|
|
基于神经网络的高速公路供电线路电能质量预测方法
|
Abstract:
随着高速公路的大力发展，特别是智慧公路的快速发展，高速公路基础设施建设逐步向数字化、信息化、智慧化方向转变。然而，数字化电力电子设备的广泛使用也带来了日益严重的电能质量问题，影响高速公路系统的正常运行和安全，增加了运营成本和维护难度。本文针对高速公路供电电能质量存在的问题，首先对现有电能质量评估指标的系统进行了归纳和总结，在此基础上，提出了一种基于时域卷积网络(TCN)和长短期记忆网络(LSTM)相结合的电能质量预测模型方法，并通过算例验证了该方法在提高预测准确性方面的优势。
With the rapid development of highways, particularly smart highways, highway infrastructure construction is gradually transitioning towards digitalization, informatization, and intelligence. However, the widespread use of digital power electronic devices has led to increasingly severe power quality issues, which affect the normal operation and safety of highway systems, while also increasing operational costs and maintenance complexity. In response to the power quality problems in highway power supply systems, this paper first summarizes and organizes the existing power quality evaluation indices systematically. On this basis, a power quality prediction model is proposed, combining Temporal Convolutional Networks (TCN) and Long Short-Term Memory (LSTM) networks. The advantages of this method in improving prediction accuracy are demonstrated through case studies.
| [1] | 刘颖英, 冯丹丹, 林才华, 张逸. 电能质量综合评估研究现状及发展趋势[J]. 电力系统保护与控制, 2020, 48(4): 167-176. |
| [2] | Mei, D., Guo, S. and Li, Y. (2022) Power Grid Electricity Prediction Model in Multi-Dimensional Scenarios. Journal of Physics: Conference Series, 2158, Article ID: 012010. https://doi.org/10.1088/1742-6596/2158/1/012010 |
| [3] | 丁泽俊, 刘平, 欧阳森, 等. 电能质量预测与预警机制及其应用[J]. 电力系统及其自动化学报, 2015, 27(10): 87-92. |
| [4] | 苏卫卫, 马素霞, 齐林海. 基于ARIMA和神经网络的电能质量稳态指标预测[J]. 计算机技术与发展, 2014, 24(3): 163-167. |
| [5] | 崔晓飞, 马智远, 许中, 等. 基于离散傅里叶分解的电能质量不平衡度指标AR预测方法[J]. 现代电力, 2013, 30(6): 38-42. |
| [6] | Bai, J., Gu, W., Yuan, X., Li, Q., Xue, F. and Wang, X. (2015) Power Quality Prediction, Early Warning, and Control for Points of Common Coupling with Wind Farms. Energies, 8, 9365-9382. https://doi.org/10.3390/en8099365 |
| [7] | Vantuch, T., Misak, S., Jezowicz, T., Burianek, T. and Snasel, V. (2017) The Power Quality Forecasting Model for Off-Grid System Supported by Multiobjective Optimization. IEEE Transactions on Industrial Electronics, 64, 9507-9516. https://doi.org/10.1109/tie.2017.2711540 |
| [8] | 翁国庆, 龚阳光, 舒俊鹏, 等. 基于聚类LSTM深度学习模型的主动配电网电能质量预测[J]. 高技术通讯, 2020, 30(7): 687-697. |
| [9] | 朱乔木, 李弘毅, 王子琪, 等. 基于长短期记忆网络的风电场发电功率超短期预测[J]. 电网技术, 2017, 41(12): 3797-3802. |
| [10] | 胡欣球, 马立新. VMD-LSTM算法在短期负荷预测中的应用[J]. 电力科学与工程, 2018, 34(6): 9-13. |
| [11] | Guo, X., Xu, P. and Shao, X. (2022) Comprehensive Evaluation of Power Quality of Coal Mine Power Grid Based on Equilibrium Empowerment and Improved Grey Relational Projection Method. Energy Reports, 8, 1680-1688. https://doi.org/10.1016/j.egyr.2022.02.287 |
| [12] | Eisenmann, A., Streubel, T. and Rudion, K. (2022) Power Quality Mitigation via Smart Demand-Side Management Based on a Genetic Algorithm. Energies, 15, Article 1492. https://doi.org/10.3390/en15041492 |
| [13] | 盛仕昌, 刘周峰, 倪杰, 田浩, 杨阳, 周霞, 卜成杰. 配电终端通信网架构及电能质量智能感知技术研究[J]. 电力信息与通信技术, 2021, 19(12): 1-8. |
| [14] | 李琼林, 刘书铭, 温佳静, 王毅, 代双寅, 谭甜源, 刘开培. 计及电能质量影响的10kV配电网损耗计算模型及其实验验证[J]. 电力自动化设备, 2022, 42(1): 212-220. |
| [15] | 常潇, 王金浩, 雷达, 李胜文, 刘军成. 电能质量综合指标评价方法研究[J]. 电力电容器与无功补偿, 2021, 42(5): 150-153. |
| [16] | 张华赢, 汪清, 游奕弘, 吴显, 孙一浩, 张文海. 电能质量数据质量对综合评估结果的影响分析[J]. 科学技术与工程, 2021, 21(24): 10341-10349. |
| [17] | 刘善伟, 郭建龙, 刘文泽, 闻成胜, 周文青. 10kV配电网电能质量综合等级评估方法研究[J]. 机电工程技术, 2021, 50(8): 152-156. |
| [18] | Limouni, T., Yaagoubi, R., Bouziane, K., Guissi, K. and Baali, E.H. (2023) Accurate One Step and Multistep Forecasting of Very Short-Term PV Power Using LSTM-TCN Model. Renewable Energy, 205, 1010-1024. https://doi.org/10.1016/j.renene.2023.01.118 |
| [19] | 吴晓丹, 范波, 王建祥, 等. 基于VMD-TCN-Attention的锂电池寿命预测[J]. 电源技术, 2023, 47(10): 1319-1325. |
