Jörg Nolte

Brandenburgische Technische Universität Cottbus, Kottbus, Brandenburg, Germany

Are you Jörg Nolte?

Claim your profile

Publications (22)0.62 Total impact

  • [Show abstract] [Hide abstract]
    ABSTRACT: Currently, new storage technologies which unite the latency and byte-addressability of DRAM with the persistence of disks are being developed. This non-volatile memory (NV-RAM) may start a software revolution. Traditionally, software was developed for two levels of storage and NVRAM reduces the hierarchy to a single-level store. Current research projects are already exploring the potential of NVRAM, but they face a challenge when they want to evaluate the performance: The new hardware is not yet available. In this paper, we discuss why benchmark results which are gained on existing DRAM are insufficient for a prediction of the performance on NVRAM. Either existing instructions have to be changed or new ones have to be introduced. We further show that the bochs emulator can be used to build systems which resemble NVRAM, to predict the NVRAM’s consequences, and it even allows a comparison of algorithms for NVRAM.
    Seventh International Conference on Simulation Tools and Techniques; 01/2014
  • [Show abstract] [Hide abstract]
    ABSTRACT: Experiments with wireless sensor networks have shown that asymmetric and unidirectional links are common. For this reason, we developed different routing protocols that can use unidirectional links, either implicitly or explicitly. However, developing protocols that use unidirectional links is difficult, not least because of inadequate simulation support. In this paper we present a simulation model based on OMNeT++ and MiXiM that we developed to simulate networks with unidirectional links and frequent link changes. We evaluate the developed simulation approach by comparison of results achieved by different routing protocols in simulation and in experiments with real sensor network hardware.
    Seventh International Conference on Simulation Tools and Techniques; 01/2014
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: A lot of applications for wireless sensor networks have been proposed in the last years. Only a few of them have led to real, non-academic deployments, partially due to the differences between end user needs and academic assumptions. In this paper we discuss a real world problem arising from an ecological question (protection of an endangered species) and the theoretical solution as well as the deployed solution that actually works.
    IEEE 36th Conference on Local Computer Networks, LCN 2011, Bonn, Germany, October 4-7, 2011; 01/2011
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Communication neighborhood in wireless sensor networks changes often as links break or appear. Therefore, monitoring link quality and (logical) network topology is necessary. As node placement has a large influence on the radio neighborhood and its changes, different positions should be evaluated before starting the actual application. In this paper we introduce Sensorium, an active monitoring system that supplies the user with an insight into the neighborhood relations between nodes and their changes in time. It can be used before the actual deployment to evaluate different possibilities of node placement and choose the one that offers the best connectivity.
    Ad Hoc Networks - Second International Conference, ADHOCNETS 2010, Victoria, BC, Canada, August 18-20, 2010, Revised Selected Papers; 01/2010
  • [Show abstract] [Hide abstract]
    ABSTRACT: Energy consumption is a crucial factor for the lifetime of many embedded systems, especially wireless sensor networks. Most modern microcontrollers provide various low power sleep modes. Utilizing them can lead to great energy savings. In this paper we present an approach for power management in embedded systems, based on the event-driven operating system Reflex. The implicit power management is mostly hardware independent, lightweight and efficiently chooses the optimal power saving mode of the microprocessor automatically.
    Wired/Wireless Internet Communications, 7th International Conference, WWIC 2009, Enschede, The Netherlands, May 27-29, 2009. Proceedings; 01/2009
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Wireless sensor networks operate in an unstable envi-ronment and thus are subject to arbitrary transient faults. Self-stabilization is a promising technique to add tolerance against transient faults in a self-contained non-masking way. A core factor for the applicability of a given self-stabilizing algorithm is its convergence time. This paper analyses the average stabilization time of three algorithms commonly regarded as central building blocks for wireless sensor networks. The analysis is accomplished with Self-WISE, a framework providing programming abstractions for self-stabilizing algorithms. The performed analysis con-siders the target models as well as network size and density. This demonstrates the usability of SelfWISE for evaluating self-stabilizing algorithms under a wide range of models.
