A selection of the chair's projects

This list shows the currently running and typically publically funded projects of our chair. These projects are typically carried out in cooperation with other research institutes and companies.

Model-based Analysis of Next-Generation Networks

ModANet covers various methods for performance analysis, e.g. resource-based models, models based on Network Calculus, and simulations. A framework for model evaluationis created, which allows for automated determination of the quality and scope of models. Calibration and evaluation of the analyzed models use machine learning techniques.

Artificial Intelligence for Performance

AI4Performance covers the analysis, modeling and evaluation of software network solutions, by proposing a new methodology for performance analysis and an experimental platform for the data collection, model validation and deployment of new network architectures. The project focuses on different levels of the packet processing stack.

Vertrauenswürdige IT für autonomes Fahren (Trustworthy IT for Autonomous Driving)

The vehicle of the future is a internally and externally highly networked computer system. Based on a plethora of sensor data, which are evaluated by complex algorithms, the car is able to temporarily take corrective actions or to drive autonomously for a longer period of time. The safety of an autonomous car now depends on the trustworthiness of the data collected by sensors. The protection of this sensor data is the aim of the VITAF project.

Measurements for Composable Performance Models of Cyber-Physical Network Components

The Moonshine project aims for a measurement-based approach towards composable models for cyber-pysical networked systems (CPNs), considering different wireless technologies and software stacks while employing modelling techniques such as stochastic network calculus.

Decentralized Anomaly Detection

Today's IT systems used by corporations a caracterized by a steadily growing number of computers and other devices. Furthermore, virtually all devices are connected via networks. Lastly, the complexity of dependencies between computers and services is growing. The named reasons make it difficult to understand, protect and maintain the functionality of computer networks already today.

Automatisiertes Performance-Monitoring

The AutoMon project studies and develops processes to provide cross-layer correlation of network monitoring data in enterprise networks. This allows to detect outages and disruptions in a timely fashion and identify their root causes. To this end the developed system executes automated and visually comprehensible outage analysis. The integrated business intelligence solution provides data for organizational planning and decision making.

Cost Action on Resilient Communication Services Protecting End-user Applications from Disaster-based Failures

Cost Action on Resilient Communication Services Protecting End-user Applications from Disaster-based Failures

TUM Secure Email and User Certification

Earlier Projects