Skip to content
empresstPublic

About

Code for our STI 2024 paper: hybrid BiLSTM/BiGRU/TCN with self-attention and XGBoost for load profile prediction

Topics

Resources

Stars

0 stars

Watchers

1 watching

Forks

Repository files navigation

STI

created a hybrid model with the combination of BiLSTM, BiGRU, TCN, XGBRegressor and temporal multihead Attention.

Created and modified the temporal multihead attention class for better time series forecasting

trained and tested it on both industry level real time data, climate and stock market

hyperparameters, btach sizes were tuned according to the dataset sizes

About

Code for our STI 2024 paper: hybrid BiLSTM/BiGRU/TCN with self-attention and XGBoost for load profile prediction

Topics

Resources

Stars

0 stars

Watchers

1 watching

Forks

Releases

Packages

Contributors

Languages