Table 3 Comparison of Related Digital Twin and Thermal Comfort Prediction Models.

From: Digital twin based deep learning framework for personalized thermal comfort prediction and energy efficient operation in smart buildings

Study

Model type

Target output

Main contribution

Norouzi et al. (2023)

Deep Neural Network

Indoor Temperature (RMSE \(0.16^{\circ }\hbox {C}\))

Accurate temperature prediction for HVAC Digital Twin

Zhang et al. (2023)

Attention-LSTM + Bayesian Optimization

Environmental, Temporal

Improved prediction using temporal attention

Chaudhary et al. (2023)

BiLSTM Encoder-Decoder

Ventilation System Performance

Hybrid ventilation modeling using sequence learning

Cho et al. (2024)

Multi-head LSTM

Thermal Comfort (Subjective)

Personalized thermal comfort prediction

Li et al. (2024)

Graph-based Model

Occupant Comfort Preferences

BIM-enhanced prediction using occupant context

Ours (2025)

Attention-Based LSTM

Thermal Comfort Classes (UC, N, UW)

Real-time classification integrated with Digital Twin

Back to article page