A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Multi-zone indoor temperature prediction with LSTM-based sequence to sequence model
Highlights End-to-end methodology for multi-zone indoor temperature prediction. LSTM-based seq2seq model. Cross-series learning strategy. Tailor-made metric adapted to the special characteristic of indoor temperature. Evaluation of the forecasting capacity of the model with regard to the forecast horizon.
Abstract Accurate indoor temperature forecasting can facilitate energy savings of the building without compromising the occupant comfort level, by providing more accurate control of the HVAC (heating, ventilating, and air conditioning) system. In order to make the best use of different input variables, a long short-term memory (LSTM) based sequence to sequence (seq2seq) model was proposed to make multi-step ahead forecasting. The out-of-sample forecasting capacity of the model was evaluated with regard to different forecast horizons by various evaluation metrics. A tailor-made metric was proposed to take account of the small daily-variation characteristic of indoor temperature. The model was benchmarked against Prophet and a seasonal naive model, showing that the current model is much more skillful and reliable in very short-term forecasting. A cross-series learning strategy was adopted to enable multi-zone indoor temperature forecasting with a more generalised model. Furthermore, the uncertainty in model parameters was quantified by prediction intervals created by Monte-Carlo dropout (MC-dropout) technique.
Multi-zone indoor temperature prediction with LSTM-based sequence to sequence model
Highlights End-to-end methodology for multi-zone indoor temperature prediction. LSTM-based seq2seq model. Cross-series learning strategy. Tailor-made metric adapted to the special characteristic of indoor temperature. Evaluation of the forecasting capacity of the model with regard to the forecast horizon.
Abstract Accurate indoor temperature forecasting can facilitate energy savings of the building without compromising the occupant comfort level, by providing more accurate control of the HVAC (heating, ventilating, and air conditioning) system. In order to make the best use of different input variables, a long short-term memory (LSTM) based sequence to sequence (seq2seq) model was proposed to make multi-step ahead forecasting. The out-of-sample forecasting capacity of the model was evaluated with regard to different forecast horizons by various evaluation metrics. A tailor-made metric was proposed to take account of the small daily-variation characteristic of indoor temperature. The model was benchmarked against Prophet and a seasonal naive model, showing that the current model is much more skillful and reliable in very short-term forecasting. A cross-series learning strategy was adopted to enable multi-zone indoor temperature forecasting with a more generalised model. Furthermore, the uncertainty in model parameters was quantified by prediction intervals created by Monte-Carlo dropout (MC-dropout) technique.
Multi-zone indoor temperature prediction with LSTM-based sequence to sequence model
Fang, Zhen (author) / Crimier, Nicolas (author) / Scanu, Lisa (author) / Midelet, Alphanie (author) / Alyafi, Amr (author) / Delinchant, Benoit (author)
Energy and Buildings ; 245
2021-04-19
Article (Journal)
Electronic Resource
English
Track vibration sequence anomaly detection algorithm based on LSTM
| SAGE Publications | 2023
Fire Temperature Prediction Based on LSTM
| IEEE | 2024
CNN-LSTM architecture for predictive indoor temperature modeling
| Elsevier | 2021
Fire Prediction Based on Reverse Sequence Grey Model
| British Library Conference Proceedings | 2006