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Experiments with wireless sensor networks have shown that unidirectional communication links are quite common. What is even more, they have also shown that the range of a unidirectional link can exceed that of a bidirectional one by far. Still, most of todays routing protocols do not use them, they only eliminate their implications. Those protocols that do use unidirectional links introduce a lot of protocol over- head. In this paper we present Buckshot Routing, a robust, yet simple source routing protocol for dense wireless networks with lossy or unidi- rectional links, which reduces the overhead generated by route discovery and route maintenance signicantly.
    Ad Hoc Networks, First International Conference, ADHOCNETS 2009, Niagara Falls, Ontario, Canada, September 22-25, 2009. Revised Selected Papers; 01/2009
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Developing wireless sensor network (WSN) applications is a challenging task. Simulations are a key component in the development process, since they oer simple means of testing and evaluating the applications without the need of time consuming and tedious deployment. But simulations alone are not sucient to evaluate such applications. Only experiments on real hardware can ultimately verify the cor- rectness of a given algorithm and its implementation. To take the most benet from a WSN simulator it must be able to simulate a sensor network, where all nodes run the same implementation of the algorithm that will later be deployed. We show how to integrate event-driven operating systems into the OMNeT++ discrete event simulator. At the ex- ample of Reflex we show how an integration can be easily achieved with minor eort. Additionally we discuss an alter- native approach which promises better scalability but comes at the cost of less exibility at the application layer and re- quires more deeply intrusions into the operating system. We argue that the integration is feasible and that it yields a sim- ulation tool, which can perform similar to other tools like TOSSIM or COOJA but benets notably from the exibility of OMNeT++ and its cornucopia of readily available models provided by the community.
    Proceedings of the 2nd International Conference on Simulation Tools and Techniques for Communications, Networks and Systems, SimuTools 2009, Rome, Italy, March 2-6, 2009; 01/2009
  • Source
    Andreas Lagemann, Jörg Nolte
    [Show abstract] [Hide abstract]
    ABSTRACT: Simulation normally serves one of two purposes. The rst one is evaluation of certain algorithms. The second one is development and test of applications with infrastructural requirements which exceed those commonly available (e.g. distributed applications for wireless networks). In the latter case it is highly desirable that the code used for simulation can be easily adopted to real hardware with minor modi- cations. The .NET framework is { like Java { platform independent insofar as it only depends on a virtual machine implementation for each device it is meant to run on. There- fore for some application elds it is attractive to be able to write plain C# code which can then be run with a simulator like OMNeT++. This paper introduces CsharpSimpleModule, an extension to OMNeT++, which { like its companion JSimpleModule does for Java { allows you to write OMNeT++ simula- tion modules in C# and mix them freely with plain OM- NeT++ modules, thus allowing you to build upon existing OMNeT++ frameworks (e.g INET or MobilityFramework). Besides giving a short introduction to the usage of Csharp- SimpleModule its general architecture will be illustrated and selected implementation issues will be discussed.
    Proceedings of the 1st International Conference on Simulation Tools and Techniques for Communications, Networks and Systems & Workshops, SimuTools 2008, Marseille, France, March 3-7, 2008; 01/2008
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: typically cheap devices offering low bandwidth communication only. When physical events in the real world trigger spontaneous communication in many nodes the single communication channel is under heavy load and many messages are lost due to collisions. CSMA/CA schemes are well suited to spontaneous communica- tion, but do not provide a high channel utilization under heavy load. TDMA protocols have some conceptual advantage here, but in the case of mobile sensor nodes they need to be adaptive and establish TDMA schedules on demand. MLMAC is a novel TDMA based MAC protocol that can react on changing radio neighborhoods in mobile networks. In this paper we introduce the MLMAC protocol and present the results of real experiments with a group of mobile sensor nodes based on RCX robots.
    Sensor Technologies and Applications, 2007. SensorComm 2007. International Conference on; 11/2007
  • Proceedings of the 2007 ACM SIGPLAN/SIGBED Conference on Languages, Compilers, and Tools for Embedded Systems (LCTES'07), San Diego, California, USA, June 13-15, 2007; 07/2007
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: For economic reasons sensor networks are often implemented with resource constrained micro-controllers and low-end radio transceivers. Consequently, communication is inherently unreliable and especially multi-hop communication suffers severely from packet losses. Transmission protocols that rely on implicit acknowledges for multi-hop communication are energy efficient but require symmetric communication links to work properly. In this paper we introduce IMPACT, a family of transmission protocols that rely on implicit acknowledges and employ a cross layer approach to handle asymmetric links.
