A review of machine learning and deep learning applications in wave energy forecasting and WEC optimization - review

Aug 3, 2026

Upload by Levi

Ocean energy technologies are still at developmental stages, and to be viable in energy markets wave energy device components need further improvement. Accurate evaluation of wave-resource characteristics is essential to estimate wave-energy potential across coastal areas. Numerical and algorithmic pipelines are used to estimate, predict, and forecast wave characteristics and resources for designing wave energy converters (WECs). Optimization-based methods can be costly and unreliable, motivating machine learning and deep learning approaches for forecasting and optimal WEC configuration. Learning algorithms also support PTO coefficient selection and control, improving convergence and enabling effective optimization of wave energy harvesting potential.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages20

Reading Time50 min

AccessFree to download

Abstract

Introduction

Renewable energy context and challenges

Global renewable energy production trends

Keywords and abbreviations

Energy Strategy Reviews 49 (2023) 101180 Contents lists available at ScienceDirect Energy Strategy Reviews journal [homepage: www.elsevier.com/locate/esr](homepage: www.elsevier.com/locate/esr) | A review of machine learning and deep learning applications in wave energy forecasting and WEC optimization
Alireza Shadmania, b, Mohammad Reza Nikooc, 1, **, Amir H. Gandomid, e, *, 1, Ruo-Qian Wang f, Behzad Golparvar f
a Department of Maritime Engineering, Amirkabir University of Technology, Tehran, Iran
b Faculty of Engineering and Architecture, Department of Electromechanical, Systems, And Metal Engineering, Technologipark-Zwijnaarde 46, Ghent University, Ghent, Belgium
c College of Engineering, Department of Civil and Architectural Engineering, Sultan Qaboos University, Muscat, Oman
d Faculty of Engineering & Information Technology, University of Technology Sydney, Ultimo, Australia e University Research and Innovation Center (EKIK), ´Obuda University, 1034, Budapest, Hungary f Department of Civil and Environmental Engineering, Rutgers University, New Brunswick, USA | | | | | --- | --- | --- | --- | | A R T I C L E I N F O | | A B S T R A C T | | | Handling Editor: Xi Lu | | Ocean energy technologies are in their developmental stages, like other renewable energy sources. To be useable in the energy market, most components of wave energy devices require further improvement. Additionally, wave resource characteristics must be evaluated and estimated correctly to assess the wave energy potential in various coastal areas. Multiple algorithms integrated with numerical models have recently been developed and utilized to estimate, predict, and forecast wave characteristics and wave energy resources. Each algorithm is vital in designing wave energy converters (WECs) to harvest more energy. Although several algorithms based on optimization approaches have been developed for efficiently designing WECs, they are unreliable and suffer from high computational costs. To this end, novel algorithms incorporating machine learning and deep learning have been presented to forecast wave energy resources and optimize WEC design. This review aims to classify and discuss the key characteristics of machine learning and deep learning algorithms that apply to wave energy forecast and optimal configuration of WECs. Consequently, in terms of convergence rate, combining optimization methods, machine learning, and deep learning algorithms can improve the WECs configuration and wave characteristic forecasting and optimization. In addition, the high capability of learning algorithms for forecasting wave resource and energy characteristics was emphasized. Moreover, a review of power take-off (PTO) coefficients and the control of WECs demonstrated the indispensable ability of learning algorithms to optimize PTO parameters and the design of WECs. | | | Keywords:
Wave energy conversions
Wave characteristics Optimization algorithms Machine learning Deep learning | | | | 1. Introduction Energy systems, particularly renewable sources, play a substantial and vital role in all facets of modern society, notably the residential sector, industry, and transportation, resulting from the evolution of human civilization and its critical need for energy [1]. The capacity of energy systems to adapt to supply and demand while providing maximum performance and having low environmental effects is generally considered one of the most fundamental concerns in this field. Particular emphasis should be given to these challenges due to the growing population, the need to meet the energy demand to offer better welfare and comfort, the growing usage of fossil fuels, and their negative environmental consequences [2,3]. In 2018, 376 TWh of renewable energy was produced throughout the world, an increase of 3% from the previous year (2017) [4], whereas wind and solar energy production increased by 11% and 28%, respectively. With an increased outpu

FAQs

Why is accurate wave resource estimation important for wave energy converters (WECs)?

Accurate wave-resource characteristics are needed to assess wave energy potential in different coastal areas and to design WECs effectively for higher energy harvesting.

What limitations do optimization-based algorithms face in WEC design?

Optimization-based approaches are often unreliable and suffer from high computational costs when used for efficiently designing WECs.

How do machine learning and deep learning improve wave energy forecasting and WEC optimization?

They are used to forecast wave energy resources and optimize WEC configuration, improving convergence rates and supporting learning-based prediction of wave and energy characteristics.

Aug 3, 2026

Upload by Levi