is part of the Division of Informa PLC

This site is operated by a business or businesses owned by Informa PLC and all copyright resides with them. Informa PLC's registered office is 5 Howick Place, London SW1P 1WG. Registered in England and Wales. Number 8860726.

AI Platform Can Cut Manufacturers’ Energy Costs by 25%

Image courtesy of Alamy/Science Photo Library conceptual image of data and AI
The technology developed by Imperium Predictive Analytics helps manufacturers lock in the lowest energy rates at just the right time.

The energy that fuels plastics processing and other manufacturing operations is a significant cost. A new predictive artificial intelligence (AI) platform promises to help manufacturers lock in the lowest energy rates at just the right time.

The service is the brainchild of Imperium Predictive Analytics, which “can predict energy prices better than anyone else,” asserted Chief Sales Officer Arthur Kaplan. Imperium’s proprietary data strategy and dashboard offer businesses a smarter way to buy energy by monitoring prices in real time — putting more actionable data directly in the hands of manufacturers and processors.

“Energy procurement is a complex process, and brokers have been taking advantage of this for their own benefit for decades,” explained Imperium co-founder Nick Lessells. “There was no true consultative approach that considered the clients and their needs — it was just a sales marketplace.

“We realized that since most brokers were just salesmen, with no real value-add beyond being able to navigate the complex energy markets, we could introduce technology to further reduce the friction of procurement, as well as solve the problem of price by predicting the best time for clients to buy and eliminate the high-pressure sales techniques.”

Imperium’s service lets clients take control of their energy buying for their entire organization and see all their relevant data and bills in one spot, even if their buildings are supplied by different providers.

“Our goal is to make energy easy and transparent, while saving as much money as possible along the way,” said co-founder Lucas Grimes.

Imperium’s predictive algorithm uses an application of machine learning to assess more than 15 types of relevant data and train itself to predict energy prices.

“We take in live data by the minute as well as historical data spanning the last 25 years,” Grimes explained. “We take into account things like LMP (Locational Marginal Pricing), which is essentially the price of energy at a very granular, specific node — of which there are thousands — as well as weather, natural gas prices, day-ahead pricing, and several others. If our clients have an existing contract with a supplier, we find the best time for them to procure between now and the end of their contract. If they are not currently with a supplier, we tell them exactly when to lock in a desirable rate with a fixed rate or save even more with a managed product. The platform is completely customizable to the end user.”

The result? An average savings of 25% to 30% across all industries. “The higher the energy load, the lower the rate we are able to achieve and the more they will save,” Kaplan asserted. “This can mean as low as $2,000 a year for our smallest users, and six-figure annual savings for our largest users.” 

Imperium’s data-backed strategy “applies to any industry or application of energy use,” Lessells concluded. “Our users save money simply by knowing when to buy; there is no installation or productivity slowdown. There are physical interventions that can apply to specific industries or buildings that can be used to reduce the amount of energy used, such as solar panel installation or lighting/building upgrades, and we would consult with the client on which of these methods is right for them in addition to our predictive AI platform.”

Hide comments


  • Allowed HTML tags: <em> <strong> <blockquote> <br> <p>

Plain text

  • No HTML tags allowed.
  • Web page addresses and e-mail addresses turn into links automatically.
  • Lines and paragraphs break automatically.