Keynote Speakers

ACM e-Energy Keynotes

John Sipple

John Sipple

June 21, 2023 - 9:15 AM EST

Realizing the next AI transformation: intelligent monitoring and control for tackling the climate challenge and managing energy cost

Abstract: The next major AI wave will help tackle the climate challenge and manage increasing energy costs. However, operationalizing intelligent monitoring and optimal control in real-world settings still presents some formidable challenges.

  • Most anomaly detection algorithms are insensitive to multimodal operation, and don’t provide rich explanations for diagnosing and treating emerging faults.
  • In optimal energy control, there is a contention between efficiency and fidelity for off-line training, and multi-objective reward functions may have conflicting efficacy and efficiency objectives.
  • Hybrid action spaces are common in real systems, but few optimal control algorithms support them, and few methods adequately handle multimodal control contexts.
Google has a goal to significantly reduce carbon emission and reduce energy consumption in hundreds of its office buildings. In this talk, I will share how the Core Enterprise Machine Learning team leverages explainable AI to enable efficient diagnosis and treatment. We will also share methods and results of our Smart Buildings control project whose goal is to achieve 5% energy efficiency improvement, and 5% carbon emission reduction.

We believe that AI-enabled monitoring and control will be the next transformative technology becoming essential components of future global sustainability strategies, and we are thrilled to share our vision and progress in this important endeavor.

Biography: As Tech Lead and Staff Software Engineer of Google’s Core Enterprise Machine Learning team, John Sipple is on a mission to deploy novel fault detection and diagnostics and practical smart control to large-scale industrial problems. John leads multiple development efforts that combine multidimensional anomaly detection with model explainability. He also leads a research effort to deploy reinforcement learning to make commercial office buildings more efficient and environmentally sustainable. John has also worked on dialog summarization models for Google chat. Before joining Google, John developed and applied algorithms, statistical analysis, and machine learning solutions to cybersecurity, precision agriculture, counterfeit detection, and missile defense. As an adjunct professor at the George Washington University, John teaches graduate and undergraduate courses in Machine Learning.

Bronis R. de Supinski

Bronis R. de Supinski

June 22, 2023 - 9:00 AM EST

El Capitan: Lessons from Building An Exascale System

Abstract: Livermore Computing (LC), Lawrence Livermore National Laboratory’s (LLNL’s) supercomputing center, and HPE are deploying the first US exascale system focused on national security. This talk will provide an overview of the preparations for LC’s first exascale system, as well as details of its system architecture. Throughout, the talk will explore implications for research in energy efficient solutions.

Biography: As Chief Technology Officer (CTO) for Livermore Computing (LC) at Lawrence Livermore National Laboratory (LLNL), Bronis R. de Supinski formulates LLNL’s large-scale computing strategy and oversees its implementation. He frequently interacts with supercomputing leaders and oversees many collaborations with industry and academia. Previously, Bronis led several research projects in LLNL’s Center for Applied Scientific Computing. He earned his Ph.D. in Computer Science from the University of Virginia in 1998 and he joined LLNL in July 1998. In addition to his work with LLNL, Bronis is a Professor of Exascale Computing at Queen’s University of Belfast. Throughout his career, Bronis has won several awards, including the prestigious Gordon Bell Prize in 2005 and 2006, as well as two R&D 100s. He is a Fellow of the ACM and the IEEE.


Association for Computing Machinery ACM SIGEnergy


Virginia Tech VMWare
The ACM e-Energy 2022 Website by ACM SIGCOMM 2012 is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License. Source code is available at