Cold Wave Recognition and Wind Power Forecasting Technology Considering Sample Scarcity and Meteorological Periodicity Characteristics
Source abstract
Abstract
Accurate recognition of both cold wave occurrence and wind power during cold wave events is critically significant to ensure the stable operation of the power system under extreme meteorological conditions. In view of the above problems, this paper proposes a cold wave event recognition method and a day-ahead wind farm cluster power forecasting model. In order to effectively recognize cold wave events, this paper proposes a cold wave discrimination criterion based on wind turbine operation characteristics and NWP data. The proposed recognition criterion employs seasonal meteorological features processed through a GAN-enhanced multi-modal U-Net architecture, effectively mitigating sample scarcity issues. To improve the forecasting accuracy of wind farm cluster power during cold wave events, a combined forecasting model based on the Ns-Transformer model is constructed by combining NWP data with cold wave recognition results. A wind farm cluster is taken as an example to verify the effectiveness of the proposed method. Compared to that of LSTM, Random Forest, BP, and Transformer models, the RMSE of the proposed method is reduced by 5.65%, 5.58%, 4.81%, and 0.44%, respectively, during cold wave occurrence seasons. The results show that the proposed method is superior to the conventional method in terms of cold wave recognition ability and wind power forecasting accuracy.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Ocean Waves and Remote Sensing · Underwater Acoustics Research · Flood Risk Assessment and Management
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Electrical Engineering, Tsinghua University, Beijing 100084, China
State Grid Corporation of China, Beijing 100031, China
State Key Laboratory of Renewable Energy Grid-Integration, China Electric Power Research Institute, Haidian District, Beijing 100192, China
Key Laboratory of Modern Power System Simulation and Control & Renewable Energy Technology, Ministry of Education, Northeast Electric Power University, Jilin 132012, China
Funding
State Grid Corporation Limited Science and Technology Project Grant
References (39)
Show source-provided references
1. A centralized power prediction method for large-scale wind power clusters based on dynamic graph neural network10.1016/j.energy.2024.133210 ↗
2. National Energy Administration (2024). 2024 National Power Industry Statistics, National Energy Administration.
3. A Review on Impacts of Wind Power Uncertainties on Power Systems
4. Heat and Cold Waves in Mainland Spain: Origins, Characteristics, and Trends10.1016/j.wace.2022.100471 ↗
5. Reliability Evaluation of Wind Turbine Competitive Failure Considering Extreme Weather Impact Process
6. Quantifying the Impacts of Climate Change and Extreme Climate Events on Energy Systems10.1038/s41560-020-0558-0 ↗
7. Texas Electric Power Crisis of 2021 Warns of a New Blackout Mechanism
8. Ultra-Short-Term Wind Power Subsection Forecasting Method Based on Extreme Weather10.1109/TPWRS.2022.3224557 ↗
9. Review of Several Key Processes in Wind Power Forecasting: Mathematical Formulations, Scientific Problems, and Logical Relations10.1016/j.apenergy.2024.124631 ↗
10. Application and Prospect of Artificial Intelligence Technology in Renewable Energy Forecasting
11. Two-stage day-ahead multi-step prediction of wind power considering time-series information interaction10.1016/j.energy.2024.133580 ↗
12. Short-term wind power prediction method based on multivariate signal decomposition and RIME optimization algorithm10.1016/j.eswa.2024.125376 ↗
13. A Day-ahead Wind Speed Correction Method: Enhancing Wind Speed Forecasting Accuracy Using a Strategy Combining Dynamic Feature Weighting with Multi-Source Information and Dynamic Matching with Improved Similarity Function10.1016/j.eswa.2024.125724 ↗
