Carolina Gil Marcelino
GET-COFUND MarieS.Curie Fellow at UAH
Multiobjective and decision making mehodology to solve optimal power flow problems: an approach applied to hybrid microgrid systems
About the research project «Multiobjective and decision making mehodology to solve optimal power flow problems: an approach applied to hybrid microgrid systems»
Research line: Machine Learning in Renewable Energy Systems
Mentor: Prof. Sancho Salcedo Sanz (UAH) and Prof. Silvia Jiménez Fernández (UAH)
To meet the ambitious CO2 goals of the Paris agreement from 2015 to prevent, or at least minimize climate change, there is a global need for sustainable energy supply. Part of this energy is intended to be produced by micro-generation systems in a decentralized way. Market-driven policies are increasingly focused on promoting the use of micro-generation systems to meet customer needs. This change, however, proves to be a challenging task, particularly for those who choose to produce their own electricity based solely on locally available renewable resources, such as wind or solar power. Hybrid micro-grid systems (HMGS) are seen as a viable solution to this problem because they comprise one or more local energy sources and include demand control systems and storage devices. The proposed project has as goal to propose and improve new HMGS mathematic models and tools to provide the electric dispatch based on evolutionary computation optimization. The central idea is to propose a multiobjective model to minimize costs and losses maximizing the renewable sources. After the optimization phase’s a set of solutions will be analysed by multicriteria decision analyses techniques.
About Carolina Gil Marcelino
Carolina Gil Marcelino holds a PhD degree in Mathematical and Computational Modelling from CEFET-MG/Brazil, in which the thesis research focus was the optimization of power energy systems, 2017. She received the CAPES Foundation award for sustainability in 2014, Brazil. She have been at INESC TEC, Porto, Portugal as a guest researcher on mobility improving evolutionary algorithms by optimization, 2014. In 2016 she was a mobility visiting researcher proposing mathematical models for simulation of smart grid systems at the Karlsruher Institut für Technologie (KIT), Germany with scholarship funded by ERASMUS – BE Mundus Project. Between 2017-2019 she researched in the machine learning and pattern classification areas, as a postdoc position at University of Rio de Janeiro, Brazil. Currently, she is developing the «Multiobjective and decision making mehodology to solve optimal power flow problems: an approach applied to hybrid microgrid systems» project with a GET-COFUND Marie-Curie Fellowship. Her current research interests include population-based mono and multiobjective optimization, multi-criteria decision analysis, mathematical and statistical aspects of optimization theory, machine learning and classifier patterns applied in energy systems optimization.
Most recent publications:
MARCELINO, C.G.; ALMEIDA, PAULO E.M. ; WANNER, E.F. ; CARVALHO, L.M. ; BAUMANN, M. F. ; WEIL, M.. A Combined Optimization and Decision-Making approach for Battery-Supported HMGS. JOURNAL OF THE OPERATIONAL RESEARCH SOCIETY, 2019, v.1, p. 1-13.
MARCELINO, C. G.; PEDREIRA, C. E. ; BAUMANN, M.; WEIL, M. ; ALMEIDA, P. E. M. ; WANNER, E.F.. A Viability Study of Renewables and Energy Storage Systems Using Multicriteria Decision Making and an Evolutionary Approach. Lecture Notes in Computer Science. 1ed.: Springer International Publishing, 2019, v., p. 655-668.
MARCELINO, C. G.; ALMEIDA, PAULO E. M.; WANNER, E. F.; WEIL, M.; BAUMANN, M. F.; CARVALHO, L. M.; MIRANDA, V.. Solving security constrained optimal power flow problems: a hybrid evolutionary approach. APPLIED INTELLIGENCE, 2018, pp. 1-19.
MARCELINO, C. G.; WANNER, E. F. ; ALMEIDA, P. E. M.; BAUMANN, M. F. ; WEIL, M.. A new model for optimization of hybrid microgrids using evolutionary algorithms. IEEE Latin America Transactions, 2018, v. 16, p. 799-805
MARCELINO, C. G.; ALMEIDA, P.E.M. ; PEDREIRA, C.E.; MAGALHÃES, L.; WANNER, E.. Applying C-DEEPSO to Solve Large Scale Global Optimization Problems. In: IEEE Congress on Evolutionary Computation (CEC), 2018, pp. 1-8.
BAUMANN, M. F.; MARCELINO, C. G.; PETERS, J. ; WEIL, M. ; WANNER, E. F.; ALMEIDA, P. E. M.. Environmental Impacts of Different Battery Technologies in Renewable Hybrid Micro-Grids. Proc. on IEEE International Conference on Innovative Smart Grid Technologies, 2018, pp. 1-6.
|ID||Event Name||Duration||Start Date|
|Escuela de verano||Principles of Machine Learning – Cursos de verano UAH||1 Weeks||7 julio, 2022|