基于NRBO-VMD-WOA-ELM混合算法的短期风速预测OA

To address the limitations of existing short-term wind speed prediction methods in terms of accuracy,this study proposes a hybrid prediction model that integrates the variational mode decomposition(VMD),the Newton-Raphson-based optimizer(NRBO),whale optimization algorithm(WOA),and the extreme learning machine(ELM).The penalty factor α and mode number K of VMD are dynamically optimized by NRBO,yielding intrinsic mode functions(IMFs)with well-separated center frequencies and narrow bandwidths,effectively suppressing mode mixing and improving the learning efficiency and prediction accuracy of each sub-sequence.The decomposition produces four high-frequency components(IMF1～IMF4,accounting for 4.95%of total energy)and one low-frequency trend component(IMF5,accounting for 95.05%of total energy),where IMF5ʼs prediction accuracy primarily determines the upper bound of the overall model error through error propagation.The weights and thresholds of ELM for each component are subsequently optimized by WOA to enhance individual component prediction and final signal reconstruction.Validated using field-measured wind speed data at a bridge site,the results demonstrate that,relative to the baseline model WOA-ELM,the introduction of VMD decomposition reduces EMAE by 60.09%,and the subsequent incorporation of NRBO further reduces EMAE by 41.67%.Compared with four conventional single models,EMAE reductions of 80.11%,80.53%,63.79%,and 80.37%are achieved,respectively.Furthermore,WOA optimization of ELM weights and thresholds improves model stability and generalization capability,confirming the effectiveness of the proposed parameter dynamic optimization strategy with demonstrated potential for engineering applications.