Matthias Werner

Matthias Werner
Technische Universität Chemnitz · Department of Computer Science

Prof. Dr.-ing. habil.

About

163
Publications
19,943
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
398
Citations
Citations since 2016
31 Research Items
95 Citations
20162017201820192020202120220510152025
20162017201820192020202120220510152025
20162017201820192020202120220510152025
20162017201820192020202120220510152025
Introduction
Matthias Werner currently works at the Department of Computer Science, Chemnitz University of Technology. Matthias does research in Distributed Computing, Operating Systems and non-functional properties such as Reliability, Safety or Security.
Additional affiliations
January 2008 - present
Technische Universität Chemnitz
Position
  • Professor (Full)
September 2002 - December 2007
Technische Universität Berlin
Position
  • Professor (Assistant)
January 1995 - August 2002
Humboldt-Universität zu Berlin
Position
  • Research Assistant
Education
September 1988 - November 1993
Humboldt-Universität zu Berlin
Field of study
  • Electrical Eng.

Publications

Publications (163)
Presentation
Full-text available
The emergence of Cyber-Physical Systems leads to an integration of the digital and physical world through sensors and actuators. Programming such systems is error-prone and complex as a plethora of changing heterogeneous devices is involved. In existing approaches, the developer views the world from the digital point of view. He or she has to impli...
Conference Paper
The emergence of Cyber-Physical Systems leads to an integration of the digital and physical world through sensors and actuators. Programming such systems is error-prone and complex as a plethora of changing heterogeneous devices is involved. In existing approaches, the developer views the world from the digital point of view. He or she has to impli...
Presentation
Full-text available
The presentation explains the categorization derived from the systematic literature review on the simulation of range-limited particle interactions.
Conference Paper
Mobile cyber-physical systems consist of possibly moving heterogeneous execution units, which interact with their environment through sensors and actuators. Programming such systems without taking motion into account has already proven to be error-prone and complex, as challenges like communication or programming multiple different devices have to...
Poster
Full-text available
Task parallelism is omnipresent these days; whether in data mining or machine learning, for matrix factorization or even molecular dynamics. Despite the success of task parallelism on CPUs, there is currently no performant way to exploit task parallelism of synchronization-critical algorithms on GPUs. Hence, our goal is the development of a task-ba...
Conference Paper
Full-text available
During the last years many industry areas started to use microservices. They show advan- tages like scalability, independent service development, and complexity management. Never- theless, from a researcher point of view we observe also drawbacks in using microservices. The aim of this paper is to present some of them to initiate a discussion wheth...
Conference Paper
Full-text available
Der klassische Entwicklungsprozess für Software im Bereich eingebetteter Echtzeitsysteme geht von einem statischen System mit festgelegten Komponenten aus. Die Marktnachfrage führt zu einem Bedarf anstärkerer Dynamik. Dadurch erhöht sich dieKomplexität und es wird wichtiger, den Erhalt von sicherheitskritischen Eigenschaften (safety) durch stringen...
Conference Paper
Linear time-invariant hybrid automata (LTI-HA) have been introduced to model space missions in early design phases. One of LTIHA’s main objectives was therefore to allow a composition of (sub) models. In this paper, we evaluate the expressiveness of the composition in LTI-HA. To compare their expressiveness with the existing hybrid automata formali...
Conference Paper
Full-text available
Future automotive software needs to deal with an increasing level of dynamicity, reasoned by the wish for connected driving, software updates, and dynamic feature activation. Such functionalities cannot be properly realized with today's classic AUTOSAR development approach, since it relies on the static configuration of all software units at build...
Article
Hybrid automata are a well-established modelling approach. The formalism is used in many real-time and control systems engineering projects, which makes model composition an increasingly relevant topic. A well-defined composition support allows concurrent engineering activities and the validation of larger systems. However, many existing publicatio...
Conference Paper
The increasing adoption of virtualization in high-performance computing domain makes it necessary to reduce the performance loss due to virtualization for the workloads. In a single computing node, the loss is mainly incurred by memory virtualization. To take the advantages of virtual memory, page tables are commonly adopted for the mapping from vi...
Conference Paper
Designing a spacecraft is a costly and time-consuming activity. Engineers in this domain therefore rely on model-based analysis and verification methods, which give them feedback about expectable mission parameters already in the early design phases. We present an operational semantics for a customized language for spacecraft design by means of lin...
Chapter
A cyber-physical system (CPS) is a system of collaborating computational elements controlling physical entities. Nowadays cyber-physical systems can be found in areas as diverse as robotics, automotive, chemical processes, civil infrastructure, energy, healthcare, manufacturing, transportation, entertainment, and consumer appliances. In this paper,...
Conference Paper
In the existing abundance of different hybrid automata for- malisms concurrent composition is seldom considered or requires addi- tional semantics which is not always defined. This work considers three common reasons of problems with hybrid automata composition: con- tradicting resets in the discrete transitions, global time reference with contradi...
Conference Paper
