Digital twins: modernizing the oldest source of clean energy

Ranney Falls OPG
Ranney Falls (Credit: OPG)

Considering each hydropower plant has unique quirks in design, size, and age, it can be difficult to model and anticipate when issues will occur on an individual plant basis. A newly updated tool gives hydropower operators a “digital twin” of their hydropower systems, now including factors that can affect turbine health.

Experts from multiple domains collaborated and developed a platform called Digital Twins for Hydropower Systems in 2023, meant to reduce outages and extend the lifespan of dams. With new updates released in September 2024, dam operators can now use the dashboard to adjust factors that can potentially wear down a turbine’s efficiency, like unexpected electricity demand or extreme water level changes.

“Hydropower facilities are like snowflakes; even individual turbines within a plant are unique due to their individualized construction and varying upgrades over the years,” said Nathan Fletcher, senior hydropower engineer at the Department of Energy’s Pacific Northwest National Laboratory (PNNL).

With the nation’s dams sitting at an average age of 60 years, multiple generations of employees have likely worked on each turbine, leaving behind knowledge with each handover. Hydropower digital twins can record and simulate changes made to the dam over subsequent years, which is meant to help pass down knowledge and help future generations make decisions.

“Each dam requires a unique maintenance strategy to improve efficiency, and the new digital twins platform can provide those solutions,” said Chitra Sivaraman, PNNL principal investigator of the project. “The platform is both extensible and scalable—capable of adapting to new facilities, data and models.”

The digital twins solution allows hydropower operators to simulate different scenarios, like low water flow or varying water levels, including a prediction of future performance or maintenance needs. To build the digital twin, a team at DOE’s Oak Ridge National Laboratory (ORNL) used real-time data from a hydropower generation unit at Alder Dam on the Nisqually River in western Washington State, operated by Tacoma Public Utilities. The team collected data, such as the river’s pressure as it enters the hydropower facility, how fast the turbines spin, and how much power the dam generates over time. 

In the original version of the digital twin, dam operators could only observe how normal or expected conditions affected the dam’s mechanical parts. In version 2.0, operators have more control, PNNL argues. Operators can adjust water levels, flow rates, and turbine speeds that might change based on weather, droughts, or energy demand.

The updated digital twins model also aims to address an emerging need: as more wind and solar generation comes online, hydropower systems need to be adaptable and responsive to support the grid. Hydropower can be ramped up to meet demand, but too much use can age the dam’s components quicker than usual. The digital twin solution aims to address this by allowing operators to simulate and review real-world power demand fluctuations. Operators can then choose to proceed if the model shows optimal conditions to run the hydro turbines, PNNL said.

The team is also working with Chelan County Public Utility in north-central Washington state to collect and analyze years of operation data records from the Rocky Reach Dam to develop a digital twin.

The Digital Twins for Hydropower framework, a collaboration between PNNL and ORNL, was sponsored by the U.S. Department of Energy’s Water Power Technologies Office (WPTO). The platform is meant to serve as a place for the hydropower industry to evaluate and replace mechanical components, accelerate technology development, and improve hydropower operations and performance. These improvements reduce service downtime and shutdowns, which interfere with delivering electricity to the grid.

There are 50 hydropower plants in the U.S. that have been in service since 1908, according to the U.S. Energy Information Administration. As the fleet ages, the industry faces the challenges of operational stress to older mechanical components and the associated costs of degrading functions. With an average life expectancy of 40 to 60 years, hydropower plants need preventative maintenance much like an aging car. By predicting and planning for components that need to be replaced or updated, the hydropower industry can maintain flexible and reliable energy services.

Digital twins use next-generation technologies — including artificial intelligence, machine learning, and virtual reality — to simulate hydropower generation, transmission, and distribution systems. The simulations can predict plant performance under various types of market demand and complexities.

Trump’s ‘unpredictability’ shakes investors – This Week in Cleantech

This Week in Cleantech is a weekly podcast covering the most impactful stories in cleantech and climate in 15 minutes or less.
wind turbines in front of an orange sunset

Renewables permitting has been ‘paralyzed’ by Trump – This Week in Cleantech

This Week in Cleantech is a weekly podcast covering the most impactful stories in cleantech and climate in 15 minutes or less.