Research Article
An Empirical Study for Adopting Machine Learning Approaches for Gas Pipeline Flow Prediction
Table 5
Performance changes under different neighbors numbers and averaging methods.
| | Weighed | Neighbors | 7 | 6 | 5 | 4 | 3 | 2 | 1 |
| | Uniform | MSE | 3.00 × 103 | 2.80 × 103 | 2.70 × 103 | 2.50 × 103 | 2.20 × 103 | 1.80 × 103 | 1.50 × 103 | | MRE | 1.93 × 10−3 | 1.82 × 10−3 | 1.77 × 10−3 | 1.59 × 10−3 | 1.45 × 10−3 | 1.10 × 10−3 | 6.80 × 10−4 | | 1.61 × 10−5 | 1.50 × 10−5 | 1.41 × 10−5 | 1.30 × 10−5 | 1.18 × 10−5 | 9.66 × 10−6 | 7.84 × 10−6 |
| | Distance | MSE | 1.30 × 103 | 1.30 × 103 | 1.30 × 103 | 1.30 × 103 | 1.4 × 103 | 1.40 × 103 | 1.50 × 103 | | MRE | 7.63 × 10−4 | 7.47 × 10−4 | 7.64 × 10−4 | 7.38 × 10−4 | 7.95 × 10−4 | 7.51 × 10−4 | 6.80 × 10−4 | | 6.97 × 10−6 | 6.80 × 10−6 | 6.75 × 10−6 | 6.78 × 10−6 | 7.30 × 10−6 | 7.29 × 10−6 | 7.84 × 10−6 |
|
|