    Proceedings of the 26th IEEE International Performance Computing and Communications Conference, IPCCC 2007, April 11-13, 2007, New Orleans, Louisiana, USA; 01/2007
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Cocos (COordinated COmmunicating Sensors)1 is a lean middleware platform for wireless sensor and actuator net- works. The major programming abstractions of Cocos are distributed sensor spaces, which enable the collective con- trolling of sensors or actuators on remote nodes. Thus, Co- cos brings high-level data-parallel programming concepts such as global reductions into the world of small networked systems. In this paper we discuss the design rationale of Cocos as well as its in-network processing and aggregation capabilities.
    Proceedings of the First ACM Workshop on Sensor and Actor Networks, SANET 2007, Montréal, Québec, Canada, September 10, 2007; 01/2007
  • Karsten Walther, Jörg Nolte
    [Show abstract] [Hide abstract]
    ABSTRACT: Deeply embedded systems become more and more im- portant in everyday life. As the number of systems increases, the demand for programming platforms, which help with handling non-functional properties like synchronization, grows. Using the event-flow principle for programming leads to implicit synchro- nization for the application programmer's point of view and al- lows efficient explicit synchronization. We show the internals for implicit synchronization and propose efficient mechanisms for synchronization in event-driven systems. The implementation is written for our runtime environment for deeply embedded sys- tems REFLEX (Real-Time Event Flow Executive).
  • Source
    Reinhardt Karnapke, Jörg Nolte
    [Show abstract] [Hide abstract]
    ABSTRACT: Typical sensor nodes are composed of cheap hardware because they have to be affordable in great numbers. This means that memory and communication bandwidth are small, CPUs are slow and energy is limited. It also means that all unnecessary software components must be omitted. Thus it is necessary to use application specific communication protocols. As it is cumbersome to write these from scratch every time a configurable framework is needed. Copra provides such an architectural framework that allows the construction of application specific communication protocol stacks from prefabricated components.
    Euro-Par 2006, Parallel Processing, 12th International Euro-Par Conference, Dresden, Germany, August 28 - September 1, 2006, Proceedings; 01/2006
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Reflex is a generic event driven OS for embedded devices. Event handlers and control functions are all represented by passive ob-jects that are scheduled preemptively according to an earliest deadline first (EDF) strategy. The synchronization of events is based on an event flow model similar to the data flow paradigm. In this paper we will present the design rationale of Reflex and particularly discuss the lan-guage level aspects of our approach.
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: On many-core processors that do not provide hard-ware cache coherence, using shared memory in parallel com-putations is challenging. Reverting to pure message passing would avoid consistency issues, but replicating large shared datasets by messages is less efficient than accessing them di-rectly through shared memory. The TACO-MESH framework provides lightweight remote method calls and shared objects with software-managed consistency. This paper presents experience from porting a graph partitioning algorithm to the framework. A performance evaluation on the experimental Intel SCC pro-cessor, which has no hardware cache coherence, shows that parallelization can be efficient despite the overhead of software-level consistency management.
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Many-core processors combine fast on-chip commu-nication with access to large amounts of shared memory. This makes it possible to exploit the benefits of distributed as well as shared memory programming models within single parallel algorithms. While large amounts of data can be shared in the memory and caches, coordinating the activities of hundreds of cores relies on cross core communication mechanisms with ultra low latency for very small messages. In this paper we discuss two communication protocols for the Intel SCC and compare them to the MPI implementation of the SCC. Our micro-benchmark results underline that special purpose protocols for small messages make much finer levels of parallelism possible than general purpose message passing systems.
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Experiments have shown that unidirectional links are quite common in wireless sensor networks. Still, many MAC protocols ignore their existence, even though they have a tremendous impact on the performance of both TDMA-and contention based protocols. In contention based protocols the medium may be assumed free when it is indeed busy. In TDMA based protocols two neighboring nodes might get assigned the same slot even though there is an unidirectional link between them. In this paper we discuss the influence of unidirectional links on communication protocols in wireless sensor networks, focusing on MAC protocols. We also present two protocols that do not only eliminate the negative side effects of unidirectional links, but use them for message transmission as well.