Deep dive — chart 1

Chart 1 — rolling mean shortage-risk by market zone

The chart your VP Operations should look at first. Where the silent E3 divergence begins, in one visual.

7-day rolling mean shortage-risk score per market zone over 90 days

7-day rolling mean shortage-risk score per market zone over the 90-day audit period. E3 divergence begins Day 44 and never recovers; E5 diverges even more sharply from Day 30.

What you are looking at

X-axis: Day 1 through Day 90 of the audit period
Y-axis: 7-day rolling mean of the AI's shortage-risk score (0-100 scale)
Each line: one market zone (E1 = baseline fossil, E2 = mixed-fuel, E3 = high-renewable duck-curve, E4 = nuclear-heavy, E5 = storage + DR heavy)
Baseline window: the first 30 days establishes what "normal" looks like per zone

What the eye sees

Three zones stay roughly parallel across the 90 days. Two zones — E3 and E5 — move. E3 drops sharply from Day 44 and does not recover. E5 diverges even earlier, from Day 30 forward, with much larger KL-divergence values.

This is the pattern an operator's shift supervisor instinctively recognizes: something in the E3 and E5 streams changed, and the AI is scoring shortage risk differently than baseline. The 22 percentage-point lane-rate shift on E3 is the operational follow-on.

What the sensor fires on

The sensor is not looking at the eye's pattern. It is running four quantitative thresholds against each 7-day window per zone:

Mean-shift: is the 7-day mean > 1.5 standard deviations from baseline mean?
Variance-ratio: is the 7-day variance > 1.5x baseline variance?
KL-divergence: is the shape divergence between baseline and current distribution > 0.2?
Zone-differential: is the max cross-zone shift > 12%?

Day 30 fires E5 KL-divergence 1.218 (6x the threshold). Day 44 fires E3 KL-divergence 0.526. Day 65 fires E5 KL-divergence 2.394. The pattern the eye sees is the pattern the sensor quantifies.

What NERC + FERC staff care about

Regulators do not read charts — they read attestations. But when an attestation is challenged, the chart is the exhibit. NERC compliance auditors, FERC Section 206 staff, ISO/RTO market monitors, state PUC customer-hearing panels, and plaintiff's expert witnesses in a wholesale-market-manipulation matter all understand the "one zone drops silently" pattern instantly.

The chart also tells the counterfactual story: had this monitoring been in place operationally, the drift window would have been ~7-14 days rather than 45+.

The next chart

The rolling-mean chart shows when. The baseline-vs-drifted chart shows how the E3 distribution shape shifted.

Chart 2 — baseline vs recent distribution →

$499 Snapshot. 3 business days.

Same 3-chart set for your operator's actual AI surface + full analysis report.

Buy $499

Back to energy sample hub.