Embedded Files
Tutorial Session
Tutorial Session
Resilient Scheduling in Distributed Systems: Benchmarking and Adversarial Analysis with SAGA
Resilient Scheduling in Distributed Systems: Benchmarking and Adversarial Analysis with SAGA
Abstract
Abstract
Scheduling in heterogeneous distributed systems (spanning cloud, HPC, and edge environments) remains a fundamental challenge in distributed computing. This tutorial introduces SAGA, an open-source Python framework that provides a unified environment for implementing, benchmarking, and comparing scheduling algorithms. SAGA includes a library of common schedulers, standardized datasets, and metrics for reproducible evaluation. It also includes PISA, a tool for adversarial analysis that automatically generates problem instances where one algorithm underperforms another. Through short lectures and guided hands-on exercises, participants will learn to use SAGA to benchmark and extend schedulers, analyze results, and apply PISA to uncover instance-specific and worst-case behaviors. Attendees will gain practical experience using open, reproducible tools for studying and improving scheduling resilience in modern distributed systems.
This material is based upon work supported by the National Science Foundation under Award No. 2451267. This work was supported in part by Army Research Laboratory under Cooperative Agreement W911NF-17-2-0196.
Speakers
Speakers
Dr. Jared Coleman is an Assistant Professor of Computer Science at Loyola Marymount University and director of the Kubishi Research Group. His research spans distributed and decentralized computing, cooperative multi-agent systems, and task-graph scheduling. He is the lead developer of the SAGA framework and co-developer of PISA. His recent work appears at IPDPS, JSSPP, and ICMCIS, and he has collaborated with organizations including NATO’s Science and Technology Organization.
Dr. Bhaskar Krishnamachari is a Professor of Electrical and Computer Engineering and Computer Science at the University of Southern California, where he directs the Autonomous Networks Research Group. His research covers algorithms and protocols for wireless networks, edge computing, distributed systems, and AI. An IEEE Fellow and author of Networking Wireless Sensors (Cambridge University Press), he has co-authored over 300 publications and received multiple best paper awards at leading conferences including IPSN and MobiCom.
From Nature to Code and Back Again: Designing Bio-Inspired Computing Algorithms and Transferring Them to Modern Biology
From Nature to Code and Back Again: Designing Bio-Inspired Computing Algorithms and Transferring Them to Modern Biology
Authors: Dr. Melanie Heck (University of Stuttgart, Germany), Prof. Dr. Stefan Fischer (University of Lübeck, Germany), Prof. Dr. Christian Becker, University of Stuttgart, Germany)
Abstract
Abstract
Modern computing systems must adapt to dynamic, unpredictable environments. Drawing on nature’s robustness, bio-inspired paradigms have enabled adaptive systems with self-* properties guided by the MAPE-K loop. Advances in biology and nanotechnology now reverse this flow, with computing concepts shaping biological engineering. This tutorial explores this dual transfer, focusing first on algorithmic foundations and control architectures for computing and communication systems, before discussing their application to the Internet of Bio-Nano Things (IoBNT) for applications in precision medicine and diagnostics.
Speakers
Speakers
Speaker 1: Prof. Dr. Christian Becker, University of Stuttgart, Germany
Biography: Christian Becker is a full professor for computer science and the director of the Institute of Parallel and Distributed Systems at the University of Stuttgart in Germany. His research interests are distributed systems and context-aware computing, with a focus on architectures for adaptive systems and their application to distributed systems. Christian has published more than 200 technical papers. He is active in the community, e.g., as a member of the IEEE PerCom steering committee, PerCom general chair in 2010 and TPC chair in 2016, general chair of IEEE Mobile Data Management in 2007 and 2023, and ACSOS TPC chair in 2024.
Speaker 2: Dr. Melanie Heck, University of Stuttgart, Germany
Biography: Melanie Heck is a postdoctoral researcher at the Institute of Parallel and Distributed Systems at the University of Stuttgart. She received her PhD about adaptation of multimodal user interfaces from the University of Mannheim in 2023. Prior to that, she studied Business Administration at the Universities of Flensburg and Mannheim, where she graduated in 2019. Her research interests are adaptive user interfaces with a focus on the integration and automatic detection of user states.
Speaker 3: Prof. Dr. Stefan Fischer, University of Lübeck, Germany
Biography: Stefan Fischer is a full professor for computer science at the University of Lübeck in Germany. He is also the director of the Institute of Telematics. His research interest focuses on network and distributed system structures such as ad-hoc and sensor networks, Internet of Things, and nanonetworks based on molecular communication. He has (co-)authored more than 200 scientific books and articles. He is an experienced academic teacher and has conducted several tutorials at major conferences throughout his career.
Page updated
Google Sites
Report abuse