Long Short Term Memory Neural Network and Energy Applications in the Smart Grid Framework
The research is focused on implementing neural network architectures in the field of Deep Learning for various applications involving energy context. In particular, recurrent neural networks (RNN) of type Long Short Term Memory (LSTM) have been studied for the classification of signals and are being upgraded, with particular attention to the augmentation of the dataset in order to obtain a wider ability of generalization of the results from the obtained nets, with suitable hyperparameters, choice of the more effective layers and relative options of training.
Authors
- Silvia Licciardi (ORCID: https://orcid.org/0000-0003-4564-8866)
- Maurizio La Villetta (ORCID: https://orcid.org/0000-0002-2655-6088)
- Antonio Piacentino
- Guido Ala (ORCID: https://orcid.org/0000-0003-2558-4164)
- Rossano Musca (ORCID: https://orcid.org/0000-0002-7544-1631)
- Eleonora Riva Sanseverino (ORCID: https://orcid.org/0000-0003-0113-7650)
- Hamid Samadi (ORCID: https://orcid.org/0000-0003-0698-6520)
- Pietro Catrini (ORCID: https://orcid.org/0000-0002-1341-8946)
- Elisa Francomano (ORCID: https://orcid.org/0000-0003-0438-5115)
Institutions
- University of Palermo (IT)
Publication Details
- Published
- 2024-09-18
- DOI
- https://doi.org/10.1109/rtsi61910.2024.10761755
- Primary Topic
- Neural Networks and Applications
- Type
- article
- Field-Weighted Citation Impact
- 0.00