Search
2023
19
Excellent presentation paper award by Korean Institute of Architectural Sustainable Environment and Building Systems (KIAEBS)
At the 2023 Autumn Conference of the Korean Institute of Architectural Sustainable Environment and Building Systems (2023 KIAEBS Autumn Conference), two conference papers from Betlab were honored with the award for excellent conference presentation paper.
Appropriateness of dynamic exergy analysis method depending on thermal diffusivity and system length by Habin Jo, Shukuya Masanori, Wonjun Choi
Analysis of outlet fluid temperature variation of ground heat exchanger induced by uncertainty of ground heat exchanger design parameters by Yoonseong Kim, Euntak Shin, Young-Sang Kim, Wonjun Choi
Awarded Paper
by Habin Jo
by Yoonseong Kim
Excellent presentation paper award at the autumn conference of KIAEBS 2023
2023/11/10
Awards and Honors
Euntak was awarded the excellent presentation paper award at the autumn conference of the Korean Solar Energy Society (2023 KSES Autumn Conference ). Congratulations!
Awarded papers
by Euntak Shin
Excellent presentation paper award at the autumn conference of KSES 2023
2023/11/07
Awards and Honors
Excellent conference paper award by Korean Society for Geothermal and Hydrothermal Energy (KSGHE)
The betlab's one conference papers, presented at the 2023 Autumn Conference of Korean Society for Geothermal and Hydrothermal Energy (2023 KSGHE Autumn Conference ), received the excellent conference paper award.
Congratulations!
Awarded papers
by Euntak Shin
Excellent paper award at the autumn conference of KSGHE 2023
2023/10/13
Awards and Honors
Excellent presentation paper by The Society of Air-conditioning and Refrigerating Engineers of Korea (SAREK)
The betlab's two conference papers, presented at the 2023 Summer Conference of Society of Air-conditioning and Refrigerating Engineers of Korea (2023 SAREK Summer Conference ), received the excellent conference presentation paper award.
Congratulations!
Analysis of Temporal Contribution Change for Parameters Affected to Uncertainty of Ground Thermal Response Function in Various Ground Heat Exchanger Clusters by Yoonseong Kim, Euntak Shin, and Wonjun Choi
Unsteady-state exergy anlaysis in the building envelope considering radiation and convection by Sieun Kim, Habin Jo and Wonjun Choi
Awarded papers
by Yoonseong Kim
by Sieun Kim
Excellent presentation paper award at the summer conference of SAREK 2023
2023/06/23
Awards and Honors
Excellent presentation paper award by Architectural Institute of Korea (AIK)
The betlab's two conference papers, presented at the 2023 Spring Conference of Architectural Institute of Korea (2023 AIK Spring Conference ), received the excellent presentation conference paper award.
Congratulations!
Uncertainity Quantification of Borehole Heat Exchanger Design length Using a Global Sensitivity Analysis by Euntak Shin, Yoonseong Kim, Young-sang Kim, and Wonjun Choi
Analysis of Temporal Contribution Change for Parameter Related to Ground Thermal Response Function Using Global Sensitivity Analysis by Yoonseong Kim, Euntak Shin, and Wonjun Choi
Awarded papers
by Euntak Shin
by Yoonseong Kim
Excellent presentation paper award at the spring conference of AIK 2023
2023/04/28
Awards and Honors
A new paper titled, has been published.
Paper link
Summary
Buildings and their energy systems are characterized by unique and complex features that can evolve over time. Moreover, building data is highly seasonal, which means that it is subject to variations according to the time of the year. Therefore, an effective deep learning model with exceptional adaptability (i.e., high performance with little data) is required to accurately forecast and control the energy systems of buildings.
Considering the intricate nature of the building-energy field, we conducted a benchmark study to compare the performance of six different deep learning architectures. These included the multilayer perceptron (MLP), simple recurrent neural network (RNN), long short-term memory, gated recurrent unit (GRU), dilated convolutional neural network (DCNN), and transformer. To analyze the effect of data seasonality on forecasting performance, we also developed a data similarity analysis method.
To ensure the reproducibility and accessibility of our benchmark, we utilized a publicly accessible data generator and the open-source Python library DeepTimeSeries. Our forecasting targets were the zone temperatures and thermal loads over a future 24-hour period. The benchmark results, with varying training dataset sizes ranging from 0.3 to 0.9 y, showed that the transformer architecture performed the best, especially on small training datasets. The GRU and RNN came in second and third place, respectively, while the rankings of other architectures varied depending on the training dataset size and forecasting targets.
Additionally, the data similarity analysis revealed that simply increasing the training dataset size does not necessarily improve the model performance. This highlights the importance of model training with highly similar data for the forecasting period.
Featured figure
Matrix plot summarizing the performance rank of six deep learning architectures
Performance evaluation of deep learning architectures for load and temperature forecasting under dataset size constraints and seasonality
2023/04/06
Papers
2022
3