Alexandros Tzortzis
His research primarily focuses on the utilization of machine learning and deep learning methodologies for power grid time series forecasting, with a strong emphasis on EU-funded research and innovation projects.
AI Researcher
Technical Skills
- Languages: C/C++, Java, Python, SQL, Bash
- Tools: Docker, Kubernetes, Git/Github, LaTeX
Education
-
Ph.D. Student, Electrical and Computer Engineering National Tecnical University of Athens (2023 - present) -
B.Sc/MSci Electrical & Computer Engineering (Integrated Master) University of Thessaly (2017 - 2023)
Work Experience
Data Scientist @ Decision Support Systems Lab EPU (April 2023 - Present)
- Assistance in academic obligations regarding undergraduate courses
- Contribution in European projects part of the Horizon programme
- Research and development of technologies and services, regarding energy efficiency using machine learning techniques
Publications
- Tzortzis AM, Pelekis S, Spiliotis E, Karakolis E, Mouzakitis S, Psarras J, Askounis D. Transfer Learning for Day-Ahead Load Forecasting: A Case Study on European National Electricity Demand Time Series. Mathematics. 2024; 12(1):19. https://doi.org/10.3390/math12010019
Projects
AI4EF @ Enershare
The aim of the service is to provide a solid methodological framework for assessing renovation actions in residential buildings. This service consists of two ML models for implementing two different tasks related to the domain of building retrofitting and energy autonomy in the residential scale. The first model is tailored for assessing specific actions in building level, while the second model aims at assessing the potential of installing rooftop solar panels in residential buildings. A backend is implemented with a combination of fastAPI/postgREST, employing RESTful APIs to establish communication between models and frontend/database respectively.
