How AI and Machine Learning Are Helping Utilities Digitize
Though fairly new, predictive maintenance use cases in the utility industry are particularly suited for wind turbines and other heavily instrumented machinery, according to Neil Strother, principal research analyst with Navigant. “If something like that is down for a half day, there are untold costs,” he said.
Predictive and proactive maintenance can monitor for anomalies such as excessive heat, leaks or unusual wear patterns. Changing a gear before a failure can eliminate costly downtime and lost revenue, he said.
The electricity industry is strongly committed to moving forward, but full digitalization won’t happen for the next eight to 10 years, according to Chris Moyer, senior director of content and research for Zpryme, an energy-focused researcher based in Austin, Texas.
“IoT sensors will be found at every point of the flow of electricity from generation, to transmission, to distribution and ultimately consumption,” Moyer said. “AI will be crucial to make decisions based on the monumental amount of real-time data being created in the modern grid.”
Zpryme recently surveyed more than 150 global utility leaders on their usage of IoT and AI. They found that 69 percent of utilities agree IoT is critical to the company’s success and 57 percent are already using IoT technology. “The industry still has a way to go to fully realize the potential of IoT devices, but there is a very strong commitment to digitalization,” he said.
Strother, the Navigant analyst, said the industry is probably in the second inning of the ball game when it comes to making full use of IoT capabilities.
The long-term view is what Navigant calls the Energy Cloud transformation. That’s a scenario where the grid supports multiple networks and two-way flow created when customers produce some of their own energy via solar panels or windmills to offset their reliance on the grid, Strother said. Powering up electric vehicles at home or at remote charging stations also has implications for the Energy Cloud.
Technology has already had considerable effect if you consider how utilities typically operated as recently as 15 years ago. “Someone would call in to say they lost power,” said Lance Brown, the retired director of customer service with the Los Angeles Department of Water and Power, the largest municipal utility in the U.S.
“The grid didn’t even know that a transformer was out,” he said. “We’d start to draw a map, and if enough people called in we were pretty sure we knew the location.”
Today, the process starts with alerts from the advanced metering infrastructure, GPS and load and line interrupters. The utility can then ping all the meters in the area to see if it’s an isolated incident or a widespread outage, said Brown, who is now vice president, customer service solutions for Smart Energy Water, a SaaS and analytics provider in the utilities industry. “And we can text customers that we’re responding and what the restoration time will be.”