| KEYWORD |
ELECTRONIC DESIGN AUTOMATION - EDA
Machine Learning techniques to forecast energy produced by Wave Energy Converters
keywords ARTIFICIAL INTELLIGENCE, ARTIFICIAL NEURAL NETWORK, DEEP NEURAL NETWORKS, FORECAST, RENEWABLE ENERGY SOURCES, WAVE ENERGY
Reference persons EDOARDO PATTI
External reference persons Rafael Fontana Crespo (rafael.fontana@gmail.com
Research Groups DAUIN - GR-06 - ELECTRONIC DESIGN AUTOMATION - EDA, ELECTRONIC DESIGN AUTOMATION - EDA, Energy Center Lab, GR-06 - ELECTRONIC DESIGN AUTOMATION - EDA, ICT4SS - ICT FOR SMART SOCIETIES
Thesis type EXPERIMENTAL
Description Wave Energy has recently emerged as a serious contender in the renewables field. To transform the power from the waves into electrical Energy, a Wave Energy Converter (WEC) is needed. However, the power generated from wave energy fluctuates. In the context of a Smart Grid Scenario, the accurate prediction of the power generated by the WEC and delivered to the grid is crucial to enable the full penetration of WECs in the smart grid. To this end, advanced machine learning (ML) techniques for forecasting energy production can be implemented.
This thesis aims to develop an innovative methodology to forecast the power delivered to the grid of WEC devices by taking advantage of advanced deep learning techniques (e.g. Long-Short Term Memory (LSTM) Neural Network, Transformer Neural Network (TNN), etc). In detail, the model would consider past measurements of the power delivered to the grid, as well as other exogenous inputs such as rotor speed, tilt, buoy, wind speed, etc. Additionally, the methodology will employ Prediction Intervals to calculate the inherent uncertainties.
The ideal candidate should be familiar with Python.
Required skills Python
Deadline 30/10/2025
PROPONI LA TUA CANDIDATURA