基于集成学习与深度学习的日供水量预测方法
|
|
周欣磊,顾海挺,刘晶,许月萍,耿芳,王冲
|
Daily water supply prediction method based on integrated learning and deep learning
|
|
Xin-lei ZHOU,Hai-ting GU,Jing LIU,Yue-ping XU,Fang GENG,Chong WANG
|
|
| 表 7 4座水厂不同供水预测方法的性能对比 |
| Tab.7 Performance comparison of different water supply forecasting models for four water plants |
|
| 方法 | 赤岸水厂 | | 大陈水厂 | | 佛堂水厂 | | 中心水厂 | | NSE | MAE/
(m3·d−1) | RMSE/
(m3·d−1) | NSE | MAE/
(m3·d−1) | RMSE/
(m3·d−1) | NSE | MAE/
(m3·d−1) | RMSE/
(m3·d−1) | NSE | MAE/
(m3·d−1) | RMSE/
(m3·d−1) | | RF | 0.852 | 171.5 | 239.1 | | 0.943 | 499.5 | 674.0 | | 0.897 | 1 205.1 | 1 812.2 | | 0.894 | 1 122.7 | 1 827.5 | | AdaBoost | 0.844 | 187.8 | 245.2 | 0.892 | 791.9 | 929.8 | 0.816 | 1 587.6 | 2 420.7 | 0.836 | 1 611.3 | 2 275.0 | | LSTM | 0.900 | 158.3 | 196.1 | 0.961 | 475.9 | 557.7 | 0.913 | 1 190.0 | 1 662.0 | 0.905 | 1 258.9 | 1 733.6 | | 改进LSTM | 0.929 | 118.4 | 165.2 | 0.971 | 402.2 | 484.8 | 0.925 | 1 131.8 | 1 545.2 | 0.924 | 1 113.9 | 1 547.2 |
|
|
|