14. Wind Speed Forecasting Using the Stationary Wavelet Transform and Quaternion Adaptive-gradient Methods10.1109/ACCESS.2021.3111667 ↗
15. A Hybrid Model Based on Multi-Stage Principal Component Extraction, GRU Network, and KELM For Multi-Step Short-Term Wind Speed Forecasting10.1109/ACCESS.2020.3043812 ↗
16. A Novel Genetic LSTM Model for Wind Power Forecast10.1016/j.energy.2021.120069 ↗
17. Viet, D.T., Phuong, V.V., Duong, M.Q., and Tran, Q.T. (2020). Models for Short-Term Wind Power Forecasting Based on Improved Artificial Neural Network Using Particle Swarm Optimization and Genetic Algorithms. Energies, 13.10.3390/en13112873 ↗
18. EALSTM-QR: Interval Wind-power Prediction Model Based on Numerical Weather Prediction and Deep Learning10.1016/j.energy.2020.119692 ↗
19. A Hybrid Model for Long-term Wind Power Forecasting Utilizing NWP Subsequence Correction and Multi-Scale Deep Learning Regression Methods10.1109/TSTE.2023.3283242 ↗
20. Wind Power Ultra-short-term Forecasting Method Based on NWP Wind Speed Correction and Double Clustering Division of Transitional Weather Process10.1016/j.energy.2023.128947 ↗
21. Research on Ultra-short-term Subsection Forecasting Method of Offshore Wind Power Considering Transitional Weather
22. Wind Power Forecasting Focused on Extreme Power System Events10.1109/TSTE.2012.2189442 ↗
23. An Integrated Modeling Strategy for Wind Power Forecasting Based on Dynamic Meteorological Visualization10.1109/ACCESS.2024.3401588 ↗
24. Research on Short-term Wind Power Forecasting Technology Under Low Temperature and Cold Wave Weather
25. Combined Approach for Short-term Wind Power Forecasting Under Cold Weather With Small Sample
26. Alerting to Rare Large-scale Ramp Events in Wind Power Generation10.1109/TSTE.2018.2822807 ↗
27. Power Forecasting Considering NWP Wind Speed Error Tolerability: A Strategy to Improve the Accuracy of Short-term Wind Power Forecasting Under Wind Speed Offset Scenarios10.1016/j.apenergy.2024.124720 ↗
28. Ultra-short-term Power Generation Modeling and Prediction for Small Hydropower in Data-scarce Areas Based on Sample Data Transfer Learning
29. Short-Term Wind Power Forecasting Based on Stacked Denoised Auto-encoder Deep Learning and Multi-evel Transfer Learning10.1002/we.2856 ↗
30. Data-augmented Sequential Deep Learning for Wind Power Forecasting10.1016/j.enconman.2021.114790 ↗
31. Physics-informed Reinforcement Learning for Probabilistic Wind Power Forecasting Under Extreme Events10.1016/j.apenergy.2024.124068 ↗
32. Ultra-short-term prediction of wind farm cluster power based on embedded graph structure learning with spatiotemporal information gain10.1109/TSTE.2024.3455759 ↗
33. An Objective Recognition Method for Wintertime Cold Fronts in Eurasia10.1007/s00376-021-0315-8 ↗
34. Grochowicz, A., van Greevenbroek, K., and Bloomfield, H. (2024). Using power system modelling outputs to identify weather-induced extreme events in highly renewable systems. Environ. Res. Lett., 19.10.1088/1748-9326/ad374a ↗
35. Li, Y., Chen, F., Yan, J., Ge, C., Han, S., and Liu, Y. (2025). Adaptive Short-term Wind Power Forecasting for Extreme Weather Based on Transfer Learning and AutoEncoder. Autom. Electr. Power Syst., 1–13.
36. Li, F., Liu, D., Sun, K., Hong, S., Peng, F., Zhang, C., Tao, T., and Qin, B. (2024). Stochastic and Extreme Scenario Generation of Wind Power and Supply–demand Balance Analysis Considering Wind Power-temperature Correlation. Electronics, 13.10.3390/electronics13112100 ↗
37. Road Extraction by Deep Residual U-Net10.1109/LGRS.2018.2802944 ↗
38. Generative Adversarial Networks: Introduction and Outlook10.1109/JAS.2017.7510583 ↗
39. A Non-stationary Transformer Model for Power Forecasting with Dynamic Data Distillation and Wake Effect Correction Suitable for Large Wind Farms10.1016/j.enconman.2024.119292 ↗