Alexandru Costan

Associate Professor, HDR, INSA Rennes

Permanent member of the KerData research team.

Contact Details

IRISA / Inria centre at Rennes University

Campus Universitaire de Beaulieu, 35042, Rennes, France

  • Office: D169
  • Phone: + 33 2  99 84 75 66
  • E-mail: alexandru.costan at

Research interests

I work on efficient support for AI (Federated Learning in particular) execution on large scale infrastructures, reproducibility and Big Data management on the Computing Continuum (clouds, fog, edge), stream processing and workflow data management.

Recent highlights

  • [Workshop co-chair] The 14th FlexScience workshop co-chaired with Bogdan Nicolae (ANL) and Kento Sato (RIKEN) will be co-located with HPDC’24, July 3-7, Pisa, Italy. You’re invited to submit a paper!
  • [Programme Committees] 2024: I am serving as PC member for IPDPS’24 (Parallel and Distributed Algorithms for Data Science track), EuroPar 2024 (Data analytics and AI track)
  • [ACM SRC Co-chair] I am co-chairing the ACM Graduate Student Research Competition at SC’23. You’re invited to submit your poster!
  • [Conference PC co-chair] I am co-chairing the technical PC of the IEEE ISPDC 2023 conference. Submit your paper!
  • [WP Lead] I am leading the WP2. Storage and Data Processing on the Computing Continuum of the PEPR CLOUD Steel project (2023-2028)
  • [Programme Committees] 2023: I am serving as PC member for IEEE/ACM SuperComputing 2023 (Clouds and Distributed Computing track), IEEE BigData 2023, IEEE/ACM UCC 2023
  • [PhD Defense] Congratulations to Daniel Rosendo, for defending his PhD thesis “Methodologies for Reproducible Analysis of Workflows on the Edge-to-Cloud Continuum”  (June 1st, 2023)!
  • [Programme Committees] 2022: I am serving as PC member for IEEE/ACM SuperComputing 2022 (Clouds and Distributed Computing, Posters, ACM Student Research Competition tracks), IEEE BigData 2022, IEEE/ACM UCC 2022
  • [Promotion] 2022: I was promoted to the Hors Classe of the Maître de conférences (Associate Professor – outstanding category)
  • [WP Lead] I am leading the WP2. Reproducible Deployment and Scheduling Strategies for AI Workloads of the Inria-DFKI ENGAGE project (2022-2025)
  • [Impact] Our joint work with the Lacodam team and Rutgers University was cited by Le Monde
  • [Programme Committees] 2021: I am serving as PC member for IEEE/ACM SuperComputing 2021 (Posters Track, ACM Student Research Competition), IEEE BigData 2021, IEEE/ACM UCC 2021
  • [Award] Our paper Distributed Multi-Sensor Machine Learning Approach to Earthquake Early Warning“, accepted at 34th AAAI Conference on Artificial Intelligence (AAAI-20, an A*-level conference), received the  Outstanding Paper Award: Special Track on AI for Social Impact
  • [Principal Investigator] of the FlexStream PHC PROCOPE project with the University of Dusseldorf, Germany, budget 10,000 EUR (2020-2022)
  • [HDR Defense] I defended my HDR titled: “From Big Data to Fast Data: Efficient Stream Data Management” on March 14, 2019, at ENS Rennes

Short bio

I am an Associate Professor at INSA Rennes and a researcher within the KerData team at IRISA Rennes. In 2011, I obtained my Ph.D. in Computer Science from the Politehnica University of Bucharest (PUB), under the supervision of Valentin Cristea (PUB) and Iosif Legrand (California Institute of Technology). The Ph.D. thesis focused on self-adaptive behavior of large-scale distributed systems based on monitoring information, bringing several contributions to the MonALISA monitoring system, developed in collaboration with Caltech and CERN. After the Ph.D., I joined Inria as a postdoctoral researcher within the KerData team, working with Gabriel Antoniu and Luc Bougé, on scalable storage in cloud environments. In 2012, I became an Associate Professor at INSA Rennes, where I am currently leading the Data Science track. My research interests include efficient support for AI (Federated Learning in particular) execution on large scale infrastructures, reproducibility and Big Data management on the Computing Continuum (clouds, fog, edge), stream processing and workflow data management. I published one book, more than 20 articles in international journals and 30 papers in international conferences. I serve as PC member of several top-level conferences and workshops in the domain of distributed computing (SuperComputing, IPDPS, EuroPar, CCGrid, Cluster, Big Data). I am the co-chair of the FlexScience workshop at HPDC (since 2015) and a member of the JLESC: Joint Laboratory on Extreme-Scale Computing.


