A data-driven long-term metocean data forecasting approach for the design of marine renewable energy systems. (October 2022)

• Record Type: Journal Article
• Authors: Penalba, Markel; Aizpurua, Jose Ignacio; Martinez-Perurena, Ander; Iglesias, Gregorio
• Is Part Of: Renewable & sustainable energy reviews. Volume 167(2022)
• Publication Date: 2022-10
• Subjects: Metocean data -- Re-analysis data -- Long-term trend -- Wave forecasting -- Machine learning -- Regression algorithms -- Classification algorithms; Renewable energy sources -- Periodicals; Power resources -- Periodicals; Énergies renouvelables -- Périodiques; Ressources énergétiques -- Périodiques; 333.794
• DOI: 10.1016/j.rser.2022.112751
• Languages: English
• ISSNs: 1364-0321

Abstract

Abstract: The potential of Marine Renewable Energy (MRE) systems is usually evaluated based on recent metocean data and assuming the stationarity of the MRE resource. Yet, different studies in the literature have shown long-term resource variations and even the connection between ocean warming and wave power variations. Therefore, it is crucial to accurately characterise the future resource, including these long-term variations. To that end, this paper presents a novel data-driven forecasting approach through the combination of machine-learning (ML) and oceanic engineering concepts. First, the historical resource is characterised in the Bay of Biscay, including the different long-term trends identified based upon the dataset obtained via the SIMAR model ensemble. Secondly, the most relevant features of the metocean dataset are extracted and selected via advanced statistical techniques. Finally, three different ML algorithms are designed, validated and tested. All three ML models demonstrate to adequately represent the overall pattern of the dataset, although showing difficulties with reproducing particular peak values. Accordingly, an alternative interval prediction approach is presented for three different wave height discretisation levels, showing a greater potential for long-term metocean data forecasting. Highlights: A data-driven marine renewable energy resource characterisation is presented. A pioneering long-term data-driven metocean data forecasting approach is suggested. The SVR model shows to over-perform ANN and RF models for long-term metocean data forecasting. A novel discrete interval prediction approach based on the SVC method is presented for different wave-height intervals. The accuracy of the SVC is satisfactory, demonstrating that when the predictive model fails to predict the correct rank, only fails by one rank.