Future Grid Strategy Advisory Group AI Symposium

Event Description

FGSAG AI Symposium Schedule

SPP’s Future Grid Strategy Advisory Group (FGSAG) advises SPP and its Members of future-grid capabilities needed to assure continued reliable and affordable grid operations. The FGSAG provides periodic reports to the SPP Strategic Planning Committee that contain forward-looking utility perspectives and proposed strategic action plans.    

As part of this charter, the FGSAG is hosting an Artificial Intelligence (AI) Symposium focused on future use and potential benefits of AI in the energy sector, particularly in transmission planning, load forecasting, and analysis.  This Symposium will include members and regular attendees of the FGSAG along with relevant SPP Staff. In keeping with the usual operation of the FGSAG, this meeting will be open to the public. Registration will be required for admission into the meeting.   

 SPP is pleased to welcome the following special guests:

 Carl Elkin - Staff Software Engineer, Google Research

“Improving Renewables and Demand forecasting with ML-driven weather models “

GraphCast and GenCast are state-of-the-art AI models able to make medium-range weather forecasts with unprecedented accuracy. They can be customized to predict arbitrary labels or objective functions and (in the case of GenCast) can produce well-calibrated probabilistic forecasts (forecasts ensembles of trajectories for hundreds of weather variables, up to 15 days at 1 degree resolution globally). Google Research and Google DeepMind are currently exploring their use for applications in the energy grid, such as wind and solar supply, and energy demand. We are particularly interested in predicting distributions of outcomes, such as the probability of an energy production shortfall or unexpected rise in demand.

Elkin will discuss early-stage Research into how these models can be used to improve reliability of the electric grid, including progress and current challenges.

Andy Ott - Head of Technical and Partner Operations, Tapestry, an Alphabet project at X, the moonshot factory

“Tapestry – Making the Grid Visible”

Tapestry is a project at X, Alphabet’s innovation lab, that is building AI-powered products for a greener and more reliable future grid. Tapestry’s mission is to make the grid visible by weaving technology, information, and partners to build a grid that can power our future. By making the grid visible to everyone who works with it, we aim to make it greener, fairer, and more reliable for everyone who depends on it.

Mr. Ott will discuss Tapestry’s first two products, GridAware and Grid Planning Suite, that are being tested with partners across the globe with a focus on grid intelligence, planning, and operations

Luis Piloto - Senior Research Scientist, Google DeepMind

“Accelerating Grid Optimization with Machine Learning”

Solving optimization problems is a critical part of power grid operations. Traditional methods for solving optimization problems in power grids are computationally demanding, often leading to the use of approximations that compromise efficiency and reliability. These problems are exacerbated by an increasingly complex grid, rapidly changing patterns of generation and consumption, and increasingly congested transmission lines. The need for accurate and fast solvers is greater than ever. Mr. Piloto will discuss CANOS, a novel data-driven approach that leverages graph neural networks to solve optimal power flow problems. CANOS significantly outperforms commonly used DC approximations in terms of accuracy and is substantially faster than full AC methods.  They also explore strategies for grid operators to collaborate with researchers, enabling the integration of data-driven approaches such as CANOS into operational and planning processes, highlighting the potential benefits and challenges of such collaborations.

Greg McDonald – Managing Director Technology American Electric Power

“Best Practices for Applying AI in an Ethical and Secure Manner

Due to legal restrictions, we are unable to record the symposium.

Contact Information: Mark Hodges / mhodges@spp.org