International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395-0056
Volume: 13 Issue: 05 | May 2026
p-ISSN: 2395-0072
www.irjet.net
Power Quality Disturbance Detection using CNN and Deep Learning Venkatesh Daggupati Department of Electrical and Computer Engineering Texas Tech University
-------------------------------------------------------------------------------***----------------------------------------------------------------------------Abstract— The rising use of renewable energy and nonlinear loads makes it difficult for modern smart grids to deal with power quality disturbances such as voltage sags, swells, harmonics, transients, interruptions, and flickers. Proper and automatic classification of PQDs plays a big part in keeping the grid running smoothly and responding to power failures. Here, Deep Learning is used with the STFT and CNNs to recognize PQDs in the IEEE 9-bus system. It was simulated with electrical faults in place and the voltage data was turned into spectrograms by using STFT to analyze timefrequency features. After that, the CNN model was trained using the spectrograms for automated identification of PQD variants. It is shown by the simulation results that the method gives excellent scores for accuracy, precision, and recall in situations where there is noise. Classification with the CNN accomplished better results than ELM and other Figure 1: Common power quality disturbances. standard classifiers. Monitoring data in real-time is possible because the framework is fast and handles problems efficiently. The research shows the advantages of using STFT The troubles can stem internally from things such as and CNNs to detect different types of power quality switches, capacitors, or motors being switched on, or disturbances and points to the development of advanced PQD externally from lightning or technical faults in the classification tools that can be used in today’s power systems. transmission network. Such disruptions might make a system less efficient, decrease device efficiency, and result in serious Index Terms: Power quality disturbances, IEEE 9-bus breakdowns in particular cases. Unexpected breakdowns, system, Short-Time Fourier Transform, Convolutional loss of data, and costly maintenance may happen to Neural Network, classification, smart grids, real-time industries that use PQDs. This is why timely and correct identification of PQDs helps improve the reliability of the monitoring. power system and its quality of service (QoS). I. INTRODUCTION Commonly, detecting the phase-quiet features in sound is Modern power systems have grown more complex because of done mathematically, including the Fourier Transform (FT), the rise in solar energy, electric vehicles, and distributed the Short-Time Fourier Transform (STFT), and the Wavelet energy resources, leading to harder challenges controlling Transform (WT). The frequency domain analysis provided by power quality. Power used to be sourced from centralized the FT is very useful, but the tool is not suitable for occasions stations with loads that varied less and usual lack of where timing matters. It fixes this problem by examining time interference. However, the modern smart grids work in a and frequency with sliding windows. Still, it is limited by the flexible, decentralized way, and the variety of power fact that fixing one becomes fixed for the other. WT analyzes electronic devices in them causes the system to be less linear a signal at multiple resolution levels, matching the signal’s and regular. Increasing the usage of these appliances has characteristics, so it is effective in detecting many types of made the distribution of electricity more likely to cause PQDs. Still, because they must be made by hand and power quality disturbances (PQDs), which means deviations interpreted by someone, traditional methods take a lot of from standard voltage, frequency, or waveform. time and are more likely to make mistakes, especially when there are many obstacles or when noise in the signal is high. PQDs consist of a lot of anomalies, like voltage sags, voltage swells, harmonic distortion, transients, flickers, and interruptions.
© 2026, IRJET
|
Impact Factor value: 8.315
|
ISO 9001:2008 Certified Journal
|
Page 54