Zeynep Kiziltan is an assistant professor in computer science at the Department of Computer Science and Engineering of the University of Bologna (Italy) since 2006. She is also habilitated as associate professor in computer science by the Italian National Scientific Habilitation of the Italian Ministry of Education, University and Research (MIUR) since 2014. She was previously a post-doctoral researcher
at the Department of
Electronics, Computer Sciences and Systems of the University of Bologna.
She received her Ph.D. degree in March 2004 from the University of
Uppsala (Sweden) where she was also appointed as "docent"
(associate professor). The Ph.D. thesis of Dr. Kiziltan has won the 2004
Artificial Intelligence Dissertation Award of the European Association for Artificial Intelligence.
Dr. Kiziltan's research area is Artificial Intelligence (AI). Since her Ph.D. studies, she has worked on AI-based approaches to combinatorial decision making and optimization which is ubiquitous in diverse domains of science, business and industry. Her research work has contributed to various topics in the field, ranging from modelling to solution methods. In particular, she has focused on the foundations of Constraint Programming (CP), which is a widely-used component in intelligent systems to support decision making. She has studied effective modelling techniques and the computational complexity of propagation, and has designed and developed propagation algorithms for global constraints and hybrid CP-based search and heuristic search algorithms. She has further investigated how Machine Learning (ML) could be useful in CP, such as in managing a solver portfolio and constraint detection in natural language problem descriptions.
In recent years, Kiziltan's research is application driven, motivated by the need of sustainability in High-Performance Computing Systems (HPCs) so as to achieve exascale performance. Specifically, she has concentrated on how Data Science and AI could help together to cognify HPC systems to tackle energy efficiency, resiliency and workload management problems. Towards this, she has worked on the use of Data Science and CP for (power-aware) job dispatching, as well as on the use of ML for fault detection. Her interest in the HPC domain has also lead to the development of tools for research in workload management and fault detection.