International Workshop on
Artificial Intelligence for Smart Grids
and Smart Buildings

In conjunction with AAAI 2017
San Francisco, CA, USA
February 4 or 5, 2017

This workshop invites works from different strands of the AI community that pertain to the design of algorithms, models, and techniques to deal with smart grids and smart buildings.

Important Dates:

  • November 12, 2016 - Submission Deadline EXTENDED
  • November 29, 2016 - Acceptance Notification EXTENDED
  • December 1, 2016 - Camera-Ready Deadline
  • February 4 or 5, 2017 - Workshop Date

Call for paper [txt]

Registration and hotel information


The availability of advanced sensing and communication infrastructures, electric monitoring facilities, computational intelligence, widespread use and interest in renewable energy sources, and customer-driven electricity usage, storage and generation capabilities, have posed the foundations for a robust and dynamic next generation economic interplay between the demand-side: smart buildings, and the supply-side: smart power grids. Three key aspects distinguish this evolving economy from more traditional market forces: (1) Information: both energy producers and consumers have access to information (e.g., production costs, customers’ electricity needs, time distribution of demands); (2) Exchange: communication is possible on a continuous basis, thus enabling both individual as well as group decision processes (e.g., producers and consumers can negotiate prices and energy exchanges); (3) energy can be produced not only by power plants, but also by customers (e.g., via solar panels) and stored for later use (or redistributed through the electric grid), and (4) given all of the above, customers can employ advanced tactical measures for improving building operations and reducing energy consumption without sacrificing occupant satisfaction, which has direct economic implications for producers.

IIn general terms, a smart grid enables the distributed generation and two-directional flow of electricity and information, within an integrated system of connected smart buildings as key agents within this new ecosystem.

AI plays a key role in the relationship between the smart grid and smart buildings. New technologies offer infrastructure that provides information to support automated decision making on how to (automatically) adapt production/consumption, optimize costs, waste, and environmental impact, and provide reliability, safety, security, and efficiency. Indeed, several research projects have already developed the view of this ecosystem as a multi-agent system, where agents coordinate and negotiate to achieve smart grid and smart building objectives.

The goal of this workshop is to bring together researchers and practitioners from diverse areas of AI to explore both established and novel applications of AI techniques to address problems related to the design, implementation, deployment, and maintenance of both smart buildings and the smart grid – either as independent topics or together in an overarching multi-agent system. Topics include, but are not limited to:

  • Distributed decision making and distributed optimization
  • Agents and multi-agent applications in smart grids
  • Data analytics and machine learning techniques applied to smart grids and energy management
  • Advanced machine learning techniques used to improve building maintenance and operations and reduce energy consumption without sacrificing occupant satisfaction
  • Novel information and sensing technologies that can be used to enable the deployment of advanced machine learning and data mining techniques within the built environment
  • Knowledge-based methods in design of smart buildings and smart grids
  • Coordination of intelligent agents in smart grids
  • Negotiation and trading strategies in energy markets
  • Human-computer interactions and human-in- the-loop systems within smart grids
  • Simulations of energy markets and smart grids


Participants should submit a paper (maximum 6 pages + 1 page of references), describing their work on one or more of the topics relevant to the workshop. Accepted papers will be presented during the workshop and will be published as AAAI technical reports, which will be made freely available in AAAI's digital library.

Authors are requested to prepare their papers using the AAAI style files:

All submissions are conducted via the following website:

Submissions should include the name(s), affiliations, and email addresses of all authors in the body of the email. We welcome the submission of papers rejected from the AAAI 2017 technical program. The deadline for receipt of submissions is December 1, 2016. Papers received after this date may not be reviewed.

Submissions will be refereed on the basis of technical quality, novelty, significance, and clarity. Each submission will be thoroughly reviewed by at least two program committee members.

For questions about the submission process, contact the workshop co-chairs.


