Amazon re:MARS conference: weather tracking

Written by Faith PR


weather

Ground-breaking technology that will revolutionize the way energy prices are predicted in relation to weather, which has been developed in collaboration with Kinect Energy Group and Amazon Web Services (AWS), was unveiled at the re:MARS conference in Las Vegas last week.

Hosted by Amazon and headlined by Amazon Founder and CEO Jeff Bezos and Robert Downey Jr., the re:MARS conference — which stands for machine learning, automation, robotics and space – took place between June 4 – 7 in Las Vegas at the Aria Resort & Casino.

Global energy management and fulfilment specialist, Kinect Energy Group, unveiled its pioneering advanced machine learning capabilities that will predict electric spot prices for re­gional power markets using real-time weather tracking.

The technology uses the Amazon SageMaker DeepAR time-series forecasting model and incorporates historical pricing and weather data to drive the machine learning models. The technology has been designed to improve price predictions and assist with increased trading volumes for forward pricing contracts.

Richard Delisser, VP of Global Infrastructure at World Fuel Services, Kinect Energy Group’s parent company, who spoke at the event alongside Amazon’s data scientist Elena Ehrlich, said: “The volatility of the energy market is at some of the highest levels it’s ever been. Affected by factors such as the increased adoption of renewable energy, geopolitical tension, macro-economics and more unpredictable weather – forward pricing can be difficult to predict.

“Kinect Energy’s ethos is about helping our clients buy better and buy less energy and we can do this by using the latest technologies as well as developing our own. We trade around power price movements on behalf of our customers to get the best possible price from their preferred source, which can often take days to predict due to fluctuations with the weather.

“Working in partnership with AWS, we have created something revolutionary that will transform the way energy spot prices are predicted. By tracking the weather more closely, and better understanding that relationship to market pricing, we will be able to support our customers in making more informed choices about their energy purchasing.”

You currently have JavaScript disabled. This site requires JavaScript to be enabled. Some functions of the site may not be usable or the site may not look correct until you enable JavaScript. You can enable JavaScript by following this tutorial. Once JavaScript is enabled, this message will be removed.