Fault tree analysis, as many other dependability evaluation techniques, relies on given knowledge about the system architecture and its configuration. This works sufficiently for a fixed system setup, but becomes difficult with resilient hardware and software that is supposed to be flexible in its runtime configuration. The resulting uncertainty ab...
Conference Paper
In the new era of cyber-physical systems, software must adapt itself to ever-changing environmental conditions and situations. This is currently not reflected in the design of embedded operating systems, since they are primarily optimized for fixed usage scenarios with tight resource constraints. We discuss the idea of interpreted operating system...
Conference Paper
According to the model-based systems engineering paradigm, all engineers contribute to a single centralized data model of the system. The German Aerospace Center (DLR) develops a software tool Virtual Satellite which enables the engineers to store, exchange and alter their corresponding subsystem data on base of a distributed system model and thus...
Presentation
Full-text available
Fault trees are a well-known and widely used method for dependability predictions in engineering sciences. They enable a structured analysis of error propagation chains, which is especially important in safety critical systems. Classical fault trees are based on complete knowledge about the modelled system. This kind of information is available onl...
Conference Paper
Full-text available
In real-world spacecraft systems, concurrent system activities must be constrained for energy efficiency and functional reasons. Such constraints must be considered in the early design phases, in order to avoid costly reiterations and modifications of the proposed system design in later phases. Although some initial attempts for using formal specif...
Conference Paper
In some cases, tasks may be allowed to migrate from one processor to another, e.g., due to hardware failures or for workload balancing. If a mixed-criticality setting is considered, it is necessary to decide whether new tasks with different levels of criticality may be accepted by a processor without compromising the already running tasks. Since th...
Conference Paper
While the future importance of cyber-physical systems is widely acknowledged, there is surprisingly rare discussion about the design of operating systems for these kinds of systems. We present an extended view on the low-level abstractions to be offered by the operating system to applications. The central idea is the treatment of all relevant cyber...
Article
In this paper we investigate Timed Petri nets (TPN) with fixed, possibly zero, durations and maximal step semantics. We define a new state representation where a state is a pair of a marking for the places and a marking for the transitions (a matrix of clocks). For this representation of states we provide an algebraic state equation. Such a state e...
Conference Paper
Full-text available
We present a runtime system for swarms of mobile robots that manages distributed resources and provides a com-mon programming interface for distributed swarm applications. The programming abstraction follows a systemic view and allows to specify the spatial-temporal behavior of applications. The runtime system analyzes application code, creates a d...
Conference Paper
Full-text available
Todays situation is characterized by an increasing pervasiveness of a plethora of mobile devices featuring different capabilities and exhibiting different system interfaces making the handling of these devices and especially the cooperation between different devices a complex task. In this paper, we consider the sum of all these devices as one emer...
Article
We suggest an improvement to the RMST assignment scheme by Burchard et al., a heuristics for finding approximate solutions to the NP-complete problem of MP scheduling of RT tasks.
Conference Paper
The choice of periods in a periodic task set has a significant impact on its utilization bound under Rate-monotonic Scheduling (RMS). It ranges from the Liu/Layland bound [3] in the worst, and thus general, case to the full uniprocessor utilization of 1 in the case of simply periodic (aka harmonic) task sets. First, it is a challenge to exploit per...
Conference Paper
Virtualized runtime environments like Java Virtual Machine (JVM) or Microsoft .NET's Common Language Runtime (CLR) introduce additional challenges to real-time software development. Since applications for such environments are usually deployed in platform independent intermediate code, one issue is the timing of code transformation from intermediat...
Conference Paper
Contrary to the optimal scheduling algorithm Earliest Deadline First (EDF), Rate-Monotonic Scheduling (RMS) can lead to non-schedulable task sets for total utilizations below 1 on a uniprocessor. The quantification of this deficiency has been a topic in real-time science for a long time. We show weaknesses of the scheduling algorithm metrics breakd...
Conference Paper
Software is getting larger and more complex. To simplify programming, languages with automatic memory management are used. In embedded systems the languages C/C++ are commonly used, which do not provide such functionalities. This paper addresses real-time garbage collection for embedded systems. We developed a conservative collector, which supports...
Article
Full-text available
Dealing with cyber-physical systems (CPS) puts a strong emphasis on the interaction between computing and non-computing elements. Since the physical world is characterized by being strongly distributed and concurrent, this is also reflected in the computational world making the design of such systems a challenging task. If a number of tasks shall b...
Conference Paper
Bei der Entwicklung von Anwendungen für Echtzeitsysteme werden höhere Programmiersprachen zunehmend attraktiv, besonders wenn Anwendungen in plattformunabhängigem Zwischencode verteilt werden können. Um einen Einsatz in Echtzeitsystemen zu ermöglichen, müssen die diesen Sprachen unterliegenden Laufzeitumgebungen eine zeitlich deterministische Ausfü...
Article
Full-text available
With the advent of multi-core computer systems, real-time (RT) scheduling on multiprocessors (MPs) is gaining more and more practical relevance. Basic algorithms developed in the 1970s or earlier are strongly influential on state-of-the-art preemptive hard real-time scheduling algorithms. These relationships will be revealed and visualized by four...
