| Title |
| Population-Based Metaheuristics and Machine Learning for Complex Optimization Problems |
| Speaker |
Oğuzhan Ceylan, PhD
Kadir Has University, Assoc. Prof. |
| Date |
February 26th, 2026
Thursday |
| Time |
| 15:00 (GMT+3) |
| Location |
ITU Informatics Institute
Room 413
|
| Abstract |
Decision-making problems from buying a house or a car to minimizing portfolio risk or maximizing profit in electricity markets can be modelled as optimization problems. Many real world objectives are nonconvex, noisy, constrained, or expensive to evaluate, making classical analytical methods difficult to apply. This talk introduces population-based heuristic (metaheuristic) optimization, a family of derivative-free numerical methods that search for good solutions by evolving a population of candidate points. Starting from randomly generated candidates within predefined bounds, these methods repeatedly evaluate the objective function and update candidates using operations such as perturbation, crossover, mutation, and selection until a stopping criterion is met.
Beyond classical metaheuristics, the talk will discuss how machine learning can enhance optimization workflows. ML-based surrogate models can reduce computation by approximating expensive objectives (useful when each evaluation requires simulation).
In smart-grids, these methods are especially useful because many tasks are nonconvex, constrained, mixed-integer, and simulation-heavy. Population-based heuristics have been applied to problems such as distribution network reconfiguration, optimal power flow (OPF) variants, DER and storage sizing/placement, battery and PV scheduling, Volt/VAR control, demand response, and EV charging coordination. The talk will conclude with practical guidelines on algorithm selection, constraint handling, and validation to support reliable decision-making in real applications.
|
| Bio |
Oğuzhan Ceylan is a faculty member of the Management Information Systems Department at Kadir Has University. He has an electrical engineering degree from Istanbul Technical University. His MSc and PhD degrees are from Istanbul Technical University, Informatics Institute. He was a visiting trainee at Digsilent GMBH from 2005 to 2006 through Leonardo Da Vinci Program. He was a postdoctoral researcher at University of Tennessee, Knoxville from 2013 to 2014. From 2014 to 2015 he was a research associate at Oak Ridge National Laboratory. From 2015 to 2017 he was a faculty member of the Electrical and Electronics Engineering Department at Kemerburgaz University, Turkey. From 2017 to 2021 he was a member of the Management Information Science Department at Kadir Has University, Istanbul. From 2021 to 2023 he was a faculty member at Marmara University Electrical and Electronics Engineering Department.
His research interests are mainly concentrated on solving complex optimization problems using either by nature inspired computation techniques or derivative based numerical methods. He is interested in applying solution techniques to mostly power systems-based problems. He is also interested in improving the speed of the solutions by applying parallel computing techniques as well.
Dr. Ceylan is a member of IEEE and he is international committees of conferences such as: Universities Power Engineering Conference (UPEC), International Symposium on Industrial Electronics (INDEL), Mediterranean Conference on Power Generation, Transmission, Distribution and Energy Conversion (MEDPOWER) and so on.). Dr. Ceylan has organized UPEC 2022 international conference, 2 international workshops. He has been the PI and researcher of several national projects. Currently he is the PI of MSCA-SE project titled as DIVERSE Data-DrIVen Solutions for Efficient PoweR DiStribution Network OpErations and a Tubitak 1001 project.
Dr. Ceylan has authored and co-authored several journal and conference papers. His google scholar page can be accessed at:
https://scholar.google.com/citations?user=asaGk3cAAAAJ&hl=en
|
|