October 1, 2025TechnologiesOpen Access

Direct Multiple-Step-Ahead Forecasting of Daily Gas Consumption in Non-Residential Buildings Using Wavelet/RNN-Based Models and Data Augmentation— Comparative Evaluation

View Full Paper

Ask AI

Bookmark

The Wavelet-LSTM model achieved the best accuracy for forecasting natural gas consumption in healthcare facilities during winter.
Prediction accuracy improved through individual wavelet component forecasting, yielding nMAE of 5.71% and NRMSE of 7.80%.
Data augmentation methods enhanced model performance, although predicted temperatures slightly reduced prediction accuracy.
The study emphasizes the importance of optimizing operational costs while ensuring user comfort through effective energy management.

Discussion

No takes yet. Share an insight, caveat, or question.

Implication

Comparative evaluation shows wavelet decomposition and LSTM models optimize gas consumption predictions, suggesting improved operational cost management.

Cite This Study

Mižáková et al. (2025) studied this question.

synapsesocial.com/papers/68dd89e6fe798ba2fc498278 https://doi.org/10.3390/technologies13100435

View Full Paper

Ask AI

Bookmark

Implication

Comparative evaluation shows wavelet decomposition and LSTM models optimize gas consumption predictions, suggesting improved operational cost management.

Direct Multiple-Step-Ahead Forecasting of Daily Gas Consumption in Non-Residential Buildings Using Wavelet/RNN-Based Models and Data Augmentation— Comparative Evaluation

Key Points

Discussion

Implication

Cite This Study

Direct Multiple-Step-Ahead Forecasting of Daily Gas Consumption in Non-Residential Buildings Using Wavelet/RNN-Based Models and Data Augmentation— Comparative Evaluation

Key Points

Discussion

Implication

Cite This Study

Keep reading

Keep reading