Fuzzy queueing theory (FQT) is a powerful tool used to model queueing systems taking into account their natural imprecision. The traditional FQT model assumes a fixed number of servers with constant fuzzy arrival and service rates. It is quite common, however, to encounter situations where the number of servers, the arrival rate, and the service rate change with time. In those cases, the variability of these parameters can significantly impact the behavior of the queueing system and complicate its analysis. In this paper, we propose a simulation method to deal with these problems that leads to realistic estimations of the behavior of the queueing system. To demonstrate the applicability of the technique, we have employed it to solve a real-world problem: the prediction of the impact of electric vehicles on power networks. Electric vehicles have recently become a popular topic for research and development, mainly for their potential ability to reduce emissions and dependence on fossil fuels. Their demanding charging requirements can, nevertheless, significantly impact the performance of the power grid. In this paper, we propose modeling the recharging process as a fuzzy queueing problem. This approach is more realistic than previous treatments, while leading to accurate descriptions of the performance of the system.

Electric vehicles are a promising technology for reducing CO2emissions and dependence on fossil fuels. Their market is expected to grow quickly in the next years with the increased concern about global warming and the advances in technology. However, due to their large batteries, with high energy capacity, their impact on power networks remains uncertain. Several studies have been carried out trying to predict this impact. In this paper we propose a more realistic approach based on modeling electric-vehicle recharging as a queueing problem. Vehicles arrive following a nonhomogeneous Poisson process with fuzzy arrival rate and their energy requirements follow an exponential distribution. To solve this queueing problem we will use a simulation procedure that will provide realistic quality measures about the performance of the system. Additionally, we present a case study on the impacts of electric vehicles on the Spanish power network. In particular we will analyze two possible scenarios corresponding to the expected situation for years 2014 and 2020.

Evidential-reasoning methods, such as the Dempster-Shafer calculus of evidence, are widely applied to information fusion problems. In this paper we examine methodological requirements as well as conceptual issues that are relevant to their understanding and applicability. These matters include interpretation of its basic constructs and that of the notion of evidential independence, the characterization of generalized conditional probability relations, the definition and interpretation of conflicting evidence, and the identification and use of generalized measures of information content.

Summary form only given. In the past, we have endeavored to develop a better understanding of the nature of fuzzy-logic approaches on the basis of their relation to other fundamental scientific notions. While many of these efforts evolved in the context of specific applications, their ultimate motivation was the enhancement of basic understanding-particularly in the area of the relations between various approximate-reasoning methodologies. In this presentation we review applied methods stemming from these foundations-relating fuzzy-logic concepts to notions of utility, cost, and similarity-emphasizing the need for the understanding of basic conceptual structures in the development of effective approaches to treat a wide variety of problems. We will review recent applications of approaches based on this view of fuzzy logic to three major Intelligent-system development problems: distributed robotics, qualitative description of complex objects, and knowledge discovery and retrieval in very large databases. We will present major technical issues arising in the consideration of these problems while addressing also fundamental questions of essential importance to the development and understanding of applicable approaches. In particular, we will consider matters related to the notions of team and individual goals, negotiation, and agent-based preferences in the context of distributed robotics; the concepts of cluster and clustering in the context of data analysis and understanding; and the relations between knowledge-based structures, such as ontologies and know ledge-bases, and similarity measures in the context of information-retrieval problems.

Mobile robots, if they are to perform useful tasks and become accepted in open environments, must be fully autonomous. Autonomy has many different aspects ; here the focus is on three central ones: the ability to attend to another agent, to take advice about the environment, and to carry out assigned tasks. All three involve complex sensing and planning operations on the part of the robot, including the use of visual tracking of humans, coordination of motor controls, and planning. It is shown how these capabilities are integrated in the Saphira architecture, using the concepts of coordination of behaviour, coherence of modelling, and communication with other agents.