The thesis presents a comprehensive exploration of advanced network management strategies. It identifies and addresses critical challenges in aligning the predictive capabilities of machine learning models, particularly Deep Neural Networks (DNNs), with the nuanced objectives of Intent-based Networking. The proposed models, which resolve the “loss-metric mismatch” and ensure unified goal achievement, mark significant advancements in automated network management. These models are not only theoretically relevant but also validated through extensive real-world applications, demonstrating their practical efficacy and adaptability in dynamic networking environments. Furthermore, the thesis emphasizes the importance of explainability in machine learning, highlighting its crucial role in ensuring the reliability, transparency, and ethical integrity of automated systems. By delving into the explainability of DNN models, the research significantly contributes to the development of more transparent and trustworthy machine-learning solutions, offering a robust framework for the future of network management.

About Alan Collet

Alan Collet is currently a Ph.D. student in the Network Data Science research group at IMDEA Networks Institute, Madrid, Spain. He received his B.S. and M.S. degrees in Telecommunications Engineering from the University of Bordeaux, France. He also received a second M.S. degree in computer science from the Illinois Institute of Technology of Chicago, USA. He is mainly working on neural network optimization for real-world networking problems.

PhD Thesis Advisor: Dr. Marco Fiore & Dr. Albert Banchs, IMDEA Networks Institute, Spain

University: University Carlos III of Madrid, Spain

Doctoral Program: Telematic Engineering

PhD Committee members:

• President: Pablo Serrano Yáñez-Mingot, Associate professor. Universidad Carlos III de Madrid.
• Secretary: José Suarez-Varela, Research Scientist. Telefónica Research.
• Panel member: Dario Bega. Research Scientist. Nokia Bell Labs.