This paper proposes a multiobjective model to solve the mathematical problem of optimizing reliabilitycentered maintenance planning of an electric power distribution system (EPDS). The main goal is to minimize the preventive maintenance costs while maximizing the index of reliability of the whole system. In the proposed model, the limits of the indices, such as SAIDI and SAIFI, are considered as constraints of the maintenance programs. The reliability indices of the EPDS components are evaluated and updated by a fuzzy inference system. A NSGA-II algorithm was proposed to solve the multiobjective model that provides an optimized Pareto frontier. The results obtained from applying the proposed methodology to a system with three feeders and 733 components are presented, showing its robustness and quality for maintenance planning in EPDS.

This paper presents a methodology for automated disturbance analysis and fault location on electric power distribution systems using a combination of modern techniques for network analysis, signal processing and intelligent systems. New algorithms to detect, classify and locate power quality disturbances are developed. The continuous process of detecting these disturbances is accomplished through statistical analysis and multilevel signal analysis in wavelet domain. The behavioral indices of the current and voltage signals are extracted employing the discrete wavelet transform, multiresolution analysis and the concept of signal energy. These indices are used by a number of independent Fuzzy-ARTMAP neural networks, which aim to classify the fault type and the power quality events. The fault location is performed after the classification process. A real life three-phase distribution system with 134 nodes, 13.8 kV and 7.065 MVA was used to test the proposed algorithms, providing satisfactory results, attesting that the proposed algorithms are efficient, fast and, above all, intelligent.

The system reliability depends on the reliability of its components itself. Therefore, it is necessary a methodology capable of inferring the state of functionality of these components to establish reliable indices of quality. Allocation models for maintenance and protective devices, among others, have been used in order to improve the quality and availability of services on electric power distribution systems. This paper proposes a methodology for assessing the reliability of distribution system components in an integrated way, using probabilistic models and fuzzy inference systems to infer about the operation probability of each component.