In smart grids and microgrids, time series prediction is a fundamental tool for enabling intelligent energy resource management and advanced interactions between heterogeneous agents. In this work, we propose a solution to the energy forecasting problem based on two machine learning techniques: Convolutional Neural Network and Long Short-Term Memory Network. These techniques are combined with a new embedding format to appropriately feed the time series to the stacked network architecture. The resulting novel deep learning scheme is able to retrieve information from the data by inferring time dependent correlation structures. The model is validated using real-world examples, showing good performances with a 3-days forecasting horizon.

A combined deep learning approach for time series prediction in energy environments / Rosato, A.; Succetti, F.; Araneo, R.; Andreotti, A.; Mitolo, M.; Panella, M.. - 2020-:(2020), pp. 1-5. (Intervento presentato al convegno 56th IEEE/IAS Industrial and Commercial Power Systems Technical Conference, I and CPS 2020 tenutosi a Las Vegas (virtual), U.S.A.) [10.1109/ICPS48389.2020.9176818].

A combined deep learning approach for time series prediction in energy environments

Rosato A.;Succetti F.;Araneo R.;Panella M.
2020

Abstract

In smart grids and microgrids, time series prediction is a fundamental tool for enabling intelligent energy resource management and advanced interactions between heterogeneous agents. In this work, we propose a solution to the energy forecasting problem based on two machine learning techniques: Convolutional Neural Network and Long Short-Term Memory Network. These techniques are combined with a new embedding format to appropriately feed the time series to the stacked network architecture. The resulting novel deep learning scheme is able to retrieve information from the data by inferring time dependent correlation structures. The model is validated using real-world examples, showing good performances with a 3-days forecasting horizon.
2020
56th IEEE/IAS Industrial and Commercial Power Systems Technical Conference, I and CPS 2020
convolutional Neural Network; deep learning; long short-term memory network; smart grids; time series prediction
04 Pubblicazione in atti di convegno::04b Atto di convegno in volume
A combined deep learning approach for time series prediction in energy environments / Rosato, A.; Succetti, F.; Araneo, R.; Andreotti, A.; Mitolo, M.; Panella, M.. - 2020-:(2020), pp. 1-5. (Intervento presentato al convegno 56th IEEE/IAS Industrial and Commercial Power Systems Technical Conference, I and CPS 2020 tenutosi a Las Vegas (virtual), U.S.A.) [10.1109/ICPS48389.2020.9176818].
File allegati a questo prodotto
File Dimensione Formato  
Rosato_Combined-deep-learning_2020.pdf

solo gestori archivio

Tipologia: Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 493.18 kB
Formato Adobe PDF
493.18 kB Adobe PDF   Contatta l'autore

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11573/1441345
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 5
  • ???jsp.display-item.citation.isi??? 2
social impact