Real-time Monitoring Technology of Voltage Sag Disturbance in Distribution Network Based on TCN-Attention Neural Network and Flink Flow Computing
DOI:
https://doi.org/10.13052/dgaej2156-3306.38512Keywords:
Voltage sag, TCN, attention, Flink, real-time monitoringAbstract
In the face of the challenges brought by the complexity of power grid, diversification of disturbance factors, isolation of monitoring points and other issues to the cause identification of voltage sag disturbance, this paper proposes a real-time monitoring technology for voltage sag disturbance in distribution network based on TCN-Attention neural network and Flink flow calculation, which has important practical significance for controlling voltage sag and reducing economic losses. This method uses Temporal Convolutional Network (TCN) to extract the cross time nonlinear characteristics of voltage sag time series data, which effectively solves the problems of long-term dependence on time series and low training output efficiency of existing time series models. In order to further improve the recognition accuracy of the model, Attention mechanism is introduced to mine the duration relationship in voltage sag data. At the same time, the method also constructs a parallel real-time monitoring platform based on Flink streaming computing framework, embeds the TCN-Attention voltage sag cause identification model generated by training, so as to realize real-time identification and monitoring analysis of voltage sag disturbances at each monitoring point of the distribution network. In this paper, various voltage sags are simulated on IEEE 14 bus system using PSCAD software, and the proposed method is verified and tested. The deep learning fusion model has high recognition accuracy for the cause of voltage sag, and the flow computing platform has excellent performance in time delay and throughput indicators, and can realize the parallel real-time monitoring and analysis of voltage sag causes in distribution network.
Downloads
References
Qu Hezuo, Liu Heng, Li Xiaoming, et al. A feature combination optimization method in power quality multi disturbance classification [J]. Electric Power Automation Equipment |Electr Power Autom Eq, 2017, 37(03): 146–152.
Zhicong Zheng, Linhai Qi, Hong Wang, et al. Recognition Method of Voltage Sag Causes Based on Bi-LSTM[J]. IEEJ Transactions on Electrical and Electronic Engineering, 2020, 15(3): 415–428.
Ahmadi Hamid Reza, Mahdavi Navideh, Bayat Mahmoud. A novel damage identification method based on short time Fourier transform and a new efficient index[J]. Structures, 2021, 33.
Li Jinsong, Liu Hao, Wang Dengke, et al. Classification of Power Quality Disturbance Based on S-Transform and Convolution Neural Network[J]. Frontiers in Energy Research, 2021.
Jürgen Schmidhuber. Deep learning in neural networks: An overview[J]. Neural Networks, 2015, 61: 85–117.
Sagi Omer, Rokach Lior. Approximating XGBoost with an interpretable decision tree[J]. Information Sciences, 2021. 572.
Shuai Zhikang, Special Editor’s Message [J]. Automation of Electric Power Systems, 2017, 41(8): 1–1.
Shang Yuwei, Guo Jianbo, Wu Wenchuan, et al. A Preliminary Study of Electric Brain: A Multimodal Adaptive Learning System [J]. Proceedings of the CSEE, 2018, 38(11): 3133–3143.
Liu Jiahan, Chen Kexu, Ma Jian, et al. Classification of three-phase voltage sags based on convolutional neural network and random forest [J]. Power System Protection and Control, 2019, 47(20): 112–118.
Wang Wei, Li Kaicheng, Xu Liwu, et al. Power quality disturbance identification method based on one-dimensional convolutional neural network multi task learning [J]. Electrical Measurement and Instrumentation, 2022, 59(03): 18–25.
Qu Xiangshuai, Duan Bin, Yin Qiaoxuan, et al. Power quality disturbance classification method based on sparse automatic encoder depth neural network [J]. Electric Power Automation Equipment | Electr Power Autom Eq, 2019, 39(05): 157–162.
Shanmugapriya S, Maharajan D. Most Valuable Player Algorithm Based State Estimation for Energy Systems[J]. Distributed Generation and Alternative Energy Journal, 2021.
M. D. Zeiler, M. Ranzato, R. Monga, et al. On rectified linear units for speech processing[C] //2013 IEEE International Conference on Acoustics, Speech and Signal Processing. Vancouver, BC, Canada: IEEE, 2013: 3517–3521.
Zheng Zhicong, Wang Hong, Qi Linhai. Voltage sag source identification method based on deep learning model fusion [J]. Proceedings of the CSEE, 2019, 39(01): 97–104+
Kang Rui, Qi Linhai, Wang Hong, et al. Parallel real-time monitoring technology for transient voltage disturbances based on flow computing [J]. Power System Protection and Control, 2020, 48(02): 129–136.
Lea Colin, Flynn M D, Vidal R, et al. Temporal convolutional networks for action segmentation and detection[C]//30th IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, USA, 2017: 1003–1012.
Krizhevsky A, Sutskever I, Hinton G. ImageNet classification with deep convolutional neural networks[C]// NIPS’12 Proceedings of the 25th International Conference on Neural Information Processing Systems, December 3–6, 2012, Nevada, USA: 1097–1105.
Vaswani A, Shazeer N, Parmar N, et al. Attention Is All You Need[J]. arXiv, 2017.
Alnafessah A, Casale G. A Neural-Network Driven Methodology for Anomaly Detection in Apache Spark[C]// 11th International Conference on the Quality of Information and Communications Technology. 2018.
Karunaratne P, Karunasekera S, Harwood A. Distributed stream clustering using micro-clusters on Apache Storm[J]. Journal of Parallel & Distributed Computing, 2017, 108(Oct.):74–84.
Carbone Paris, Ewen Stephan, Fóra Gyula, et al. State management in Apache Flink®
: consistent stateful distributed stream processing[J]. Proceedings of the VLDB Endowment, 2017, 10(12): 1718–1729.
Electrical I O. IEEE Guide for Voltage Sag Indices[C]// IEEE Std. IEEE, 2014:1–59.
Li Xialin, Liu Yajuan, Zhu Wu A new method for classification and identification of composite voltage sag sources based on distribution network [J] Power System Protection and Control, 2017, 45(2): 131–139.
Dou J, Liu Z, Xiong W, et al. Research on Multi-level Cooperative Detection of Power Grid Dispatching Fault Based on Artificial Intelligence Technology[J]. Distributed Generation and Alternative Energy Journal, 2021.
Zheng Y, Xue X. Simulation of Wind-solar Complementary Distribution Power Generation System Based on PSCAD[J]. Distributed Generation and Alternative Energy Journal, 2021.
