Accurate and rapid load forecasting for industrial customers has been playing a crucial role in modern power systems. Due to the variability of industrial customers' activities, individual industrial loads are usually too volatile to forecast accurately. In this paper, a short-term load forecasting model for industrial customers based on the Temporal Convolutional Network (TCN) and Light Gradient Boosting Machine (LightGBM) is proposed. Firstly, a fixed-length sliding time window method is adopted to reconstruct the electrical features. Next, the TCN is utilized to extract the hidden information and long-term temporal relationships in the input features including electrical features, a meteorological feature and date features. Further, a state-of-the-art LightGBM capable of forecasting industrial customers' loads is adopted. The effectiveness of the proposed model is demonstrated by using datasets from different industries in China, Australia and Ireland. Multiple experiments and comparisons with existing models show that the proposed model provides accurate load forecasting results.

Short-term load forecasting (STLF) for industrial customers has been an essential task to reduce the cost of energy transaction and promote the stable operation of smart grid throughout the development of the modern power system. Traditional STLF methods commonly focus on establishing the non-linear relationship between loads and features, but ignore the temporal relationship between them. In this paper, an STLF method based on ensemble hidden Markov model (e-HMM) is proposed to track and learn the dynamic characteristics of industrial customer’s consumption patterns in correlated multivariate time series, thereby improving the prediction accuracy. Specifically, a novel similarity measurement strategy of log-likelihood space is designed to calculate the log-likelihood value of the multivariate time series in sliding time windows, which can effectively help the hidden Markov model (HMM) to capture the dynamic temporal characteristics from multiple historical sequences in similar patterns, so that the prediction accuracy is greatly improved. In order to improve the generalization ability and stability of a single HMM, we further adopt the framework of Bagging ensemble learning algorithm to reduce the prediction errors of a single model. The experimental study is implemented on a real dataset from a company in Hunan Province, China. We test the model in different forecasting periods. The results of multiple experiments and comparison with several state-of-the-art models show that the proposed approach has higher prediction accuracy.

To improve the accuracy of faulty feeder selection based on zero sequence current mutation, distribution networks with inverter-interfaced distributed generators (IIDGs) are analyzed in detail. It is found that the IIDGs cannot be completely equivalent to a positive sequence current source due to their boosting increments. Thereby, a more accurate IIDG current estimation model based on the Gauss-Seidel method that considers the control strategy at the moment of fault is established. Moreover, a real-time estimation algorithm is introduced for faulty feeder detection to adjust the compensation degree of the Petersen coil. On this basis, this paper proposes a novel faulty feeder detection approach using the zero-sequence current space relative distance between the increments of each feeder and an estimation of the faulty path generated by Kalman filtering (KAF). The feasibility of the proposed approach is demonstrated in both a PSCAD/EMTDC simulation and a MATLAB experimental laboratory. The test results indicate that the proposed approach can achieve a high speed when employed for different fault conditions.

In order to achieve selective ground fault protection for bus-connected Powerformers and improve the reliability of the protection scheme, this paper presents a novel stator single-line-to-ground (SLG) fault protection scheme for bus-connected Powerformers based on S-transform (ST) and bagging ensemble learning algorithm. The scheme utilizes ST to decompose the zero-sequence current signals acquired from the Powerformer terminal to obtain the amplitude-time-frequency matrix. Then, fault features extraction is presented, and three features including the transient energy, the comprehensive correlation coefficient, and the zero-sequence active power are discussed and selected as feature vectors. The calculated data set is then extracted from feature vectors and used as inputs to the bagging ensemble learning algorithm to detect faults. Simulation results have shown that, under different fault conditions, the novel scheme can detect in which Powerformer a stator SLG fault is occurring and can detect internal faults from external faults reliably even if the fault resistance is at 8000 Ω. The proposed protection scheme does not need to set the threshold value and has noise-tolerant ability. Furthermore, the proposed technique performs better than support vector machine (SVM), random forest (RF) and k-Nearest Neighbor (KNN) techniques in detecting faults.

Interturn fault and high-resistance connection (HRC) fault are two common faults in the stator windings of permanent magnet synchronous wind generators (PMSWGs) that have similar characteristics. Most existing detection methods can only identify one type of these faults, without distinguishing between them. Therefore, this paper presents a fault indicator based on three-phase internal impedance to detect faults, with the fault phase and fault type identified based on the three-phase angles calculated from the internal impedance. The proposed method is noninvasive, considers three types of machine-side converter (MSC) control strategies, and is not affected by external imbalance. Simulation results in MATLAB/Simulink and experimental results on a simplified platform demonstrate the effectiveness of the proposed method.

Load forecasting for industrial customers is essential for reliable operation decisions in the electric power industry. However, most of the load forecasting literature has been focused on deterministic load forecasting (DLF) without considering information on the uncertainty of industrial load. This article proposes a probabilistic density load forecasting model comprising convolutional long short-term memory (ConvLSTM) and a mixture density network (MDN). First, a sliding window strategy is adopted to convert one-dimensional (1D) data into two-dimensional (2D) matrices to reconstruct input features. Then the ConvLSTM is utilized to capture the deep information of the input features. At last, the mixture density network capable of directly predicting probability density functions of loads is adopted. Experimental results on the load datasets of three different industries show the accuracy and reliability of the proposed method.