Reinforcement-learning ventilation and air-purifier control with PINN surrogates for a small room
Simulation54 MB
Environment, training and evaluation code, 776 trained RL policies and PINN CO2/PM2.5 surrogate weights for schedule-aware control of windows, doors and an air purifier. Useful for ML-based indoor ventilation control studies.
CC BY 4.0Free to use and share, including commercially, as long as you credit the creators.
Size
54 MB · 776 trained policies, 30 surrogate pairs
How to cite
Han, B., Kim, J., & Koo, J. (2026). Code, trained policies and derived results for: Quantifying the indoor air quality benefit of schedule-aware proactive control learned by reinforcement learning [Data set]. Zenodo. https://doi.org/10.5281/zenodo.23281868
Check the repository for the citation its authors prefer.
Processed URANS outputs (regional temperature rise, passive tracer, mean-field sections), surrogate models, reference geometry, input dictionaries and analysis code comparing fan allocations at equal power in a normalised industrial hall. Useful for industrial ventilation design and surrogate modelling.
Input case list for CFD runs, ML inputs and outputs, a trained neural network and an inference script for predicting room ventilation conditions, including humidity. Useful as a ventilation surrogate-modelling example.
Field CO2 and PM2.5 measurements in a 71 m3 occupied office, with PINN training/analysis code and weights used to derive air change rate, penetration factor and field CADR. Useful for ventilation-rate inference and indoor particle modelling.
Simulation outputs and MATLAB scripts for 192 cases of a dwelling with a façade-integrated AHU with thermoelectric heat exchange. Covers ventilation, IAQ, overheating and energy across four climates.
IndoorSimulationSimulation outputSoftware & toolsMultizone model
Indoor and outdoor sensor data from the Austrian pilot's homes and schools, March 2023 to March 2025, with preprocessing, clustering and VOC analysis notebooks.
One-minute BMS time series covering zone temperature, CO2, setpoints and actuator signals, plus hourly electricity data, from schools, medical centres, care facilities and a sports arena, 2022-2025. Useful for ventilation and indoor air quality analysis and for data-driven HVAC control.
From Zenodo, added 2026-11-15.
Listed there as “Code, trained policies and derived results for: Quantifying the indoor air quality benefit of schedule-aware proactive control learned by reinforcement learning”. Tags proposed by AI and not yet checked by hand. Spotted a mistake? Tell the portal contacts.