​​

​​​​​​​​​​​​​​​​​​​​​​​​​​Workshop (W4): AI for Energy Innovation

held in conjunction with 37th AAAI Conference on A​rtificial Intelligence (AAAI-23)

Monday, February 13, 2023
Washington, D.C., USA
Walter E. Washington Convention Center
Room 140B
​​

​AIenergyWorkshop2023DC1.png



Workshop description:

​In light of pressing and transformative global needs for equitable and secure access to clean, affordable, and sustainable energy, as well as of the significant investment provided from governments and industries, the alignment of R&D efforts on AI and automation across the entire spectrum, from fundamental to applied energy sciences, is timelier than ever. Despite recent monumental AI progress and widespread interest, there may be disconnects between the AI frontier and energy-focused research. 

Many dream of a car that finds its way on its own, but few may think of a power plant with enough self-awareness and secure embedded intelligence to arrange its own maintenance and safety posture given its projected mission, or of a renewable-heavy grid that is autonomously managing its generation and storage based on ongoing and forecasted conditions, as well as on evolving sociotechnical objectives and constraints stemming from the communities it serves. ​

We envision a near future where energy systems will be equally intelligent as the most adept AI systems in existence, with energy resources equipped with smart functionalities to effectively operate under uncertainty, volatility, and threats, where communities empower their lives with reliable and sustainable energy, and where the entire AI community undertakes the challenge of providing solutions and inspiration for sustained energy innovation. 

The AAAI-23 workshop AI for Energy Innovation invites AAAI-23 attendees, researchers, practitioners, sponsors, and vendors from academia, government agencies, and the industry to present diverse views and engage in fruitful conversations on how innovation in all aspects of AI may support and propel further energy innovation. We strongly encourage dialogue-provoking contributions that summarize broader ongoing themes and efforts as well as upcoming and/or future opportunities that may stimulate a productive exchange and forge partnerships among participants. At the end of their talk, participants will be encouraged to propose a new energy-related benchmark problem that they would like to see the AI community adopting, recognizing that well-known general datasets and problems may be suitable for general AI/ML education and research, but possibly not ideal nor focused-enough vehicles to propel AI-equipped, energy-focused innovations. 

​Topics:

(i) Fundamental energy sciences. Of particular interest are AI/ML techniques for reduced order modeling, especially for multiphysics systems, digital twins, as well as general, energy-focused physics-based ML. Even if categorized as "fundamental", contributions are encouraged to cover how one can solve fundamental problems in ways that are amendable to and, possibly, enabling real-world applications. For example, how to create and intelligently update fast-enough, multifidelity models for diverse energy components ranging from multiphysics in nuclear reactors, to battery (or other energy storage) chemistry, dynamics and aging, and to power grids with significant renewable generation (and which models can, in turn, be used in conjunction with intelligent decision-making algorithms of interest to topic (ii)).

(ii) Applied energy sciences and technologies. Of particular interest are AI/ML decision-making techniques (covering state estimation, control, and supervision) for efficient, robust, and equitable management of energy. Indicative techniques of interest include reinforcement learning, particularly in connection with digital twins, other AI/ML-based optimization and control approaches, as well as intelligent forecasting techniques for renewable generation. It is expected that ideas and techniques presented will address one (or more) hard, energy-related operational problem currently faced by the energy industry (e.g., how to make grids more resilient? how to design better maintenance schedules for energy infrastructure? how to understand risk propagation in renewable-heavy grids? how to perform bidding fairly and equitably in energy markets?).

(iii) AI and AI-based assurance & cybersecurity.  Of particular interest are both (a) AI/ML methods that make energy generation, transmission, and distribution more secure against issues and/or threats, and (b) methods that address security aspects arising from the use of AI/ML techniques, as well as the possible intersection of the two directions (a) and (b).


​Invited presentations: 

To be given by:
  • Prof. Aranya Chakrabortty, U.S. National Science Foundation (NSF)
  • Prof. Jenifer Shafer, U.S. DOE Advanced Research Projects Agency – Energy (ARPA-E)
  • Dr. Guohui Yuan, U.S. DOE Solar Energy Technologies Office (SETO)
  • Dr. Amir Roth, U.S. DOE Building Technologies Office (BTO)
  • Prasad Gupte, U.S. Department of Transportation
  • Dr. Soumalya Sarkar, Senior Principal Research Scientist, Raytheon Technologies
  • Dr. Sonja Glavaski, Principal Technology Strategy Advisor, PNNL (recent program director at ARPA-E)
  • Prof. Na (Lina) Li, Harvard University​
  • Prof. Jochen Cremer, Delft University of Technology
  • Dr. Edward Y. Hua, The MITRE Corporation
  • Dr. Yingchen "YC" Zhang, Utilidata Inc​.

Organizing committee:

Humberto E. Garcia    – chair    (U.S. DOE Idaho National Laboratory)
Asok Ray                 – co-chair    (Pennsylvania State University)
Karthik Duraisamy – co-chair​​    (University of Michigan)
Hong Wang                                   (U.S. DOE Oak Ridge National Laboratory)
Draguna Vrabie                             (U.S. DOE Pacific Northwest National Laboratory)​
Dimitrios Pylorof                          ​(U.S. DOE Idaho National Laboratory)​


Logistics:

Presenters of accepted contributions as well as any other attendee will need to register in order to be present in the workshop, following the AAAI-23​ conference instructions. All such logistics are handled by AAAI-23. Please refer to https://aaai.org/Conferences/AAAI-23/registration/​.


Schedule:

(link to view/​download workshop program: ​AAAI-23 W4 AI for Energy Innovation program.pdf)
​

Contact information:



​Disclaimer:

​​This workshop is co-organized by employees of Idaho National Laboratory (INL) managed and operated by Battelle Energy Alliance LLC (BEA) under Contract No. DE-AC07-05ID14517 for the U.S. Department of Energy (DOE). Neither the United States Government nor any agency / contractor thereof, nor any of their employees, make any warranty, express or implied, or assumes any legal liability or responsibility for the accuracy, completeness, or usefulness of any information, apparatus, product, or process disclosed, or represents that its use would not infringe privately owned rights. Reference herein to any specific commercial product, process, or service by trade name, trademark, manufacturer, or otherwise does not necessarily constitute or imply its endorsement, recommendation, or favoring by the United States Government or any agency thereof. The views and opinions expressed herein do not necessarily state or reflect those of the United States Government or any agency thereof. The workshop is hosted in the context of the 37th AAAI Conference. Neither INL, DOE, BEA,  nor any agency/contractor thereof, nor any of their employees, assume any liability nor loss related to submitting manuscripts to and participating in the workshop. All attendees are expected to follow the AAAI Code of Conduct for Events and Conferences (https://aaai.org/Conferences/code-of-conduct.php), and let the organizers and/or AAAI know about any issues and/or concerns.