基于重组二次分解及LSTNet-Atten的短期负荷预测
刘洪伟,王磊,刘阳,张鹏超,乔石

Short term load forecasting based on recombination quadratic decomposition and LSTNet-Atten
Hongwei LIU,Lei WANG,Yang LIU,Pengchao ZHANG,Shi QIAO
表 9 不同季节的性能比较
Tab.9 Performance comparison between different seasons
季节tpLSTMGRUCNN-LSTM本文模型
MAPE/%RMSE/MWMAPE/%RMSE/MWMAPE/%RMSE/MWMAPE/%RMSE/MW
春季31.8732647.85191.5256504.53281.7768618.22751.1130375.1620
春季62.6604842.18772.3041729.01852.1072696.21721.5066466.8072
春季123.1097978.81462.7551862.48312.4585783.82692.3577761.4055
夏季31.7202640.54281.7152584.58691.2806467.52841.1282401.3416
夏季62.0752776.52171.8062648.34801.9220699.10921.5260540.9594
夏季122.92531076.05072.2146849.37152.4865861.74211.91401086.1290
秋季32.77081017.86792.4773948.03722.4117977.81081.5094559.3695
秋季63.14401266.91242.83871091.78962.86521097.95741.8423710.4821
秋季123.80811381.74404.58261611.78713.77331399.80272.91591061.1052
冬季32.8918892.67682.4245837.65852.6789859.98351.2748414.5248
冬季63.00451000.14132.8462927.80102.8310913.74171.6032537.4815
冬季123.16861016.14633.94791241.77993.97681217.90632.3122738.8276