Artificial intelligence based enhancement of performance evaluation and optimization methods for controlled queueing systems

Main focus of the proposed research is on reimagining the performance analysis and optimization in controlled queueing systems, namely by bridging AI methods and Queuing Theory. This research project embarks on an ambitious journey to revolutionize performance evaluation and optimization by forging a powerful alliance between machine learning, specifically Reinforcement Learning (RL), and the established principles of queuing theory. Our overarching goal is to develop a new generation of evaluation methods that overcome the limitations of traditional approaches, such as dimensionality of the state space, requirements for Markov property and so on, empowering engineers and control system designers with a more robust and informative toolkit.