| 引用本文: | 王义国,林 峰,李 琦,等.基于TCN-LSTM模型的电网电能质量扰动分类研究[J].电力系统保护与控制,2024,52(17):161-167.[点击复制] |
| WANG Yiguo,LIN Feng,LI Qi,et al.Classification of power quality disturbances in a power grid based on the TCN-LSTM model[J].Power System Protection and Control,2024,52(17):161-167[点击复制] |
|
| 摘要: |
| 随着新能源发电和众多电动汽车充电桩等非线性设备并网运行，电网电能质量问题日渐凸显。现有解决方案在电能质量扰动分类上流程复杂，且在处理扰动信号时分类准确率偏低。为应对这一挑战，引入了 TCN-LSTM 混合模型，融合了时域卷积网络(temporal convolutional network, TCN)和长短时记忆网络(long short-term memory, LSTM)。其中，TCN 专注于捕捉时序数据的局部特性，而 LSTM 负责挖掘长期依赖关系，两者结合能够有效捕捉信号的局部特征和全局关系。为验证模型性能，对 14 种加入不同信噪比白噪声的电能质量扰动信号进行分类测试。结果表明，TCN-LSTM 模型展现出较强的抗噪性能，并在与现有深度网络模型的对比中展现了更高的分类准确度。 |
| 关键词: 电能质量 扰动分类 TCN-LSTM模型 时序数据 抗噪性能 |
| DOI：10.19783/j.cnki.pspc.231582 |
| 投稿时间：2023-12-13修订日期：2024-02-12 |
| 基金项目:四川省青年科技创新研究团队项目“高铁电力牵引系统电气安全防护”(2016TD0012) |
|
| Classification of power quality disturbances in a power grid based on the TCN-LSTM model |
| WANG Yiguo1,LIN Feng2,LI Qi2,LIU Yuqi1,HU Guiyang3,MENG Xiangyu3 |
| (1. Guangdong Energy Group Co., Ltd., Guangzhou 510620, China; 2. Guangdong Yuedian Qingxi Power
Generation Co., Ltd., Meizhou 514200, China; 3. School of Electrical Engineering,
Southwest Jiaotong University, Chengdu 610000, China) |
| Abstract: |
| The increasing integration of non-linear devices such as new energy generation and a large number of electric vehicle charging stations into the power grid has led to increasingly prominent power quality problems. However, current methods face challenges in the classification of power quality disturbances, with complex steps and low accuracy when considering disturbance signals. To address these issues, this paper proposes the TCN-LSTM model, which combines a temporal convolutional network (TCN) with long short-term memory (LSTM). The TCN network excels in capturing local features of time series, while the LSTM is proficient in digging long-term dependencies within the time series. The fusion of both enables the model to effectively capture both local characteristics and global relationships of the signals. To validate the model’s performance, a classification test is conducted on 14 types of power quality disturbance signals with varying signal-to-noise ratios. Finally, the results demonstrate that the TCN-LSTM model exhibits strong noise resistance. In comparison to existing deep network models, the model proposed in this paper achieves higher classification accuracy. |
| Key words: power quality disturbance classification TCN-LSTM model time series data noise resistance performance |
