Search

Dynamic behaviors of distribution networks are of great importance for the power system analysis. Nowadays, due to the integration of the renewable energy generation, energy storage, plug-in electric vehicles, and distribution networks turn from passive systems to active ones. Hence, the dynamic behaviors of active distribution networks (ADNs) are much more complex than the traditional ones. The research interests how to establish an accurate model of ADNs in modern power systems are drawing a great deal of attention. In this paper, motivated by the similarities between power system differential algebraic equations and the forward calculation flows of recurrent neural networks (RNNs), a long short-term memory (LSTM) RNN-based equivalent model is proposed to accurately represent the ADNs. First, the adoption reasons of the proposed LSTM RNN-based equivalent model are explained, and its advantages are analyzed from the mathematical point of view. Then, the accuracy and generalization performance of the proposed model is evaluated using the IEEE 39-Bus New England system integrated with ADNs in the study cases. It reveals that the proposed LSTM RNN-based equivalent model has a generalization capability to capture the dynamic behaviors of ADNs with high accuracy. [ABSTRACT FROM AUTHOR]

Purpose: The purpose of this study is to develop an algorithm to accurately detect faults in series capacitor compensated (SCC) power transmission lines. The line fault must be distinguished from stable power swing, compensating unit malfunction and defects on other lines sharing the same bus (external faults). Design/methodology/approach: In this regard, an effective fault feature extractor based on the cumulative sum (CUSUM) of the amplified second harmonic of the phase currents is suggested. The features are then applied to an artificial neural network for classification. No-fault cases include stable power swing and several disturbances. Due to the independent analysis of each phase, faulty phase detection is also a by-product. Findings: Various fault scenarios are defined, and the algorithm success rate is compared with some newly published methods. Extensive simulations performed over a single-machine infinite bus, a 3-machine, 9-bus and the large-scale New England IEEE 39-Bus networks all indicate that the proposed algorithm can trip the faulty line more quickly and accurately than the contestant algorithms. Originality/value: Suggestion of a new algorithm based on the CUSUM of the amplified second harmonic of the phase current for the fault feature extraction that is able to isolate the transmission line internal faults from stable poser swing, line compensating unit malfunction and faults on the adjacent lines connected to the same bus. [ABSTRACT FROM AUTHOR]