Prof. Danilo Ardagna

Personal Information

Associate ProfessorPolitecnico di Milano Dipartimento di Elettronica, Informazione e Bioingegneria Via Golgi 42 20133 Milano, ItalyRoom: 315 Tel: +39 02 2399 3514 Fax: +39 02 2399 3574 danilo.ardagna<at>polimi<dot>it Curriculum Vitae

Research Interest

My research focuses on the design, prototyping, and evaluation of intelligent resource management solutions for large-scale distributed systems, with particular emphasis on infrastructures supporting Artificial Intelligence (AI), Generative AI, Agentic AI, Big Data, and Web applications. A central theme of my work is the development of optimization and learning-based algorithms for maximizing Quality of Service (QoS), improving resource and energy efficiency, and managing heterogeneous edge, cloud, and High-Performance Computing (HPC) infrastructures.

More recently, my research has increasingly focused on Generative and Agentic AI systems, investigating how AI agents and foundation models can be efficiently deployed and orchestrated across distributed and heterogeneous computing infrastructures. My interests include resource-aware agentic AI, multi-agent systems, reinforcement and multi-agent reinforcement learning, agent orchestration and routing, distributed inference, and the deployment of Large and Small Language Models (LLMs/SLMs) across the edge-to-cloud continuum. A key objective is to develop intelligent systems capable of dynamically adapting model selection, placement, resource allocation, and execution strategies according to performance, accuracy, energy, cost, and privacy requirements.

This research builds upon my work on AI applications at the edge and across the computing continuum. I recently coordinated the European AI-SPRINT project, which investigated novel methodologies and tools for developing, deploying, and operating AI applications across heterogeneous infrastructures spanning edge devices, computing clusters, and cloud resources.

A complementary and long-standing line of my research concerns the performance modeling, analysis, and optimization of large-scale distributed systems and software architectures. I have contributed to several European research projects in this area, including MODAClouds, DICE, EUBRA-BIGSEA, and ATMOSPHERE. I have also developed energy-efficient resource management solutions for virtualized infrastructures within the GAME-IT project.

During my Ph.D. studies, I investigated cost-aware design and capacity planning for distributed IT architectures. This work laid the foundations for my subsequent research on performance engineering, optimization, and intelligent resource management, which has progressively evolved toward AI-driven and autonomous management of distributed computing systems and, more recently, Agentic AI systems operating across the edge-cloud continuum.

Awards (last 10 years)

• R. Sala, B. Guindani, D. Ardagna, A. Guglielmi. d-MALIBOO: a Bayesian Optimization framework for dealing with Discrete Variables. MASCOTS 2024 (32nd IEEE International Symposium on the Modeling, Analysis, and Simulation of Computer and Telecommunication Systems). 1-8. Krakow, Poland. Best paper award.

• Included in the World’s Top 2% Scientist ranking (according to “Updated science-wide author databases of standardized citation indicators”), October 2023, November 2022.
• Google Education, May 2022.
• TETRAMAX Best project, October 2021. Best project among the 3rd call for Value Chain Technology Transfer Projects of H2020 TETRAMAX. ANDREAS selected for its exceptional contribution and innovation in power and cost management of deep learning training workloads.
• Top CompSci University Azure Adoption grant,  October 2016, September 2017, July 2018.
• D. Ardagna, S. Bernardi, E. Gianniti, S. Karimian Aliabadi, D. Perez-Palacin, J. I. Requeno. Modeling Performance of Hadoop Applications: A Journey from Queueing Networks to Stochastic Well Formed Nets.  ICA3PP 2016 Proceedings (16^th International Conference on Algorithms and Architectures for Parallel Processing). 599-613. Granada, Spain. Best paper award.

Events

• Fast Continuum 2025 General Co-Chair, Helsinki, Finland. Second International Workshop on Fast Continuum.

Previous Events (last 10 years)

• SIGMETRICS  2023 Tutorial Co-Chair, Orlando,  Florida, USA. International Conference on Measurement and Modeling of Computer Systems.
• Fast Continuum 2023 General Co-Chair, Coimbra, Portugal. First International Workshop on Fast Continuum.
• SCADL 2022 General Co-Chair, Lyon, France. 4th International Workshop on Scalable Deep Learning over Parallel And Distributed Infrastructures.
• IFIP WG 7.3 Performance 2021 General Chair, Milan, Italy. The 39th International Symposium on Computer Performance, Modeling, Measurements and Evaluation.
• SCADL 2021 PC Co-Chair, Portland, Oregon, USA. 3rd International Workshop on Scalable Deep Learning over Parallel And Distributed Infrastructures.
• IFIP WG 7.3 Performance 2020 General Chair, Milan, Italy. The 38th International Symposium on Computer Performance, Modeling, Measurements and Evaluation.
• SCADL 2020 Co-Chair, New Orleans, Louisiana, USA. 2nd International Workshop on Scalable Deep Learning over Parallel And Distributed Infrastructures.
• QUDOS 2020 Co-Chair, L’Aquila, Italy. 6th International Workshop On Quality-Aware DevOps.
• QUDOS 2019 Co-Chair, Berlin, Germany. 5th International Workshop On Quality-Aware DevOps.
• QUDOS 2018 Co-Chair, Berlin, Germany. 4th International Workshop On Quality-Aware DevOps.
• QUDOS 2017 Co-Chair, L’Aquila, Italy. 3rd International Workshop On Quality-Aware DevOps.
• QUDOS 2016 Co-Chair, Saarbrücken, Germany. 2nd International Workshop On Quality-Aware DevOps.

