Air pressure forecasting for the Mutriku oscillating‐water‐column wave power plant: Review and case study

The high variability and unpredictability of renewable energy resources require optimization the extraction, by operating at best efficiency point, which can be achieved through optimal control strategies. In particular, wave forecasting models valuable for strategies in converter devices. This work intends to exploit short-term potential on an oscillating water column equipped with innovative biradial turbine. A Least Squares Support Vector Machine (LS-SVM) algorithm was developed predict air chamber pressure compare it real signal. Regressive linear algorithms were executed reference. experimental data obtained Mutriku power plant Basque Country, Spain. Results have shown LS-SVM prediction errors varying from 9% 25%, horizons ranging 1 3 s future. There is no need extensive training sets computational effort higher. However, results a relatively small number features. slightly better performance (8–22%) significantly lower cost. Ultimately, these research findings may play essential role model predictive plant.