Conference Paper
Full-text available
Rate-Monotonic Small-Tasks from 1995 is a well-known algorithm for partitioned rate-monotonic scheduling on a multiprocessor system. While the basic idea of local harmonization of the task set in a sorted list to improve success chances of an allocation strategy is of great value, several improvements/alternatives are possible. A systematic termino...
Conference Paper
Full-text available
Partitioned scheduling algorithms are typically based on Earliest Deadline First (EDF) or Rate-Monotonic Scheduling (RMS). Often, heuristics like First Fit are applied for task allocation to processors. The performance of the heuristics can be improved by sorting tasks in a preprocessing step. While for partitioned EDF, Decreasing Utilization is th...
Conference Paper
Designing cyber-physical systems (CPS) requires consideration of interactions between several computing and non-computing elements and, thus, consideration of concurrency of actions. While concurrency alone is a complexity-introducing and error-prone concept, adding awareness of real time, real space and/or mobility makes things worse: It prohibits...
Conference Paper
Partitioned preemptive EDF scheduling is very similar to bin packing, but there is a subtle difference. Estimating the probability of schedulability under a given total utilization has been studied empirically before. Here, we show an approach for closed-form formulae for the problem, starting with n = 3 tasks on m = 2 processors.
Chapter
How does the concept of action fit within a scientifically serious world-view? This paper argues that the category of action, with its goal-seeking and orientation to the future, is not a human peculiarity, a perplexing incongruity in an otherwise mechanistic world. Rather, actions pervade the whole biological domain. The concept of action is neede...
Conference Paper
Priority-based scheduling branches into static and dynamic priority scheduling. The optimal static priority algorithm is Rate-Monotonic Scheduling (RMS, for the case of implicit deadlines). In the dynamic priority case where priorities are no longer attached to an entire task, Earliest-Deadline First (EDF) and Least-Laxity First (LLF) are optimal a...
Conference Paper
We introduce two abstractions, namely virtual swarms and spatiotemporal constraints, which can help to design applications for distributed systems consisting of mobile nodes. These abstractions create the awareness needed by the application while abstracting from the location and motion of individual nodes. This way, the application can concentrate...
Conference Paper
In this paper, we introduce an object-oriented programming and execution model to support location-aware applications for distributed mobile systems. We simplify application development by abstracting from single devices and concentrating on the collective as set of global system resources. Since in a real-world scenario, we usually have a heteroge...
Conference Paper
Multi-core processors are able to deliver excellent throughput. However, if a multi-core processor is not fully utilized, the achieved performance is below that of a processor of the same technology with less cores: To stay within the same power envelope, the power used by additional transistors of a multi-core processor must be compensated by redu...
Conference Paper
Full-text available
Energy-efficient computing as a research area has been receiving increasing attention in recent years due to rising energy costs and environmental awareness. In this paper, we present an approach to increasing the energy efficiency of modern multi-core computers, which is suitable for scenarios with varying load characteristics often found in priva...
Conference Paper
Bei der Entwicklung hochperformanter Automatisierungslösungen werden höhere Programmiersprachen gegenüber klassischen SPS-Konzepten zunehmend attraktiv. Da es eine Vielzahl von Automatisierungsplattformen gibt, gilt dies insbesondere für plattformunabhängige Sprachen wie Java oder, auf der Common Language Infrastructure (CLI) aufsetzende, Sprachen...
Article
There are two major current trends that can easily be identified in computer industry: (i) the shift towards massively parallelization fostered by multi-core technology resulting in growing numbers of cores per processor and (ii) the increasing importance of energy-awareness in computing due to rising energy costs and environmental awareness. In cu...
Chapter
Dieser Beitrag führt eine Programmierabstraktion für Anwendungen in mobilen verteilten Systemen ein. Anwendungen solcher Systeme werden in realer Raum-Zeit abgearbeitet. Dabei werden nicht nur, wie in konventionellen Echtzeitsystemen üblich, zeitliche Bedingungen berücksichtigt. Es müssen zusätzlich räumliche beziehungsweise bewegungsspezifische An...
Article
Today’s widely used programming approach for mobile distributed systems, e.g., swarms, is bottom-up. I.e., the programmer has to be aware of the system’s distribution. Such a kind of programming corrupts the principle Separation of Concerns and turns out to be complicated. This article proposes a top-down approach for the programming of mobile dist...
Conference Paper
The sharing of a medium for communication between nodes, forming a real network, is much more cost-effective than building a fully connected mesh. Due to the then possible collisions, special techniques have to be applied. Historically, the two main schemes to handle collisions are the time-triggered (TT) and the event-triggered (ET) approach. Whil...
Chapter
This chapter presents the definition of relevant terminology and a conceptual model of the basic terms. The chapter starts with the presentation of research in the area of dependability. Based on this, Web service concepts related to the dependability are introduced. The presentation leads into a statement identifying individual quality-of-service...
Chapter
In our previous work on self-stabilizing content-based routing for publish/subscribe systems, we provided algorithms to realize guaranteed recovery from transient faults. Doing this, we focused on the routing layer and did not explicitly consider the interdependency between the broker overlay topology and the contents of the routing tables. Reconfi...