Power Flow Analysis and Self-recovery of Electrical Energy Distribution Network Using Artificial Neural Networks

ABSTRACT A computational model for self-recovery of electricity distribution network was developed to simulate it, emulated by the IEEE 123 node model. The electrical system considered has automatic switches capable of identifying a momentary failure in the line and finding the best reconfiguration for its reclosing. An artificial neural network (ANN), backpropagation, was used to classify the type of failure and determine the best reconfiguration of the distribution network. Initially, five power failure scenarios were simulated in certain different parts of the power grid, and power flow analysis via OpenDSS was performed. Next, the most suitable switching was observed within the shortest time interval to restore the power supply. With the purpose of better visualization to identify the reclosing, an implementation was carried out via ELIPSE SCADA. In this way, it is possible to identify the faulted segment in order to isolate it, leaving the smallest number of consumers without power supply in shortest possible time. With the results of the simulations, tests and analyzes were performed to verify their robustness and speed, in the expectation that the model developed be faster than an experienced Operating Distribution Center.

Modelos de análise hidráulica de redes de distribuição de água considerando demanda dirigida pela pressão e vazamentos / Water distribution networks analysis considering leakage and pressure driven demand modeling

As ferramentas para análise hidráulica são componentes importantes na avaliação do funcionamento das redes de distribuição de água para abastecimento. Existem diversos métodos que podem ser utilizados para essa análise, no entanto, os modelos que procuram resolver o sistema de equações correspondente através do método Newton-Raphson ou por meio de linearizações sucessivas são os mais eficientes. Quatro formulações baseadas nestes esquemas são avaliadas neste trabalho. O objetivo deste trabalho é fazer uma comparação dos métodos Newton-Raphson, Teoria Linear, Híbrido e Gradiente para a análise de redes de distribuição de água em regime permanente, considerando a demanda dirigida pela pressão e os Vazamentos. Para tanto, foi utilizado um layout de rede frequentemente empregado na literatura dotado de válvulas. O método do Gradiente foi o que convergiu em um número menor de iterações para redes mais simples, o Método Híbrido foi o que mais se adaptou para sistemas mais complexos.

The hydraulic analysis tools are important in the performance evaluation of water distribution networks. Various methods are available for such analysis. However, the hydraulic models that solve the system of equations describing the flow problem through Newton-Raphson or through its successive linearizations are the most efficient. It is the purpose of this paper to compare Newton-Raphson, Linear Theory, Hybrid and Gradient methods for steady-state hydraulic network analysis, considering leakage and pressure driven demand modeling. The network layout with hydraulic components frequently used in the literature was employed for this analysis. The Gradient method was found to produce best results in terms of number of iterations for the more simple networks, whereas the Hybrid method was better for more complex networks.