Grid edge module to enhance data computation for utilities

US companies Utilidata and NVIDIA will develop and deploy a grid-edge AI module for utilities to accelerate complex data computation, thereby enhancing the integration of Distributed Energy Resources (DER) and strengthening grid resilience.

As more people shift to producing and storing their own energy with solar, batteries and EVs, powerful computation is needed to process massive amounts of data within seconds and provide grid operators with visibility and information over their operations.

Edge AI aims to accelerate this complex computation at the site where data is being generated by energy consumers, rather than sending large amounts of complex data to a central cloud computing data centre, which increases costs and latency and delays real-time decision making.

The module will leverage US-based tech company NVIDIA’s Jetson platform and power energy software company Utilidata’s smart grid chip, a distributed AI platform installed alongside electric meters.

The new module will bring the necessary computational power via a Graphics Processing Unit (GPU) to the edge of the grid at a power consumption, price point and security standard hoped to lower the overall cost of decarbonisation.

Have you read:
The power grid: Why a smart meter AMI system is the way to go
Enhancing grid coordination with digital twin technologies
Gridspertise CEO highlights digital leapfrog opportunities for European DSOs

According to a release issued by the two companies, the module will contain a specific-sized memory block for grid edge data, optimised clock speeds of the Central Processing Unit (CPU) and GPU to maximise energy efficiency, as well as a customised number of cores.

It is designed to rapidly process measurements like waveform data from the grid and continuously generate AI models for uses such as granular demand forecasting, identifying pre-outage conditions, and interconnecting new DERs to the grid.

A smaller-sized module, it aims to be easier to add directly into grid edge devices like EV chargers, solar inverters and electricity meters. The open hardware and software architecture also enables third-party developers to integrate proprietary software and build new grid-edge applications.

“Utilidata’s smart grid chip, with the first-ever purpose-built AI module for the grid, will transform how utilities operate the grid edge,” said Josh Brumberger, Utilidata’s CEO. “By working with NVIDIA on a custom module, we are able to make edge AI accessible to all utilities and significantly drive down the cost of electrifying transportation, add more solar and energy storage to customers’ homes and businesses and greatly increase the reliability of the grid.”

Utilidata began collaborating with NVIDIA in 2021 to develop the smart grid chip using the NVIDIA Jetson Nano system-on-module. Smart grid chips deployed in 2023 with multiple utility partners will be powered by the NVIDIA Jetson Orin™ platform.

The edge AI module will be deployed with the smart grid chips beginning in 2024.