This workshop will also consist of invited speakers who are recognized experts in the field of AI for power system resilience and security and encompass industrial, academic, and governmental research settings. Each invited talk will last 25 minutes, followed by a 5-minute discussion. The 2025 AI-PRS workshop invited speakers are:
Topic: AI Foundation Models for the Power Grid
Abstract:
The rapid emergence of Foundation Models (FM)s is reshaping the AI landscape. While FMs are well established for text and image analysis, here we introduce notion of GridFMs, which are FMs trained with grid-relevant data to improve power grid operations, planning, and control. It will be shown that GridFMs are a promising technology to overcome the growing gaps between computational capabilities and the need to cope with the increasing uncertainty and complexity of the power grid. In this presentation we highlight the salient advantages of FMs, which include excellent token prediction skills (signal reconstruction and forecasting), broad adaptability and scalability, and simulation acceleration. We then show an implementation of a GridFM pre-trained on power flow data tailored to accelerate power flow-related downstream applications (e.g., optimal power flow and contingency analysis)
Topic: AI for Cybersecurity of Distributed Energy Resource Aggregations
Abstract:
The adoption of Distributed Energy Resources (DER), such as rooftop solar systems, behind-the-meter batteries, and electric vehicles presents many challenges for system operators who are tasked with maintaining the safety and efficiency of the power grid. IoT connectivity of these devices, coupled with emerging control paradigms being put forth in DER standards, makes it possible for these devices to be remotely accessed and utilized to disrupt the operation of the power system. In this talk, I will discuss how tools from machine learning and artificial intelligence can be used to detect and mitigate certain kinds of cyber attacks on DER control systems, thereby providing system operators with new tools to secure their grids.
Topic: AI for Equitable and Resilient Infrastructure Development
Abstract:
The electricity grid is transforming with the integration of renewable energy, energy storage, residential heat pumps, electric vehicles, and advanced information technology to better manage energy use. However, these advancements also highlight a significant challenge: not all communities have equal access to these essential resources. During extreme weather events, the lack of resilience in certain areas becomes especially apparent, putting some communities at greater risk. This talk will explore how new technologies, including artificial intelligence, can help create a fairer and more resilient electricity system. We will discuss strategies to ensure everyone has access to reliable, clean energy so that no community is left behind in transitioning to a clean and modernized grid.