Aiming at the problem of strong intermittency and volatility and low prediction accuracy of wind power
this paper proposes a short-term wind power prediction model based on Beluga whale optimization algorithm based on multi-strategy fusion (MBWO)
Variational mode decomposition (VMD)
and Kernel extreme learning machine (KELM) prediction model. Firstly
the original wind power sequence is smoothed by VMD and the MBWO-KELM model is constructed. secondly
the decomposed subsequences are input into the MBWO-KELM model for prediction. Finaly
the different subsequences are reconstructed to obtain the final wind power prediction. The results show that the prediction accuracy and stability of the model are significantly better than other models under different seasons
and the MAPE values are all controlled below 6%
which can improve the utilization efficiency of wind power energy.
LIU Z F, LIU Y Y, CHEN X R, et al.A novel deep learning-based evolutionary model with potential attention and memory decay-enhancement strategy for short-term wind power point-interval forecasting[J]. Applied energy, 2024, 360: 122785.
WANG C, HE Y, ZHANG H L, et al.Wind power forecasting based on manifold learning and a double-layer SWLSTM model[J]. Energy, 2024, 290: 130076.
DING Y F, CHEN Z J, ZHANG H W, et al.A short-term wind power prediction model based on CEEMD and WOA-KELM[J]. Renewable energy, 2022, 189: 188-198.
SHAN J N, WANG H Z, PEI G, et al.Research on short-term power prediction of wind power generation based on WT-CABC-KELM[J]. Energy reports, 2022, 8: 800-809.
LI L L, LIU Z F, TSENG M L, et al.Using enhanced crow search algorithm optimization-extreme learning machine model to forecast short-term wind power[J]. Expert systems with applications, 2021, 184: 115579.
JIANG J F, ZHANG X Y, YUAN Z.Feature selection for classification with Spearman's rank correlation coefficient-based self-information in divergence-based fuzzy rough sets[J]. Expert systems with applications, 2024, 249: 123633.
FU W L, FU Y C, LI B L, et al.A compound framework incorporating improved outlier detection and correction, VMD, weight-based stacked generalization with enhanced DESMA for multi-step short-term wind speed forecasting[J]. Applied energy, 2023, 348: 121587.