A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
CNN-LSTM architecture for predictive indoor temperature modeling
https://orcid.org/0000-0002-7030-0784
https://orcid.org/0000-0002-9352-7981
Abstract Indoor temperature modeling is a crucial part towards efficient Heating, Ventilation and Air Conditioning (HVAC) systems. Data-driven black-box approaches have been an attractive way to develop such models due to their unique feature of not requiring detailed knowledge about the target zone. However, the noisy and non-linear nature of the problem remains a bottleneck especially for long prediction horizons. In this paper, we introduce a Convolutional Neural Networks-Long Short Term Memory (CNN-LSTM) architecture to combine the exceptional feature extraction of convolutional layers with the Long Short Term Memory (LSTM)’s capability of learning sequential dependencies. We experimentally collected a dataset and compared three approaches: Multi-Layer Perceptron (MLP), LSTM and CNN-LSTM. Models are evaluated and compared with 1-30-60-120 min horizons with a closed-loop prediction scheme. The CNN-LSTM outperformed all other models for all prediction horizons and showed a better robustness against error accumulation. It managed to predict room temperature with 0.9 in a 120-min prediction horizon.
Highlights CNN-LSTM architecture is proposed for data-driven indoor temperature modeling. Proposed architecture is compared to vanilla neural network and LSTM architectures. Results are evaluated in 1-30-60-120 min prediction horizons. Proposed architecture outperformed other techniques and showed superior stability.
CNN-LSTM architecture for predictive indoor temperature modeling
https://orcid.org/0000-0002-7030-0784
https://orcid.org/0000-0002-9352-7981
Abstract Indoor temperature modeling is a crucial part towards efficient Heating, Ventilation and Air Conditioning (HVAC) systems. Data-driven black-box approaches have been an attractive way to develop such models due to their unique feature of not requiring detailed knowledge about the target zone. However, the noisy and non-linear nature of the problem remains a bottleneck especially for long prediction horizons. In this paper, we introduce a Convolutional Neural Networks-Long Short Term Memory (CNN-LSTM) architecture to combine the exceptional feature extraction of convolutional layers with the Long Short Term Memory (LSTM)’s capability of learning sequential dependencies. We experimentally collected a dataset and compared three approaches: Multi-Layer Perceptron (MLP), LSTM and CNN-LSTM. Models are evaluated and compared with 1-30-60-120 min horizons with a closed-loop prediction scheme. The CNN-LSTM outperformed all other models for all prediction horizons and showed a better robustness against error accumulation. It managed to predict room temperature with 0.9 in a 120-min prediction horizon.
Highlights CNN-LSTM architecture is proposed for data-driven indoor temperature modeling. Proposed architecture is compared to vanilla neural network and LSTM architectures. Results are evaluated in 1-30-60-120 min prediction horizons. Proposed architecture outperformed other techniques and showed superior stability.
CNN-LSTM architecture for predictive indoor temperature modeling
https://orcid.org/0000-0002-7030-0784
https://orcid.org/0000-0002-9352-7981
Abstract Indoor temperature modeling is a crucial part towards efficient Heating, Ventilation and Air Conditioning (HVAC) systems. Data-driven black-box approaches have been an attractive way to develop such models due to their unique feature of not requiring detailed knowledge about the target zone. However, the noisy and non-linear nature of the problem remains a bottleneck especially for long prediction horizons. In this paper, we introduce a Convolutional Neural Networks-Long Short Term Memory (CNN-LSTM) architecture to combine the exceptional feature extraction of convolutional layers with the Long Short Term Memory (LSTM)’s capability of learning sequential dependencies. We experimentally collected a dataset and compared three approaches: Multi-Layer Perceptron (MLP), LSTM and CNN-LSTM. Models are evaluated and compared with 1-30-60-120 min horizons with a closed-loop prediction scheme. The CNN-LSTM outperformed all other models for all prediction horizons and showed a better robustness against error accumulation. It managed to predict room temperature with 0.9 in a 120-min prediction horizon.
Highlights CNN-LSTM architecture is proposed for data-driven indoor temperature modeling. Proposed architecture is compared to vanilla neural network and LSTM architectures. Results are evaluated in 1-30-60-120 min prediction horizons. Proposed architecture outperformed other techniques and showed superior stability.
CNN-LSTM architecture for predictive indoor temperature modeling
Elmaz, Furkan (author) / Eyckerman, Reinout (author) / Casteels, Wim (author) / Latré, Steven (author) / Hellinckx, Peter (author)
Building and Environment ; 206
2021-09-01
Article (Journal)
Electronic Resource
English
LSTM-Based Model Predictive Control for Optimal Temperature Set-Point Planning
| DOAJ | 2021