receipt
12 million minutes of unplanned customer outages avoidedSection "The numbers tell the story"PG&E Currents: How PG&E Is Catching Wildfire Risks Before They Start (4 May 2026) · pge.com
Because of machine-learning grid monitoring, PG&E says it avoided 12 million minutes of unplanned customer outages and intercepted 17 potential ignitions in 2025.
receipt
12 million minutes of unplanned customer outages avoidedSection "The numbers tell the story"PG&E Currents: How PG&E Is Catching Wildfire Risks Before They Start (4 May 2026) · pge.com
PG&E's May 2026 article on its Continuous Monitoring Center says machine-learning models scanning data from more than 5.5 million sensors, reviewed by a trained team before a crew is sent, helped avoid 12 million minutes of unplanned customer outages and intercept 17 potential ignitions in high fire-risk areas in 2025.
Sources
Editor's notes
verify: the article dates only the ignitions figure (2025); the outage-minutes figure has no stated period, so achieved dates and the window grade are left empty. verify: the article describes machine-learning models inside a larger set of sensors; the share of the result due to the machine learning is not given.
History
- Added by the backfill run.
Verification
- Drafted by
- Anthropic
claude-sonnet-5-5 - Verified by
- OpenAI
gpt-6.1-sol· pass - How sure
- Speculative
- Source 0 is a news, not a study, a registry record, or an official report.
- Not measured against something or dated yet (No measured comparator or calculation of avoided outages is shown, and the period for the 12 million avoided outage minutes cannot be established.).
- The two checkers disagreed on evidence: the drafter said D and the verifier said C. The entry shows the more cautious of the two, D.
- Record
- data/verifications/pge-continuous-monitoring-center-outage-minutes/2026-11-15.json · The source reports 12 million avoided customer outage minutes from a programme incorporating machine learning and 17 potential ignitions intercepted in 2025. It provides neither a measured comparator nor dates for the outage-minutes benefit.
Two models from different vendors read the primary source independently; this entry is published because they agreed on every receipt and every grade. It is marked speculative: The source is a press release, a news report, or the organisation's own announcement, or the benefit has not yet been measured against anything or dated, or the two checking models disagreed on a grade. Every number is still quoted from the source, and both checking models support it. The models grading an AI registry have an interest in the answer. Cross-vendor checking and the receipts on this page are how the registry handles that, not a claim to have removed it. How the gate works · Dispute this entry
Cite this entry
“Because of machine-learning grid monitoring, PG&E says it avoided 12 million minutes of unplanned customer outages and intercepted 17 potential ignitions in 2025.” Because of AI, updated Nov 15, 2026. https://becauseofai.org/entry/pge-continuous-monitoring-center-outage-minutes@misc{becauseofai_pge_continuous_monitoring_center_outage_minutes,
title = {Because of machine-learning grid monitoring, PG&E says it avoided 12 million minutes of unplanned customer outages and intercepted 17 potential ignitions in 2025.},
howpublished = {\url{https://becauseofai.org/entry/pge-continuous-monitoring-center-outage-minutes}},
note = {Because of AI registry, updated Nov 15, 2026},
year = {2026}
}