A list of my recent publications:


  • E2CLab is a framework that implements a rigorous methodology that allows to deploy real-life application workflows to representative settings of the physical infrastructure underlying this application in order to accurately reproduce its relevant behaviors and therefore understand end-to-end performance.
  • ProvLight is a framework that allows researchers to efficiently capture provenance data of workflows running on IoT/Edge infrastructures. ProvLight presents low capture overhead in terms of: capture time; CPU and memory usage; network usage; and power consumption.
  • Planner is middleware for cost-efficient execution plans placement for uniform stream analytics on Edge and Cloud. Planner automatically selects which parts of the execution graph will be executed at the Edge in order to minimize the network cost. Real-world micro-benchmarks show that Planner reduces the network usage by 40% and the makespan (end-to-end processing time) by 15% compared to state-of-the-art.
  • KerA is a low-latency storage for stream processing (currently under development at Inria, in collaboration with Universidad Politécnica de Madrid, in the framework of a contractual partnership between Inria and Huawei Munich). By eliminating storage redundancies between data ingestion and storage, preliminary experiments with KerA successfully demonstrated its capability to increase throughput for stream processing.
  • Tyr is a transactional object storage system aimed at storage-based convergence between HPC and Big Data. Tyr natively offers data access coordination in the form of transactions. It offers a POSIX-compliant, transactional, distributed file system implementation built as a thin layer atop. This file system performs well and shows near-linear scalability properties on both HPC and Big Data platforms.
  • JetStream is a high performance batch-based streaming middleware. The system is able to self-adapt to the streaming conditions by modeling and monitoring a set of context parameters. It further aggregates the available bandwidth by enabling multi-route streaming across cloud sites.
  • TomusBlobs is a concurrency-optimized data storage system which federates the virtual disks associated to the Virtual Machines running the application code on the cloud. It is used in the Azure cloud for efficient data-intensive processing based on MapReduce.
  • MonALISA, which stands for Monitoring Agents using a Large Integrated Services Architecture, has been developed over the last years by Caltech and its partners with the support of the U.S. CMS software and computing program. The framework is based on Dynamic Distributed Service Architecture and is able to provide complete monitoring, control and global optimization services for complex systems.


  • PEPR CLOUD Steel (2023-2028): I am the WP2 leader of this national project focusing on efficient and secure data storage and processing on cloud-based infrastructures. Budget: 2.8M Euros.
  • Inria-DFKI Engage (2022-2025): I am the WP2 leader of this collaborative project between Inria and DFKI focusing on faster and more reliable AI in the processing of complex tasks. Budget: 500K Euros.
  • EuroHPC ACROSS (2021-2024): I am one of the Inria technical correspondants of this EuroHPC project focusing on combining traditional HPC techniques with Artificial Intelligence and Big Data analytics to enhance application outcomes. Budget: 4M Euros.
  • PHC PROCOPE FlexStream (2020-2022): I was the Principal Investigator of this collaborative project with University of Dusseldorf focusing on automatic scaling of streaming applications. Budget: 20K Euros.
  • ANR OverFlow (2015-2021): I was the Principal Investigator of this ANR JCJC project focusing on Workflow Data Management as a Service for Multi-site Applications. Budget: 250K Euros.
  • Inria Project Lab – HPC Big Data (2018-2022): I worked with other Inria teams at the intersection of HPC, Big Data and IA. In this context, I supervised the thesis of Daniel Rosendo.
  • BigStorage (2015-2018) is an European Training Network (ETN) project. Area: Storage-based Convergence of HPC and Cloud infrastructures to handle Big Data. Role: local coordinator for Inria Rennes Bretagne Atlantique.
  • Z-CloudFlow (2013-2016): geographically distributed workflows on Azure clouds. A project of the Microsoft-Inria Joint Research Centre.

