Researchers in the biological and health industries need powerful and stable systems for their work. These systems must be dependable, fault-tolerant, highly available and easy to use. To cope with these demands we propose the use of computational and data clusters in a fail-over configuration combined with the grid technology and job scheduling. Our infrastructure has been deployed successfull...

We present a unified notation that captures many common models of deliberation for a resourcebounded agent in a time-critical environment. We analyze a greedy time-slicing meta-deliberation procedure within our framework, the same procedure that forms the basis of many diverse metadeliberation algorithms. The procedure is computationally efficient, and our analysis makes explicit the domains ov...

Human errors in aviation, process plants and other critical industries can result in dire consequences and hence it is essential to understand the operator behavior and task characteristics in order to improve task performance and safety. The time available and how it is used by the operator are important factors in multi-task situations. Polychrons are people, who favor doing multiple tasks at...

Many real-time systems have timing requirements that are diicult to fulll if the system is implemented b y software running on a microprocessor. One way to remedy this problem is to implement the most time-critical parts in application-speciic integrated circuits instead. Hardwareesoftware codesign aims at providing support for the designer of such a heterogeneously implemented system, and espe...

— We are interested in communication support for time-critical reliable computing. Over a two-decade period, the distributed computing community has explored a number of reliable communication models. Yet time-critical applications in which rapid response matters more than absolute reliability have received comparatively little attention. We believe that this category of application is becoming...

Modern information dissemination services can dynamically produce real-time data that is valid and useful depending on users’ on-demand data requests. Information servers must adopt a scheduling approach to maintain timely data access and system performance. Most previous studies on scheduling such data discuss on-demand data broadcasting and real-time task processing with various performance m...

Medium Access Control protocols for high speed LAN/MANs often employ a timer-controlled token passing mechanism to control station access to the shared media. These protocols support time-critical (real-time) applications, and provide priority among non time-critical applications. This paper considers the stability of systems with several target token rotation times. It shows that there do not ...

Ethernet is still gaining ground although it has been around for more than 30 years. With Ethernet being used as a universal network solution in office and web applications, production facilities, safety-critical systems, airplanes and automobiles, it has a big potential for cost savings in all areas. Engineering, maintenance and training costs are considerably lower than those for many proprie...

Anytime algorithms offer a tradeoff between solution quality and computation time that has proved useful in applying artificial intelligence techniques to time-critical problems. To exploit this tradeoff, a system must be able to determine the best time to stop deliberation and act on the currently available solution. When the rate of improvement of solution quality is uncertain, monitoring the...