Basques design technique for predicting wave energy amounts

The climate and meteorology group at the University of the Basque Country (UPV/EHU), EOLO group, has developed a technique to forecast the amount of energy waves will bring several hours in advance.

The EOLO group has developed various models for predicting the amount of wave energy for the Bay of Biscay, off northern Spain, by using a technique called random forests.

EOLO models are based on a historical set of measurements that compare the energy levels of the waves at a given moment with each other and with those that are anticipated within a few hours.

The measurements are made by means of buoys, five of which are in place in the Bay of Biscay, three off the Galician coast and two out at sea.

According to the UPV/EHU, wave energy has an advantage over wind energy because it is easier to predict optimum swell than some suitable gusts of wind.

That is why knowing how much energy the waves will be bringing within a few hours is as important as having available efficient prototypes to make use of wave power. If this information is known, the energy produced by waves can be incorporated more easily into the mains, and renewable energy consumption can be increased at the same time, UPV/UHU’s press relese reads.

Gabriel Ibarra of the EOLO group said: “Random forests (RF) is an algorithm developed in recent years in the field of machine learning. The basis of RFs are the so-called ‘regression trees’, in which the input variables are regarded as roots and the output ones, the leaves. Hence the name ‘tree’. Random forest is a development of the regression trees which uses many trees (over a thousand, as a general rule) rather than just one, thus forming a forest.”

[mappress mapid=”621″]

Image: UPV/EHU