Services

• • IEEE Transactions on Cloud Computing
    • Associate Editor. 2018- 2022
  • IEEE Sustainable Computing Technical Community
    • General Chair. May 2014 – July 2015
    • Secretary/Treasurer. 2013 – 2014
    • Information Officer. 2011 – 2103

Relevant Publications

• Sedghani, M. Passacantando, D.Ardagna. Application Component Placement and Resource Optimization in Computing Continua. IEEE Transactions on Services Computing. 18(6), 3491-3508. 2025.
• R. Sala, H. Sedghani, M. Passacantando, G. Verticale, D. Ardagna. AI Applications Resource Allocation in Computing Continuum: a Stackelberg Game Approach. IEEE Transactions on Cloud Computing. 13(1), 166-183. 2025.

• H. Sedghani, F. Filippini, D. Ardagna. SPACE4AI-D: A Design-time Tool for AI applications Resource Selection in Computing Continua. IEEE Transactions on Services Computing. 17(6), 4324-4339. 2024.

• B. Guindani, D. Ardagna, A. Guglielmi, R. Rocco, G. Palermo. Integrating Bayesian Optimization and Machine Learning for the Optimal Configuration of Cloud Systems. IEEE Transactions on Cloud Computing. 12(1): 277-294. 2024.

• F. Filippini, J. Anselmi, D. Ardagna, B. Gaujal. A Stochastic Approach for Scheduling AI Training Jobs in GPU-based Systems. IEEE Transactions on Cloud Computing. 12(1), 53-69. 2024.
• F. Filippini, M. Lattuada, M. Ciavotta, A. Jahani, D. Ardagna, E. Amaldi. A Path Relinking Method for the Joint Online Scheduling and Capacity Allocation of DL Training Workloads in GPU as a Service Systems.
  IEEE Transactions on Services Computing. 16(3). 1630-1646. 2023.
• S. Karimian-Aliabadi,  M. M. Aseman-Manzar, R. Entezari-Maleki, D. Ardagna, B. Egger, A. Movaghar. Fixed-point Iteration Approach to Spark Scalable Performance Modeling and Evaluation. IEEE Transactions on Cloud Computing. 11(1). 897-910. 2023.
• M. Ciavotta, G. P. Gibilisco, D. Ardagna, E. Di Nitto, M. Lattuada, M. A. Almeida da Silva. Architectural Design of Cloud Applications: a Performance-aware Cost Minimization Approach. IEEE Transactions on Cloud Computing. 10(3), 1571-1591. 2022.
• M. Lattuada, E. Barbierato, E. Gianniti, D. Ardagna. Optimal Resource Allocation of Cloud-Based Spark Applications. IEEE Transactions on Cloud Computing. 10(2), 1301-1316. 2022.
• E. Gianniti, M. Ciavotta, D. Ardagna. Optimizing Quality-Aware Big Data Applications in the Cloud. IEEE Transactions on Cloud Computing. 9(2), 737-752. 2021.
• D. Ardagna, M. Ciavotta, R. Lancellotti, M. Guerriero. A Hierarchical Receding Horizon Algorithm for QoS-driven control of Multi-IaaS Applications. IEEE Transactions on Cloud Computing. 9(2), 418 – 434. 2021.
• E. Ataie, R. Entezari-Maleki, L. Rashidi, K. S. Trivedi, D. Ardagna, A. Movaghar. Hierarchical Stochastic Models for Performance, Availability, and Power Consumption Analysis of IaaS Clouds. IEEE Transactions on Cloud Computing. 7(4), 1039-1056. 2019.
• J. Anselmi, D. Ardagna, J. C.S. Lui, A. Wierman, Y. Xu, Z. Yang. The Economics of the Cloud. ACM Transactions on Modeling and Performance Evaluation of Computing Systems. 2(4), 1-23. 2017.
• D. Ardagna, M. Ciavotta, M. Passacantando. Generalized Nash Equilibria for the Service Provisioning Problem in Multi-Cloud Systems. IEEE Transactions on Services Computing. 10(3), 381-395. 2017.
• D. Ardagna, B. Pernici.  Adaptive Service Composition in Flexible Processes.  IEEE Transactions on Software Engineering. 33(6), 369-384, 2007.