Machine Learning Enhanced Forecasting of Wave Energy for Optimized WEC Performance

Katikutti Rajendran Rohith Kumar¹
PG Scholar, Department of CSE,
Sree Rama Engineering College,
Tirupati-517520, A.P, India.
rohithkumarkr07@gmail.com

T. Durga²
Assistant Professor, Department of CSE,
Sree Rama Engineering College,
Tirupati-517520, A.P, India.
durga.csit05@gmail.com

Abstract
Wave power, a renewable energy source that harnesses the ocean's dynamic forces, is very promising. The importance of accurate wave energy forecasting is growing as the globe works to incorporate renewable energy sources into the grid in order to maximize energy harvesting and grid integration. Recent developments in ML approaches, including DL, ensemble methods, and hybrid models for ocean wave energy prediction, are examined in this study. The complex non-linear dynamics of ocean waves are discussed, including howto predict energy flow, significant wave height (SWH), and wave period, as well as the pros and cons of various approaches. Also covered in depth is the rise of hybrid models—those that use both physical and ML components—as a means to improve prediction accuracyover more traditional methods. This study concludes with a discussion of potential future approaches, specifically focusing on how state-of-the-art technologies like as transformers, generative adversarial networks (GANs), and real-time data assimilation might enhance processing efficiency and prediction reliability.
Keywords—Wave energy; Energy forecasting; Machine learning; Energy harvesting; Wave energy forecasting; Hybrid models; Deep Learning