Naperville, Illinois’ public power utility is using artificial intelligence to improve services and forecast electricity load growth.
The city’s investments in smart grid technology have paid off significantly for enabling analytics that are supporting capabilities ranging from solar deployment to EV charging infrastructure.
In a conversation with APPA, Naperville Electric’s deputy director Olga Geynisman detailed how the utility has leveraged data management to launch the next generation of grid modernization.
A Sound Investment
Naperville made significant investments in grid modernization starting in 2010, using a 2009 grant from the Department of Energy to develop smart metering technology that provided data on grid activity collected by 15-minute intervals. The cornerstone of this project, the Meter Data Management System (MDMS), uses its SmartWorks Compass software platform to manage meter data and process billing for customers.
This meter data management system was a significant advancement beyond Naperville’s prior grid monitoring. Geynisman noted that Naperville’s residents were initially skeptical as to the value of smart metering technology and unsure what benefits it might provide.
“We had a lot of pushback from residents, with them asking why we need 15 minute data and how it is necessary for billing,” she said.
Geynisman was surprised by the range of capabilities these earlier investments have ended up supporting, with the data provided by Naperville’s AMI aligning neatly with the requirement of AI technologies. The SmartWorks MDMS platform now performs sophisticated data analysis on load demand, rates, and energy supply that provide wide-ranging structural insights.
“We didn’t fully anticipate the potential of AI, but today we’re reaping the benefits of advancements in data and machine learning technologies. This reinforces that investing in an AMI system with robust data capabilities was absolutely the right decision - one that’s now enabling us to stay ahead as technology evolves,” she said.
Despite some residents having earlier reservations, Naperville’s data management system has allowed it to become a pioneer among public power utilities in using AI for service improvements and load forecasting. As an immediate benefit to the city’s residents, Naperville’s usage of AI is reducing energy consumption and lowering its customers’ electric bills.
“We use AI to create models which allows us to project baseline load per customer aggregated rate classes. Before, we didn't have the capabilities to do this kind of conservation voltage reduction forecasting. It now allows us to reduce demand during peak hours, which lowers energy usage and helps our customers save on their monthly bills,” Geynisman said.
Forecasting the Energy Transition
In addition to load forecasting, Naperville’s application of AI to grid management is also helping the utility accommodate a growing demand for electric vehicles and renewable energy.
The data collected from the utility’s smart meters has been used to predict how the grid might be impacted by rising EV adoption, as well as the structural adaptations that will be needed to support carbon-free transit.
“We know right now if transformers are overloaded based on meters connected to those transformers. Then if there is EV adoption around a given area you can create projections by running that through the historic data to see if a particular transformer will be overloaded,” Geynisman said.
This comprehensive grid mapping will help inform Naperville’s decisions around where – and how much – to invest in the renewables and battery storage needed to meet rising EV usage.
As a backbone of this project, the utility has created a Distributed Energy Resources (DER) dashboard that has a range of components for supporting solar energy development. The DER dashboard tracks active data, such as the number of solar installations and their current production versus capacity, while forecasting solar production and predicted growth in solar installation, all of which will be used to plan how renewable energy will be integrated with the local grid.
Geynisman noted how the data access and processing capacities enabled by AI could allow public power utilities to perform calculations and analysis at a new level of speed and sophistication – whether in terms of daily information search and inventory management, or in meeting complex challenges of load growth.
“If you need to find something for specific utilities or products, it quickly points you in the right direction and helps you to dig down and find information that could have taken weeks or months to find before that. It's definitely a huge technological jump for all of us,” she said.
Other Public Power Utilities are Also Utilizing AI
Other public power utilities are also utilizing AI.
Brian Taylor, General Manager for Tennessee public power utility CDE Lightband, and Lance Haynie, Government Affairs Director for the City of Santa Clara, Utah, on June 10 provided a variety of examples of how artificial intelligence can be utilized by public power utilities and public power cities. They participated in a panel at APPA’s National Conference in New Orleans, La., “Practical Applications of AI for Utilities.”
Taynor noted that CDE Lightband is using AI with advanced metering infrastructure.
“Most everybody has an AMI system now – you’ve got all this data on meter reading and such. We are also in the broadband business so there’s things we’re wanting to do to target market those folks,” he said.
“What we’re doing now is taking all usage data from the AMI and then clustering those into patterns and like customers so now we’re segmenting customers into like usage patterns,” Taylor noted.
CDE Lightband recently rolled out a smart thermostat program. “Rather than targeting 86,000 customers, there may be 20,000 customers that we think…this is ideal for them. So now we’re just targeting those 20,000 customers.”
For his part, Haynie detailed how AI has helped Santa Clara when it comes to load forecasting.
“We have hit 92 percent accuracy. Now, we are in Utah, where it’s sunny 300 days out of the year, so our weather is a little more predictable than some other regions,” Haynie said.
He noted that “we don’t buy all of our power…so our forecasting is about what is the demand going to be and can we generate it in house or do we have to go out in the market and buy the excess.”
Haynie said “it’s a dollars and cents thing at the end of the day. We went from” around $15,000 in savings “to a quarter million in one month. It was huge when we saw that.”
That is because “we went from manual spread sheets – we had a scheduler who was inputting weather data from weather.com…pulling in load data from a bunch of different sources,” he said.
“Our system now goes back and it pulls all of that directly…and it’s iterative. It’s not just an algorithm that’s running the math behind it and spitting out a number. If it messes up it actually knows that it messed up, sends us an alert and then tries to fix it all by itself.”
