Itron is the Industry Leader
Accurate and timely short-term forecasts provide critical decision support for operators in today's energy markets. Itron software and forecasting methods are used by the vast majority of large system operators in North America, Australia and other locations around the globe. Itron has established this market leadership position by delivering:

• A proven statistical engine with a user base of more than 200 companies
• Unparalleled forecast accuracy
• Scalable and reliable systems
• Support for both Oracle and SQL Server databases
• Advanced forecasting methods, including machine learning
• Archiving and "backcasting" support to track model performance
• Support for all data frequencies, from daily down to five-minute data
• Flexibility to model energy, solar, wind, demand response, energy prices and other variables
• Advanced modeling processes
  • Ensemble forecasts
  • Multiple weather providers
  • Uncertainty modeling
  • Built-in error correction

Download the Energy Forecasting Services Brochure >

Whatever your situation, Itron can help strengthen and improve the forecasting process. For over three decades, Itron has been building and refining methods that we believe to be industry best practices. We appreciate the opportunity to share this knowledge with our utility customers.

• Consulting Services
  Itron staff have a deep understanding of forecast processes, with experience dating back to the 70s. We have worked with hundreds of utilities to help with their most difficult problems.
  
  
• Itron Methods and Best Practices
  Itron has a proven set of best practices which we have developed over three decades and monitor continuously through annual benchmarking surveys.
  
  
• Using AMI Data
  Join the Itron network of utilities who want to leverage their AMI investment to improve financial operations and provide clarity and visibility to the future.

Download the Energy Forecasting Services Brochure >

Itron has unmatched experience and expertise in long-term energy forecasting, using both statistical and end-use models. We provide data products and services to help the industry understand what has changed at the end-use level and how it will change into the future. Our forecasting customers also benefit from:

• Energy Forecasting Group (EFG)
  This subscription service provides members with a valuable stream of regional end-use data. Both history and forecasts are provided. EFG members represent well over 50% of energy delivered in North America. And the group's annual conference is a great opportunity to keep up to date with forecasting peers.
  
  
• SAE Models
  The statistically adjusted end-use (SAE) approach was pioneered by Itron to combine the strengths of statistical modeling with the information content of end-use analysis. The approach builds on the data available through the EFG. The result is a statistical model that is calibrated to local data and that explicitly accounts for important changes in lighting, heating, cooling and other end uses, as well as new technologies such as rooftop solar and electric vehicles.
  
  

Download the Energy Forecasting Services Brochure >

Over the years, numerous clients have requested a “recipe book” for building powerful short-term load forecast models. This guide is a partial “recipe book,” providing the full list of possible ingredients with guidance as to when to use which combination of ingredients. The focus is on building the within-day and day-head load forecast models that system operators and energy traders rely on for scheduling, dispatching, and procuring generation to meet demand. The information presented is based on 20 plus years of experience forecasting in the trenches with system operators and energy traders in Australia, Europe and North America.

The Guide begins with the hard work of data review and analysis. In practice, the path to a powerful forecast model is through a very thorough analysis of the data. The first section outlines an approach for reviewing load data. This is followed by data cleaning approaches and philosophies. With the preliminaries complete, the Like Day, Multivariate Regression, and Neural Network load forecast techniques that are the bread and butter of the industry are introduced. The discussion includes descriptions of machine learning frameworks that can be used to complement today’s operational load forecast tools. Next is defining a set of explanatory variables that can be used in a load forecast model including the treatment of calendar conditions, holidays, and weather conditions. A series of load forecast model recipes and associated model building guidelines are introduced. The Guide finishes with basic concepts related to incorporating behind-the-meter solar generation into a load forecast model.

A Practitioner’s Guide to Short-term Load Forecast Modeling
Download the Guide >
View the Webinar Video >