How merit-order surveillance reconstructs a delivery hour

Given a delivery day and one or more bidding zones: which hours cleared at a price the published fundamentals do not explain, and how far past the line each one sits. The board is the whole selection at a glance; opening a zone gives one hour's full derivation.

It answers this for an analyst who already has an alert from somewhere else. It is a second opinion on an hour, not a first detection.

Zones

Which bidding zones are on the board. Zones with no ingested generation for the window are marked as such rather than silently dropped.

Delivery day

The day under review. The calibration window is the days before it, never the day itself.

Calibration lookback

How many prior days the cost parameters are fitted on. A longer window is a steadier fit and a slower read; it also decides how far back the trailing residual spread is measured.

Screen sensitivity

Moves every threshold at once - standard, or roughly two-thirds of it. The reconstruction does not change: the same hours are rebuilt with the same numbers, and only the line drawn through them moves. Every count on the page is at the setting currently selected, and the setting rides in the URL, so a link shared from a loosened line opens loosened.

Five steps, in the order the engine runs them. The zone view shows this for the selected hour with the real numbers at each step, and each step ends with the assumption most worth doubting.

1. Inputs

Realised generation per production type, the day-ahead load forecast, installed and available capacity, and the day's outage notices. Where nothing is stored for the window, these are read live at request time.

2. Availability

Installed capacity less what the outage notices remove, per technology. This is the ceiling each fleet could have produced against, and it is the step most often wrong: capacity unavailable for a reason nobody published looks, to the model, like withholding.

3. Cost

Each technology placed by short-run marginal cost, with must-run and zero-marginal-cost output at the base. The cost parameters are the fitted part.

4. Demand and imports

Residual demand for the hour, met from the stack. Net imports enter as a modelled block priced at the median of the interconnected neighbours - modelled, because the physical flow is published but the price it was contracted at is not.

5. Clearing

The block meeting the last megawatt sets the reconstructed price. The gap between that and the settled price is the residual every screen works on.

Cost parameters for a delivery day are fitted only on days that strictly precede it. A fit that has seen the day it scores has already absorbed the very anomaly the screens exist to find, and would report a quiet residual for the hour that most deserves attention.

The residual distribution from that fit is the model's error, and it is out-of-sample by construction. It is reported as MAE and bias on the board, and beside every finding in the zone view. The screens are aware of it: a margin has to beat the reconstruction's own residual spread before it counts, so an imprecise model produces fewer findings, not more.

Where the exchange publishes its order book, the zone view reports a second model beside the first. The cost parameters above are fitted against one number per delivery period: the settled price, the single point where supply met demand. The published supply curve for that same period gives several readings of what was offered at what price, and fitting the modelled stack's shape to those is more information than fitting only its intersection.

Both models are scored the same way, on the same day's settled prices, so the two error figures are comparable. The curve-fitted one is reported, not used: every finding on the page comes from the settled-price fit. Most zones publish no curve at all and must keep reconstructing the way they always have, and swapping a calibration would change what every stored finding means with nothing on screen saying so.

The comparison has now been run, and the settled-price fit wins. Over 76 delivery days of Germany-Luxembourg and France to 2 October 2026, the settled-price fit is out by 40.6 EUR/MWh on average and the curve-fitted one by 50.3, and the curve-fitted one is the better of the two on 17 of those 76 days. The reason is a limit of the published data, not of the idea: the curve is read at seven fixed prices, the two outermost of which sit far below the cheapest and far above the dearest plant in the model, so the fit attributes those extremes to whichever zero-cost fleet the stack puts there. So the second figure stays on the page as the honest record of a model that was tried and is not used, and the smaller of the two error numbers on that tile is the one to read.

Ten screens run on the fundamentals. Each states what was observed with the numbers in it, and none of them claims abuse.

Cleared above fundamentals

The settled price sits materially above the reconstruction, measured in the zone's own residual spread rather than a fixed euro amount. Severity rises where the residual clears roughly 1.7x the threshold.

Cleared below fundamentals

The mirror case. Reported at warn only: a discount has fewer abusive readings than a premium and more benign ones.

