VMD-Transformer-Based Wind Speed Forecasting for Spot Market Trading
Main Article Content
Abstract
In the power spot market, renewable energy power generation usually show very big fluctuation, so accurate wind speed forecast becomes more and more important. To solve this problem, this study propose a mixed forecasting framework which combine Variational Mode Decomposition (VMD) with a Transformer-based predict network: first, using VMD to decompose the complex wind speed series into many components of different time-scale, so that can dig out more richer and more structural dynamic feature; then, these refine signal will be put into Transformer model, who is good at catching long-short term time dependency, in order to exactly extract the micro hidden pattern in wind speed fluctuation. The experiment results show that the VMD-Transformer framework has quite strong generalization ability and also high prediction accuracy, so overall it works pretty nicely. The proposed method provides a reliable forecasting tool for renewable energy operation. It also gives effective decision support for power dispatching and participation in the electricity spot market.
Downloads
Article Details
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
References
Z. H. Huang, “Research on the trading mode of electricity spot market under the high proportion of new energy,” Market Weekly, 2025.
C. Chen, S. J. Yuan, Z. L. Yin, et al., “A quantitative evaluation method for the volatility of distributed generation power time series,” J. Electron. Inf. Technol., 2022.
Q. Wu and X. Zhu, “Optimal bidding strategy of a wind power producer in Chinese spot market considering green certificate trading,” Environmental Science & Pollution Research, vol. 31, no. 9, 2024.
X. L. Liu, Z. Lin, and Z. M. Feng, “Short-term offshore wind speed forecast by seasonal ARIMA—A comparison against GRU and LSTM,” Energy, vol. 227, Art. no. 120492, 2021.
K. Y. Shi, D. X. Zhang, X. Q. Han, et al., “Digital twin model of photovoltaic power generation based on LSTM and transfer learning,” Power Syst. Technol., vol. 46, no. 4, pp. 1363–1372, 2022.
Z. Q. Dong, “Ultra-short term wind speed prediction based on DTW-FCBF-LSTM model,” Electr. Meas. Instrum., vol. 57, no. 4, pp. 93–98, 2020.
Z. H. Chen, W. Teng, X. F. Xu, et al., “Long-term wind power prediction based on graph convolutional network and wind speed difference fitting,” China Electr. Power, vol. 56, no. 10, pp. 96–105, 2023.
R. Hu, J. F. Qiao, Y. H. Li, et al., “Long-term wind power prediction based on WOA-VMD-SSA-LSTM,” Sol. Energy, vol. 45, no. 9, pp. 549–556, 2024.
M. Ashraf, B. Raza, M. Arshad, et al., “Performance enhancement of short-term wind speed forecasting model using realtime data,” PLoS One, vol. 19, no. 5, p. 19, 2024.
R. K. Reja, R. Amin, Z. Tasneem, et al., “A new ANN technique for short-term wind speed prediction based on SCADA system data in Turkey,” Atmosphere, vol. 14, no. 10, Art. no. 1516, 2023.
B. Huang, Y. Liang, and X. Qiu, “Wind power forecasting using attention-based recurrent neural networks: A comparative study,” IEEE Access, vol. 9, pp. 40432–40444, 2021.
S. Wang, C. Liu, K. Liang, et al., “Wind speed prediction model based on improved VMD and sudden change of wind speed,” Sustainability, vol. 14, no. 14, Art. no. 8705, 2022.
S. Parri, K. Teeparthi, and V. Kosana, “A hybrid VMD based contextual feature representation approach for wind speed forecasting,” Renew. Energy, vol. 219, Art. no. 119391, 2023.
S. Zhang, C. Zhu, and X. Guo, “Wind-speed multi-step forecasting based on variational mode decomposition, temporal convolutional network, and transformer model,” Energies, vol. 17, no. 9, Art. no. 1996, 2024.
Q. Wang and L. Zhang, “Short-term wind speed prediction of wind farm based on TSO-VMD-BiLSTM,” PeerJ Computer Science, vol. 10, 2024.
Y. Liu, S. C. Wang, H. Liu, et al., “Ultra-short-term wind speed combined prediction based on WOA-VMD-CNN-Transformer,” Comput. Syst. Appl., vol. 33, pp. 1–11, 2024.
S. Li, L. Guo, J. Zhu, et al., “Medium-term offshore wind speed multi-step forecasting based on VMD and GRU-MATNet model,” Ocean Eng., vol. 325, Art. no. 120737, 2025.
M. Zhao, G. Guo, L. Fan, et al., “Author correction: Short-term natural gas load forecasting based on EL-VMD-Transformer-ResLSTM,” Sci. Rep., vol. 14, no. 1, 2024.