Power Grid Monitoring: Texas (ERCOT)

Findings report · scored 2020-01-08 to 2026-04-01 · hourly · all times UTC

Summary

Over 6.2 years of hourly ERCOT data the monitor fired 2 alerts. Of 1 target event: 1 predicted (Uri, 103 h lead); 0 missed. 1 alert fell outside every target window: 1 inside explanatory windows declared in the run config and 0 unexplained.

At a glance

Scored period6.2 years54,519 hours

Target events1

Predicted1 / 1

Detected0 / 1

Missed0

Alerts fired21 first, 0 repeat

Explained1hindsight label

Unexplained00.0/yr; 0.2/yr with explained

How it is scored

An event is PREDICTED if the first alert falls within 168 hours before onset, DETECTED if it falls within 48 hours after onset, and MISSED otherwise. The same windows apply to every event. The reasoning is in “Too early is the same as wrong”.
Onset is the time the grid operator declared the highest emergency level the event reached, converted to UTC.
Consecutive alerting hours count as one alert. A later alert inside a target window is a repeat, with no credit and no penalty.
An alert outside every target window is “explained” if it starts inside an explanatory window declared in the run config, and “unexplained” otherwise.

Target events

Event	Outcome	Lead / lag	First alert (UTC)	Onset (UTC)	Onset basis and source
Winter Storm Uri Rotating outages, up to 20,000 MW of load shed	PREDICTED	103 h lead	2021-02-11 00:00	2021-02-15 07:20 2021-02-15 01:20 local	ERCOT entered Emergency Operations Level 3 (EEA 3) and began rotating outages. ERCOT, Review of February 2021 Extreme Cold Weather Event (Feb 24, 2021), slide 11

Winter Storm Uri PREDICTED

Scoring window: 2021-02-08 07:20 to 2021-02-17 07:20 UTC (168 h before onset to 48 h after).

First alert at 2021-02-11 00:00 UTC, 103 h lead. Models flagging in that hour: demand, forecast error, and net generation.

Every alert

All 2 alert episodes in the scored period, in order. Nothing is left out.

#	Start (UTC)	End (UTC)	Hours	Class	Matched to	Models flagging at start
1	2021-02-11 00:00	2021-02-11 05:00	6	First alert	Winter Storm Uri	demand, forecast error, net generation
2	2022-12-23 08:00	2022-12-23 08:00	1	Explained	Explanatory window: Winter Storm Elliott, Dec 2022	forecast error

Configuration of this run

Signals, one HTM model each: demand, net generation, forecast error.
A model flags an hour when its anomaly likelihood is at or above 0.99. A model's warmth is the share of flagged hours over its last 8 hours.
Signals are grouped (table below). The system alerts when 2 of 2 groups are hot for at least 3 consecutive hours.
Warm-up: the first 168 hours are not scored. Learning stays on for the whole run; no labels are used.

Group	Signals	Hot when
structure	demand, net generation	2 of its 2 signals flag in the same hour, or the group's mean warmth is at least 0.45
residual	forecast error	1 of its 1 signal flags in the same hour, or the group's mean warmth is at least 0.5

Limits

One target event is a case study. It shows how the detector behaves on this event; it does not establish a detection rate.
The replay treats each hourly value as available at its timestamp. EIA publishes demand about an hour after the operating hour and net generation the next day, so a live deployment at these lead times would need the operator's own telemetry.
"Explained" is assigned in hindsight from explanatory windows declared in the run config. It never counts as a catch, and the alert rate is given both with and without those alerts.
The alert-rule settings listed above were set per region. Only the HTM model parameters, the encoder shape, the one-week warm-up and the consensus method are shared between regions.
82 hours are absent from the run's timebase because at least one input signal was missing in the source data.