Graph Neural Networks for Electric and Hydraulic Data Fusion to Enhance Short-term Forecasting of Pumped-storage Hydroelectricity
##plugins.themes.bootstrap3.article.main##
##plugins.themes.bootstrap3.article.sidebar##
Abstract
Pumped-storage hydropower plants (PSH) actively participate in grid power-frequency control and therefore often operate under dynamic conditions, which results in rapidly varying system states. Predicting these dynamically changing states is essential for comprehending the underlying sensor and machine conditions. This understanding aids in detecting anomalies and faults, ensuring the reliable operation of the connected power grid, and in identifying faulty and miscalibrated sensors. PSH are complex, highly interconnected systems encompassing electrical and hydraulic subsystems, each characterized by their respective underlying networks that can individually be represented as graph. To take advantage of this relational inductive bias, graph neural networks (GNNs) have been separately applied to state forecasting tasks in the individual subsystems, but without considering their interdependencies. In PSH, however, these subsystems depend on the same control input, making their operations highly interdependent and interconnected. Consequently, hydraulic and electrical sensor data should be fused across PSH subsystems to improve state forecasting accuracy. This approach has not been explored in GNN literature yet because many available PSH graphs are limited to their respective subsystem boundaries, which makes the method unsuitable to be applied directly. In this work, we introduce the application of spectral-temporal graph neural networks, which leverage self-attention mechanisms to concurrently capture and learn meaningful subsystem interdependencies and the dynamic patterns observed in electric and hydraulic sensors. Our method effectively fuses data from the PSH’s subsystems by operating on a unified, system-wide graph, learned directly from the data, This approach leads to demonstrably improved state forecasting performance and enhanced generalizability.
How to Cite
##plugins.themes.bootstrap3.article.details##
pumped-storage hydropower plant, hydroelectricity, data fusion, graph neural networks, state forecasting
Cao, D., Li, J., Ma, H., & Tomizuka, M. (2021, May). Spectral Temporal Graph Neural Network for Trajectory Prediction. In 2021 IEEE International Conference on Robotics and Automation (ICRA) (pp. 1839–1845). doi: 10.1109/ICRA48506.2021.9561461
Cao, D., Wang, Y., Duan, J., Zhang, C., Zhu, X., Huang, C.,Zhang, Q. (2021, March). Spectral Temporal Graph Neural Network for Multivariate Time-series Forecasting (No. arXiv:2103.07719). arXiv. doi: 10.48550/arXiv.2103.07719
Chen, D., Liu, R., Hu, Q., & Ding, S. X. (2021). Interaction-Aware Graph Neural Networks for Fault Diagnosis of Complex Industrial Processes. IEEE Transactions on Neural Networks and Learning Systems, 1–14. doi: 10.1109/TNNLS.2021.3132376
Fatah, M. G. A., Claessens, B. J., & Schoukens, M. (2021, August). Integrating Power Grid Topology in Graph Neural Networks for Power Flow. Eindhoven University of Technology, 11.
Grigsby, J., Wang, Z., & Qi, Y. (2022, May). Long-Range Transformers for Dynamic Spatiotemporal Forecasting (No.arXiv:2109.12218). arXiv.
Guo, W., Che, L., Shahidehpour, M., & Wan, X. (2021, January). Machine-Learning based methods in short-term load forecasting. The Electricity Journal, 34(1), 106884. doi: 10.1016/j.tej.2020.106884
Halder, M. (2018, September). Power Demand Management – Smart Grid @ SBB. Innotrans.
Jeddi, A. B., & Shafieezadeh, A. (2021, December). A Physics-Informed Graph Attention-based Approach for Power Flow Analysis. In 2021 20th IEEE International Conference on Machine Learning and Applications (ICMLA) (pp. 1634–1640). doi: 10.1109/ICMLA52953.2021.00261
Kim, H., Jeong, J., & Kim, C. (2022, November). Daily Peak-Electricity-Demand Forecasting Based on Residual Long Short-Term Network. Mathematics, 10(23), 4486. doi: 10.3390/math10234486
Kundacina, O., Cosovic, M., & Vukobratovic, D. (2022, April). State Estimation in Electric Power Systems Leveraging Graph Neural Networks (No. arXiv:2201.04056). arXiv.
Li, S., Pandey, A., Hooi, B., Faloutsos, C., & Pileggi, L. (2022, September). Dynamic Graph-Based Anomaly Detection in the Electrical Grid. IEEE Transactions on Power Systems, 37(5), 3408–3422. doi: 10.1109/TPWRS.2021.3132852
Liao, W., Bak-Jensen, B., Radhakrishna Pillai, J., Wang, Y., & Wang, Y. (2022). A Review of Graph Neural Networks and Their Applications in Power Systems. Journal of Modern Power Systems and Clean Energy, 10(2), 345–360. doi: 10.35833/MPCE.2021.000058
Liao, W., Yang, D., Wang, Y., & Ren, X. (2021, March). Fault diagnosis of power transformers using graph convolutional network. CSEE Journal of Power and Energy Systems, 7(2), 241–249. doi: 10.17775/CSEEJPES.2020.04120
Lin, W., Wu, D., & Boulet, B. (2021, November). Spatial-Temporal Residential Short-Term Load Forecasting via Graph Neural Networks. IEEE Transactions on Smart Grid, 12(6), 5373–5384. doi: 10.1109/TSG.2021.3093515
Ma, Y., Liu, X., Shah, N., & Tang, J. (2023, July). Is Homophily a Necessity for Graph Neural Networks? (No.arXiv:2106.06134). arXiv.
