【摘要】 由于各种不确性因素以及用户的非线性和随机行为,导致电力负荷预测的难度进一步加大,由此需要一个更为准确以及稳定的电力负荷预测模型。为了进一步提高负荷预测预测精度,文章提出了一种新型的电力负荷预测模型——基于鲸鱼算法优化的VMD-LSTNet预测模型。该模型首先利用鲸鱼算法对VMD分解的IMF分量个数以及惩罚因子进行寻优,再利用LSTNet网络对各个IMF分量进行单独预测,最后对单个预测分量进行重构。实验结果表明,基于鲸鱼算法优化的VMD-LSTNet预测模型具有较好的预测精度。将该模型与传统预测模型进行对比,其均值绝对误差、平均绝对百分比误差及均方根误差均低于列举的预测模型。更多还原

【Abstract】 Due to various uncertain factors and the nonlinear and random behavior of users, the difficulty of power load forecasting is further increased, so a more accurate and stable power load forecasting model is required. In order to further improve the forecasting accuracy of load forecasting, this paper proposes a new power load forecasting model:VMD-LSTNet forecasting model optimized based on whale algorithm. The model first uses the whale algorithm to optimize the number of IMF components decomposed by VMD and the penalty factor, then uses the LSTNet network to predict each IMF component separately, and finally reconstructs a single predicted component. The experimental results show that the VMD-LSTNet prediction model optimized based on the whale algorithm has better prediction accuracy.Comparing this model with the traditional forecasting model, its mean absolute error, mean absolute percentage error and root mean square error are all lower than the listed forecasting models.更多还原