Search

A variety of power electronic equipment in AC/DC distribution networks causes oscillations with unknown origin. A self‐sustained low‐frequency oscillation appeared recently in a practical AC/DC distribution network in Tongli, Jiangsu Province, China. In this paper, the accident is introduced, and the oscillation phenomenon has been successfully reproduced by theoretical modelling. Based on the small signal model, the oscillation is well analysed and an additional controller is designed to suppress this low‐frequency oscillation. The reason of the oscillation is related to the power and control parameters of buck converter; the system is critically stable within the linear system stability theory, namely, the leading eigenvalues of the small‐signal system are on the imaginary axis. Meanwhile, a novel inhomogeneity phenomenon for oscillation amplitudes on different voltage‐level DC buses, which are not proportional to their steady‐state voltages, is found. This paper provides a new case study of self‐sustained oscillations coming from a practical AC/DC distribution network and is of great significance for our understanding of oscillations in electric power engineering. [ABSTRACT FROM AUTHOR]

Accurate load forecasting is essential for ensuring safe, stable, and economical operation of energy internet. Temporal convolutional networks (TCNs) have demonstrated superior performance, when compared to recurrent neural network models, since their introduction in electrical load forecasting. However, the current TCN‐based models are unable to obtain a large receptive field and strong long‐time feature extraction capability owing to the specific kernel size of the 1D convolution structure. This paper proposes a temporal inception convolutional network based on multi‐head attention (TICN‐Att) for ultra‐short‐term load prediction. By introducing an inception structure into the TCN, the proposed model can extract multi‐dimensional information from the input features, through the multiple hidden convolutional kernels of different scales, without stacking layers depth‐wise. Simultaneously, by introducing a multi‐head attention mechanism, the TICN‐Att model has a long time‐dependent extraction capability, similar to that of the long short‐term memory network models. The generalization and validity of the model are tested using the global energy forecasting competition (GEFCOM2014) dataset, electrical load data of a city in Jiangsu (China), and PJM power system dataset. The experimental results demonstrated that the proposed model has the best prediction effect, compared to the other state‐of‐the‐art models. [ABSTRACT FROM AUTHOR]