Skip to content

Benchmark 5d9e6e63cbf0

Parameter Value
Benchmark hash 5d9e6e63cbf0
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 168
Sliding window prediction 24
Sliding window step 24
Set shared size 168
TS IDs 1.0
Related work Model Average RMSE Std RMSE Average R2-score Std R2-score
https://arxiv.org/abs/2503.17410 GRU 0.237 1.15 -0.55 1.4
https://arxiv.org/abs/2503.17410 GRU_FCN 0.229 1.15 -0.27 1.1
https://arxiv.org/abs/2503.17410 INCEPTIONTIME 0.59 1.1 -8.9 2.7
https://arxiv.org/abs/2503.17410 LSTM 0.237 1.15 -0.53 1.3
https://arxiv.org/abs/2503.17410 LSTM_FCN 0.231 1.15 -0.55 1.8
https://arxiv.org/abs/2503.17410 MEAN 0.394 1.66 0.05 0.1
https://arxiv.org/abs/2503.17410 RCLSTM 0.334 1.48 -0.64 1.9
https://arxiv.org/abs/2503.17410 RESNET 0.244 1.15 -0.77 1.6