The use of outage management systems are becoming vital for distribution utilities in the new paradigm of power systems competition and deregulation. These efforts include fuzzy logic, expert systems, heuristic applications and neural networks. These techniques allow to process and validate real-time data in order to feed a datahase for statistic analysis. This paper presents a computational system for forced outage event acquisition, validation and cause identification based on mobile computing and neural networks. The system is divided into two modules: one to collect and validate, based on mobile computing, forced-outage event data information (conditions in the surrounding environments) at local; and an other one to identify and classify the forced-outage caused using artificial neural networks (ANN).
This paper presents a pedestrian route choice model devised to represent the influence of the impedance generated by other pedestrians on the route choice process. This model is inspired by friction force equations, and considers that pedestrians avoid passing near other pedestrians with high relative velocity. The route choice process is based on a weighting of the impedance generated by pedestrians and the path length. A social force model was used to model pedestrian walking behavior. The model is able to reproduce emergent behavior among agents, allowing the assumption that the friction equations may provide a suitable approach to route choice behavior and can also be used as an indirect measure of pedestrian delay.
This paper describes a computational system to treat the forced outage events information cycle, from the field data acquisition to the reports generation, providing a tool to guiding operation and maintenance actions.
This paper presents a pedestrian route choice model and its calibration with real data. The model explicitly represents interaction between pedestrians as an impedance force influences their route choice. This model approach was inspired by friction force equations and considered efforts by pedestrians to avoid passing near other pedestrians with high relative velocity. The route choice process was a function of impedance force and route length. A social force model was used to model pedestrian walking behavior. The calibration had its basis in data acquired from a real experiment developed in a simplified network. Data collection had its basis in video analysis. The paper presents and discusses results from the calibration processes. The model presented in this paper differs from other pedestrian route choice models because it seamlessly incorporates a pedestrian social force model into the route choice decision process.
Este artigo explora a técnica de Descoberta de Conhecimento em Base de Dados (Knowledge Discovery in Databases - KDD) com o objetivo de qualificar a informação recolhida durante os trabalhos de recomposição de sistemas de distribuição por equipes de eletricistas. Esta qualificação possibilita a utilização de técnicas de Inteligência Artificial (IA) para apoiar decisões de investimentos em planejamento, operação e manutenção de sistemas de distribuição. Com o objetivo de ilustrar a importância dessa qualificação, este artigo apresenta, adicionalmente, a utilização dos resultados da aplicação de KDD para o treinamento de uma Rede Bayseana (RB). A meta principal da RB é auxiliar no diagnóstico de desempenho das redes elétricas, promovendo uma identificação indireta de causas de desligamentos forçados. A análise dos dados coletados durante uma interrupção forçada de energia elétrica indica que o principal objetivo dos eletricistas em campo é a rápida recomposição da rede e, por muitas vezes, as causas que cercam os eventos que originaram as interrupções possuem um alto nível de subjetividade e incerteza, impossibilitando a sua identificação direta. Para ilustrar essa metodologia é apresentado um caso com 570.000 eventos, ao qual o KDD proporciona um novo ambiente - com um número significativo de dados - mais apropriado para o treinamento e validação da RB para identificação de causas de desligamentos não programados.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.