To enhance the accuracy of power load forecasting in wind farms, this study introduces an advanced combined forecasting method that integrates Variational Mode Decomposition (VMD) with an Improved Particle Swarm Optimization (IPSO) algorithm to optimize the Extreme Learning Machine (ELM). Initially, the VMD algorithm is employed to perform high-precision modal decomposition of the original power load data, which is then categorized into high-frequency and low-frequency sequences based on mutual information entropy theory. Subsequently, this research profoundly modifies the traditional multiverse optimizer by incorporating Tent chaos mapping, exponential travel distance rate, and an elite reverse learning mechanism, developing the IPSO-ELM prediction model. This model independently predicts the high and low-frequency sequences and reconstructs the data to achieve the final forecasting results. Simulation results indicate that the proposed method significantly improves prediction accuracy and convergence speed compared to traditional ELM, PSO-ELM, and PSO-ELM methods.

翻译：为提高风电场电力负荷预测的精度，本研究提出一种融合变分模态分解与改进粒子群优化算法以优化极限学习机的先进组合预测方法。首先，采用VMD算法对原始电力负荷数据进行高精度模态分解，并依据互信息熵理论将其划分为高频与低频序列。随后，本研究通过引入Tent混沌映射、指数型游走距离率及精英反向学习机制，对传统多元宇宙优化器进行深度改进，构建了IPSO-ELM预测模型。该模型分别对高频与低频序列进行独立预测，并通过数据重构获得最终预测结果。仿真实验表明，相较于传统ELM、PSO-ELM及PSO-ELM方法，所提方法在预测精度与收敛速度上均有显著提升。