Continued population growth, socioeconomic improvements, and technological advancements in the past few decades have caused a significant rise in the consumption of energy and materials. Many utilities find themselves concerned -- the volatility of wind and solar power generation, the uncertainty of rooftop solar adoption, and rising gas and electricity prices pose serious challenges. The modern consumer-centric paradigm of transactive energy has changed the traditional load forecasting methodologies, as it evolves and reshapes utility strategies.

This training intends to provide a comprehensive introduction to forecasting methods and present enough information about each method for participants to use them sensibly. Examples and applications from the utility industry, including forecasting with AMI data, are included.

An outline for the training, Introduction to Forecasting in the Utilities, has been included with this document.

Earn a Certificate of Participation and Completion and Continuing Education Units (CEUs) from the University of Oklahoma.


Upon completion of this training, students will be able to:

  • Understand select applications of time series forecasting within the utility sector.
  • Use statistical and graphical approaches to exploratory data analysis with time series data.
  • Use software and/or programming languages (e.g., Python or R) to create statistical forecasts.
  • Develop load, price, wind power, and/or solar power forecasts.

Who Should Attend?

  • Analytics professionals who are interested in learning forecasting methods with applications in utilities.
  • Utility professionals who find themselves doing forecasting without prior formal training.
  • Utility Analytics 101 completers who want to continue advancing their analytics knowledge in the utility setting.
  • Positions include, but are not limited to, Data Scientists, Forecasting Analysts, Energy Analysts, and Research Analysts.


College- or university-level statistics and algebra or equivalent experience. Some exposure to statistical programming (for example, in Python or R language) is helpful but not required.

Introduction to Forecasting for Utilities

DAY 1:

Introducing Time Series and Python for Time Series

DAY 2:

Visualizing Time Series & Forecasting

DAY 3:

Machine Learning with Time Series