What question did this study set out to answer?

To compare the performance of multiple recurrent neural network architectures for multivariate time series energy demand forecasting in smart grids.

August 3, 2022Energy ReportsOpen Access

Multivariate time series prediction by RNN architectures for energy consumption forecasting

View Full Paper

Ask AI

Bookmark

Authors

IAIbtissam Amalou NMNaoual Mouhni AAAbdelmounaïm Abdali

Discussion

Member takes

Overview

Comparative analysis demonstrates superior energy consumption forecasting accuracy with gated recurrent units in smart grid data, highlighting the benefit of reduced parameters.

Key Points

To compare the performance of multiple recurrent neural network architectures for multivariate time series energy demand forecasting in smart grids.
Trained and evaluated basic RNN, LSTM, and GRU architectures using multivariate time series data from the Smart Grid Smart City project (2010–2014).
Assessed model performance using Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and R-squared (R2) metrics.
Gated Recurrent Unit (GRU) models outperformed both basic RNN and LSTM networks, achieving the lowest RMSE and the highest R2 score.
The superior performance of the GRU architecture was driven by its ability to resolve the vanishing gradient problem with fewer structural parameters.

Cite This Study

Amalou et al. (2022) studied this question.

synapsesocial.com/papers/69fcfd9c5d981208085091cb https://doi.org/10.1016/j.egyr.2022.07.139

View Full Paper

Ask AI

Bookmark

August 3, 2022Energy ReportsOpen Access

Multivariate time series prediction by RNN architectures for energy consumption forecasting

View Full Paper

Ask AI

Bookmark

Authors

IAIbtissam Amalou NMNaoual Mouhni AAAbdelmounaïm Abdali

Discussion

Member takes

Overview

Comparative analysis demonstrates superior energy consumption forecasting accuracy with gated recurrent units in smart grid data, highlighting the benefit of reduced parameters.

Key Points

To compare the performance of multiple recurrent neural network architectures for multivariate time series energy demand forecasting in smart grids.
Trained and evaluated basic RNN, LSTM, and GRU architectures using multivariate time series data from the Smart Grid Smart City project (2010–2014).
Assessed model performance using Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and R-squared (R2) metrics.
Gated Recurrent Unit (GRU) models outperformed both basic RNN and LSTM networks, achieving the lowest RMSE and the highest R2 score.
The superior performance of the GRU architecture was driven by its ability to resolve the vanishing gradient problem with fewer structural parameters.

Cite This Study

Amalou et al. (2022) studied this question.

synapsesocial.com/papers/69fcfd9c5d981208085091cb https://doi.org/10.1016/j.egyr.2022.07.139

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

View Full Paper

Ask AI

Bookmark