My Research Projects
- Master's in Embedded Artificial Intelligence (EmbeddedAI)
- Swarm Intelligence Layer to Control Autonomous Agents (SWILT)
- ICT solutions for energy saving in smart homes (CPSwarm)
- Enhanced Materials, Methods & Applications for Power Devises & Systems (EM2APS)
- ICT solutions for energy saving in smart homes (MONERGY)
- Smart Microgrid Lab Project (SMARTGRID)
- Research on Power Technology Reliability (REL4POWER)
- Evolutionary Design of Self-organizing Embedded Systems (EVOSOS)
- Modeling and Engineering of Self-Organizing Networks (MESON)
- Design Methods for Self-Organizing Systems (DEMESOS)
- Time-Triggered Communication Architecture for an Autonomous Mobile Robot System (TTCAR)
- Configuration and Maintenance of the TTP/A Fieldbus (CoMa)
EmbeddedAI - Master's in Embedded Artificial Intelligence
The main objective of EmbeddedAI is to establish an international Master of Science program in embedded Artificial Intelligence, with a focus on embedded systems and strong industrial involvement. This program will cover application domains such as agriculture, healthcare, telecommunication, and manufacturing. The plan is to create a curriculum with clear guidelines for admission, evaluation, teaching methodologies, certification awarding, and accreditation. The goal is to equip Nigerian students with the latest technological trends, enhancing their employability and entrepreneurial skills. Additionally, EmbeddedAI aims to facilitate cultural exchange and promote globalization by enabling Nigerian Higher Education Institutions to collaborate with various EU counterparts.SWILT - Swarm Intelligence Layer to Control Autonomous Agents
The goal of SWILT is to perform agent-based swarm modelling of an industrial plant on the use cases of production scheduling and transportation in logistics. Since the problem sizes in these use cases are extremely large and traditional pre-calculated schedules or transportation tables are not sufficient, the innovation is to use swarm algorithms with reactive local rules on individual agents which are able to compensate dynamic changes in their local vicinity. The SWILT concept embeds the local swarm rules in a three-layered architecture: L1 – central management layer, L2 – swarm control layer, and L3 – autonomous agent layer. Several research questions will be addressed, including choosing suitable algorithms to build up a library, intra- and inter-swarm communication (requirements to join and leave a swarm, data abstraction/fusion/aggregation between layers, requirements to produce a 5G network application), applying scenario-specific swarm intelligence algorithms, and extending swarm approaches with human-in-the-loop concepts.CPSwarm - Swarms of Cyber-Physical Systems
The project aims at defining a complete tool chain that enables the designer to: Set-up collaborative, autonomous CPSs; Test the swarm performance with respect to the design goal; and Massively deploy solutions towards “reconfigurable” CPS devices.Model-centric design and predictive engineering are the pillars of the project, enabling definition, composition, verification and simulation of collaborative, autonomous CPS while accounting for various dynamics, constraints and for safety, performance and cost efficiency issues.EM2APS - Enhanced Materials, Methods & Applications for Power Devises & Systems
Im Projekt EM2APS wird eine Belastungsmethodik für leistungselektronische Systeme und Applikationen entwickelt.MONERGY - ICT solutions for energy saving in smart homes
Increased energy efficiency and savings fundamental goals to contribute to the Sustainable Growth that is specified by the “Europe 2020 strategy. A common thought is that energy saving is achievable by making the consumers aware of the energy consumption of their household appliances. Most people don’t even have an idea of how electricity is generated or how it gets into their homes. In this respect, a complete solution for monitoring and controlling the household appliances and devices is of great importance. MONERGY will address these issues carrying out fundamental research about home-automation and developing concrete solutions for the increase of energy efficiency in the Friuli-Venezia-Giulian and Carinthian homes.Smart Microgrid Lab Project
The transformation from centralized to distributed energy resources brings new challenges for metering, pricing, communication, and distribution. We strive to optimize the combination of power networks and communication networks (so called smart microgrids) by self-organizing algorithms and mechanisms. An example is the intelligent integration of the behavior of all users (generators and consumers) of an electricity grid to optimize the operation of the system, e.g. by balancing energy consumption based on availability. This goal can only be achieved if an appropriate know-how is established and a large number of well-trained engineers that have experience in the area of smart electric grids become available. It is the objective of this project to contribute to the establishment of such know-how and to provide an experimental environment where motivated students can learn and gain practical experience in the domain of smart microgrids at Lakeside Labs.REL4POWER - Research on Power Technology Reliability
The project “REL4POWER”, funded by FFG and KWF, researches power technology reliability with focus on stress conditions and failure modes of advanced power semiconductor technologies as well as on their automotive and industrial applications and related reliability issues. Project parters are KAI Kompetenzzentrum Automobil- und Industrieelektronik GmbH together with Infineon Technologies Austria and scientific partners from Austrian universities and institutes.Evolutionary Design of Self-organizing Embedded Systems (EVOSOS)
The trend toward pervasive computing and embedded networked systems leads to an increased complexity and dynamics of technical systems. Many current embedded systems suffer already from this complexity issue, which results in increased maintenance costs and the need of frequent firmware updates after deployment. Future systems are expected to be even more complex, which requires to research new ways to handle complex embedded systems. One approach to solve this problem is to increase the level of self-organization in networked systems.
