The 1st ACM International Workshop on
Big Data and Machine Learning for Smart Buildings and Cities

In conjunction with 
ACM BuildSys 2021, Nov. 16th, 2021
Coimbra, Portugal

Welcome to ACM BALANCES 2021

The proliferation of urban sensing, IoT, and big data in buildings, cities, and urban areas provides unprecedented opportunities for a deeper understanding of occupant behavior, transportation, and energy and water usage patterns. However, utilizing the existing data sources and modeling methods in building science to model urban scale occupant behaviors can be pretty challenging. Therefore, technological progress is needed to unlock its full potential. In order to fulfill the latter task, this workshop focuses on the methodologies for big urban and building data collection, analytics, modeling, and real-world technology deployment. Additionally, a spotlight will be put on the ongoing project IEA EBC Annex 79 Subtask 2: Data-driven occupant modeling strategies and digital tools.

The workshop aims to open up discussions on 1) challenges of the current modeling approaches in building science, 2) big data modeling paradigms that could be applicable in building science, urban infrastructure data modeling, 3) requirements on the data collection infrastructure required for increasing the volume of data collection, and 4) future research directions using urban big data. An important part of the workshop will be dedicated to accelerating the open-world deployment of developed technologies. For instance, how can the guidelines, model benchmarking, and standardization unlock the potential of the big data, buildings, urban scale occupant behavior modeling and energy consumption data.

BALANCES'21 will be held in conjunction with ACM BuildSys'21

Important Dates


Nov. 16, 2021

Workshop Day

Oct. 14, 2021

Camera Ready Submission

Sep. 25, 2021

Notification to Authors

Sep. 23, 2021

Reviewer Deadline

Sep. 18, 2021

Paper Submission

Call for Papers

The topics include, but are not limited to the following:

  • Machine learning for modeling big data from buildings, cities, and various urban-scale data
  • AI-driven building automation
  • Modeling of human mobility in cities
  • Urban sensing
  • Data-driven urban scale occupant behavior modeling
  • Scaling up models to big data and large scale deployment
  • Model standardization and benchmarking
  • Fault-free data-driven building operation 
  • City-scale model scalability
  • Urban scale building energy modeling
  • Outdoor thermal comfort
  • Big data for Grid-interactive efficient buildings (GEB)
  • Buildings-to-grid integration

Submission Guidelines

The workshop will accept the submissions of original work or work in progress. Submitted papers must be unpublished and must not be currently under review for any other publication. Submissions must be full papers, at most 4 single-spaced US Letter (8.5” x 11”) pages, including figures, tables, references and appendices. Submissions for All submissions must use the LaTeX (preferred) or Word styles found here. All submissions must be submitted using the submission website. Authors must make a good faith effort to anonymize their submissions by: (1) using the "anonymous" option for the class and (2) using "anonsuppress" section where appropriate. Papers that do not meet the size, formatting, and anonymization requirements will not be reviewed. Please note that ACM uses 9-pt fonts in all conference proceedings, and the style (both LaTeX and Word) implicitly define the font size to be 9-pt. 

The tentative presentation formats are regular oral presentation (15 minutes) and a spotlight presentation (2 minutes). 

Register through ACM BuildSys 2021


Tentative Workshop Schedule (Nov. 16, 2021; All Times in EST)


Closing Remarks


Building Sensor Fault Detection and Diagnostic System
D. Kumar, X. Ding, W. Du, A. Cerpa

Open Set Anomaly Classification
M. Dix, R. Borrison

Dynamic Bayesian Network-Based Fault Diagnosis for ASHRAE Guideline 36: High Performance Sequence of Operation for HVAC Systems
O. Pradhan, J. Wen, Y. Chen, X. Lu, M. Chu, Y. Fu, Z. O'Neill, T. Wu, K. Candan

A linked-data paradigm for the integration of static and dynamic building data in Digital Twins
D. Mavrokapnidis, K. Katsigarakis, P. Pauwels, E. Petrova, I. Korolija, D. Rovas


Keynote II

Challenges in Building Ecosystems – Enabling Data-Driven Services
Matthias Berning




Data-driven Identification of Occupant thermostat Interactions in Small Commercial Buildings
B. Huchuk, F. Bahiraei, S. Dutta

Fifty shades of black: Uncovering physical models from symbolic regressions for scalable building heat dynamics identification
J. Leprince, C. Miller, M. Frei, H. Madsen, W. Zeiler

Application of Occupant Behavior Prediction Model on Residential Big Data Analysis
Y. Mo, D. Zhao

Towards Sensing Urban-scale COVID19 Policy Compliance in New York City
T. Chowdhury, A. Bhatti, I. Mandel, T. Ehsan, W. Ju, J. Ortiz


Keynote I

User-interactive systems for smart buildings and connected communities
Panagiota Karava


Opening Remarks

Keynote Speaker 

Matthias Berning

Title: Challenges in Building Ecosystems – Enabling Data-Driven Services

Abstract: Today’s buildings need to meet a multitude of demands from different stakeholders, to provide sustainable, comfortable, and cost-efficient working, living and recreational spaces. To reach this goal, they need to become Smart Buildings, aware of their occupants and their environment, acting proactively and transparently. Given the fragmented state of the building industry, crucial data is currently stored in silos, underutilized and inaccessible for digital innovators. An open ecosystem is needed to connect all players and address common challenges of data representation, privacy, security, quality, and market access.

Bio: Dr. Matthias Berning is Senior Scientist and Project Manager at ABB corporate research in Germany. He is part of the Sensor Solutions team and his research interests include distributed sensing and information processing in different domains, including building automation. He started to work on wireless sensor networks during his studies at TU Kaiserslautern and continued his research in the field of pervasive computing during his PhD in the TECO research group at the Karlsruhe Institute of Technology.

Panagiota Karava

Title: User-interactive systems for smart buildings and connected communities

Abstract: The development of smart devices and machine learning algorithms provides unique opportunities to revolutionize energy and comfort management systems for buildings by making them user-interactive. The first part of this presentation will introduce a new paradigm for self-tuned comfort delivery for intelligent thermal environments and will discuss insights from its field deployment in an occupied open-plan office building. The second part will introduce a software platform for smart and connected (S&C) energy-aware residential communities, the SmartEnergy (SmartE) app, and will present findings from a 4-year field study on real-world S&C technology deployment in 100 households.

Bio: Panagiota Karava currently is the Jack and Kay Hockema Professor in Civil Engineering at Purdue and is affiliated with both Ray W. Herrick Laboratories and the Center for High Performance Buildings (CHPB). Dr. Karava joined Purdue in 2009 as founding member of the Architectural Engineering Program within the School of Civil Engineering. Since then, she has played a leading role in establishing the new program as well as developing new teaching and research infrastructure. Dr. Karava’ research interests are broadly related to high performance buildings and smart building technology. She has authored more than 100 journal and conference publications, and has a track-record in leading ambitious and high-impact research partnerships and interdisciplinary teams. She is the recipient of the 2014 Wansik Research Excellence Award at Purdue and the New Investigator Award from ASHRAE (2013) and serves as an editor in Energy and Buildings journal.


Technical Program Committee

Workshop Chairs

Prof. Bing Dong

Syracuse University

Prof. Salvatore Carlucci

The Cyprus Institute

Dr. Ing. Romana Markovic

Karlsruhe Institute of Technology

* Webmasters: Yapan Liu & Wei Mu

Best Regards from the ACM BALANCES Team
Made with Mobirise