The con uence of computers, communications and databases is quickly creating a global virtual database where many applications require real-time access to both temporally accurate and multimedia data. We are developing a global virtual database, called BeeHive, which is enterprise speci c and o ers features along real-time, fault tolerance, quality of service for audio and video, and security dimensions. Support of all these features and tradeo s between them will provide signi cant improvement in performance and functionality over browsers, browsers connected to databases, and, in general, today's distributed databases. We present a high level design for BeeHive andvarious novel component technologies that are to be incorporated into BeeHive.

Due to the high number of sensors managed and need to perform complex reasoning activities, real-time control systems of autonomous robots exhibit a high potential for overload, i.e., real-time tasks missing their deadlines. In these systems overload should be regarded as a likely occurrence and hence managed accordingly. In this paper we illustrate a novel scheduling technique for adaptation of soft real-time load to available computational capacity in the context of autonomous robot control architectures. The technique is based on rate modulation of a set of periodic tasks in a range of admissible rates. The technique is shown to be easily computable and several variations in implementation are reviewed within the paper. 1 Introduction Robot control systems have always relied upon realtime operation for their safe, deterministic behavior and smooth trajectory control. However, in the majority of traditional robot control systems real-time constraints have been enforced by means of...

This paper presents an architectural framework and algorithms for engineering dynamic realtime distributed systems using commercial off-the-shelf technologies. In the proposed architecture, a real-time system application is developed in a general-purpose programming language. Further, the architectural-level description of the system such as composition and interconnections of application software and hardware, and the operational requirements of the system such as timeliness and survivability are specified in a system description language. The specification of the system is automatically translated into an intermediate representation (IR) that models the system in a platform-independent manner. The IR is augmented with dynamic measurements of the system by a language run-time system to produce a dynamic system model. The dynamic model is used by resource management middleware strategies to perform resource management that achieves the timeliness and survivability requirements. The mid...

Most of today's commercial Real-Time Operating Systems (RTOSs) offer multiple scheduling policies which are applied on a per-process basis. The best illustrations of this are the Posix1003.1b compliant OSs that provide two real-time scheduling policies, namely sched_fifo and sched_rr, which under some limited hypotheses are respectively the equivalent of Fixed Priority Pre-emptive (FPP) and Round-Robin (RR). In the field of processor scheduling, schedulability analysis has been extensively studied and the problem of assessing the schedulability of multi-policy systems has been recently addressed in [38]. When FPP and RR are used in conjunction, no optimal priority/policy assignement, such as Audsley's algorithm for FPP [3], is known, a fortiori when other criteria besides feasibility are considered. Because of the size of the solution space, an exhaustive search is not possible; an optimisation technique is required. A schedulability analysis provides valuable help for the application designer but it simply asserts whether a given configuration is feasible or not, in general it does not propose any feasible configurations (1) and, as stated by Gerber and Hong in [23] "it can rarely help to tune the system (2), which is the inevitable next step". To address problems (1) and (2), we propose in this study an approach using a Genetic Algorithm (GA) to best set task priorities and scheduling policies, according to a chosen criterion, on Posix 1003.1b uniprocessor systems. Moreover, it will be shown in this study that the use of RR, in conjunction with FPP, may improve the schedulability as well as the satisfaction of additional application-dependent criteria.

ABSTRACT: We introduce Embedded CD++ (eCD++), an engine that can execute DEVS models in embedded environments. It deploys a Flat Coordinator and the GGAD Graphical Modeling tool, which supports the Parallel DEVS formalism. Its real-time extensions allow users to develop hardware-in-the-loop applications with ease, being able to integrate them in DEVS-based environments. 1.

Static scheduling of tasks in embedded distributed real-time systems often implies a tediuos iterative design process. The reason for this is the lack of exibility and expressive power in existing scheduling frameworks, which makes it di cult to both model the system accurately and provide correct optimization guidelines in a rst attempt. The most detrimental e ect this has on the scheduling process is that the real-time tasks are over-constrained due to a careless use of rules-of-thumb. We have developed a scheduling framework based on constraint programming which attempts to tackle these de ciencies. First, the framework allows for expressing the scheduling problem in terms much closer to the actual system requirements. This is because of the support provided by the framework for modeling constraints that are usually not handled by existing scheduling tools, for example, di erent types of task allocation constraints such as clustering and proximity to resources. A second strong feature of the framework is that it supports di erent strategies for single- and multi-objective optimization, something that is very important in the design of embedded real-time systems. An evaluation study encompassing a set of applications with typical embedded system constraints suggests that our approach does in fact provide the salient features necessary. 1

Posix1003.1b compliant operating systems provide two real-time scheduling policies, namely sched_fo and sched_rr, which under some limited hypotheses are respectively the equivalent of Fixed Priority Pre-emptive (FPP) and RoundRobin (RR). In the eld of processor scheduling, schedulability analysis has been extensively studied and the problem of assessing the schedulability of multi-policy systems has been recently addressed. A schedulability analysis provides valuable help for the application designer but it simply asserts whether a given conguration is feasible or not, in general it does not propose any feasible congurations (1) and, as stated by Gerber and Hong "it can rarely help to tune the system (2), which is the inevitable next step". To address problems (1) and (2), we propose in this study an approach using a Genetic Algorithm (GA) to best set task priorities and scheduling policies, according to a chosen criterion, on Posix 1003.1b uniprocessor systems. Moreover, it will be shown that the use of RR, in conjunction with FPP, may improve the schedulability as well as the satisfaction of additional applicationdependant criteria.

Les cartes à puces ont évolué vers le concept de cartes ouvertes. Ce sont des cartes où l'on peut charger des applications après qu'elles aient été émises (distribuées à leur porteur). De nombreux travaux ont consisté à sécuriser le code mobile qui pouvait être chargé dans la carte afin d'assurer l'intégrité et la confidentialité des données. Cependant, établir des garanties plus larges comme le contrôle des ressources ou le temps réel reste une question ouverte. Nous étudions ici les concepts de qualité de service (disponibilité, déni de service) liés aux systèmes extensibles dans le domaine de la carte à puces.

The WWW is a new advertising media in recent years where corporations utilize it to increase their exposure to consumers. For a very large website whose content is derived from some source database, it is important to maintain its freshness in response to changes to the base data. This issue is particularly signicant for websites presenting fast changing information such as stock exchange information and product information. In this paper, we formally dene and study the freshness of a website that is refreshed by scheduling a set of queries to fetch fresh data from the databases. Then, we propose several online scheduling algorithms and compare the performance of the algorithms on the freshness metric. Our conclusion is veried by empirical results. Keywords: Internet Data Management, View Maintenance, Query Optimization, Hard Real-Time Scheduling 1 Introduction The popularity of the World-Wide Web (WWW) has made it a prime vehicle for disseminating information. More and ...

. As websites grow large and become more sophisticated, organizations use structured database systems as a source of base data for information on the website. Thus, it has become critical to keep a very large website up-to-date in response to the frequent changes in base data. This gives rise to an important issue: Can a website be timely refreshed by executing a set of queries against the base data? In this paper, we investigate the feasibility of scheduling a set of queries to refresh a very large website. Based on two types (tight and loose) of feasibility requirements, we present feasibility results when the base data change with uniform, regular and random periods. We found that tight feasibility depends on the interval length between two consecutively raised cell refresh requests while it is NP-Hard to determine loose feasibility when the base data have regular or random update periods. For the case when the base data have the uniform update periods, loose feasibilit...