Open load forecasts that beat US grid operators on 6 of 7 RTOs

Name: Open load forecasts that beat US grid operators on 6 of 7 RTOs
Availability: InStock
Author: tylergibbs1

by tylergibbs1·Apr 20, 2026·4 points·0 comments

Visit Project View on HN

AI Analysis

●●●BangerBig BrainDark HorseZero to One

Beats utility forecasts on 6 of 7 RTOs using only public EIA data and open models.

Strengths

•Macro MAE 40% lower than operator submissions on 2025 hold-out dataset
•Fully reproducible with code, model weights, and benchmark scripts on HuggingFace
•Probabilistic forecasts with 80% confidence intervals for all 53 balancing authorities

Weaknesses

•ISO-NE remains an outlier where operator forecasts still outperform the model
•Research disclaimer limits use for trading or regulated bidding decisions

Post Description

Fine-tuned Chronos-2 on 7 years of EIA-930 demand + ASOS temperature for every US balancing authority that publishes a load series — 53 across the three interconnections.

On a 2025 hold-out (~61,000 hours), it beats the operators' own day-ahead submissions to EIA — the production forecasts they use to schedule generation — on 6 of 7 major RTOs. Macro MAE ~40% lower. The one loss is ISO-NE, whose forecasting is just very good (24h-ahead MASE 0.34). On the same window, CAISO and SPP operator submissions did worse than "same as yesterday."

The site plots the median + 80% PI band against the operator submission, with 48h of actuals running into the forecast.

Code, model on HF, operator-comparison benchmark reproduces from one script:

- https://github.com/tylergibbs1/surge - https://huggingface.co/Tylerbry1/surge-fm-v3