webinar:

Integrating AMI Enabled Deep Learning into your Load Forecasts to Drive New Business Value

Learn how innovative utilities like APS are successfully integrating AMI and machine learning into their load forecasting applications

_____________________________________________________________________________

Load forecasting for today's Utilities and Retail energy providers has become an increasingly complex challenge. The decentralization of energy resources, new customer technology, changing consumption patterns- not to mention increasing swings in weather patterns- has moved load forecasting to center stage as a core competency for utilities of tomorrow.

Most utilities concede that while the "top down" forecasting methods used today have been sufficient at anticipating aggregate load obligations and system requirements, they are woefully inadequate at providing the insight and flexibility needed to operate in the type of decentralized and dynamic energy environments many utilities find themselves operating in today. This realization is causing many utilities to start incorporating "bottoms up" forecasting methods such as Innowatts to better serve today's needs and provide a more dynamic and versatile solution for the future.

For the last 5 years, Innowatts has worked with leading utilities and energy providers to perfect a "bottoms up" forecasting methodology built upon AMI data and machine learning from over 18 million smart metered customers worldwide. This approach has enabled a broad range of new applications for predictive analytics and load forecasting across the business, while improving the accuracy of system level forecasts by up to 40%.

During this webinar, Innowatts will discuss some of the key tenets of their forecasting approach and some of the insights gained as they have perfected the methodology. APS will share how this new approach to predictive AMI intelligence is being used in their companies to address key forecasting challenges and drive new sources of business value including:

  • major improvements in system forecasting accuracy
  • reduced risk in gross margins
  • improved network intelligence for DMS and DERMS
  • Improved targeting and operation of DR and EE programs
  • enabling new types of predictive customer engagement