Two startups connect Jetson to smart grid meters

Say hello to the smart electricity meter of tomorrow, literally.

You can ask questions about next-gen home energy hubs, just like you do with Alexa or Siri.

Some devices, which will arrive this year, will display real-time simulations – vibrating like a video game – to show how you can lower your energy bill or reduce your carbon footprint. They will help manage power flows for solar panels and electric vehicle chargers.

Like smartphones, they will run apps. And they will give utilities a clearer picture of the network, including warnings if a component on a nearby power line could soon fail.

The story of two innovators

Devices from startup Anuranet will power up in hundreds, if not thousands, of homes starting this fall using the cutting-edge NVIDIA Jetson AI platform.

Utilidata, a Rhode Island-based company that has been developing grid software for a decade, is working with NVIDIA to develop a Jetson-based smart grid chip. It will be used in meters to bring real-time AI applications to the edge.

These efforts are part of a vision for a smarter, cleaner, and safer network that NVIDIA and its partners are helping to make a reality.

“Today’s smart meters aren’t very smart, but with cutting-edge Jetson GPU computing power and our software platform, we’re going to create truly smart meters that will change the energy control network. one house and one building at a time,” said Diane. Zuckerman (pictured above), co-founder of Austin, Texas-based Anuranet, the latest of half a dozen startups she’s started around the world.

Engaging Simplicity

Anuranet develops the Bullfrog brand of smart meters and circuit panels powered by the cutting-edge NVIDIA Jetson AI platform. They can connect to the grid as well as smart appliances, home energy hubs, solar panels, electric vehicle chargers and their batteries to help customers save on their energy bills while reducing their carbon footprint by real time.

“Their simplicity will engage consumers, creating value with high performance and security,” Zuckerman said.

Although only eight months old, the startup has signed contracts with two companies that will start rolling out its devices to new homes this year.

Richland Partners in Nashville will use the Anuranet Bullfrog energy ecosystem in the homes and apartments it builds. Neu Communities in Austin will use them to run private microgrids in the new residential neighborhoods it is building.

Jetson is reshaping edge computing

Today’s smart meters throw away most energy-related data in the home because they don’t have the computing power to process it. It’s a treasure trove of real-time data that Anuranet, Utilidata and others will use to improve the network.

For example, smart meters powered by NVIDIA Jetson can take readings tens of thousands of times per second.

“This data contains information about the quality of the power flow and what might be interfering with it,” explained Marissa Hummon, CTO of Utilidata, an NVIDIA Inception partner that has already built apps for some of the largest measurement companies in the world.

“A branch of a tree can impact the waveform and if we can see that we can predict a failure – that kind of information is something a lot of applications can use, so it creates an environment for others are innovating,” she said.

Deploy the best algorithms

Backed by investments from Microsoft and NVIDIA, Utilidata aims to understand energy flows in ways that benefit both consumers and utilities. It requires machine learning and the computing power to run it.

Hummon shows off a prototype device containing Utilidata’s smart grid chip.

“No human can look at all these patterns to find the key information, but computers can, and our software running on the Jetson-based smart grid chip will allow us to deploy the best algorithms,” Hummon added.

Utilidata and the US National Renewable Energy Lab are collaborating to run the lab’s real-time energy flow software on Utilidata’s smart grid chip. And several utilities are in talks with Utilidata to pilot its chip in smart meter deployments.

Why the network needs AI

Smart meters are well positioned to track and respond to bi-directional energy flows rapidly arriving at the edge of the grid.

Homes and businesses are installing batteries and solar panels that turn them into generators of electricity. At the same time, they are installing electric vehicle chargers that consume more than three times the power of the large air conditioners that were supplying grid demand. And with recent funding in the US, many more chargers and their network applications will come online quickly.

“You can’t write a good physical model to track all of this, it requires a different approach to the problem that’s incredibly well suited for GPU computing,” said Hummon, who holds a Ph.D. in physics from Harvard.

“That’s why cutting-edge AI has gone from a pleasant need to an urgent need for utilities to prepare for what their customers are doing,” she added.

Startups are accelerating

Both startups’ products will be based on full-stack NVIDIA technologies and an open platform for third-party application developers.

Utilidata’s Hummon praised NVIDIA Inception, which supports tech startups, providing investor introductions, expertise and technology.

As part of the software-defined smart grid chip development work with NVIDIA, Inception gave its team access to cloud GPUs and training on how to get the most out of them. Inception has also provided links to other electrical industry innovators.

Smart meters have their say

For its part, Anuranet will bring its Bullfrog devices to life with conversational AI that combines its internal code for natural language understanding with automatic speech recognition in NVIDIA Riva, a GPU-accelerated software development kit for creating applications for voice AI.

“Our code accuracy is already double that of competing offerings, and with Riva I believe we will outperform anything on the market by an order of magnitude,” said Anuranet CTO David L. Brock, Ph.D. in Robotics and AI from MIT, who developed a new approach to natural language understanding.

“Riva is very exciting, and we plan to expand its use in the future,” he added.

It’s one more way for NVIDIA to fuel the transition to a more resilient network and a sustainable future.

In separate sessions at GTC, Utilidata will explain how cutting-edge AI is redefining network operations and tackling climate change. Register for free and experience the full range of sessions on food and utilities.

Comments are closed.