Distributed Systems
We Make Services Valuable
The Distributed Systems (DSY) research group of the InIT focuses on scalable and reliable implementation of sophisticated IT-based services. We address questions such as:
- What architecture best suits your specific cloud application?
- Which service model (IaaS, CaaS, PaaS, FaaS, ...) ensures optimal implementation of an application?
- Which tools are needed for development, operation and monitoring of the services?
- How to offer applications "as a service" (SaaS)?
- How to monetize modern IT services?
- How to integrate the "physical world" into complex IT services?
The research group is engaged in international projects within the EU research framework and works closely with partners from the private sector on innovative products within Innosuisse funded or directly financed projects.
The knowledge gained from applied research and development is transferred to students of computer science courses in the following modules:
Research Topics
Cloud Computing
The Init Cloud Computing Lab (ICCLAB) is dedicated to the automated deployment, operation and usage of configurable, highly scalable and resilient IT resources on a pay-per-use basis. In addition to infrastructure virtualization, this includes platform services for automated application delivery, scalable back-end, and monitoring of services and applications.
Service Prototyping
The Service Prototyping Lab (SPLAB) addresses the implementation and validation of complex services in cloud or post-cloud environments. In addition to the migration of existing services to the cloud, the main focus is on modern application architectures (Cloud Native Applications, Microservices, Serverless), the provisioning of tools for optimal implementation, the experimental validation of concepts and their monetization (Cloud Accounting and Billing).
Cloud Robotics
The Init Cloud Comupting Lab (ICCLAB) also addresses the integration of robotic applications into complex networked services. The usage of elastic cloud services allows to extend the capabilities of robots (computing power, context information, artificial intelligence, ...) as well as to manage and coordinate them. Programming frameworks and automation services enable developers to integrate robots into services without having in-depth knowledge at device level.
Projects
-
MA4K8s: Machine advice for GitOps-managed Kubernetes configuration optimisation
The profitability of cloud providers is often negatively affected by misconfiguration of application resource constraints. In this research study, we check the feasibility of integrating ML on usage-dependent configurations into a GitOps workflow. The result will be a novel advisor service that tells GitOps ...
-
TomGrowthAI
Crops growth management in greenhouses is fundamental for their economical and ecological sustainability. Typically, smaller size greenhouses have the challenge to grow more than one crop variety, each having different growth control strategies. A precise estimate of the expected harvest and crop balance allows ...
-
NEPHELE – A Lightweight Software Stack and Synergetic Meta-Orchestration Framework for the Next Generation Compute Continuum
The main vision for the NEPHELE project is to enable efficient, reliable and secure end-to-end orchestration of hyper-distributed applications over programmable infrastructure that is spanning across the compute continuum from Cloud-to-Edge-to-IoT. Together with other 17 great partners from industry and academia, ...
Publications
-
Birchler, Christian; Khatiri, Sajad; Bosshard, Bill; Gambi, Alessio; Panichella, Sebastiano,
2023.
Machine learning-based test selection for simulation-based testing of self-driving cars software.
Empirical Software Engineering.
28(71).
Available from: https://doi.org/10.1007/s10664-023-10286-y
-
Toffetti, Giovanni; Militano, Leonardo; Murphy, Seán; Maurer, Remo; Straub, Mark,
2022.
Cloud native robotic applications with GPU sharing on Kubernetes [paper].
In:
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Kyoto, Japan, 23-27 October 2022.
arXiv.
Available from: https://doi.org/10.48550/arXiv.2210.03936
-
Militano, Leonardo; Zafeiropoulos, Anastasios; Fotopoulou, Eleni; Bruschi, Roberto; Lombardo, Chiara; Edmonds, Andy; Papavassiliou, Symeon,
2022.
AI-powered Infrastructures for intelligence and automation in beyond-5G systems [paper].
In:
Proceedings of 2021 IEEE Globecom Workshops (GC Wkshps).
2021 IEEE Globecom Workshops (GC Wkshps), Madrid, Spain, 7-11 December 2021.
IEEE.
pp. 1-6.
Available from: https://doi.org/10.1109/GCWkshps52748.2021.9682117
-
Spillner, Josef; Gkikopoulos, Panagiotis; Delgado, Pamela; Choirat, Christine,
2022.
Towards reproducible software studies with MAO and Renku.
SoftwareX.
17(100947).
Available from: https://doi.org/10.1016/j.softx.2021.100947
-
Gkikopoulos, Panagiotis; Schiavoni, Valerio; Spillner, Josef,
2021.
Analysis and improvement of heterogeneous hardware support in Docker images [paper].
In:
Distributed Applications and Interoperable Systems.
21st International Conference on Distributed Applications and Interoperable Systems (DAIS), Valletta, Malta (online), 14-18 June 2021.
Cham:
Springer.
pp. 125-142.
Lecture Notes in Computer Science ; 12718.
Available from: https://doi.org/10.1007/978-3-030-78198-9_9