Giorgia Ghione

Ph.D. candidate in Ingegneria Elettrica, Elettronica E Delle Comunicazioni , 38th cycle (2022-2025)
Department of Electronics and Telecommunications (DET)

Profile

PhD

Research topic

Advanced machine learning for factory optimization

Tutors

Research interests

Big Data, Machine Learning, Neural Networks and Data Science
Systems, Automation and Control

Biography

Giorgia Ghione is currently a PhD student in Electrical, Electronics and Communications Engineering at the Neuronica Lab research group at Politecnico di Torino.

Giorgia Ghione got a M.SC. degree in Computer Engineering at Politecnico di Torino in 2022, presenting the thesis An interpretable BERT-based architecture for SARS-CoV-2 variant identification: the thesis project revolved around the classification of the variants of SARS-CoV-2 genetic sequences using the Bidirectional Encoder Representations from Transformers (BERT) algorithm, and the interpretation of the behaviour of the model.

Her current primary research interests are time series forecasting, predictive maintenance, and energetic and resource optimization in factories using advanced machine learning methods.

The main projects Giorgia Ghione has been involved in are the following:
  • Advanced photovoltaic power production and energy load forecasting: Giorgia Ghione developed and compared various deep learning algorithms for the photovoltaic power production forecasting of a solar station. The project was carried out in collaboration with Trigenia S.r.l, an Energy Service Company which supports businesses in the digital and energy transition. Secondly, Giorgia Ghione is researching and developing a deep learning algorithm for predicting the energy loads of a microgrid in collaboration with Università degli Studi di Palermo.
  • Optimization of CHP and energy storage utilization in a large power plants: Giorgia Ghione is currently working on the development of a deep learning algorithm for the optimized utilization of energy storage in a large-scale power plant, which includes several sources of electricity. In addition, the development of a deep learning algorithm for optimising the utilisation of a cogenerator (Combined Heat and Power or CHP) in a second plant is underway. Both the projects are carried out in collaboration with Trigenia S.r.l.
  • Enhanced Neural real-time digital TWIN for Electrical Drivers (ENTWINED): ENTWINED is a research project involving Politecnico di Torino, Università degli Studi Roma Tre and Consiglio Nazionale delle Ricerche to develop a Digital Twin architecture for real-time monitoring and control of electricla drives and power converters. In particular, Giorgia Ghione is developing the big data analytics strategy and the neural model for system monitoring, predictive maintenance and fault diagnosis.

Publications

Latest publications View all publications in Porto@Iris