Comparative Analysis of Multivariable Deep Learning Models for Forecasting in Smart Grids

E. Escobar Avalos, M. A.Rodriguez Licea, H. Rostro Gonzalez, A. Espinoza Calderon, A. I.Barranco Gutierrez, F. J.Perez Pinal

Producció científica: Capítol de llibreContribució a congrés/conferènciaAvaluat per experts

6 Cites (Scopus)

Resum

Clean-energy generation in smart grids is limited by the availability of the energy to be transformed and advanced energy management strategies requires solid and anticipated information about its dynamic behavior. This includes multivariable prediction of meteorological and user consumption data simultaneously in time series. The selection of a predicting model, from long short-Term memory (LSTM), convolutional neural networks (CNN), gated recurrent units (GRU), or their hybrid models merging CNN with LSTM and GRU, is a very complex task. In this paper, a mean absolute error, absolute percentage error (MAPE), and root mean square error (RMSE) comparative analysis, for prediction of energy consumption, and solar and onshore wind generation, is presented. A three-day prediction-horizon is used, with four-year hourly training data from Madrid. The combination of the best GRU and CNN models found, subject to the given hyperparameters grid, has a better prediction performance, including if they predict separated. Relevant information about training and coding appreciations is also presented.

Idioma originalAnglès
Títol de la publicació2020 IEEE International Autumn Meeting on Power, Electronics and Computing, ROPEC 2020
EditorInstitute of Electrical and Electronics Engineers Inc.
ISBN (electrònic)9781728199535
DOIs
Estat de la publicacióPublicada - 4 de nov. 2020
Publicat externament
Esdeveniment2020 IEEE International Autumn Meeting on Power, Electronics and Computing, ROPEC 2020 - Ixtapa, Mexico
Durada: 4 de nov. 20206 de nov. 2020

Sèrie de publicacions

Nom2020 IEEE International Autumn Meeting on Power, Electronics and Computing, ROPEC 2020

Conferència

Conferència2020 IEEE International Autumn Meeting on Power, Electronics and Computing, ROPEC 2020
País/TerritoriMexico
CiutatIxtapa
Període4/11/206/11/20

Fingerprint

Navegar pels temes de recerca de 'Comparative Analysis of Multivariable Deep Learning Models for Forecasting in Smart Grids'. Junts formen un fingerprint únic.

Com citar-ho