| Theme: | Theme - Applications (Theme - Apps), Activity - Project (Activity - P) |
| Status: | Active |
| Start Date: | 2020-12-23 |
| End Date: | 2020-12-23 |
| Lead |
| Ardakanian, Omid |
Project Overview
Buildings account for a large portion of the total energy consumption in Canada. Most of this energy is consumed to maintain occupants' thermal and visual comfort. Thus, understanding the building occupancy is critical for designing energy-efficient building controls, maximizing human comfort, and creating a safe and healthy workplace during the pandemic. Despite the importance of incorporating occupancy information in the control of HVAC, lights, and window blinds, this information is often unavailable or inaccurate. Machine learning models can help fuse data from various sources (e.g., WiFi association logs, prox cards, cameras) to estimate occupancy at different spatial and temporal resolutions. Leveraging reinforcement learning algorithms, it is possible to determine optimal (energy-efficient) control policies which satisfy stringent safety requirements.
This project aims to analyze the estimated building occupancy levels, whole-building energy consumption patterns, and operational data from the Building Management System (BMS) to
- Refine the estimated number of occupants in each building and identify/address data quality issues. This is an important task as there is not a one-to-one mapping between WiFi users and building occupants. The refined occupancy information will be useful for monitoring building occupancy and issuing warnings if social distancing rules are violated (during the pandemic).
- Understand what percentage of the whole-facility energy use can be attributed to occupants, and utilizing this information to optimize the operation of HVAC and lighting systems. The optimal control policy is expected to reduce the building energy use while satisfying comfort requirements.
Outputs
| Title |
Category |
Date |
Authors |
| A domain adaptation technique for fine-grained occupancy estimation in commercial buildingsFine-grained occupancy information is essential to improve human experience and operational efficiency of buildings, yet it is quite challenging to obtain this information due to the lack of special-purpose sensors for occupancy monitoring, and insufficient training data for developing accurate data-driven models. This paper addresses this challenge by (a) utilizing recurrent neural network models to uncover latent occupancy patterns in individual rooms from trend data available through the building management system, and (b) applying a domain adaptation technique to transfer existing occupancy models trained in a controlled environment (i.e., the source domain) to another environment (i.e., the target domain) where labelled data is sparse or non-existent. We adjust the model parameters based on the apparent differences between the two environments and apply the adapted model to estimate the number of occupants in the target domain. Our results from two test commercial buildings in two continents indicate that the adapted model yields only slightly lower accuracy than a model that is originally built on the target domain given a large amount of labelled data. Furthermore, we study how much labelled data is required from the target domain for the semi-supervised domain adaptation technique to achieve promising results. University of Alberta | Publication | 2019-04-01 | Tianyu Zhang, Omid Ardakanian |
| ODToolkit: Extensible Toolkit for Occupancy Detection in Smart BuildingsRecent years have witnessed a steady increase in the number of occupancy detection algorithms and people counting systems designed for residential and commercial buildings, yet comparing the accuracy of existing solutions has been impossible to date due to the lack of publicly available test data sets, open-source implementation of the state-of-the-art algorithms, and consensus on the evaluation metrics. This paper addresses this problem by presenting the design and implementation of an open-source toolkit for occupancy detection. ODToolkit is capable of importing and converting sensor data acquired from various buildings into a common data format, provides implementation of a broad suite of data-driven occupancy detection techniques, and calculates a set of evaluation metrics for each experiment. We present several case studies to show how this toolkit facilitates the development of new occupancy detection algorithms. In particular, we extend this toolkit by implementing novel domain-adaptive occupancy detection algorithms and compare them with the benchmark supervised learning algorithms on multiple data sets. Furthermore, we investigate what sensing modalities and precision are needed to achieve a desired level of accuracy for occupancy estimation through sensor fusion. ODToolkit code and documentation are available at https://odtoolkit.github.io/. University of Alberta | Publication | 2019-06-01 | Tianyu Zhang, Abdullah Al Zishan, Omid Ardakanian |
| Addressing Data Inadequacy Challenges in Personal Comfort Models by Combining Pretrained Comfort Models University of Alberta | Publication | 2022-06-01 | "Tianyu Zhang", "Jake Gu", Omid Ardakanian, "Joyce Kim" |
| Current practices and infrastructure for open data based research on occupant-centric design and operation of buildings University of Alberta | Publication | 2020-06-01 | Mikkel Kjærgaard, Omid Ardakanian, Salvatore Carlucci, Bing Dong, Steven Firth, Nan Gao, Gesche Huebner, Ardeshir Mahdavi, Mohammad Rahaman, Flora Salim, Fisayo Sangogboye, Jens Schwee, Dawid Wolosiuk, Yimin Zhu |