Associated Teams

  • SmartFastData (2019-2022): I was the French Principal Investigator of this joint team between Inria (KerData) and Instituto Politécnico Nacional, Mexico. The team focused on the data support for smart-cities. It financed several PhD internships and Invited Professors in both teams. Budget: 60K Euros.
  • Unify (2019-2022): I was involved in setting up and animating this joint team between Inria (KerData, DataMove) and Argonne National Laboratory (USA) focusing on flexible data support for scientific workflows.

PhD students

  • Thomas Bouvier (2021-2024) co-advised with Gabriel Antoniu (Inria). Topic: “Deployment and scheduling strategies for AI workloads on heterogeneous resources (HPC, cloud, fog, edge)”
  • Cédric Prigent (2022-2025) co-advised with Gabriel Antoniu (Inria) and Loic Cudennec (DGA-MI). Topic: “Supporting Online Learning and Inference in Parallel across the Digital Continuum”
  • Mathis Valli (2023-2026) co-advised with Cédric Tedeschi (Inria) and Loic Cudennec (DGA-MI). Topic: “Dynamic Adaptation of Machine Learning Workflows across the Cloud-Fog-Edge Continuum


Invited talks

  • Smart Big Data Seminar, Institituto Politécnico Nacional Ciudad de Mexico: The Fast Data as a means of HPC / Big Data / AI convergence, 2019
  • International Staff Week, Tbilissi State University:  From Big Data to Fast Data, 2019
  • UPB Scientific Days, University Politehnica of Bucharest: The Path Towards the HPC / Big Data / IA convergence, 2019
  • UPB Scientific Days, University Politehnica of Bucharest: On the Challenges of the Edge/Cloud Hybrid Deployments, 2018
  • Huawei Workshop, Huawei Research, Munich: Low-Latency Stream Storage, 2017
  • BigStorage Summer School, FORTH Institute of Computer Science, Heraklion:  Making Cities Smarter : A Storage-based View on Stream Processing Engines, 2017
  • UPB Scientific Days, University Politehnica of Bucharest:  Science Driven, Scalable Data-Intensive Processing on Clouds, 2017
  • Smart Big Data Seminar, Institituto Politécnico Nacional Ciudad de Mexico: Science Driven, Scalable Data-Intensive Processing on Clouds, 2016
  • Distributed Systems Lab Seminar, University Politehnica of Bucarest: 
Big Data and Extreme Computing : A Storage-Based Pathway to Convergence, 2016
  • Future Cloud Symposium, EIT Digital Rennes: 
Enhancing video gaming user experience with Big Data analytics based on Apache Flink, 2015
  • Conf’Lunch, Inria / IRISA Rennes:  Clouds and MapReduce Programming, 2015
  • IFB School on Cloud Computing, CumuloNumBio’15, Aussois:  Big Data Management on Clouds, 2015
  • Distributed Systems Workshop, University Politehnica of Bucharest:  Scalable Data Management on Clouds and Beyond, 2015
  • Trusted Cloud Workshop, EIT ICT Labs Rennes
: Experience on running large scale scientific applications on public clouds, 2014
  • 3rd Workshop on Storage and Cloud Computing, Technicolor Rennes:  Scalable data management for scientific applications on cloud, 2013
  • Cloud Computing Seminar, EIT ICT Labs Rennes: Challenges of data storage on IaaS and PaaS clouds, 2013
  • High Performance Cloud and Big Data, Orange Labs Paris:  On the issues of porting HPC applications to the clouds, 2013
  • Computing in the Cloud Workshop, EIT ICT Labs Rennes:  Dealing with Big Data on clouds and beyond, 2013
  • IFIP Workshop, Futuroscope Poitiers
: Cloud Computing : from technological advances to scientific challenges, 2013
  • Atelier France Grilles, Institut de Physique Nucléaire de Lyon:  Gestion des données dans les clouds : l’approche BlobSeer, 2012
  • Séminaire BILab : Business Intelligence, Télécom-ParisTech:  Stockage capable de passer à l’échelle pour les applications MapReduce, 2012
  • Séminaire Aristote : Big Data, École Polytechnique
: Stockage à grande échelle pour les applications de traitement intensif des données, 2012

Former postodcs

  • Pedro Silva (2018-2019). Research topic: “Stream processing on Cloud, Edge and hybrid Cloud/Edge environments”, now Data Software Engineer at Oracle, Germany 
  • Elena Apostol (2015), now Associate Professor at University Politehnica of Bucharest, Romania