In-merit capacity idle

Capacity whose modelled marginal cost sat below the clearing price and which did not generate. Both an absolute floor in MW and a share of demand have to be cleared, so a small zone and a large one are held to comparable evidence.

Demand above modelled supply

The stack could not meet residual demand at all. Always high severity, and usually a coverage problem rather than a market one - it is the first thing to check against the sources table.

Thin reserve margin

Available capacity was close to demand. Graded info or warn, never high: a tight hour explains a high price rather than indicting it.

Steep merit order at the clearing point

The euro move per 100 MW at the margin. A steep clearing point is where a small withheld block moves the price a lot, so it is context that raises the value of the other screens.

Pivotal supplier

The residual supply index below 1: demand could not have been met without that fleet. Deliberately graded low - at technology-fleet granularity this is common in a concentrated zone, and it is context rather than an alert unless deeply pivotal.

Cleared above the whole stack

The settled price exceeded the most expensive modelled block. Either the stack is missing a technology or the hour cleared on something the fundamentals do not carry.

Import-dependent clearing

The net-import block set the price. The import block is modelled, not published, so an hour that clears on it carries more model error than one clearing on a domestic technology.

Coupling divergence

The zone's price diverged from its coupled neighbours by more than the threshold, which is the shape a congested or decoupled hour takes.

Where the exchange publishes its aggregated order book (13 clusters covering 23 bidding zones), a further six screens read the orders that actually cleared rather than an estimated stack. They are deliberately the ones the reconstruction cannot do, and where the two views of an hour disagree, that disagreement is itself the finding.

Price up on falling volume

The clearing price above its trailing band for this delivery period while the crossing volume sits below its own. Demand moving a price takes the volume with it: a cold snap clears more MW at the higher price. Supply leaving the curve takes it the other way. The one screen here no price series can imitate.

Thin book at the crossing

The euro move per 100 MW withdrawn at the crossing, measured on the published curves rather than on the modelled stack. Where the estimate and the book disagree about how steep an hour was, the book is the one to believe.

One block at the clearing price

Price-invariant volume sitting at exactly the clearing price, meaning the curve ran vertical there and a single price step carried that much MW and chose the price. It is the closest an aggregated curve gets to naming a price-setter, and it stops at 'one order of this size' - never at whose.

Day-ahead premium unwound intraday

Day-ahead cleared well above the same delivery period's later intraday auctions. Consistent with capacity held out of day-ahead and offered later, and equally with a forecast that improved after gate closure - which is the ordinary explanation and the one to rule out first.

Demand that could not discipline the price

Demand moved barely any MW per euro around the crossing, so almost none of a supply-side move would have been absorbed by buyers backing away. Context for the leverage readings above it, never a finding about anyone's conduct.

Less volume offered at the clearing band

The MW offered at or below a fixed price band fell against what this delivery period usually sees. Measured on the supply curve at a fixed price, so a demand-side move cannot produce it; an outage or a genuine fuel-cost repricing can. Reported in MW, not as a z-score.

The last of those is the only one that measures the supply curve directly rather than inferring that it moved. The first infers a leftward shift from price and volume moving opposite ways, because a price and a crossing volume are all a stored result used to carry; the offer ladder is the volume genuinely offered at a fixed price, so a demand-side move cannot produce it. An outage or an ordinary fuel-cost repricing can, which is why it is still an indicator.

Because it is the direct measurement, it is the heaviest screen in the ranking, and the inferred one sits just below it. Measured over 7,296 delivery periods of Germany-Luxembourg and France to 2 October 2026, the direct screen raised 365 findings and the inferred one 27, and the two agreed on 17 periods. So they are not two readings of one event in the ordinary case: the ladder sees shifts the price-and-volume shape cannot, and on the rare period where both fire the hour ranks at the top of the queue on either of them alone.

One screen reads both views at once, and it is the only one that does:

Price reversed across the gates

A delivery period clears up to four times, and this is the shape where the price falls to one gate and recovers after it: the fall and the recovery must each reach 15 EUR/MWh, which 2.5% of delivery periods do. A price that only ever falls is a forecast resolving; a reversal is capacity returning to the market and then leaving it. The reconstruction turns the euro move into the MW of capacity sitting between the two prices. Intraday wind and solar forecasts are revised upward as readily as downward, and produce exactly this shape, which is the ordinary explanation.

