Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

ERCOT: Load Forecasts #259

Open
colinpbowen opened this issue Aug 10, 2023 · 0 comments
Open

ERCOT: Load Forecasts #259

colinpbowen opened this issue Aug 10, 2023 · 0 comments

Comments

@colinpbowen
Copy link
Contributor

colinpbowen commented Aug 10, 2023

Load forecasting is one of the most important operations in ISO Planning. It therefore behooves us to understand the different types of forecasts issued by ERCOT.

The Load Forecast page on ERCOT summarizes key information. ERCOT supplies two types of Load Forecasts: the Long-Term Load Forecast (LTLF) and the Medium-Term Load Forecast (MTLF).

The LTLF is an hourly forecast for the next 10 years based on forecasted economic data and historical weather. They offer two forecast products:

  1. Monthly Peak Demand (in MW) and Total Energy consumed in the month (in MWh) for the next 10 years.
  2. The main product, the Hourly Forecast for the next 10 years, by Weather Zone, for gross load, PV forecast, and net load.

They also include Load Forecast Scenarios, which include peak demand scenarios, including both coincident and non-coincident peaks.

The MLTF is an hourly forecast for the next 168 hours (7 days) based on current weather forecast parameters within each weather zone. Load forecast error is measured by Mean Absolute Percentage Error; last month, the day-ahead forecast had a MAPE of ~2.7%, the 6 hour ahead ~2.4%, and the 3 hour ahead ~1.6%.

In EMIL, we can find the following data products which significantly expand upon the scope described above. These include some intra-hour products. Descriptions are provided.

(LTLF) Long Term Hourly Peak Demand and Energy Forecast. Long Term Hourly Peak Demand & Energy Forecast Report includes supporting information on weather and economic data used in the forecast.
(MLTF) Seven-Day Load Forecast by Weather Zone. Forecasted hourly demands by Weather Zone and system total, for the current day and six days forward.
(MLTF) Seven-Day Load Forecast by Forecast Zone. Forecasted hourly demands by Forecast Zone and system total, for the current day and six days forward. Seven-Day Load Forecast by Forecast Zone. This is supplemented by the already-scraped Actual System Load by Forecast Zone. We are currently scraping this but dropping all columns except for the SystemTotal.
(MLTF) Seven-Day Load Forecast by Model and Weather Zone. Hourly system-wide Mid-Term Load Forecasts (MTLFs) for all forecast models with an indicator for which forecast was in use by ERCOT at the time of publication for current day plus the next 7.
(MLTF) Seven-Day Load Forecast by Model and Study Area. Forecasted hourly demands by Study Area, for the current day plus the next seven days. Currently the only study area is the Valley.
(MLTF) Load Distribution Factors. Load forecast distribution factors from which Market Participants can calculate Load at the Electrical Bus level for by hour for the next seven days.
Intra-Hour Load Forecast by Weather Zone. IHLF provides a rolling two hour, five minute forecast of ERCOT-wide load by weather zone.
Forecasted Load Profiles. 15-minute kWh values fore forecasted load profiles for all profile types and weather zones. Load Profiling, within the ERCOT market, is the practice of estimating 15-minute interval Load for Customers where interval consumption is not available.

kmax12 added a commit that referenced this issue Aug 16, 2023
* ERCOT Load Forecasts

* Implementing changes for linting and to pass test cases. Added functionality to grab latest, and by publish time. Cleaned up clutter.

* Update get_load_forecast() with default param for ercot to pass test.

* override _check_forecast() for ercot

* remove commented code.

* update changelog

---------

Co-authored-by: Colin <colin@Colins-M1-MacBook.local>
Co-authored-by: Max Kanter <kmax12@gmail.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant