Search

Precise prediction of wave energy is indispensable and holds immense promise as ocean waves have a power capacity of 30–40 kW/m along the coast. Utilising this energy source does not generate harmful emissions, making it a superior substitute for fossil fuel-based energy. The computational expense associated with simulating and computing intricate hydrodynamic interactions in wave farms restricts optimisation methods to a few thousand evaluations and makes a challenging situation for training in deep neural prediction models. To address this issue, we propose a new solution: a Meta-learner gradient boosting method that employs four multi-layer convolutional dense neural network surrogate models combined with an optimised extreme gradient boosting. In order to train and validate the predictive model, we used four wave farm datasets, including the absorbed power outputs and 2D coordinates of wave energy converters (WECs) located along the southern coast of Australia, Adelaide, Sydney, Perth and Tasmania. Furthermore, the capability of the transfer learning strategy is evaluated. The WECs used in this study are of the fully submerged three-tether converter type, similar to the CETO prototype. The effectiveness of the proposed approach is assessed by comparing it with 15 well-established and effective machine learning (ML) methods. The experimental findings indicate that the proposed model is competitive with other ML and deep learning approaches, exhibiting considerable accuracy of 88.8%, 90.0%, 90.3%, and 84.4% in Adelaide, Perth, Sydney and Tasmania and improved robustness in predicting wave farm power output. [ABSTRACT FROM AUTHOR]

Ocean wave renewable energy is becoming a key part of the renewable energy industry over the recent decades. By developing wave energy converters (WECs), their power take-off (PTO) systems have been investigated to enhance the power extraction from the ocean. Adjusting PTO parameters is a challenging optimization problem because there is a complex and nonlinear relationship between these parameters and the absorbed power output. In this regard, this study aims to optimize the PTO system parameters of a point absorber wave energy converter in the wave data-set in Perth, on the Western Australian coasts. The converter is numerically designed to oscillate against irregular and multi-dimensional waves and sensitivity analysis for PTO settings. Then, to find the optimal PTO system parameters which lead to the highest power output, ten optimization approaches are incorporated to solve the nonlinear problem, including the Nelder-Mead search method, Active-set method, Sequential quadratic Programming method (SQP), Multi-Verse Optimizer (MVO), and six modified combination of Genetic, Surrogate and fminsearch techniques. After a feasibility landscape analysis, the optimization outcome is carried out and gives us the best answer in terms of PTO system settings. Finally, the investigation shows that the modified combinations of Genetic, Surrogate, and fminsearch approaches can outperform the others in the selected wave scenario, as well as with regard to the interaction between PTO system variables. • Optimizing the system parameters of a point absorber's HPTO to maximize power. • Comparing performance of numerical methods, metaheuristics, and modified combinations. • High and low values of piston area and LPA pre-charge pressure increases power output. • Piston area, LPA pre-charge pressure, and large HPA volumes affect the power ratio. • The modified combined method achieved the best result. [ABSTRACT FROM AUTHOR]