The Wind and Photovoltaic Power Forecasting Method Based on Digital Twins
Source abstract
Abstract
Wind and photovoltaic (PV) power forecasting are crucial for improving the operational efficiency of power systems and building smart power systems. However, the uncertainty and instability of factors affecting renewable power generation pose challenges to power system operations. To address this, this paper proposes a digital twin-based method for predicting wind and PV power. By utilizing digital twin technology, this approach provides a highly realistic simulation environment that enables accurate monitoring, optimal control, and decision support for power system operations. Furthermore, a digital twin platform for the AI (Artificial Intelligence) Grid is established, allowing real-time monitoring, and ensuring the safe, reliable, and stable operation of the grid. Additionally, a deep learning-based model WPNet is developed to predict wind and PV power at specific future time points. Four datasets are constructed based on weather conditions and historical wind and PV power data from the Flanders and Wallonia regions. The prediction models presented in this paper demonstrate excellent performance on these datasets, achieving mean square error (MSE) values of 0.001399, 0.001833, 0.000704, and 0.002708; mean absolute error (MAE) values of 0.025164, 0.027854, 0.018592, and 0.033501; and root mean square error (RMSE) values of 0.037409, 0.042808, 0.026541, and 0.052042, respectively.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Energy Load and Power Forecasting · Power System Reliability and Maintenance · Solar Radiation and Photovoltaics
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Electronic Information and Artificial Intelligence, Shaanxi University of Science & Technology, Xi’an 710016, China
Funding
Shaanxi Provincial Department of Education Service Local Special Plan Project
References (25)
Show source-provided references
1. AI Grid-The new and improved power grid: A survey10.1109/SURV.2011.101911.00087 ↗
2. Brosinsky, C., Westermann, D., and Krebs, R. (2018, January 3–7). Recent and prospective developments in power system control centers: Adapting the digital twin technology for application in power system control centers. Proceedings of the 2018 IEEE International Energy Conference (ENERGYCON) of the Conference, Limassol, Cyprus.10.1109/ENERGYCON.2018.8398846 ↗
3. Review of digital twin about concepts, technologies, and industrial applications10.1016/j.jmsy.2020.06.017 ↗
4. Kummerow, A., Nicolai, S., Brosinsky, C., Westermann, D., Naumann, A., and Richter, M. (2020, January 2–6). Digital-Twin based Services for advanced Monitoring and Control of future power systems. Proceedings of the 2020 IEEE Power & Energy Society General Meeting (PESGM) of the Conference, Montreal, QC, Canada.10.1109/PESGM41954.2020.9354468 ↗
5. Digital twin framework and its application to power grid online analysis
6. Saad, A., Faddel, S., and Mohammed, O. (2020). IoT-based digital twin for energy cyber-physical systems: Design and implementation. Energies, 13.10.3390/en13184762 ↗
7. A digital twin approach for fault diagnosis in distributed photovoltaic systems10.1109/TPEL.2019.2911594 ↗
8. Using the ensemble Kalman filter for electricity load forecasting and analysis10.1016/j.energy.2016.03.070 ↗
9. Nonparametric regression based short-term load forecasting10.1109/59.708572 ↗
10. Local regression-based short-term load forecasting10.1023/A:1012094702855 ↗
11. Pattern-based local linear regression models for short-term load forecasting10.1016/j.epsr.2015.09.001 ↗
12. Forecasting day-ahead electricity load using a multiple equation time series approach10.1016/j.ejor.2015.12.030 ↗
13. Xishuang, D., Lijun, Q., and Lei, H. (2017, January 13–16). Short-term load forecasting in AI Grid: A combined CNN and K-means clustering approach. Proceedings of the 2017 IEEE International Conference on Big Data and Smart Computing (BigComp) of the Conference, Jeju, Republic of Korea.10.1109/BIGCOMP.2017.7881726 ↗
14. Algorithm AS 136: A k-means clustering algorithm
15. Wang, J., Zhou, Y., and Chen, X. (2007, January 18–21). Electricity Load Forecasting Based on Support Vector Machines and Simulated Annealing Particle Swarm Optimization Algorithm. Proceedings of the 2007 IEEE International Conference on Automation and Logistics of the Conference, Jinan, China.10.1109/ICAL.2007.4339064 ↗
16. Ren, G., Wen, S., Yan, Z., Hu, R., Zeng, Z., and Cao, Y. (2016, January 12–15). Power load forecasting based on support vector machine and particle swarm optimization. Proceedings of the 2016 12th World Congress on Intelligent Control and Automation (WCICA) of the Conference, Guilin, China.10.1109/WCICA.2016.7578535 ↗
17. Short-term load forecasts using LSTM networks10.1016/j.egypro.2019.01.952 ↗
18. Choi, H., Ryu, S., and Kim, H. (2018, January 29–31). Short-Term Load Forecasting based on ResNet and LSTM. Proceedings of the 2018 IEEE International Conference on Communications, Control, and Computing Technologies for AI Grids (SmartGridComm) of the Conference, Aalborg, Denmark.10.1109/SmartGridComm.2018.8587554 ↗
19. He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 26). Deep residual learning for image recognition. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) of the Conference, Las Vegas, NV, USA.10.1109/CVPR.2016.90 ↗
20. A hybrid deep learning architecture for wind power prediction based on bi-attention mechanism and crisscross optimization10.1016/j.energy.2021.121795 ↗
21. Zheng, J., Chen, X., Yu, K., Gan, L., Wang, Y., and Wang, K. (2018, January 6–8). Short-term Power Load Forecasting of Residential Community Based on GRU Neural Network. Proceedings of the 2018 International Conference on Power System Technology (POWERCON) of the Conference, Guangzhou, China.10.1109/POWERCON.2018.8601718 ↗
22. Poczeta, K., and Papageorgiou, E.I. (2022). Energy Use Forecasting with the Use of a Nested Structure Based on Fuzzy Cognitive Maps and Artificial Neural Networks. Energies, 15.10.3390/en15207542 ↗
23. Benchmarking physics-informed machine learning-based short term PV-power forecasting tools10.1016/j.egyr.2022.05.006 ↗
24. Cordeiro-Costas, M., Villanueva, D., Eguía-Oller, P., and Granada-Álvarez, E. (2022). Machine learning and deep learning models applied to photovoltaic production forecasting. Appl. Sci., 12.10.3390/app12178769 ↗
25. (2023, April 14). Elia Open Data Portal. Available online: https://opendata.elia.be/pages/home/.