As the grid becomes more modern and profits get tighter, the pursuit for a more accurate load forecasting model often takes the spotlight. Load forecast data is often made available by the area's ISO or the EMS may even provide this information, but these systems don't allow for any changes or improvements to be done. This guide will take it a step further and create a model to predict loads at a substation level, something valuable for many reasons that we will cover later.


Let's start from the end. The image below is a screenshot of a PI Vision display showing actual load (green) and forecasted load (red) for a 7 day period:




This guide will be broken down into different parts as detailed below:


Part I:

Data preparation - The data used to build the model is assumed to be in the PI System and modeled in AF. For the sake of keeping things simple we will only use temperature and time for predicting MWs and the PI Integrator for AZURE will be used to:

  • Cleanse
  • Augment
  • Shape
  • Transmit


Part II:

Forecast model - AZURE Machine Learning will be used in this example although the focus is not this tool but the process of integrating with PI and building a forecast model. Other platforms could be used instead such as Hadoop, SAP HANA, R, etc. The process to build a forecasting model is usually comprised of:

  • load data
  • train
  • score
  • deploy



Required for this example:

  • PI Data Archive 2015+         //Future data support
  • PI Vision                               //Visualization
  • PI Integrator for AZURE       //Data integration
  • MSFT AZURE subscription  //machine learning