Research on the Construction of Short-term Prediction Model of Wind Farm Output Power Based on Deep Learning Model
DOI:
https://doi.org/10.13052/spee1048-5236.4418Keywords:
Deep learning, wind farms, power prediction, model optimizationAbstract
With the shift in the global energy structure, wind energy has become increasingly prominent in the energy market. However, wind power generation poses great challenges to grid dispatching due to its intermittency and randomness, so accurate wind power output prediction is of great significance to improve grid stability and reduce operating costs. Based on deep learning technology, this paper constructs a model for short-term power forecasting of wind farms, aiming to improve the accuracy of wind power forecasting. The model in this paper has been improved in data preprocessing, feature extraction and algorithm optimization. We used the actual operation data of a wind farm in a coastal area. The data covered three years of historical wind speed, wind direction and power output information, totaling more than 500,000 data records. The model adopts a long-term and short-term memory network architecture and combines self-attention mechanism to perform multi-step prediction. Finally, the average absolute error on the test set is reduced to 0.045, prediction accuracy 15% traditional statistical. This study shows that the application of deep learning in wind power forecasting has significant advantages and provides an important reference for the construction of smart grids in the future.
Downloads
References
Ahmad, H. A., and Rashid, T. A. Planning the development of text-to-speech synthesis models and datasets with dynamic deep learning. Journal of King Saud University – Computer and Information Sciences, vol. 36(7), pp. 102131, 2024.
Alsoufi, M. A., Siraj, M. M., Ghaleb, F. A., Al-Razgan, M., Al-Asaly, M. S., Alfakih, T., and Saeed, F. Anomaly-Based Intrusion Detection Model Using Deep Learning for IoT Networks. CMES – Computer Modeling in Engineering and Sciences, vol. 141(1), pp. 823–845, 2024.
Chen, E., Andersen, M. S., and Chandra, R. Deep learning framework with Bayesian data imputation for modelling and forecasting groundwater levels. Environmental Modelling & Software, vol. 178, pp. 106072, 2024.
Sedighizadeh, M., Yarmohammadi, H., and Esmaili, M. Enhancing FRT performance and smoothing output power of DFIG wind farm equipped by SFCL and SMES in a fuzzy framework. Engineering Science and Technology, an International Journal, vol. 22(3), pp. 801–810, 2019.
Sobolewski, R. A., and Feijóo, A. E. Estimation of wind farms aggregated power output distributions. International Journal of Electrical Power & Energy Systems, vol. 46, pp. 241–249, 2013.
Wang, S., Li, B., Li, G., Li, B., Li, H., Jiao, K., and Wang, C. A comprehensive review on the development of data-driven methods for wind power prediction and AGC performance evaluation in wind–thermal bundled power systems. Energy and AI, vol. 16, pp. 100336, 2024.
Cheng, Z., Chen, M., Liu, H., Xia, M., and Gong, W. Channel modeling for diffusion-based molecular MIMO communications using deep learning. Nano Communication Networks, vol. 42, pp. 100543, 2024.
Guo, Z., Wang, H., Zhu, H., and Qu, Z. Constraint-incorporated deep learning model for predicting heat transfer in porous media under diverse external heat fluxes. Energy and AI, vol. 18, pp. 100425, 2024.
Olanrewaju-George, B., and Pranggono, B. Federated learning-based intrusion detection system for the internet of things using unsupervised and supervised deep learning models. Cyber Security and Applications, vol. 3, pp. 100068, 2025.
Su, G., Qin, Y., Xu, H., and Liang, J. Automatic real-time crack detection using lightweight deep learning models. Engineering Applications of Artificial Intelligence, vol. 138, pp. 109340, 2024.
Tian, J., Chen, C., Lu, X., Li, Y., and Chen, J. Deep transfer learning-based time-varying model for deformation monitoring of high earth-rock dams. Engineering Applications of Artificial Intelligence, vol. 138, pp. 109310, 2024.
Uçkan, T. Integrating PCA with deep learning models for stock market Forecasting: An analysis of Turkish stocks markets. Journal of King Saud University – Computer and Information Sciences, vol. 36(8), pp. 102162, 2024.
Wang, D., Zhou, S., and Zhang, Y. A spatiotemporal chaos based deep learning model watermarking scheme. Applied Soft Computing, vol. 164, pp. 112004,2024.
Wang, Y., Lu, X., Gao, Y., and Chen, Y. An anti-swing control method combining deep learning prediction models with a multistate fractional-order terminal sliding mode controller for wave motion compensation devices. Mechanical Systems and Signal Processing, vol. 223, pp. 111819, 2025.
Xia, H. Modeling and control strategy of small unmanned helicopter rotation based on deep learning. Systems and Soft Computing, vol. 6, pp. 200146, 2024.
Yan, Y., Yang, Y., Fang, S., Gao, M., and Chen, Y. MUS Model: A Deep Learning-Based Architecture for IoT Intrusion Detection. Computers, Materials and Continua, vol. 80(1), pp. 875–896, 2024.
Liao, X., Zhang, Y., Li, Z., Wei, H., and Ding, H. Probabilistic interval power flow calculation method for distribution networks considering the correlation of distributed wind power output. International Journal of Electrical Power & Energy Systems, vol. 157, pp. 109827, 2024.
Liu, C., Li, Q., Wei, L., and Li, C. Wind power system based state estimation and measurement using weighted Grey Wolf Optimization. Computers and Electrical Engineering, vol. 110, pp. 108797, 2023.
Pedersen, J., Weinand, J. M., Syranidou, C., and Rehfeldt, D. An efficient solver for large-scale onshore wind farm siting including cable routing. European Journal of Operational Research, vol. 317(2), pp. 616–630, 2024.
Zeng, B., Huang, G., and Chen, W. Research progress and prospects of urban flooding simulation: From traditional numerical models to deep learning approaches. Environmental Modelling & Software, vol. 183, pp. 106213, 2025.
Bibih, M., Choukri, K., khaili, M. E., and Chakir, H. E. Assessing the potential of green hydrogen production from wind power: Case of microgrid. Procedia Computer Science, vol. 236, pp. 25–32, 2024.
Bull, L. A., Gardner, P. A., Rogers, T. J., Dervilis, N., Cross, E. J., Papatheou, E., Maguire, A. E., Campos, C., and Worden, K. Bayesian modelling of multivalued power curves from an operational wind farm. Mechanical Systems and Signal Processing, vol. 169, pp. 108530, 2022.
Dong, Y., and Xiao, L. Enhancing wind power generation prediction using relevance assessment-based transfer learning. Knowledge-Based Systems, vol. 303, pp. 112417, 2024.
Gao, J., Ji, M., Wang, H., and Du, Z. Research on the IL-Bagging-DHKELM Short-Term Wind Power Prediction Algorithm Based on Error AP Clustering Analysis. Computers, Materials and Continua, vol. 79(3), pp. 5017–5030, 2024.
Han, R., Hu, Q., Fang, X., Qian, T., and Zhang, Y. Frequency security-constrained unit commitment with fast frequency support of DFIG-based wind power plants. International Journal of Electrical Power & Energy Systems, vol. 160, pp. 110119, 2024.
https://aeeeuropeenergy.com/