Former PhD students

  • Daniel Rosendo (2019-2023) co-advised with Gabriel Antoniu (Inria) and Patrick Valduriez (Inria). Topic: “Enabling HPC-Big Data Convergence for Intelligent Extreme-Scale Analytics”. Currently, Postdoctoral Researcher at Oak Ridge National Laboratory, USA. 
  • Ovidiu Marcu (2015-2018), co-advised with Gabriel Antoniu (Inria) and Maria S. Péréz (Universidad Politécnica de Madrid). Topic: “KerA: A Unified Ingestion and Storage System for Scalable Big Data Processing” . Currently, Postdoctoral Researcher at University of Luxembourg
  • Paul Le Noac’h (2016-2019) co-advised with Luc Bougé (ENS Rennes / IRISA). Topic: “Workflow Data Management as a Service for Multi-Site Applications”. Currently, Software Developer at myNewsDesk, Sweden.
  • Pierre Matri (2015-2018), co-advised with Gabriel Antoniu (Inria) and Maria S. Péréz (Universidad Politécnica de Madrid). Topic: “Tyr: Storage-Based HPC and Big Data Convergence Using Transactional Blob”. Currently, Postdoctoral Researcher at Argonne National Laboratory, USA
  • Luis Pineda (2014-2017), co-advised with Gabriel Antoniu (Inria). Topic: “Efficient support for data-intensive scientific workflows on geo-distributed clouds”. Currently, Technical Project Manager at TeraLab, France.
  • Radu Tudoran (2011-2014), co-advised with Gabriel Antoniu (Inria) and Luc Bougé (ENS Rennes / IRISA). Topic: “Efficient Big Data Management across Cloud Data Centers”. Currently, Software Development Manager at Amazon, Germany

Former Master students

  • Malvin Chevallier (INSA Rennes), 2023, co-advised with Thomas Bouvier (Inria) and Bogdan Nicolae (ANL ). Topic: “Accelerating AI workloads with Continual Learning
  • Juliette Fournis d’Albiat (ENS Cachan), 2022, co-advised with Daniel Rosendo and Gabriel Antoniu (Inria). Topic: “Enabling Rigorous Experiments of HPC Application Deployment on Distributed Platforms”
  • Hugo Chaugier (ENS Rennnes), 2021, co-advised with Gabriel Antoniu (Inria) and Bogdan Nicolae (ANL ). Topic: “Study of catastrophic forgetting in Deep Learning”
  • Laurent Prosperi (ENS Cachan), 2018. Topic : planification des application de flux sur des
    infrastructures edge / cloud.
  • Mukkram Rahman (Université de Rennes 1), 2017. Topic : optimisations au stockage des
    flux de données avec Apache HDFS.
  • Najeeb Aslam (Université de Rennes 1), 2016. Topic : analyse des performances Apache Flink et Apache Spark pour les requêtes SQL.
  • Roxana Roman (Université de Rennes 1), 2015. Topic : analyse des performances Apache Spark sur des clouds hybrides.
  • Andreea Pintilie (Université Politehnica de Bucarest), 2014. Topic : amélioration de l’accès sur demande pour les fichiers de workflows, utilisant la collaboration et la déduplication.
  • Stefan Ene (Université Politehnica de Bucarest), 2014. Topic : ordonnancement des don- nées et des tâches pour les applications MapReduce exécutées sur des plate-formes hybrides cloud / grid.
  • Rui Wang (Télécom Bretagne), 2013. Topic : transfert uniforme de données des applications géographiquement distribuées, s’appuyant sur la surveillance de l’état du cloud.
  • Ruxandra Ion (Université Politehnica de Bucarest), 2013. Topic : stockage pour les applications MapReduce exécutées sur des plate-formes hybrides (clouds / desktop grids).
  • Bharath Vissapragada (IIIT Hyderabad), 2012. Topic : validation de l’intégration BlobSeer / BitDew avec des expériences à large échelle sur le cloud Nimbus et la grille de calcul Grid’5000.
  • Radu Tudoran (ENS Cachan, Antenne de Bretagne), 2012. Topic : améliorations au sto- ckage d’Azure Cloud.
  • Julien Baste (ENS Cachan), 2012. Topic : optimisations traitement / stockage pour les ap- plications scientifques.

Comments are closed.