Future's smart grid consists of an increasing number of dispersed energy generation and consumption devices. Due to its complexity, the energy sector yields development of decentralized monitoring and control framework, where each node in the grid will be a potential location for power quality device. In order to continually improve the stability of the energy system, those devices need a tool for accurate and real-time detection and classification of power quality disturbances. However, despite the continuous progress in the field, the development of that kind of tool is still a challenge. This manuscript presents a real-time implementation of optimized power quality events classifier for detection and classification of 21 classes of single and combined disturbances. The focal point of the presented classifier is the real-time implementation of: optimal feature extraction, optimized classification, accurate zero-crossing detection and efficient handling of different noise levels present in the voltage signal. The implementation is performed on myRIO-1900 using LabVIEW interface. Testing and validation results show that this implementation exhibits high classification accuracy, even in cases when the classification relies on classes obtained as combination of four power quality disturbances.

The wavelet transform has been successfully used in the area of power quality analysis. There are many published papers with methods for power quality disturbance classification or harmonics measurement, which use wavelet transform. However, the properties of the wavelet transform can drastically vary from the choice of the wavelet. In this paper we analyze the influence of the choice of the wavelet to the accuracy of the power quality classification method and to high frequency harmonics measurements. Additionally to the well known wavelet filters we introduce near perfect reconstruction filter banks. The simulation results indicate that these filter banks are a good choice for classification of power quality disturbances, especially in the presence of noise and for high frequency harmonics measurements

The detection and classification of power quality (PQ) disturbances remains a significant challenge because of the rapid integration of renewable energy sources (RES), widespread use of power electronics, and increasing prevalence of sensitive microcontrollers. These evolving PQ issues necessitate the development of accurate and reliable methods for identifing and classifying PQ disturbances. In this paper, we propose a novel model based on a deep convolutional neural network (DCNN) for the feature extraction and classification of PQ disturbances. The architecture of the model was inspired by the visual geometry group (VGG), which is known for its effectiveness in image processing. The extracted features are highly suitable for both multi-class (MC) and multi-label (ML) classification tasks, effectively addressing the complexity of PQ disturbance signals. The ML approach proved its excellence in the classification of complex PQ disturbances. The performance of the model was rigorously evaluated using various metrics across different scenarios, which demonstrated exceptional accuracy and robustness. The model was trained, validated, and tested using synthetically generated data under different signal-to-noise ratio (SNR) scenarios ensuring its effectiveness in practical applications.

This paper presents multi-scale edge detection method using an undecimated Haar wavelet transform. The use of undecimated transform improves the localization of detected edges when compared to the classical, decimated Haar wavelet transform. The presented method tracks for edges that exist at several dyadic scales, favoring edges at larger scales. Edge points are obtained by non-maximum suppression in four possible directions, combined with hysteresis thresholding. The experimental results show that this method is competitive to classical edge detection methods. This multi-scale approach brings robustness to noise, while the redundancy from the undecimated transform ensures good edge localization.

The increasing number of polluting loads requires higher power quality (PQ) in the generation, transmission and distribution systems. In order to improve the power quality, the power disturbances should be monitored continuously. Power quality monitoring and analysis must be able to detect and classify the disturbances on the electrical system. A new method for optimal features selection and classification using a wavelet based random forest (RF) classifier is proposed in this paper. The classification results are compared with some previously published results, obtained from similar works. The experiments have shown that the proposed method has better classification accuracy.

This paper presents semi-fragile watermarking system for video authentication. We focus on protection and verification of the I-frame's integrity in MPEG-1/2 coded videos. Using the DC difference between blocks, we compute binary feature string with semi-fragile characteristics from the I-frames. We use this feature string as a key to generate binary watermark, and then robustly embed this content-dependent watermark into the I-frame. Using this method, it is possible to differentiate among content-preserving and content-changing modifications of the video. The watermark is embedded into DCT-domain using binary quantization index modulation. Watermark detection is performed without use of the original video. The experimental results show the robustness of this system to content-preserving manipulations and its fragility to content-changing manipulations.