Benchmark d03ba8db5892
| Parameter | Value |
|---|---|
| Benchmark hash | d03ba8db5892 |
| Original paper | https://doi.org/10.48550/arXiv.2503.17410 |
| Dataset | CESNET-TimeSeries24 |
| Aggregation | AGG_1_HOUR |
| Source | INSTITUTION_SUBNETS |
| Type | Time-Based |
| Train size | 0.35 |
| Val size | 0.05 |
| Test size | 0.6 |
| Uni/Multi variate | Univariate |
| Metrics | n_bytes |
| Default value | 0 |
| Filler | None |
| Transformer | MinMaxScaler |
| Anomaly handler | None |
| Sliding window train | 744 |
| Sliding window prediction | 168 |
| Sliding window step | 168 |
| Set shared size | 744 |
| TS IDs | 1.0 |
| Related work | Model | Average RMSE | Std RMSE | Average R2-score | Std R2-score |
|---|---|---|---|---|---|
| https://arxiv.org/abs/2503.17410 | GRU | 0.265 | 1.23 | -0.61 | 1.4 |
| https://arxiv.org/abs/2503.17410 | GRU_FCN | 0.269 | 1.23 | -1.67 | 3.3 |
| https://arxiv.org/abs/2503.17410 | INCEPTIONTIME | 0.613 | 1.18 | -8.85 | 2.8 |
| https://arxiv.org/abs/2503.17410 | LSTM | 0.265 | 1.23 | -0.55 | 1.3 |
| https://arxiv.org/abs/2503.17410 | LSTM_FCN | 0.265 | 1.23 | -0.94 | 2.2 |
| https://arxiv.org/abs/2503.17410 | MEAN | 0.402 | 1.69 | 0.0 | 0.1 |
| https://arxiv.org/abs/2503.17410 | RCLSTM | 0.326 | 1.37 | -2.26 | 2.9 |
| https://arxiv.org/abs/2503.17410 | RESNET | 0.275 | 1.23 | -0.91 | 1.8 |