Distributed Fog Middleware
This position has already been filled.
Host: Vienna University of Technology (TU Wien), Distributed Systems Group
- Main supervisor: Assistant Prof. Stefan Schulte, s.schulte@infosys.tuwien.ac.at (contact person)
- Co-supervisor: Prof. Schahram Dustdar, dustdar@dsg.tuwien.ac.at
Requirements:
- Mandatory requirements for all PhD positions
- Master in Computer Science or equivalent
- Knowledge of algorithms and data structures
- Experience with developing large complex software
- Knowledge about Internet of Things and Cloud technologies is a plus
- Demonstrated ability to write scientific papers is a plus
Objectives:
- Design a distributed scalable Fog middleware to enable apps to communicate and manage data, simplifying the development & deployment of fog-native applications.
- Develop a prototype implementation for the middleware, evaluating two options: hierarchical and a peer-to-peer distribution of the middleware.
Expected Results:
- A detailed design of the Fog middleware functionality and the associated API for apps, for the control of Fog Nodes and orchestration of groups of Fog Nodes.
- Prototype implementations of the middleware, using rapid application development, which are scalable: can run both on low-end and high-end Fog Nodes.
- Mechanisms for resource provisioning.
- Evaluation of the middleware in real-world industrial experiments.
Planned Visits and Collaboration:
- ABB (Dr. Magnus Larsson): Learn about M2M communication, gather the middleware requirements and formulate the API.
- UNIBAP (Dr. Fredrik Bruhn): Evaluate the middleware on a mobile robot setup using an image analysis use case.
Description:
Within this PhD project, the candidate is expected to develop a distributed middleware for the control of a Fog landscape. The middleware should provide functionalities covering all phases of software running in the fog, i.e., design, implementation, execution, monitoring, and adaptation of fog-based applications. The work conducted within this project will follow an iterative approach, i.e., first, rather centralized approaches to fog middlewares will be realized. From the second project year, the focus will be on decentralized approaches.
Relevant Publications:
- O. Skarlat, M. Nardelli, S. Schulte, S. Dustdar, “Towards QoS-aware Fog Service Placement,” in IEEE International Conference on Fog and Edge Computing, pp. 89-96, 2017.
- O. Skarlat, S. Schulte, M. Borkowski, P. Leitner, “Resource Provisioning for IoT Services in the Fog,” in 9th IEEE International Conference on Service Oriented Computing and Applications, pp. 32–39, 2016.
- E. Elmroth, P. Leitner, S. Schulte, S. Venugopal, “Connecting Fog and Cloud Computing,” IEEE Cloud Computing, Volume 4, Number 2, 22-25, 2017.