Best paper at Buildsys '23

© 2023 Clayton Miller

© 2023 Clayton Miller

The best paper at Buildsys 2023 in Istanbul, Turkey was awarded to ETHOS's collaborative work with the Intelligent and Connected Systems Lab at Columbia University and the Intelligent Mobile and Embedded Computing Lab at Northwestern University.

Our paper, "RECA: A Multi-Task Deep Reinforcement Learning-Based Recommender System for Co-Optimizing Energy, Comfort and Air Quality in Commercial Buildings" was a collaborative effort between building engineers and electrical engineers focused on recommending actions to users of buildings to improve the multi-objective performance of buildings. According to the conference chairs, the paper was unanimously ranked at the top by the award jury.


We present the design and implementation of RECA, a novel human-centric recommender system for co-optimizing energy consumption, comfort and air quality in commercial buildings. Existing works generally optimize these objectives separately, or by only controlling energy consuming resources within the building without directly engaging occupants. We develop a deep reinforcement learning architecture based on multitask learning, demonstrate how it can be used to jointly learn energy savings, comfort and air quality improvements for different actions, and build a recommender system with humans-in-the-loop. Through real deployments in multiple commercial buildings, we found that RECA has the potential to further reduce energy consumption by up to in energy-focused optimization, improve all objectives by in joint optimization, and improve thermal comfort by up to in comfort and air quality focused optimization, over existing solutions.