Real-Time Edge Analytics for Microgrids

edge analytics

Quickly deciding whether to store power, rely on a utility, or discharge a battery is difficult on a grid with variable energy sources such as solar. Here’s how ELM and Dell tackle the challenge with controllers, gateways, and edge analytics for on-site and remote power systems.

Name of Organization: ELM Energy, LLC

Industry: Energy Management

Location: Peoria, IL USA

Business Opportunity or Challenge Encountered:

For today’s diverse energy management environments, real-time analytics is essential. Many power management systems, such as those attached to generators, rely on more than one power source. For example, microgrids may rely on solar power as well as a battery backup. Since solar isn’t available at the end of the day—or in cloud cover—a smart system needs to detect when to switch to battery power mode or even to the conventional utility power grid.

That kind of decision requires real-time processing and edge analytics, according to ELM Energy, LLC, which works with companies to manage power loads from generators. When solar is suddenly unavailable, microgrids need to “either pull some energy from battery storage, or increase the generator to a higher level of efficiency,” says Aron Bowman, vice president of product development at ELM Energy. The system “needs to be able to make those kind of demand decisions, which take a lot of computing horsepower right at the edge.”

Add to this challenge the fact that many generator sites, particularly in developing nations, may not have Internet access nearby—so the analytics that determine power efficiency may need to reside on-site.

How This Business Opportunity or Challenge Was Met:

To address these requirements for remote real-time energy management, ELM installed localized analytics capabilities alongside its energy management devices. The company’s offering, FieldSight Microgrid Monitoring, includes Dell’s IoT Gateway to enhance its capability to handle the information and processing right at the point of contact, Bowman says.

ELM Energy’s FieldSight Microgrid Monitoring and Control solution optimizes and balances power generation by automatically maximizing the use of renewables. It also improves power reliability by managing electricity demand against supply, reducing grid instability, and enabling demand response program participation. With the Dell IoT gateway, the FieldSight solution automatically computes forecasts around load requirements, managed energy storage, and power generation dispatch.

Power demand “isn’t always syncing up with availability,” says Bowman, “With a battery, I can take that power and pump it into batteries to be stored and used later when I have the power demand. But what that requires is a gateway technology that allows you to monitor, command and control that solution. Our FieldSight solution provides a site controller that allows you to monitor usage and power output, divert power to batteries, and later program to use batteries and flip over to a gas generator.”

As a result, he continues, there’s a need to “take a lot of processing at the edge,” which is basically on-site.

“We have to be able to read what’s happening with the multiple energy sources that our solution is monitoring, and then be able to process that information at the location, and then make decisions on how to operate other components of the system,” Bowman said. “If I’m doing 20 percent solar, and the sunlight changes, and all of a sudden I’m only able to generate 10 percent solar, then I either need my system to pull energy from battery storage that I’ve stored up, or I need the generator to operate at a higher level to make up the difference. I need to be able to make those kind of demand decisions which take a lot of computing horsepower right at the edge.”

Where connectivity is available, the solution supports cloud uploads, “which is where the user interface and the reporting happens,” says Bowman. “We take all of that information and the decisions that are being made at the site, and we put those up into the cloud for further analytics that we provide our customers. We also provide alerts via text messages, emails, and automated phone calls to notify customers of changes in parameters of their equipment.”

 Measurable/Quantifiable and “Soft” Benefits from This Initiative:

As a result of introducing on-site, real-time analytics, ELM is able to provide capabilities to customers in remote areas that may not have continuous Internet connectivity, or even reliable power sources. “A lot of our customers are places like large data centers that have to have reliable backup power—data centers, hospitals, manufacturers,” says Bowman. “But we also have systems in areas like ‘islands’ that don’t have any grid power at all. For example, we service mines. Also, in India, there are neighborhoods that are starting to grow, but grid isn’t expanding fast enough to keep up with the power demand in these neighborhoods. So, they’re generating their own power. Distributed energy solutions really have broad applications when you get outside the United States.”

Because of this versatility, the solution cuts costs for a range of facilities that employ a mix of energy sources—military bases, factories, office buildings and houses, Bowman says.

(Source: ELM Energy, LLC)

Want more? Check out our most-read content:

Frontiers in Artificial Intelligence for the IoT: White Paper
How Real-Time Railroad Data Keeps Trains Running
Operational Analytics: Five Tips for Better Decisions
Why Gateways and Controllers Are Critical for IoT Architecture

Liked this article? Share it with your colleagues!


About Joe McKendrick

Joe McKendrick is RTInsights Industry Editor and industry analyst focusing on artificial intelligence, digital, cloud and Big Data topics. His work also appears in Forbes an Harvard Business Review. Over the last three years, he served as co-chair for the AI Summit in New York, as well as on the organizing committee for IEEE's International Conferences on Edge Computing. (full bio). Follow him on Twitter @joemckendrick.

Leave a Reply

Your email address will not be published. Required fields are marked *