Preprint Article Version 1 Preserved in Portico This version is not peer-reviewed

Providing a Prediction Model to the Output Power of a Wave Energy Converter by Artificial Neural Network

Version 1 : Received: 7 March 2021 / Approved: 11 March 2021 / Online: 11 March 2021 (09:29:20 CET)
Version 2 : Received: 11 April 2021 / Approved: 13 April 2021 / Online: 13 April 2021 (09:51:25 CEST)

How to cite: Mousavi, S.M.; Ghasemi, M.; Dehghan Manshadi, M.; Mosavi, A. Providing a Prediction Model to the Output Power of a Wave Energy Converter by Artificial Neural Network. Preprints 2021, 2021030302. https://doi.org/10.20944/preprints202103.0302.v1 Mousavi, S.M.; Ghasemi, M.; Dehghan Manshadi, M.; Mosavi, A. Providing a Prediction Model to the Output Power of a Wave Energy Converter by Artificial Neural Network. Preprints 2021, 2021030302. https://doi.org/10.20944/preprints202103.0302.v1

Abstract

The technologies pertaining to ocean waves has been continuously improving since its creation and the major focus is to come up with accurate predication of power generation from the oceans waves. The precise forecast can not only reduce costs for investment but also it is essential for management and operation of electrical power. The purpose of the current paper is to numerically investigate a new economical wave energy converter named “Searaser”. The simulation is done with Flow-3D software which has high capability in analyzing the fluid solid interactions. by collecting the experimental data of another study and the exerted data which is from numerical simulation, the wind speed and output power are related with a long short term memory (LSTM). By doing comparative analysis between these data, it can be concluded that the artificial intelligence method is so accurate and fast. The network output figures show a good agreement and the root mean square is 0.49 in mean value which was related to the accuracy of LSTM method. One of the novelties of this study is to provide a scatter plot that generates power in terms of wind speed. Due to the accumulation of data, the power can be predicted for other wind speeds by using the intermediate values. Furthermore, the mathematical relation between the generated power and wave height was introduced by curve fitting the power function to the result of LSTM method.

Keywords

Searaser; Flow-3D; Prediction; Long short term memory; deep neural network; Root mean error.

Subject

Computer Science and Mathematics, Algebra and Number Theory

Comments (0)

We encourage comments and feedback from a broad range of readers. See criteria for comments and our Diversity statement.

Leave a public comment
Send a private comment to the author(s)
* All users must log in before leaving a comment
Views 0
Downloads 0
Comments 0
Metrics 0


×
Alerts
Notify me about updates to this article or when a peer-reviewed version is published.
We use cookies on our website to ensure you get the best experience.
Read more about our cookies here.