Abstract

Abstract
This paper evaluates the performance of three popular technologies used to interconnect machines on clusters: Fast Ethernet, Myrinet and Giganet. To achieve this purpose, we used the NAS Parallel Benchmarks. Surprisingly, for the LU application, the performance of Fast Ethernet was better than Myrinet. We also evaluate the performance gains provided by VIA, a user lever communication protocol, when compared with TCP/IP, a traditional, stacked-based communication protocol. The impacts caused by the use of Remote DMA Write are also evaluated. The results show that Fast Ethernet, when combined with a high performance communication protocol, such as VIA, has a good cost-benefit ratio, and can be a good choice to connect machines on a small cluster environment where bandwidth is not crucial for applications.

Abstract
In this paper we present an information system architecture, addressing the needs of an advanced order planning system for industrial networked enterprises environments. Firstly, the general objectives of the system are described focusing on the relevant business processes identified. Then, the related general functionality (business solutions) of a distributed system supporting those processes is described, focusing on the particular case of order change acceptance. An agent based architecture supporting this business solution is outlined, emphasizing the agent framework and the legacy systems integration.

Abstract
This paper proposes an environment intended for the development of fault-tolerant real-time Ada 95 applications conforming to the Ravenscar profile. This environment is based on the transparent replication of application components, and it provides a set of generic task interaction objects, which are used as the basic building blocks of the supported applications. These objects provide the usual task interaction mechanisms used in hard real-time applications, and allow applications to be developed without considering replication and distribution issues.

Abstract
This paper analyses the security of an Electric Power System (EPS) using an efficient contingency filtering and ranking algorithm. The proposed technique is divided in three modules, with different complexity levels. The contingencies are ranked in accordance with severity indices that allow to accurately evaluate the impact of the overloads and voltage limit violations in the power network. The last module also includes indices that can detect voltage instability situations. The computer programs developed by the authors were applied to the IEEE 118 busbars test power network and the results obtained were analysed. Finally, some conclusions that provide a valuable contribution to the understanding of the power system security analysis are pointed out.

Abstract
The WorldFIP protocol is one of the profiles that constitute the European fieldbus standard EN-50170. It is particularly well suited to be used in distributed computer-controlled systems where a set of process variables must be shared among network devices. To cope with the real-time requirements of such systems, the protocol provides communication services based on the exchange of periodic and aperiodic identified variables. The periodic exchanges have the highest priority and are executed at run time according to a cyclic schedule. Therefore, the respective schedulability can be determined at pre-run-time when building the schedule table. Concerning the aperiodic exchanges, the situation is different since their priority is lower and they are handled according to a first-come-first-served policy. In this paper, a, response-time-based schedulability analysis for the real-time traffic is presented. Such analysis considers both types of traffic in an integrated way, according to their priorities. Furthermore, a fixed-priorities-based policy is also used to schedule the periodic traffic. The proposed analysis represents an improvement relative to previous work and it can be evaluated online as part of a traffic online admission control. This feature is of particular importance when a planning scheduler is used, instead of the typical offline static scheduler, to allow online changes to the set of periodic process variables.