
Marek Lóderer
Research areas: machine learning, ensemble learning, metaheuristic and nature inspired computation, time series forecasting
Position: Researcher
Marek uses machine learning, ensemble learning and metaheuristic optimization algorithms to explore various microgrid-related problems in energy economics, with a focus on prediction and optimization of energy consumption. He has presented his work at local and international conferences and published his findings in scientific journals and proceedings of professional organizations, such as ACM and IEEE.
During his PhD studies at the Slovak University of Technology in Bratislava, he led a student team developing a learning platform to revitalize geography teaching in elementary and high school using VR and AR technologies. In other projects, he and his students created a web-based application for modeling and simulating behavior in microgrids, as well as a high-speed GPU accelerated columnar database (qikkDB) suitable for big data. He has participated in several national and international research projects, such as Newton H2020 and ICERISE, as well as industry projects involving sféra, ATOS and Instarea.
In 2021, he obtained a Doctoral degree in Informatics from the Technical University of Košice.
Selected Projects
Other notable projects
International Centre of Excellence for Research of Intelligent and Secure Information-Communication Technologies and Systems – II. Stage
International Centre of Excellence for Research of Intelligent and Secure Information-Communication Technologies and Systems
Intelligent Analysis of Big Data by Semantic-Oriented and Bio-Inspired Methods in a Parallel Environment
Knowledge-Based Approaches for Intelligent Analysis of Big Data
NEWTON – Networked Labs for Training in Sciences and Technologies for Information and Communication
Optimization in Microgrid
Selected Publications
Selected Student Supervising
Master
- Gemeľa Juraj – Detection of non-standard customer behavior in the power grid. Defended 2021
- Kubík Dávid – Optimization of power load consumption in microgrids. Defended 2020
- Vidiečanová Dominika – Optimization of power load consumption using high-capacity batteries. Defended 2020
- Cuper Matúš – Identification of abnormal behavior of customers in the power grid. Defended 2019
- Matula Marek – Prediction of electricity consumption by ensemble learning. Defended 2018
- Halaš Peter – Prediction of electricity consumption using biologically inspired algorithms. Defended 2017
Bachelor
- Bubán Michal – Biologically inspired algorithm in R language. Defended 2020
- Fano Adam – Biologically inspired algorithm in R programming language. Defended 2020
- Šoltés Pavol – Biologically inspired algorithm in R language. Defended 2019
- Cuper Matúš – Optimizing configuration parameters of prediction methods. Defended 2017
- Cvíčela Martin – Electric load forecast including external factors. Defended 2016