Abstract
Wind-generated wave energy is a renewable energy source that exhibits a huge potential for sustainable growth. The design and deployment of wave energy converters at a given location require the prediction of the amount of available wave energy flux. This and other wave parameters can be estimated by means of Computational Intelligence techniques (Neural, Fuzzy, and Evolutionary Computation). This paper reviews those used in wave energy applications, both in the resource estimation and in the design and control of wave energy converters. In particular, most of the applications of Neural Computation techniques, considered here in a broad sense, focus on the prediction of a variety of wave energy parameters by means of Multilayer Perceptrons and, at a lesser extent, by Support Vector Machines, and Extreme Learning Machines. Fuzzy Computation is also applied to estimate wave parameters and control floating wave energy converter. Evolutionary Computation algorithms are used to estimate parameters and design wave energy collectors. We complete this paper with a case study that illustrates, for the first time to the best of our knowledge, the potential of hybridizing a Coral Reefs Optimization algorithm with an Extreme Learning Machine to tackle the problem of significant wave height reconstruction.