Machine Learning for Renewable Energies: An Interdisciplinary Perspective

Please join a PELS supported event, 12th Session of Online Meetings of the Worldwide Energy NEtwoRk W-ENER   

Episode 12 WENER 13

Machine Learning for Renewable Energies: An Interdisciplinary Perspective  

Speaker: Cesar Astudillo

Panelists: Yamisleydi Salgueiro & Colin Bellinger

Date: Tuesday, 6 October 2020

Time: 9:30am (Chilean time)                          

Summary: Power converters are essential for the use of renewable energy resources. For example, a photovoltaic system produces DC energy that is transformed into AC by the VSI. This power is used by a motor drive that operates at different speeds, generating variable loads. Two parameters, namely, resistance and inductance, are essential to correctly adjust the model predictive control (MPC) in a VSI.  On the other hand, Machine Learning (ML) is a field within Artificial Intelligence that focuses on algorithms that learn from data. The motivation is to support the design and development of non-intrusive models to predict the resistance and inductance of a voltage source inverter (VSI) under different conditions. We will explain how we generated data comprising simulations varying the inductance and the resistance within a VSI, and how we benchmark ML methods to predict those variables, finding accurate models. We will also give our insights on how interdisciplinary research is essential for solving complex problems in engineering.


Register Here