Efficient online detection system of power disturbances based on Deep-Learning approach

Abstract

The economic and social effects from electric disruptions have been increasing. They can cause current and voltage interferences and result in disasters. Therefore, online assessment of transit stability is essential for the control of power systems, which can prevent transmission of power disturbances and enable operators to decide on emergency control measures. This paper proposes a power-disturbance-detection system to analyze online voltage signals and prevent transmission of disturbance signals. The system consists of four stages. The first stage is data augmentation, which adds noisy signals and more generated signals with multiple events with different magnitudes of disturbance time and locations. The second stage is data division, which partitions the generated dataset into trained and evaluated datasets. The third stage constructs convolutional neural network (CNN) architecture and trains it. The fourth stage develops the constructed CNN model into an electronic circuit to analyze the online voltage signal and prevent transmission of the disturbance signal. To investigate the suggested stages of the detection system, several experiments are conducted. The experimental results demonstrate that the proposed data augmentation stage provides a beneficial influence, and the proposed CNN model is architecturally efficient. It is not affected by the noise, period of modifications, or displacements of the disturbance signals in the real-time detection process. In addition, it obtained a clear improvement rate in the weighted accuracy metrics over the state-of-the-art algorithms.

Keywords

• Power disturbances
• Deep learning
• Convolutional neural network
• Waveform features
• Data augmentation