The selected hour's published book can load separately from the assessment. An Archive call notice means its curves are being read from a saved capture and can take longer to arrive. The completed chart states whether its source was live or archived.

A delivery period clears more than once. Day-ahead settles it first, then the intraday auctions IDA1, IDA2 and IDA3 re-clear the same period as the gate moves closer. The zone view puts all of them side by side for the period you have open.

Findings on the intraday auctions are read alongside the day-ahead assessment, never added to it. Each auction is screened against its own trailing band, because each is its own distribution; and an intraday move happens after day-ahead's gate has already closed, so it cannot be evidence about how day-ahead cleared. An hour with a striking intraday finding and an ordinary day-ahead price does not climb the zone's triage queue on that account.

Coverage is uneven and the view says which kind of gap it is looking at. IDA2 and IDA3 in particular do not run for every period, so an auction absent from one hour of a day it otherwise covers is a gap in the period rather than a gap in collection. A zone in none of the clusters that publish aggregated curves has no intraday data at any hour, which is a scope limit rather than a gap at all.

Zone

The bidding zone. A row appears only where realised generation per production type was ingested for the calibration window; a zone without it is listed as uncovered rather than shown empty.

Risk

The composite triage score, 0-100. It orders a queue. It is not a probability, and two hours with the same score are not equally interesting - read the findings.

Severity

The highest severity among the zone's findings that day: info, warn or high. A zone whose only findings are info has raised context, not an alert.

Hours with alerts

Delivery hours where at least one screen fired at the sensitivity currently selected. Changing the sensitivity changes this count and nothing else about the reconstruction.

Near misses

Hours where no screen fired but one came close. This column exists because a threshold is a line drawn through a continuum, and the hours just short of it are the ones an alerting engine would hide.

Top finding

The highest-ranked single finding in the zone that day, named so the board can be scanned without opening every zone.

Model MAE (day)

The reconstruction's out-of-sample mean absolute error for that zone on that day, in EUR/MWh. A large MAE is a weak basis for calling an hour anomalous, and the number sits beside the findings rather than in a footnote.

Bias

Whether the reconstruction ran systematically high or low that day. A persistent offset is a model-quality problem; an isolated spike against a well-behaved baseline is what the screens are for.

The grid is one cell per zone-hour for the whole day, coloured by whichever metric you choose, whether or not a screen fired. That is the point of it: an alerting engine that publishes only what crossed hides the block that was 180 MW when the screen wanted 200. Every metric the grid can be coloured by is also a column in the ledger below it.

The ledger is the complete reconstruction for the selection, nothing filtered and nothing rounded away, ordered however you choose and exportable as CSV. It carries twenty columns, including both risk score and screen pressure, the closest unfired screen, and how close that screen came as a percentage of its threshold. It is the table to read when you distrust the ranking.

The under the radar queue holds hours that raised no alert, ordered by how close the nearest screen came to firing. Each row names the binding screen and the distance it still had to travel, so the queue can be read as evidence rather than as a list of near-things.

The composite risk score, where a screen did fire, sums a per-screen weight times how far past its threshold the finding sits, capped at twice the threshold so one extreme reading cannot dominate, then maps the total onto 0-100 through a saturating curve - roughly 55 at one strong finding and 85 by three. It orders a queue and nothing more.

Reservoir hydro reflects a scheduling opportunity cost rather than a fuel cost. Scarcity prices can reflect willingness to pay. Cross-zonal capacity is not ingested, so congested hours rely on an approximate coupling reference. Read the zone's reported error before weighing a finding.

The reconstruction is an estimate and the settled price is a fact. Where the two disagree about how steep an hour was and a published aggregated curve exists, believe the curve: it is the book, and the reconstruction is the thing with a reported error.

Legitimate explanations the public data cannot see produce every shape these screens look for: unit commitment and start-up constraints, heat obligations, network constraints, and hedged positions. The feeds carry no participant identity either, so a finding attributes to a technology fleet in a zone and never to a firm. Verify against outage disclosures and the exchange's own data before drawing any inference.