Nauck, C., Lindner, M., Sch ̈urholt, K., Zhang, H., Schultz, P., Kurths, J., Hellmann, F. (2022, April). Predicting Basin Stability of Power Grids using Graph Neural Networks. New Journal of Physics, 24(4), 043041. doi: 10.1088/1367-2630/ac54c9
Nguyen, B., Vu, T., Nguyen, T.-T., Panwar, M., & Hovsapian, R. (2022, October). Spatial-Temporal Recurrent Graph Neural Networks for Fault Diagnostics in Power Distribution Systems (No. arXiv:2210.15177). arXiv. doi: 10.48550/arXiv.2210.15177
Nicolet, C., Greiveldinger, B., Herou, J. J., Kawkabani, B., Allenbach, P., Simond, J.-J., & Avellan, F. (2007, November). High-Order Modeling of Hydraulic Power Plant in Islanded Power Network. IEEE Transactions on Power Systems, 22(4), 1870–1880. doi: 10.1109/TPWRS.2007.907348
Pagnier, L., & Chertkov, M. (2021a, March). Embedding Power Flow into Machine Learning for Parameter and State Estimation (No. arXiv:2103.14251). arXiv. doi: 10.48550/arXiv.2103.14251
Pagnier, L., & Chertkov, M. (2021b, February). Physics-Informed Graphical Neural Network for Parameter & State Estimations in Power Systems (No. arXiv:2102.06349). arXiv. doi: 10.48550/arXiv.2102.06349
Ringsquandl, M., Sellami, H., Hildebrandt, M., Beyer, D., Henselmeyer, S., Weber, S., & Joblin, M. (2021, October). Power to the Relational Inductive Bias: Graph Neural Networks in Electrical Power Grids. In Proceedings of the 30th ACM International Conference on Information & Knowledge Management (pp. 1538–1547). doi: 10.1145/3459637.3482464
Simeunovi ́c, J., Schubnel, B., Alet, P.-J., & Carrillo, R. E. (2022, April). Spatio-Temporal Graph Neural Net-
works for Multi-Site PV Power Forecasting. IEEE Transactions on Sustainable Energy, 13(2), 1210–1220. doi: 10.1109/TSTE.2021.3125200
Simond, J.-J., Allenbach, P., Nicolet, C., & Avellan, F. (Eds.). (2006). Simulation tool linking hydroelectric production sites and electrical networks. Proceedings of 27th Int. Conf. on Electrical Machines, ICEM.
Wang, F., Chen, P., Zhen, Z., Yin, R., Cao, C., Zhang, Y., & Dui ́c, N. (2022, October). Dynamic spatio-temporal correlation and hierarchical directed graph structure based ultra-short-term wind farm cluster power forecasting method. Applied Energy, 323, 119579. doi: 10.1016/j.apenergy.2022.119579
Wu, H., Wang, M., Xu, Z., & Jia, Y. (2022, November). Graph Attention Enabled Convolutional Network for Distribution System Probabilistic Power Flow. IEEE Transactions on Industry Applications, 58(6), 7068–7078. doi: 10.1109/TIA.2022.3202159
Wu, T., Scaglione, A., & Arnold, D. (2022, September). Complex-Value Spatio-temporal Graph Convolutional Neural Networks and its Applications to Electric Power Systems AI (No. arXiv:2208.08485). arXiv. doi: 10.48550/arXiv.2208.08485
Wu, Y., Dai, H.-N., & Tang, H. (2022, June). Graph Neural Networks for Anomaly Detection in Industrial Internet of Things.IEEE Internet of Things Journal, 9(12), 9214–9231. doi: 10.1109/JIOT.2021.3094295
Zhao, M., & Fink, O. (2024, January). DyEdgeGAT: Dynamic Edge via Graph Attention for Early Fault Detection in IioT Systems (No. arXiv:2307.03761). arXiv. doi: 10.48550/arXiv.2307.03761
Zheng, J., Xu, C., Zhang, Z., & Li, X. (2017, March). Electric load forecasting in smart grids using Long-Short-Term-Memory based Recurrent Neural Network. In 2017 51st Annual Conference on Information Sciences and Systems (CISS) (pp.1–6). doi: 10.1109/CISS.2017.7926112
Zhu, J., Song, Y., Zhao, L., & Li, H. (2020, June). A3T-GCN: Attention Temporal Graph Convolutional Network for Traffic Forecasting (No. arXiv:2006.11583). arXiv. doi: 10.48550/arXiv.2006.11583
Zhu, Y., Gu, C., & Li, F. (2020, July). Cross-Domain Data Fusion On Distribution Network Voltage Estimation with D-S Evidence Theory. In 2020 International Joint Conference on Neural Networks (IJCNN) (pp. 1–6). doi: 10.1109/IJCNN48605.2020.9207414
This work is licensed under a Creative Commons Attribution 3.0 Unported License.
The Prognostic and Health Management Society advocates open-access to scientific data and uses a Creative Commons license for publishing and distributing any papers. A Creative Commons license does not relinquish the author’s copyright; rather it allows them to share some of their rights with any member of the public under certain conditions whilst enjoying full legal protection. By submitting an article to the International Conference of the Prognostics and Health Management Society, the authors agree to be bound by the associated terms and conditions including the following:
As the author, you retain the copyright to your Work. By submitting your Work, you are granting anybody the right to copy, distribute and transmit your Work and to adapt your Work with proper attribution under the terms of the Creative Commons Attribution 3.0 United States license. You assign rights to the Prognostics and Health Management Society to publish and disseminate your Work through electronic and print media if it is accepted for publication. A license note citing the Creative Commons Attribution 3.0 United States License as shown below needs to be placed in the footnote on the first page of the article.
First Author et al. This is an open-access article distributed under the terms of the Creative Commons Attribution 3.0 United States License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.