providing a framework to interpret the complexities of different methodological approaches. We then explore the interconnections between ensemble learning and decomposition-based frameworks and the integration of individual forecasting techniques within ensemble and hybrid models. In our empirical analysis, we rigorously assess the performance of these state-of-the-art algorithms using multiple, diverse datasets. Our findings reveal that ensemble methods generally surpass individual techniques in accuracy, with the extreme learning machine ranking as the least effective among the randomized neural networks. Looking ahead, we identify limitations in current forecasting models and propose new directions for research, including improvements in SWH model architecture, SWH data imperfection, forecasts for new buoy, and multimodality-enhanced methods.