Advanced Computing in the Age of AI | Monday, June 24, 2024

IBM Spins Out Analytics Platform For Utilities 

(Jordi C/Shutterstock)

An IBM-backed energy startup will attempt to advance the smart grid via a new cloud-based analytics platform designed to forecast renewable energy supplies along with the overall health of a statewide and regional power grids.

IBM (NYSE: IBM) and electric power transmission specialist Vermont Electric Power Co. (Velco) said last week the energy startup called Utopus Insights Inc. would incorporate researchers and intellectual property from IBM's smart energy team. IBM Fellow Chandu Visweswariah will serve as president and CEO of the energy analytics startup, which is scheduled to begin operations around March 1.

Despite the Vermont focus, the smart energy spin-out from IBM Research will be based in Valhalla, NY. Headquartered in Rutland, Vt., Velco, is owned by several state electric distribution companies. Terms of the agreement were not disclosed.

Electrical grids have become increasingly complex on both the power generation and demand sides, forcing operators to identify new tools for managing fluctuating renewable energy sources, growing energy demand and far-flung assets.

Another factor fueling the energy management startup is the rise of extreme weather. "Increasing extreme weather events coupled with explosive growth in weather-dependent renewable energy sources led Velco to look for new analytical tools to ensure grid reliability," company CEO Tom Dunn noted in a statement. Velco worked with IBM Research to develop grid management software that will serve as the basis of the Utopus platform.

The software suite includes tools for accurately forecasting wind and solar power generation. The partners said their energy analytics platform would be deployed for cloud, on-premise and Internet of Things operations.

IBM's Visweswariah added that the energy distribution platform would be based on open APIs to allow integration of third-party tools. Planned applications range from renewable energy forecasting, network risk analysis and "grid asset health."

IBM Research has been among the early leaders in areas such as applying predictive and prescriptive analytics to the asset-intensive utility industry. Hence, the emphasis on "grid asset health" tools used to determine, for example, when aging grid infrastructure needs to be replaced. Those efforts reflect what IBM researchers assert is an industry consensus on moving away from "time-based maintenance" to an "asset health management" approach that takes into account such factors as reducing customer downtime and regulatory standards.

"Incomplete information, fragmented data and a diversity of asset classes collectively make a holistic assessment of the grid extremely challenging," IBM researchers noted in a technical paper published last year.

Working with other energy companies, IBM developed an analytics platform designed to model the state of grid assets ranging from transformers to switching gear. Those metrics can be used to determine network reliability by predicting factors such as asset lifecycles, then using that data to compute network health.

Data inputs for the analytics platform range from emerging smart grid metering infrastructure to weather forecasting tools. "The algorithms systematically evaluate asset health and prioritize preventive, proactive and corrective maintenance strategies for all asset classes in the electrical network," the IBM researchers reported.

Along with Velco, Utopus Insights also has a joint development agreement with Bonneville Power Administration in the Pacific Northwest.



About the author: George Leopold

George Leopold has written about science and technology for more than 30 years, focusing on electronics and aerospace technology. He previously served as executive editor of Electronic Engineering Times. Leopold is the author of "Calculated Risk: The Supersonic Life and Times of Gus Grissom" (Purdue University Press, 2016).