Current transformer (CT) saturation is one of the significant problems for protection engineers. If CT saturation is not tackled properly, it can cause a disastrous effect on the stability of the power system, and may even create a complete blackout. To cope with CT saturation properly, an accurate detection or classification should be preceded. Recently, deep learning (DL) methods have brought a subversive revolution in the field of artificial intelligence (AI). This paper presents a new DL classification method based on unsupervised feature extraction and supervised fine-tuning strategy to classify the saturated and unsaturated regions in case of CT saturation. In other words, if protection system is subjected to a CT saturation, proposed method will correctly classify the different levels of saturation with a high accuracy. Traditional AI methods are mostly based on supervised learning and rely heavily on human crafted features. This paper contributes to an unsupervised feature extraction, using autoencoders and deep neural networks (DNNs) to extract features automatically without prior knowledge of optimal features. To validate the effectiveness of proposed method, a variety of simulation tests are conducted, and classification results are analyzed using standard classification metrics. Simulation results confirm that proposed method classifies the different levels of CT saturation with a remarkable accuracy and has unique feature extraction capabilities. Lastly, we provided a potential future research direction to conclude this paper.

Since the penetration level of wind energy is continuously increasing, the negative impact caused by the fluctuation of wind power output needs to be carefully managed. This paper proposes a novel real-time coordinated control algorithm based on a wavelet transform to mitigate both short-term and long-term fluctuations by using a hybrid energy storage system (HESS). The short-term fluctuation is eliminated by using an electric double-layer capacitor (EDLC), while the wind-HESS system output is kept constant during each 10-min period by a Ni-MH battery (NB). State-of-charge (SOC) control strategies for both EDLC and NB are proposed to maintain the SOC level of storage within safe operating limits. A ramp rate limitation (RRL) requirement is also considered in the proposed algorithm. The effectiveness of the proposed algorithm has been tested by using real time simulation. The simulation model of the wind-HESS system is developed in the real-time digital simulator (RTDS)/RSCAD environment. The proposed algorithm is also implemented as a user defined model of the RSCAD. The simulation results demonstrate that the HESS with the proposed control algorithm can indeed assist in dealing with the variation of wind power generation. Moreover, the proposed method shows better performance in smoothing out the fluctuation and managing the SOC of battery and EDLC than the simple moving average (SMA) based method.

The reliability and stability of differential protection in power transformers could be threatened by several types of inferences, including magnetizing inrush currents, current transformer saturation, and overexcitation from external faults. The robustness of deep learning applications employed for power system protection in recent years has offered solutions to deal with several disturbances. This paper presents a method for detecting internal faults in power transformers occurring simultaneously with inrush currents. It involves utilizing a data window (DW) and stacked denoising autoencoders. Unlike the conventional method, the proposed scheme requires no thresholds to discriminate internal faults and inrush currents. The performance of the algorithm was verified using fault data from a typical Korean 154 kV distribution substation. Inrush current variation and internal faults were simulated and generated in PSCAD/EMTDC, considering various parameters that affect an inrush current. The results indicate that the proposed scheme can detect the appearance of internal faults occurring simultaneously with an inrush current. Moreover, it shows promising results compared to the prevailing methods, ensuring the superiority of the proposed method. From sample N–3, the proposed DNN demonstrates accurate discrimination between internal faults and inrush currents, achieving accuracy, sensitivity, and precision values of 100%.

This paper proposes a three-level discrete Fourier transform (DFT) method to provide an accurate estimate of power system frequency in real time. The first level decomposes a power system signal into two orthogonal cosine- and sine-filtered signals. The second and third levels are used to determine the amplitude ratio of the cosine- and sine-filtered signals without encountering the zero-crossing problem and with an increase in ability to suppress harmonics and inter-harmonics. The performance of the three-level DFT method is evaluated using computer-simulated signals with harmonics and inter-harmonics. The three-level DFT method is also implemented on a digital signal processor (DSP)-based hardware prototype, and its performance in the hardware implementation is evaluated using a real-time digital simulator (RTDS). The evaluation results show that the three-level DFT method can achieve real-time estimation of power system frequency with satisfactory performance.

Malfunctions in relay protection devices are predominantly caused by current transformer (CT) saturation which produces distortion in current measurements and disturbances in power system protection. The development of deep learning in power system protection is on the rise recently because of its robustness. This study presents a CT saturation detection where the secondary current becomes distorted. The proposed scheme offers a wide range of saturation detection and consists of a moving-window technique and stacked denoising autoencoders. Moreover, Bayesian optimization was used to minimize the difficulty of determining neural network structure for the proposed approach. The performance of the algorithm was evaluated for a-g faults on 154 kV and 345 kV overhead transmission line in South Korea. The waveform variation has been generated by PSCAD for different scenarios that heavily influence CT saturation. Moreover, a comparative analysis with other methods demonstrated the superiority of the proposed DNN method. With the proposed algorithm to detect CT saturation, it significantly yielded high accuracy and precision for CT saturation detection which were approximately 99.71% and 99.32%, respectively.

The purpose of this paper is to remove the exponentially decaying DC offset in fault current waveforms using a deep neural network (DNN), even under harmonics and noise distortion. The DNN is implemented using the TensorFlow library based on Python. Autoencoders are utilized to determine the number of neurons in each hidden layer. Then, the number of hidden layers is experimentally decided by comparing the performance of DNNs with different numbers of hidden layers. Once the optimal DNN size has been determined, intensive training is performed using both the supervised and unsupervised training methodologies. Through various case studies, it was verified that the DNN is immune to harmonics, noise distortion, and variation of the time constant of the DC offset. In addition, it was found that the DNN can be applied to power systems with different voltage levels.