Self-organizing systems (SOS) usually consist of a large number of autonomous components, which interact with each other and also with their environment. These interactions are guided by internal rules presenting the agents’ behaviour, which allows them to work in a completely decentralized way and also makes them highly adaptable to external effects. Although self-organizing systems offer numerous advantages over traditional ones like robustness against a failure of a component and scalability, due to the distributed structure there is no straightforward way to design such a system.
This project targets the three key issues for developing self-organizing embedded systems:
- Identification of system properties and requirements necessitating the application of SOS structure.
- Investigation of possible design methods based on automated parameter search using evolutionary computing.
- The problem of verification and trust in such evolved systems.
This project is funded by the Österreichische Forschungsförderungsgesellschaft (FFG).
Modeling and Engineering of Self-Organizing Networks 
The MESON project builds on the results from the DEMESOS project and aims at integrating promising methods such as genetic algorithms with neural networks for the design of self-organizing systems. Consecutively, an optimization tool based on an evolutionary algorithm applied to simulation-based validation will be provided. Furthermore, we will elaborate case studies showing how the approach can be applied in different domains.
The project tackles the areas of complex systems, bio-inspired systems, software engineering and robotics.
This project is funded by the European Regional Development Fund and the Carinthian Economic Promotion Fund (KWF) under grant KWF 20214|21532|32604 within the Lakeside Labs activity.
→ http://meson.lakeside-labs.com
→ Project publications (open access)
Design Methods for Self-Organizing System (DEMESOS)
The behavior of a self-organizing system (SOS) is typically defined by the local interaction rules of the components.
While this emergent behavior typically is very flexible, i.e., working at different scales being robust against disturbances and failures, there exists no straight-forward way for the design of these rules so that the overall system shows the desired properties.
The try and error methods, even when being improved using notions such as the "friction" between two components often suffer from counter-intuitive interrelationships between local rules and emergent behavior. Imitation approaches, such as the bio-inspired methods or the programming of the local behavior by analyzing an example using perfect knowledge are limited to the cases where an appropriate example model is available.
The goal of this project is to investigate on novel generic approaches for designing self-organizing systems.
The goal of this research activity is to elaborate basic concepts for a straightforward generic design process for creating self-organizing solutions, consisting of the stages modeling, simulation and iteration, validation, re-iteration or deployment.
This project is funded by the European Regional Development Fund and the Carinthian Economic Promotion Fund (KWF) under grant KWF 20214|18128|26673 within the Lakeside Labs activity.
Video introduction to DEMESOS:
→ Project publications (open access)
Time-Triggered Communication Architecture for an Autonomous Mobile Robot System (TTCAR)
An autonomous mobile robot requires the integration of a set of sensors, actuators, and a control system. In contrast to monolithic designs with a central processor, we focus on a distributed system for the sake of parallel processing, complexity reduction, reuse of components, maintainability, and the flexibility to change the set-up of an existing robot according to its actual task. To achieve these goals, it is necessary to precisely define a communication architecture fulfilling the following requirements: (i) comprehensibility -- in order to support users in the application of the system and to reduce faults induced by human error, (ii) real-time communication -- since the instrumentation of sensors and actuators of a mobile robot is a hard real-time problem, (iii) flexibility in implementation -- since the nodes of the system may be built using different processors of different performance, (iv) support for computer-aided set-up and configuration, (v) support for diagnosis and maintenance. The objective of this project is to develop a generic communication system for mobile robots that supports the interconnection of a set of distributed sensors, actuators, data processing and control nodes. The system will be based upon a time-triggered architecture and implemented for the Tinyphoon robot platform as a case study.
→ TTCAR Publications (most papers are open access)
Configuration and Maintenance of the TTP/A Fieldbus (CoMa)
The focus of the CoMa project is to elaborate concepts and methods for the configuration and maintenance of the time-triggered fieldbus system TTP/A.
The requirement for configuration support can be justified by three arguments: First, an automatic or semi-automatic configuration saves time and therefore leads to better maintainability and lower costs. Second, the necessary qualification of the person who sets up the system is lower when the overall system is easier configured. Third, the number of configuration faults will decrease, since monotone and error-prone tasks like looking up configuration parameters in heavy manuals are done by the computer.
A fully automatic configuration will in most cases only be possible if the functionality of the system is reduced to a manageable subset. For more complex applications consulting a human mind is inavoidable. Thus, we distinguish two use cases, the automatic set-up of simple subsystems and the computer-supported configuration of large distributed systems.
Furthermore, developers expect diagnostic services, which are deterministic, reproducible, and do not interfere with realtime services.
The CoMa project was funded by the Hochschuljubiläumsstiftung der Stadt Wien as project number H-965/2002.