12  Paper Discussions

During this part of the course, we shift from foundational concepts to examining how researchers and practitioners apply those concepts to real-world problems. Each week, we will read and discuss one or two papers from the recent literature on smart buildings, energy systems, and related topics. The goal is not just to understand what each paper does, but to critically evaluate the methods, identify connections to what we have learned, and think about what questions remain open.

The papers below are drawn primarily from BuildSys (ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation), one of the leading venues for research at the intersection of computing, sensing, and the built environment. They span topics including occupancy sensing, energy disaggregation, thermal modeling, control, and grid interaction.

Papers marked with a checkmark will be discussed in class. The rest are provided as additional reading for interested students.

12.0.1 Papers Under Consideration

12.0.1.1 Occupancy and Human Sensing

  1. Nonintrusive Occupant Identification by Sensing Body Shape and Movement — Nacer Khalil, Driss Benhaddou, Omprakash Gnawali, Jaspal Subhlok. BuildSys 2016. DOI

  2. Sonicdoor — Nacer Khalil, Driss Benhaddou, Omprakash Gnawali, Jaspal Subhlok. BuildSys 2017. DOI

  3. The Impact of Occupancy Resolution on the Accuracy of Building Energy Performance Simulation — Fisayo Caleb Sangogboye, Krzysztof Arendt, Muhyiddine Jradi, Christian Veje, Mikkel Baun Kjærgaard, Bo Nørregaard Jørgensen. BuildSys 2018. DOI

  4. Robust and Practical WiFi Human Sensing Using On-device Learning with a Domain Adaptive Model — Elahe Soltanaghaei, Rahul Anand Sharma, Zehao Wang, Adarsh Chittilappilly, Anh Luong, Eric Giler, Katie Hall, Steve Elias, Anthony Rowe. BuildSys 2020. DOI

  5. FTM-Sense: Robust Sensor-free Occupancy Sensing Leveraging WiFi Fine Time Measurement — Fateme Nikseresht, Bradford Campbell. BuildSys 2023. DOI

  6. TODOS: Thermal Sensor Data-driven Occupancy Estimation System for Smart Buildings — Hamid Rajabi, Xianzhong Ding, Wan Du, Alberto Cerpa. BuildSys 2023. DOI

  7. ScreenSense: Screen Activity Detection in Real-World Environments with Indoor Light Sensors — Tushar Routh, Nurani Saoda, Fateme Nikseresht, Md Fazlay Rabbi Masum Billah, Jiechao Gao, Viswajith Govinda Rajan, Bradford Campbell. BuildSys 2024. DOI

12.0.1.2 Energy Disaggregation and Monitoring

  1. BOLT: Energy Disaggregation by Online Binary Matrix Factorization of Current Waveforms — Henning Lange, Mario Bergés. BuildSys 2016. DOI

  2. Towards Reproducible State-of-the-Art Energy Disaggregation — Nipun Batra, Rithwik Kukunuri, Ayush Pandey, Raktim Malakar, Rajat Kumar, Odysseas Krystalakos, Mingjun Zhong, Paulo Meira, Oliver Parson. BuildSys 2019. DOI

  3. EffiSenseSee: towards classifying light bulb types and energy efficiency with camera-based sensing — Alex Yen, Zeal Shah, Benjamin Ochoa, Pat Pannuto, Jay Taneja. BuildSys 2022. DOI

  4. Can Attention Improve Sequence-to-Point Load Disaggregation? A Comparative Assessment — Mazen Bouchur, Nan Li, Andreas Reinhardt. BuildSys 2025. DOI

12.0.1.3 Grid and Infrastructure

  1. Hypertemporal Imaging of NYC Grid Dynamics — Federica B. Bianco, Steven E. Koonin, Charlie Mydlarz, Mohit S. Sharma. BuildSys 2016. DOI

  2. Observability: A Principled Approach to Provisioning Sensors in Buildings — Anshul Agarwal, Vitobha Munigala, Krithi Ramamritham. BuildSys 2016. DOI

  3. GridInSight: Monitoring Electricity Using Visible Lights — Zeal Shah, Alex Yen, Ajey Pandey, Jay Taneja. BuildSys 2019. DOI

  4. SolarWalk: smart home occupant identification using unobtrusive indoor photovoltaic harvesters — Md Fazlay Rabbi Masum Billah, Nurani Saoda, Victor Ariel Leal Sobral, Tushar Routh, Wenpeng Wang, Bradford Campbell. BuildSys 2022. DOI

12.0.1.4 Control and Optimization

  1. Data Predictive Control for Peak Power Reduction — Achin Jain, Rahul Mangharam, Madhur Behl. BuildSys 2016. DOI

  2. Gnu-RL: A Precocial Reinforcement Learning Solution for Building HVAC Control Using a Differentiable MPC Policy — Bingqing Chen, Zicheng Cai, Mario Bergés. BuildSys 2019. DOI

  3. SMITE: Using Smart Meters to Infer the Thermal Efficiency of Residential Homes — Joe Brown, Jonathan Chambers, Alessandro Abate, Alex Rogers. BuildSys 2020. DOI

  4. Adversarial Poisoning Attacks on Reinforcement Learning-Driven Energy Pricing — Sam Gunn, Doseok Jang, Orr Paradise, Lucas Spangher, Costas J. Spanos. BuildSys 2022. DOI

  5. RECA: A Multi-Task Deep Reinforcement Learning-Based Recommender System for Co-Optimizing Energy, Comfort and Air Quality in Commercial Buildings — Stephen Xia, Peter Wei, Yanchen Liu, Andrew Sonta, Xiaofan Jiang. BuildSys 2023. DOI

12.0.1.5 Thermal Modeling and Simulation

  1. Unmasking the Thermal Behavior of Single-Zone Multi-Room Houses: An Empirical Study — Ozan Baris Mulayim, Mario Bergés. BuildSys 2023. DOI

  2. Modeling the Impact of Passive Ventilation Systems on Multi-Zone Thermal Dynamics — James Onyejizu, Sandipan Mishra, Koushik Kar. BuildSys 2024. DOI

  3. OmniFlow: A Framework for Generalizable Surrogates for Real-Time Airflow Simulation and Control in Unseen Indoor Environments — M Tanjid Hasan Tonmoy, Upal Mahbub, Tauhidur Rahman. BuildSys 2025. DOI

12.0.1.6 Indoor Environment and Comfort

  1. TEA-bot: a thermography enabled autonomous robot for detecting thermal leaks of HVAC systems in ceilings — Weijia Cai, Le Zhang, Lei Huang, Xinran Yu, Zhengbo Zou. BuildSys 2022. DOI

12.0.1.7 Data Centers

  1. PyDCM: Custom Data Center Models with Reinforcement Learning for Sustainability — Avisek Naug, Antonio Guillen, Ricardo Luna Gutiérrez, Vineet Gundecha, Sahand Ghorbanpour, Lekhapriya Dheeraj Kashyap, Dejan Markovikj, Lorenz Krause, Sajad Mousavi, Ashwin Ramesh Babu, Soumyendu Sarkar. BuildSys 2023. DOI