Refine
Year of publication
Document Type
- Article (10)
- Conference Proceeding (7)
- Book (1)
- Part of a Book (1)
Has Fulltext
- yes (19)
Is part of the Bibliography
- no (19)
Keywords
Institute
Ein sehr großer Anteil der in Rechensystemen auftretenden Fehler ereignet sich im Speicher. In dieser Arbeit wird ein zerlegungsorientiertes Modell entwickelt, das die Wechselwirkungen zwischen Speicherfehlern und Systemleistung untersucht. Zunächst wird das Speicherverhalten eines Auftrags durch ein mehrphasiges Independent-Reference-Modell charakterisiert. Dies dient als Grundlage eines Modells zum Auftreten von Störungen, in das Lastcharakteristika wie die Auftrags-Verweildauer, die Seitenzugriffs-Rate und die Paging-Rate eingehen. Anschließend kann die Wahrscheinlichkeit, mit der ein Speicherfehler entdeckt wird, berechnet werden. Die zur Behandlung von Speicherfehlern erforderlichen Maßnahmen bestimmen die mittlere durch Fehler induzierte Last. Die Wechselwirkungen zwischen Fehler- und Leistungsverhalten werden durch ein System nichtlinearer Gleichung beschrieben, für dessen Lösung ein iteratives Verfahren abgeleitet wird. Abschließend wird mit ausführlichen Beispielen das Modell erläutert und der Einfluß einiger Modell-Parameter auf Leistungs- und Zuverlässigkeitskenngrößen untersucht.
Das Kapitel (aus dem Buch "Mikrorechner-Systeme : Mikroprozessoren, Speicher, Peripherie", siehe Quelle) behandelt verschiedene Konzepte der Speicherverwaltung und stellt Bausteine vor, die diese Verwaltung hardwaremäßig durchführen. Außerdem werden verschiedene Maßnahmen zur Hardware-Unterstützung von Mikroprozessor-Betriebssystemen beschrieben.
In this article, we present the software architecture of a new generation of advisory systems using Intelligent Agent and Semantic Web technologies. Multi-agent systems provide a well-suited paradigm to implement negotiation processes in a consultancy situation. Software agents act as clients and advisors, using their knowledge to assist human users. In the presented architecture, the domain knowledge is modeled semantically by means of XML-based ontology languages such as OWL. Using an inference engine, the agents reason, based on their knowledge to make decisions or proposals. The agent knowledge consists of different types of data: on the one hand, private data, which has to be protected against unauthorized access; and on the other hand, publicly accessible knowledge spread over different Web sites. As in a real consultancy, an agent only reveals sensitive private data, if they are indispensable for finding a solution. In addition, depending on the actual consultancy situation, each agent dynamically expands its knowledge base by accessing OWL knowledge sources from the Internet. Due to the standardization of OWL, knowledge models easily can be shared and accessed via the Internet. The usefulness of our approach is proved by the implementation of an advisory system in the Semantic E-learning Agent (SEA) project, whose objective is to develop virtual student advisers that render support to university students in order to successfully organize and perform their studies.
Decision support systems for traffic management systems have to cope with a high volume of events continuously generated by sensors. Conventional software architectures do not explicitly target the efficient processing of continuous event streams. Recently, event-driven architectures (EDA) have been proposed as a new paradigm for event-based applications. In this paper we propose a reference architecture for event-driven traffic management systems, which enables the analysis and processing of complex event streams in real-time and is therefore well-suited for decision support in sensor-based traffic control sys- tems. We will illustrate our approach in the domain of road traffic management. In particular, we will report on the redesign of an intelligent transportation management system (ITMS) prototype for the high-capacity road network in Bilbao, Spain.
In service-oriented architectures the management of services is a crucial task during all stages of IT operations. Based on a case study performed for a group of finance companies the different aspects of service management are presented. First, the paper discusses how services must be described for management purposes. In particular, a special emphasis is placed on the integration of legacy/non web services. Secondly, the service lifecycle that underlies service management is presented. Especially, the relation to SOA governance and an appropriate tool support by registry repositories is outlined.
In recent years, multiple efforts for reducing energy usage have been proposed. Especially buildings offer high potentials for energy savings. In this paper, we present a novel approach for intelligent energy control that combines a simple infrastructure using low cost sensors with the reasoning capabilities of Complex Event Processing. The key issues of the approach are a sophisticated semantic domain model and a multi-staged event processing architecture leading to an intelligent, situation-aware energy management system.
In huge warehouses or stockrooms, it is often very difficult to find a certain item, because it has been misplaced and is therefore not at its assumed position. This position paper presents an approach on how to coordinate mobile RFID agents using a blackboard architecture based on Complex Event Processing.
Complex Event Processing (CEP) has been established as a well-suited software technology for processing high-frequent data streams. However, intelligent stream based systems must integrate stream data with semantical background knowledge. In this work, we investigate different approaches on integrating stream data and semantic domain knowledge. In particular, we discuss from a software engineering per- spective two different architectures: an approach adding an ontology access mechanism to a common Continuous Query Language (CQL) is compared with C-SPARQL, a streaming extension of the RDF query language SPARQL.
M2M (machine-to-machine) systems use various communication technologies for automatically monitoring and controlling machines. In M2M systems, each machine emits a continuous stream of data records, which must be analyzed in real-time. Intelligent M2M systems should be able to diagnose their actual states and to trigger appropriate actions as soon as critical situations occur. In this paper, we show how complex event processing (CEP) can be used as the key technology for intelligent M2M systems. We provide an event-driven architecture that is adapted to the M2M domain. In particular, we define different models for the M2M domain, M2M machine states and M2M events. Furthermore, we present a general reference architecture defining the main stages of processing machine data. To prove the usefulness of our approach, we consider two real-world examples ‘solar power plants’ and ‘printers’, which show how easily the general architecture can be extended to concrete M2M scenarios.
Smart Cities require reliable means for managing installations that offer essential services to the citizens. In this paper we focus on the problem of evacuation of smart buildings in case of emergencies. In particular, we present an abstract architecture for situation-aware evacuation guidance systems in smart buildings, describe its key modules in detail, and provide some concrete examples of its structure and dynamics.