IDEAS Lab

Integrated Data, Energy Analysis + Simulation

A Passion for Better Buildings

Join Us View Research

IDEAS Lab is a research group in the Department of Building at the National University of Singapore (NUS) that engages in the integration building performance simulation with real-time data and machine learning. The group focuses on various aspects of building performance simulation including uncertainty quantification, model calibration, and building data analytics with the aim of creating energy efficient and healthier buildings.

Also, check out our two sibling labs: the Building and Urban Data Science (BUDS) Lab and the Urban Analytics Lab (UAL), with whom we collaborate closely within NUS. .

Projects

*

COVID-19: Rethinking building design and operations

Experiments and CFD studies for droplet and bioaerosol transmission inside building. A project funded by NUS COVID-19 Research Seed Grant.

Advanced machine learning based control for HVAC systems

Advanced machine learning based control for the HVAC systems

An automated framework for model predictive control

This study aims at improving the scalability of MPC by addressing modeling-related issues and establishing an automated framework.

Building lifecycle automatic data segmentation using natural language processing

Building lifecycle automatic data segmentation using natural language processing

Epwshiftr: an R package for creating future weather files under climate changes for building energy simulation

An R package for creating future weather files under climate changes for building energy simulation

Impacts of climate change on building energy systems

Impacts of climate change on building energy systems

Life cycle cost optimization

Life cycle cost optimization

Quantifying the impact of occupancy on ECMs’ performance using building energy simulation

A framework for identifying and quantifying the impact of occupancy-related schedules on ECMs’ performance using building energy simulation

eplusr: A framework for integrating building energy simulation and data-driven analytics

A framework for seamless integration between Building Energy Simulation (BES) and data-driven analytics.

Generating certified energy models in Singapore through an M&V framework.

Generating certified energy models in Singapore through an M&V framework.An NUS project in collaboration with Professor Godfried L. Augenbroe (Georgia Institute of Technology)

Postdoctoral Researchers

Avatar

Xilei Dai

Postdoctoral Fellow

Deep learning, Indoor air quality, Building modelling and simulation

Avatar

Yuzhen Peng

Senior Postdoctoral Fellow

Smart buildings and systems, Automation and controls, Machine learning and optimization, Data-driven modeling, User-centric design, IoT and sensing platforms, Human-machine interfaces

Avatar

Zeynep Duygu Tekler

Postdoctoral Fellow

IoT Applications, Occupancy Detection, Smart Energy Management Systems, Data Analytics and Applied Machine Learning

PhD Students / Research Assistants

Avatar

Jintong Han

PhD Student

Continual Learning, Physical-based Deep Learning

Avatar

Long Zheng

PhD Student

Computational Fluid Dynamics, Convective Heat transfer, Microclimate

Avatar

Sicheng Zhan

PhD Student

Building Energy Simulation, Building Data Analytics, Model Predictive Control

Avatar

Siyu Cheng

PhD Student

Building Performance Modelling and Optimization

Avatar

Yaonan (Claire) Gu

PhD Student

Building Energy Simulation, Bayesian Calibration, Data Analytics and Applied Machine Learning

Avatar

Yue Lei

PhD Student

Building Performance Modelling and Optimization, Model Prodictive Control (MPC), Indoor CFD Application, Data Analytics

Alumni

Avatar

Hongyuan Jia

Assistant Professor (Chongqing University of Science and Technology)

Avatar

Wenxin Li

Assistant Professor (Southeast Univesity, China)

Contact

  • +65 98210638
  • Department of Building, School of Design and Environment, National University of Singapore, Singapore
  • email

Recent Publications

Quickly discover relevant content by filtering publications.

Significant reduction in energy demand from non-domestic buildings is required if greenhouse emission reduction targets are to be met …

Model predictive control (MPC) has shown great potential in improving building performance and saving energy. However, after over 20 …

Occupancy is a significant area of interest within the field of building performance simulation. Through Bayesian calibration, the …

Building energy simulation (BES) has been widely adopted for the investigation of building environmental and energy performance for …

The ever-changing data science landscape is fueling innovation in the built environment context by providing new and more effective …