Power Output Prediction of Wave Farms Using Fully Connected Networks
Abstract
One of the most important factors in the amount of power generated by a wave farm is the Wave Energy Converters (WECs) arrangement along with the usual wave conditions. Therefore, forming an appropriate arrangement of WECs in an array is a significant parameter in maximizing power absorption. This paper focuses on developing a fully connected neural model in order to predict the total power output of a wave farm based on the placement of the converters, derived from the four real wave scenarios on the southern coast of Australia. The applied converter model is a fully submerged three-tether converter called CETO. Data collected from the test sites is used to design a neural model for predicting the wave farm's power output produced. A precise analysis of the WEC placement is investigated to reveal the amount of power generated by the wave farms on the test site. We finally proposed a suitable configuration of a fully connected neural model to forecast the power output with high accuracy.