Yang Xiaomei, Wang Jinfei, Huang Xingrui, Wang Yang, Xiao Xianyong
College of Electrical Engineering, Sichuan University, Chengdu 610065, China.
Sensors (Basel). 2025 Apr 20;25(8):2607. doi: 10.3390/s25082607.
The detection of forced oscillations, especially distinguishing them from natural oscillations, has emerged as a major concern in power system stability monitoring. Deep learning (DL) holds significant potential for detecting forced oscillations correctly. However, existing artificial neural networks (ANNs) face challenges when employed in edge devices for timely detection due to their inherent complex computations and high power consumption. This paper proposes a novel hybrid network that integrates a spiking recurrent neural network (SRNN) with long short-term memory (LSTM). The SRNN achieves computational and energy efficiency, while the integration with LSTM is conducive to effectively capturing temporal dependencies in time-series oscillation data. The proposed hybrid network is trained using the backpropagation-through-time (BPTT) optimization algorithm, with adjustments made to address the discontinuous gradient in the SRNN. We evaluate our proposed model on both simulated and real-world oscillation datasets. Overall, the experimental results demonstrate that the proposed model can achieve higher accuracy and superior performance in distinguishing forced oscillations from natural oscillations, even in the presence of strong noise, compared to pure LSTM and other SRNN-related models.
强迫振荡的检测，尤其是将其与自然振荡区分开来，已成为电力系统稳定性监测中的一个主要问题。深度学习（DL）在正确检测强迫振荡方面具有巨大潜力。然而，现有的人工神经网络（ANN）由于其固有的复杂计算和高功耗，在边缘设备中用于及时检测时面临挑战。本文提出了一种新颖的混合网络，该网络将脉冲递归神经网络（SRNN）与长短期记忆（LSTM）相结合。SRNN实现了计算和能源效率，而与LSTM的集成有助于有效捕获时间序列振荡数据中的时间依赖性。所提出的混合网络使用通过时间反向传播（BPTT）优化算法进行训练，并进行了调整以解决SRNN中的不连续梯度问题。我们在模拟和实际振荡数据集上评估了我们提出的模型。总体而言，实验结果表明，与纯LSTM和其他与SRNN相关的模型相比，即使在存在强噪声的情况下，所提出的模型在区分强迫振荡和自然振荡方面也能实现更高的准确性和卓越的性能。
