Advances, Systems and Applications
Table 2 Comparison of Root Mean Square Error indicators for prediction results of different time steps of various models throughout the year
From: Short-term forecasting of surface solar incident radiation on edge intelligence based on AttUNet
Model | Step1 | Step2 | Step3 | Step4 | Step5 | Step6 | Step7 | Step8 |
|---|---|---|---|---|---|---|---|---|
ConvLSTM | 100.08 | 109.65 | 121.06 | 133.25 | 154.93 | 183.92 | 211.48 | 235.49 |
PhyDNet | 96.52 | 103.82 | 115.22 | 128.47 | 151.91 | 178.44 | 195.59 | 227.88 |
Traj-GRU | 97.88 | 104.77 | 119.31 | 130.21 | 150.32 | 174.46 | 190.93 | 224.31 |
E3D-LSTM | 95.24 | 101.92 | 116.01 | 125.44 | 142.09 | 163.44 | 180.19 | 207.23 |
PredRNN | 89.29 | 96.48 | 114.61 | 127.23 | 145.37 | 169.23 | 187.04 | 211.19 |
PredRNN++ | 87.11 | 93.22 | 107.42 | 124.23 | 141.50 | 162.91 | 184.75 | 209.41 |
EDA-AttUNet | 90.47 | 97.84 | 109.37 | 124.74 | 139.93 | 158.37 | 175.74 | 192.93 |