Utilidata Software-Defined Smart Grid Chip

  • December 20, 2021
  • William Payne

Grid-edge software specialist Utilidata is developing a software-defined smart grid chip in collaboration with NVIDIA. The chip will be powered by NVIDIA’s AI platform and embedded in smart meters to enhance grid resiliency, integrate distributed energy resources (DERs) — including solar, storage, and electric vehicles (EVs) — and accelerate the transition to a decarbonised grid.

The U.S. Department of Energy’s (DOE’s) National Renewable Energy Laboratory (NREL) will be among the first to test the software-defined smart grid chip as a way to scale and commercialise the lab’s Real-Time Optimal Power Flow (RT-OPF) technology, with support from the Solar Energy Technologies Office Technology Commercialisation Fund.

Originally developed with funding from DOE’s Advanced Research Projects – Energy (ARPA-E) programme, RT-OPF enables highly localised load control to integrate an increasing number of DERs while ensuring stable and efficient grid operations.

The complexity of the power grid will grow exponentially as more distributed energy resources and intermittent renewables come online. Current meters lack the computing power necessary to support real-time, autonomous grid operations that will help achieve decarbonisation goals and improve grid resiliency.

Utilidata’s machine learning software leverages real-time data from smart meters and other distribution grid devices to detect anomalies that are precursors to system failures and outages, optimise grid operations, and integrate exponentially more DERs onto the utility system. The company is also a member of NVIDIA Inception, a programme designed to nurture cutting-edge startups.

“To date, the scalability and commercial potential of technologies like RT-OPF have been limited by single-use hardware solutions,” said Santosh Veda, Group Manager for Grid Automation and Controls at NREL. “By developing a smart grid chip that can be embedded in one of the most ubiquitous utility assets – the smart meter – this approach will potentially enable wider adoption and commercialisation of the technology and redefine the role of edge computing for DER integration and resiliency. Enhanced situational awareness and visibility from this approach will greatly benefit both the end customers and the utility.”

“To maximise the value of DERs and integrate these resources into grid operations, utilities are going to need decentralised solutions, like RT-OPF,” said Marissa Hummon, Chief Technology Officer at Utilidata. “Existing meters don’t have the computational power or communications bandwidth to support this kind of real-time operation. But combining our real-time grid software solutions with NVIDIA’s advanced edge computing capabilities unlocks new value from the meter and offers a path to scale for solutions like NREL’s RT-OPF.”

NVIDIA Jetson is the leading AI-at-the-edge computing platform, used by over 850,000 developers. Pretrained AI models, developer SDKs, and support for cloud-native technologies across the full Jetson lineup allow developers to build and deploy high-quality, software-defined features on embedded and edge devices targeting robotics, AIoT, smart cities, healthcare, energy, industrial applications, and more. Cloud-native support for Jetson will help Utilidata implement frequent improvements in accuracy and quickly deploy new algorithms throughout an application’s lifecycle, at scale, while minimising downtime.

“Our collaboration with Utilidata and NREL to bring AI to grid edge operations will increase resiliency and reduce energy consumption and costs to consumers through new capabilities in meters,” said Marc Spieler, Head of Global Energy Business Development at NVIDIA. “With the availability of an open, software-defined meter platform, utilities and consumers will no longer be locked into closed, proprietary systems that hamper innovation by limiting third-party applications.”