Building Energy Optimization

Introduction

While buildings are becoming smarter with increasing number of energy monitoring endpoints, the real-time effect of an occupant’s personal actions on the overall energy consumption of the building is still unclear. Currently, we are exploring a number of avenues towards increasing awareness of personal energy consumption at the building and city scale, and different methods for recommending real-time energy saving actions.

Projects

The first part of this project is personal energy footprinting in commercial buildings. By building on top of existing indoor localization and building energy monitoring techniques, we propose a system that tracks each individual’s energy usage in a shared environment, and provides visibility into his or her real-time energy footprint. More information can be found on the ePrints project page.

The second part of this project extends personal energy footprinting to actionable energy saving recommendations. We designed an recommender system to sense energy information from the environment and coarse grained location information from the occupants to learn and disseminate intelligent energy saving recommendations in real-time. More information can be found on the RecEnergy project page.

Our most recent work attempts to extend personal energy footprinting to the city scale. We utilize open source city-wide datasets provided by the city of New York to estimate the energy consumption and population of buildings in the city. Using this information, we are able to estimate the personal energy footprint for a citizen in any location in Manhattan. More information can be found on the CityEnergy project page.

Future Work

Looking forward, we are interested in adding additional metrics for occupant optimization. Our next project focuses on low cost occupant comfort sensing. In the future, we hope to incorporate comfort sensing into a recommender system alongside energy consumption, in hopes of optimizing both metrics in tandem.

Publications

IEEE Internet of Things Journal
A Deep Reinforcement Learning Based Recommender System for Occupant-Driven Energy Optimization in Commercial Buildings
Peter Wei, Stephen Xia, Runfeng Chen, Jingyi Qian, Chong Li, Xiaofan Jiang

The 6th ACM International Conference on Systems for Energy-Efficient Built Environments (BuildSys 2019)
Data-Driven Energy and Population Estimation for Real-Time City-Wide Energy Footprinting
Peter Wei, Xiaofan Jiang
Best Paper Runner-Up Award

ACM Combining Physical and Data-Driven Knowledge in Ubiquitous Computing (CPD 2019)
City-Scale Vehicle Tracking and Traffic Flow Estimation using Low Frame-Rate Traffic Cameras
Peter Wei, Haocong Shi, Jiaying Yang, Jingyi Qian, Yinan Ji, Xiaofan Jiang

The 5th ACM International Conference on Systems for Energy-Efficient Built Environments (BuildSys 2018)
A data-driven system for city-scale personal energy footprint estimations
Peter Wei, Xiaofan Jiang

ACM User Modeling, Adaptation, and Personalization (UMAP 2018)
Energy Saving Recommendations and User Location Modeling in Commercial Buildings
Peter Wei, Stephen Xia, Xiaofan Jiang

ACM Transactions on Sensor Networks
A Scalable System for Apportionment and Tracking of Energy Footprints in Commercial Buildings
Peter Wei, Xiaoqi Chen, Jordan Vega, Stephen Xia, Rishikanth Chandrasekaran, Xiaofan Jiang

The 5th ACM International Conference on Systems for Energy-Efficient Built Environments (BuildSys 2018)
ePrints: a real-time and scalable system for fair apportionment and tracking of personal energy footprints in commercial buildings
Peter Wei, Xiaoqi Chen, Jordan Vega, Stephen Xia, Rishikanth Chandrasekaran, Xiaofan Jiang
Best Paper Runner-Up Award

The 4th ACM International Conference on Systems for Energy-Efficient Built Environments (BuildSys 2017)
Adaptive and Personalized Energy Saving Suggestions for Occupants in Smart Buildings
Peter Wei, Xiaoqi Chen, Rishikanth Chandrasekaran, Fengyi Song, Xiaofan Jiang
Best Poster Award

ACM/IEEE International Conference on Information Processing in Sensor Networks (IPSN 2016)
Personal energy footprint in shared building environment
Xiaoqi Chen, Rishikanth Chandrasekaran, Fengyi Song, Xiaofan Jiang