Scientific publications

Architectural stress is the inability of a system design to respond to new market demands. It is an important yet often concealed issue in high tech systems. In From scientific instrument to industrial machine, we look at the phenomenon of architectural stress in embedded systems in the context of a transmission electron microscope system built by FEI Company.

The inherently unreliable communication infrastructure compel WSN protocols to employ error control mechanisms. Traditionally, error control is achieved by a retransmission scheme using acknowledgment mechanisms. WSN architectures are severely resource constrained and the additional energy expense of transmitting error control messages can seriously degrade network lifetime.

Wireless Body Area Networks (WBANs) have characteristic properties that should be considered for designing a proper network architecture. Movement of on-body sensors, low quality and time-variant wireless links, and the demand for a reliable and fast data transmission at low energy cost are some challenging issues in WBANs.

Warehouses play a critical role in supply chains: they are responsible for the distribution of goods of many suppliers to many customers. Because of increasing customer demands, warehouse processes are becoming too complex to be controlled optimally by their traditional centralised control systems. Several results in the literature show that decentralised controllers are a viable alternative.

Peer-to-peer botnets, as exemplified by the Storm Worm, and the spreading phase of Stuxnet, are a relatively new threat to security on the internet: infected computers automatically search for other computers to be infected, thus spreading the infection rapidly. In a recent paper, such botnets have been modeled using Stochastic Activity Networks, allowing the use of discrete-event simulation to judge strategies for combating their spread.

The quality of the communication links in a Wireless Sensor Network often shows significant asymmetry and variation over time, due to, for example, heterogeneous settings of the transmission power, moving nodes or chang- ing external interference. This makes it difficult for nodes to accurately maintain system-level properties, such as the minimum-energy path from the node to a given reference node, as required by many protocols.

In many applications of Wireless Sensor Networks (WSNs), heterogeneity is a common property in terms of different sensor types and different circumstances like node location, link quality, and local node density. In many applications, there are several different sensor types with entirely different Quality-ofService (QoS) requirements.

Synthesizing an implementation from a model in a predictable way is one of the major challenges in real-time systemdesign. In our previous work we addressed this problem by generating in real-time an execution path through a modeland by synchronizing the model time with the physical time. The execution path as observed in model time has a timedifference with the execution path as observed in physical time.

In this short paper I will address the question whether the methods and techniques we develop are applied well in industrial practice. To address this question, I will make a few observations from the academic field, as well as from industrial practice. This will be followed by a concise analysis of the cause of the perceived gap between the academic state-of-the-art and industrial practice.

The ever increasing performance gap between processors and memories is one of the biggest performance bottlenecks for computer systems. In this paper, we propose a task scheduling technique that schedules an application, modeled with a task graph, on a multiprocessor system-onchip (MPSoC) that contains a limited on-chip memory.