Problem Formulation

  • To predict electric load of the total average power as well as individual components for two residencies from experimental data
  • Individual residential forecasting is difficult due to high variability of appliance usage and random human behavior influences
  • Separate the HVAC load from total load as a desired profile using weather relationship and minimum HVAC load at night
  • Data driven approach to reduce the amount of information about the home required

Document Type


Publication Date


Notes/Citation Information

A virtual poster presentation at the 2021 IEEE Power & Energy Society General Meeting.

Funding Information 

This work was supported by the NSF, grant ECCF 1936494.