ObservatoryReal EIA-930 data for Texas (ERCOT) — the last 336 hourly points. The forecast is the grid operator’s own day-ahead demand forecast (not ours); the error is actual − forecast, peaking at +3,005 MW in this window. The evidence statistic stayed under the page line: no regime change detected. That is not proof nothing happened. Back-in-band is a display heuristic, not a certificate of absence. 
live preview
Has Texas (ERCOT)'s demand forecast drifted?
ERCO · updated Jul 6, 22:08 UTC
No regime change detected
Texas (ERCOT) — no forecast-error regime change detected
The day-ahead forecast's error has stayed within its calibrated band. Not a certificate that nothing happened.
quiet streak 26 daysbudget ≈1 false page per BA-yearwatching since Jan 2021
- 2.52%
- mean abs. forecast error
- 51,114 MW
- mean demand
- 912 MW
- typical error
- 6,285 MW
- worst-hour error
of demand (MAPE)
median |error|
99th pctile |error|
The evidence, last two weeks
Because the baseline is the operator’s own forecast, seasonality is subtracted for free — what’s left is the miss. The detector pages only when that miss enters a new regime and clears the page line.
Forecast-error regime changes17 in the monitored history
Each is a dated page inside the stated budget. Labels attach only where a window overlaps a documented grid-stress event — never invented. We detect that the forecast’s error changed regime, not that the grid failed or why.
- EndedJun 9, 2026 → Jun 10, 2026
- peak evidence
- 9.23
- forecast miss at onset
- +3,405 MW
- load at onset
- 97th pctile of this grid
- back in-band
- Jun 10, 2026
- EndedJan 27, 2026 → Jan 30, 2026January–February 2026 cold wave (Winter Storm Fern)
- peak evidence
- 9.92
- forecast miss at onset
- −9,995 MW
- load at onset
- 90th pctile of this grid
- back in-band
- Jan 30, 2026
- EndedFeb 22, 2025 → Feb 23, 2025
- peak evidence
- 9.35
- forecast miss at onset
- −4,456 MW
- load at onset
- 83th pctile of this grid
- back in-band
- Feb 23, 2025
- EndedFeb 20, 2025 → Feb 22, 2025
- peak evidence
- 9.99
- forecast miss at onset
- −3,538 MW
- load at onset
- 99th pctile of this grid
- back in-band
- Feb 22, 2025
- EndedJan 21, 2025 → Jan 24, 2025January 2025 cold wave
- peak evidence
- 10.63
- forecast miss at onset
- −7,285 MW
- load at onset
- 81th pctile of this grid
- back in-band
- Jan 24, 2025
- EndedJan 6, 2025 → Jan 7, 2025
- peak evidence
- 9.21
- forecast miss at onset
- +3,577 MW
- load at onset
- 71th pctile of this grid
- back in-band
- Jan 7, 2025
- EndedDec 21, 2024 → Dec 22, 2024
- peak evidence
- 9.96
- forecast miss at onset
- −3,710 MW
- load at onset
- 51th pctile of this grid
- back in-band
- Dec 22, 2024
- EndedJul 9, 2024 → Jul 10, 2024
- peak evidence
- 10.82
- forecast miss at onset
- −9,589 MW
- load at onset
- 69th pctile of this grid
- back in-band
- Jul 10, 2024
- EndedJun 18, 2024 → Jun 19, 2024
- peak evidence
- 9.76
- forecast miss at onset
- +5,929 MW
- load at onset
- 93th pctile of this grid
- back in-band
- Jun 19, 2024
- EndedJan 2, 2024 → Jan 3, 2024
- peak evidence
- 9.59
- forecast miss at onset
- +6,558 MW
- load at onset
- 61th pctile of this grid
- back in-band
- Jan 3, 2024
- EndedDec 24, 2023 → Dec 25, 2023
- peak evidence
- 10.59
- forecast miss at onset
- +5,028 MW
- load at onset
- 6th pctile of this grid
- back in-band
- Dec 25, 2023
- EndedFeb 4, 2023 → Feb 6, 2023
- peak evidence
- 10.33
- forecast miss at onset
- −6,869 MW
- load at onset
- 47th pctile of this grid
- back in-band
- Feb 6, 2023
- EndedDec 25, 2022 → Dec 27, 2022December 2022 cold (Winter Storm Elliott)
- peak evidence
- 9.39
- forecast miss at onset
- −5,966 MW
- load at onset
- 16th pctile of this grid
- back in-band
- Dec 27, 2022
- EndedMay 26, 2021 → May 28, 2021
- peak evidence
- 10.02
- forecast miss at onset
- +4,038 MW
- load at onset
- 79th pctile of this grid
- back in-band
- May 28, 2021
- EndedMay 25, 2021 → May 26, 2021
- peak evidence
- 9.21
- forecast miss at onset
- +3,245 MW
- load at onset
- 52th pctile of this grid
- back in-band
- May 26, 2021
- EndedMay 22, 2021 → May 23, 2021
- peak evidence
- 9.23
- forecast miss at onset
- +3,768 MW
- load at onset
- 52th pctile of this grid
- back in-band
- May 23, 2021
- EndedFeb 10, 2021 → Feb 13, 2021Winter Storm Uri
- peak evidence
- 11.46
- forecast miss at onset
- +6,088 MW
- load at onset
- 58th pctile of this grid
- back in-band
- Feb 13, 2021
How this verdict is formed
The hourly error runs through a conformal band that learns Texas (ERCOT)’s own normal forecast-error rate, into a Shiryaev–Roberts e-detector on a bounded rolling window. An alarm fires only when accumulated evidence crosses the page line — and because the statistic is anytime-valid, checking as often as you like never inflates the false-alarm rate. Full recipe, and exactly what we do not claim, on the methodology page.
Embed this badge
A live status pill for Texas (ERCOT), refreshed every publish. Drop it in a README, status page, or dashboard — it always shows the current verdict and links back here. It reads no regime change while the forecast holds, and flips to forecast drift detected when the e-detector pages.
Markdown
[](https://validanytime.com/observatory/ERCO)HTML
<a href="https://validanytime.com/observatory/ERCO"><img src="https://validanytime.com/observatory/badge/ERCO" alt="Texas (ERCOT) demand-forecast monitor · ValidAnytime"></a>