Ocean wave power forecasting using convolutional neural networks

Abstract

Climate change "fuelled" by anthropogenic causes has been identified as the greatest threat faced by societies. In this respect, the roadmap to a "greener" generation mix certainly includes a greater heterogeneity in terms of renewable energy sources. In this regard, one of the leading candidates is ocean wave energy. One of the issues with renewables in general is their unpredictably and variability, as it is crucial to address the subject of wave power forecasting, to facilitate a future market integration. Hence, to tackle this prediction problem, a new approach to short-term wave power forecasting is proposed, based on deep learning capabilities. These highly popular networks were traditionally developed to deal with images (2D data), so the authors discuss all the necessary implementation and design details to employ these networks with 1D input data, to solve a regression-based problem. These case-studies include wave data from three different locations. The proposed approach was tested across all seasons of the year, revealing the suitability to extract the relevant input data dependencies from the time-series. As such, especially for horizons up to 6 h, the proposed approach outperforms other conventional methods.

Artificial Intelligence and Machine Learning in Energy Conversion and Management

“…Fully connected layers link every node in one layer to every node in another layer [141]. Between 2018 and 2022, the most notable publications in energy conversion used CNNs to forecast fuel cells power generation accurately [144], ocean wave power prediction [145], and solar panel output forecasting [146], which provided an 11-60% improvement on the benchmark using between 17,000 and 77,000 real data samples.…”

A deep learning method for the prediction of focused waves in a wave flume

“…More recently, Convolutional Neural Networks (CNN) have been applied to predict short-term wave power. Comparisons indicate that CNN outperform ANN in terms of predicting long wave patterns [16]. Recurrent Neural Networks (RNN) may outperform traditional ANN and CNN due to their ability to handle sequential data [13,17].…”

Phase-resolved real-time ocean wave prediction with quantified uncertainty based on variational Bayesian machine learning

“…Recently, machine learning (ML) based approaches are starting to gain attention in ocean wave predictions. Many works focused on the phase-averaged wave information, such as the prediction of the wave height and period, for the purposes of storm forecasting [32], vessel operations [33,34], and wave power forecasting [35]. While on the other hand, the number of studies on phase-resolved wave prediction, which is the main focus of this paper, is still limited.…”