Prediction and optimization of wave energy converter arrays using a machine learning approach

Abstract

a b s t r a c tOptimization of the layouts of arrays of wave energy converters (WECs) is a challenging problem. The hydrodynamic analysis and performance estimation of such systems are performed using semi-analytical and numerical models such as the boundary element method. However, the analysis of an array of such converters becomes computationally expensive, and the computational time increases rapidly with the number of devices in the system. As such determination of optimal layouts of WECs in arrays becomes extremely difficult. In this paper, a methodology involving multiple optimization strategies is presented to arrive at the solution to the complex problem. The approach includes a statistical emulator to predict the performance of the WECs in arrays, followed by an innovative active learning strategy to simultaneously explore and focus in regions of interest of the problem, and finally a genetic algorithm to obtain the optimal layouts of WECs. The method is extremely fast and easily scalable to arrays of any size. Case studies are performed on a wavefarm comprising of 40 WECs subject to arbitrary bathymetry and space constraints.

Analytical and computational modelling for wave energy systems: the example of oscillating wave surge converters

“…We optimized layouts for 40 WECs under different constraints, but the approach would work equally well for even larger arrays. The performance of arrays of Oyster WECs has been evaluated for the most probable sea-state at the Isle of Lewis in Scotland [43, 50] —see Sect. 4 on wave climate.

Fig.

…”

Advances and Challenges in Wave Energy Park Optimization—A Review

“…modes (De Chowdhury and Manasseh, 2017;Wolgamot et al, 2017), interaction distance cut-off (Göteman et al, 2015a), a nearest neighbor approach (Sarkar et al, 2016), and Haskind's relation (Flavià and Clément, 2017) have been introduced. Both the iterative and non-iterative versions of the multiple scattering theory have been further developed and used to model the hydrodynamics of wave energy parks (Ji et al, 2015;Konispoliatis and Mavrakos, 2016;Göteman, 2017;Ruiz et al, 2017;Fang et al, 2018;Giassi and Göteman, 2018;Zheng et al, 2018Zheng et al, , 2019Liu et al, 2019).…”

Adaptive Neuro-Surrogate-Based Optimisation Method for Wave Energy Converters Placement Optimisation

“…The neuro-surrogate is trained prior to each placement using sampled positions used for the previous buoy placement. 2) Use EvalSet = {2 nd , 3 rd , 6 th , 9 th , ..., 15 th } so the neuro-surrogate is used to place buoys: 4, 5, 7,8,10,11,13,14,16.…”