Vol.:(0123456789) SN Computer Science (2021) 2:64 https://doi.org/10.1007/s42979-020-00435-1 SN Computer Science ORIGINAL RESEARCH A Deep Learning Approach for the Detection and Classifcation of Power Quality Disturbances with Windowed Signals Wilson L. Rodrigues Jr 1  · Fabbio A. S. Borges 2  · Antonio O. de Carvalho Filho 3  · Ricardo de A. L. Rabelo 1 Received: 10 May 2020 / Accepted: 17 December 2020 / Published online: 30 January 2021 © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. part of Springer Nature 2021 Abstract The modernization of Power Systems (PSs) to smart grids, the expansion of microgrids, the ever-increasing presence of distributed power generation, the more frequent use of non-linear and voltage-sensitive loads by the consumers have caused problems to the Power Quality (PQ). The studies in PQ are commonly related to disturbances that alter the sinusoidal characteristics of the voltage waveforms and/or current. The frst step to analyzing the PQ is to detect and then classify the disturbances, since by identifying the disturbance, it is possible to know its causes and deliberate over strategies to mitigate it. Thus, this paper proposes a deep-learning approach using voltage signals, without pre-processing, extraction, nor manual selection of features in order to detect and classify PQ disturbances automatically. The proposed approach is composed of convolution layers, a pooling layer, a long short-term memory layer, and batch normalization. A 1D convolution was used to adapt the data from the voltage signals. Overlapping windowed signals with diferent Signal–Noise Ratio (SNR) (40 dB, 30 dB, 20 dB and 0 dB) and with diferent sampling rates (16, 32, and 64 samples/cycle) were used. For a more in-depth view of the results, the proposed approach was evaluated for its accuracy, precision, recall, and F1-Score in diferent scenarios. An analysis of the obtained results shows that even for the worst case scenario (SNR of 20 dB and sampling rates of 16 samples/ cycle), the approach performs satisfactorily with values above 0.97 for the analyzed metrics, allowing, thus, consumer action in a demand-side management scenario. Keywords Deep learning · Long short-term memory · Power quality · Convolutional neural networks Introduction The increase in energy consumption due to the populational growth and the addition of new equipment connected to the power grid is mostly supplied by the electric utility, and, when possible, by the consumers themselves via their own local methods of power generation or storage [35]. Cur- rently, the increased integration of distributed power gen- eration, especially using renewable energy sources (photo- voltaic and eolic), and the consolidation of microgrids [16] has lead to a change in the management and operation of the electrical system [10]. Thus, the electric system has become smarter and its operations more decentralized [2]. This integration is one of the biggest sources of power quality (PQ) disturbances, and can cause, such as overvolt- age and undervoltage, increased outages, elevation, volt- age sags, interruption, etc [13, 40]. The change in load by consumers’ facilities [27] regardless if they are residential, industrial, or commercial, is also one of the main causes of disturbances. The ample use of non-linear and voltage sensitive loads such as electronic equipment (computers and energetically efcient lighting) has caused PQ disturbances afecting the consumers’ experience, as these disturbances can cause malfunctioning or damage equipment, and, in the * Ricardo de A. L. Rabelo ricardoalr@ufpi.edu.br Wilson L. Rodrigues Junior wilsonlealjunior@ufpi.edu.br Fabbio A. S. Borges fabbio@prp.uespi.br Antonio O. de Carvalho Filho antoniooseas@ufpi.edu.br 1 Department of Computer Science, Federal University of Piauí, Teresina, PI, Brazil 2 Department of Computer Science, State University of Piauí, Piripiri, PI, Brazil 3 Department of Computer Science, Federal University of Piauí, Picos, PI, Brazil