8:45: Welcome and Introductions (Enrico Pontelli, Rodney Martin, Thanh-Long Tran, and Son Tran)

Session 1

  • 9:00-10:00: Invited Talk: Machine Learning and Inference using Bayesian Network with Application to Sustainability and Smart Buildings

    Speaker: Professor Ole Mengshoel (CMU-SV)

    Abstract: Research on probabilistic graphical models, including Bayesian networks, has enjoyed significant progress in recent years. Bayesian networks have, for example, been successfully employed in sustainability, model-based diagnosis, biology, natural language understanding, probabilistic risk analysis, intelligence analysis, and error correction coding. In addition to being well-suited to automated reasoning and machine learning, these probabilistic graphical models are also very useful in structuring visualizations such that people can interact with and understand them relatively easily. I will discuss a few areas where progress on Bayesian network computation has recently been made, including applications to sustainability and smart buildings. For example, emerging smart buildings such as NASA's Sustainability Base have a broad range of energy-related systems, including systems for heating and cooling. While the innovative technologies found in Sustainability Base and similar smart buildings have the potential to increase the usage of renewable energy, they also add substantial technical complexity. Consequently, managing a smart building can be a challenge compared to managing a traditional building, sometimes leading to adverse events including unintended thermal discomfort for occupants. Targeting this challenge, I will discuss a Scalable Causal Learning (SCL) method that integrates dimensionality reduction and Bayesian network structure learning techniques. The causal variables identified by SCL are found to be very effective in predicting adverse events, namely abnormally low room temperatures, in a conference room in Sustainability Base. I will end the talk by discussing challenges and opportunities related to developing artificial intelligence methods, including those based on probabilistic graphical models, for sustainability.

  • 10:00-10:30: Fast Electrical Demand Optimization under Real-time Pricing
    Shan He, Mark Wallace, Campbell Wilson and Ariel Liebman

10:30-11:00: Break

Session 2

  • 11:00-11:30: Comparison of Clustering Techniques for Residential Energy Behavior using Smart Meter Data
    Ling Jin, Doris Lee, Alex Sim, Sam Borgeson, John Wu, Anna Spurlock and Annika Todd
  • 11:30-12:00 Solar Decathlon Competition: Towards a Solar-Powered Smart Home
    A. Leah Zulas, Kaitlyn Franz, Darrin Griechen and Matthew Taylor
  • 12:00-12:30 A Multiagent System Approach to Scheduling Devices in Smart Homes
    Ferdinando Fioretto, William Yeoh and Enrico Pontelli

12:30-1:30 Lunch

Session 3

  • 1:30-2:00 An Extension of Network Security Games for Large-Scale Infrastructure Protection
    Denis Kolev and Chris Johnson
  • 2:00-2:30 Energy disaggregation methods for commercial buildings using smart meter and operational data
    Shubham Bansal and Mischa Schmidt
  • 2:30-3:00 Data Analytic Policy Design Applied to Energy Conservation in College Dormitories
    Lei Zhan and Dah Ming Chiu
  • 3:00-3:30 An Empirical Analysis of Constrained Support Vector Quantile Regression for Nonparametric Probabilistic Forecasting of Wind Power
    Kostas Hatalis, Shalinee Kishore, Katya Scheinberg and Alberto Lamadrid

3:30-4:00 Break

Session 4

  • 4:00-4:30 Roundtable discussion: Future of AISGSB


  • Seb Stein, University of Southampton (UK)
  • Alex Rogers, University of Oxford (UK)
  • Alessandro Farinelli, Computer Science Department, Verona University (Italy)
  • Meritxell Vinyals, Commissariat à l’énergie atomique et aux énergies alternatives (CEA) (France)
  • Matt Wytock, Carnegie Mellon University (USA)
  • Mario Berges, Carnegie Mellon University (USA)
  • Sylvie Thiebaux, ANU (Australia)
  • Gauthier Picard, Laboratoire Hubert Curien UMR CNRS 5516, Institut Henri Fayol, MINES Saint-Etienne (France)
  • Paul Scott, ANU and NICTA (Australia)
  • Christopher Kiekintveld, University of Texas at El Paso (USA)
  • William Yeoh, New Mexico State University (USA)
  • Mathijs de Weerdt, Delft University of Technology (The Netherlands)
  • Enrico H Gerding, University of Southampton (UK)


Workshop Co-Chairs: