In addition to gobbling insane amounts of power, AI can help make the grid more efficient, reliable, & resilient. Here, we’ll look at promising use cases on the bulk power supply system, including transmission:
W/transmission, AI can aid predictive maintenance. Operationally, it can also help boost transmission line performance by enabling certain grid enhancing technologies (GETs) to make more efficient use of existing infrastructure. Dynamic line rating replaces historical methods of limiting capacity based on static ratings, in favor of an approach using actual ambient conditions. Lower temps/higher wind speeds pull heat from lines, allowing greater power flows, in some cases 50%+.
That helps limit congestion bottlenecks & aids w/the interconnection of new generating assets, especially wind, since logically when wind turbine output is high, that wind dissipates heat from the lines.
Then there’s topology optimization – opening and closing breakers to route power differently, facilitating higher asset utilization. Here, AI can help by more quickly assessing a wider variety of scenarios.
There’s also interconnection: In 2000, the process took two years, as planners dealt with fewer, larger projects – mostly big gas and coal plants, with about 300 projects in the queue. That number is now over 10,000. Here, AI can help cut time required to evaluate scenarios and increase the number of scenarios that can be assessed.
On the gen side, gas turbines can run more efficiently, based on operating conditions rather than prescribed schedules. Algorithms applied to data from sensors can tell grid operators how hard to run a turbine, while better understanding when to take turbines out for maintenance, rather than relying on fixed schedules.
AI also helps generate longer term, geographically precise weather forecasts aiding asset operators refine output projections and dispatch strategies, while also optimizing battery storage and dispatch.
Within a wind farm, AI can minimize the disruptions in wind flow affecting downwind turbines by steering wakes and optimizing output. This can cut land requirements for future wind plants by an average 18% and up to 60% in some cases.
AI also aids advanced geothermal projects. Machines and algorithms inform operators where to drill, physically guide the drill bit through rock, predict reservoir behavior and determine how much heat to extract from given areas over specified durations.
Some of these applications already take place with AI and machine learning. But as the large language models become increasingly powerful and sophisticated, the ability to develop generative AI – to understand the patterns of existing data and then generate new data to improve decision making – will take us to the next level.
If these AI-driven datacenters are going to stress the grid with unprecedented demands, we should create as much value with these new capabilities as we possibly can.
