This page contains information related to ERCOT’s Mid-Term Load Forecast (MTLF) and Long-Term Load Forecast (LTLF).
Long Term Load Forecast
The Long-Term Load forecast is an hourly forecast for the next 10 years. It is based on forecasted economic data and historical weather from 2006 – 2020.
*Click the button to view the image in greater detail.
Contains the 90th percentile weather zone summer peak demand forecasts for 2023 – 2032. Includes the gross 90th percentile summer peak forecast, net 90th percentile summer peak forecast, and the Rooftop PV impact on the 90th percentile summer peak demand.
Contains ERCOT summer peak demand forecast scenarios for 2023 – 2032. These scenarios are based on using historical weather years in the forecast model. Includes the ERCOT gross summer peak forecast, ERCOT net summer peak forecast, and the Rooftop PV impact on ERCOT’s summer peak demand. Also includes the 90th percentile forecast (denoted as P90).
Contains weather zone coincident summer peak demand forecasts for 2023 -2032.
Includes the gross summer peak forecast, net summer peak forecast, and the Rooftop PV impact on summer peak demand.
Contains weather zone non-coincident summer peak demand forecasts for 2023 – 2032. Includes the gross summer peak forecast, net summer peak forecast, and the Rooftop PV impact on summer peak demand. Also contains historical non-coincident peak demands.
Jan 18, 2023 - xlsx - 19.6 KB
Mid-Term Load Forecast
The Mid-Term Load forecast (MTLF) is an hourly forecast for the next 168 hours based on current weather forecast parameters within each Weather Zone. The MTLF Monthly Mean Absolute Percentage Error (MAPE) chart below contains average MAPE values for the 3 hour ahead, 6 hour ahead, and day ahead forecast horizons for each calendar month. The MTLF Monthly Backcast chart contains the average model error for each calendar month. Note that a backcast is created by using the current MTLF forecast models with actual weather data and calendar variables (day-of-week, holiday) as input. The backcasted values are then compared to the actual load values to arrive at model error.
*Click the button to view the image in greater detail.
*Click the button to view the image in greater detail.
