GREAT BRITAIN / DAY-AHEAD RESEARCH

Tomorrow’s price, with its evidence

This is a live forecast and we are learning in public. Every hour of tomorrow’s Great Britain day-ahead reference price, published before the outcome is known, with its uncertainty and its sources attached. The record further down is research on 92 days the models had already seen, so it is not a live track record. That one starts with the forecasts published here, and it will include the days we get wrong.

For information only. These forecasts are experimental and unproven at extreme prices. Do not rely on them for trading, dispatch or investment decisions. Read the limitations

HISTORICAL REPLAY / NOT A LIVE FORECAST

Wednesday 15 July 2026

Low Carbon Contracts Company reference price, pounds per MWh, London delivery time

Research reference

Median forecastExperimental 80% rangePublished actualBenchmark

Inspect delivery hour18:00 BST

Each step is one delivery hour. The band is the model’s own tenth to ninetieth percentile for that hour on its own. It is not a guarantee for the day, and it does not yet carry the empirical widening used in the research, because that needs a history of errors from this model as published and that history starts now.

SYSTEM CONTEXT

Forecast inputs
for this delivery day

Metered wind forecast—

National demand forecast—

Wind and demand are separate inputs. These charts do not establish causation or total GB renewable generation.

Read the hourly values Accessible data table

Historical research, 15 July 2026. Prices in £/MWh.
London hour	UTC start	Median	Lower	Upper	Actual	Benchmark

Reconstructed input cutoff14 Jul 2026 · 09:10 BSTTargetLCCC IMRP / hourlyMethodHistorical research / windLive scorecardNot eligible

THE RECORD, WITHOUT THE SALES PITCH

Both methods beat both benchmarks,
on days they had already seen

Historical research ≠ live performance

Same days. Same target.

Lower error is better

June to August 2026 · 92 complete days · £/MWh average absolute error

Days receive equal weight. These periods have been examined during development. No fresh-test or world-leading performance claim is made.

UNCERTAINTY / WIND REFERENCE

77.4%of hourly outcomes fell
inside the experimental range

Target: 80%. Overall coverage can conceal poor coverage of extreme prices. The range is not a guarantee.

0verified live days included
in this implementation package

DIAGNOSTIC / WHERE THE ADVANTAGE COMES FROM

Every summer day stays in the record.Daily absolute error, wind reference · darker marks mean larger errors

1 June 31 August 2026

OBSERVED FAILURE / 4 JUNE 2026, MARKED IN RED ABOVE

HOW IT UPDATES

New evidence in.
Accountable updates out.

Updating is a recorded process and it carries no promise of daily improvement. Every update has to use outcomes that were already available at the time it was made.

Research seed in useAutomatic feedback service has not been connected in this preview.

Collect

Keep the original inputs and their receipt times. Freeze what was known.

Sources → time checks

Forecast

Archive the prediction before publication. Never replace yesterday’s forecast.

Model → immutable record

Measure

Join published actuals. Preserve revisions and missed forecasts.

Actuals → scored outcomes

Update

Refresh eligible corrections and refit under a fixed, approved policy.

Evidence → versioned update

Daily bias and range updates are proposed. Core refits: every 14 days.New methods require approval. No automatic promotion.

READ THE SMALL PRINT, IN NORMAL TYPE

What this does.
What it doesn’t.

A public research space for the next delivery day. It is not a two-year price outlook or a ten-year financing case.

What price are we forecasting?

The hourly LCCC Intermittent Market Reference Price (IMRP), a GB day-ahead benchmark using EPEX and N2EX indices. It is not an executable quote on one exchange. Prices are in GBP/MWh.

What does the middle line mean?

A median price estimate, not expected trading revenue. The average of hourly medians is neither the expected daily mean nor the median of daily baseload.

How should I read the shaded range?

As an experimental marginal range for each hour, with a nominal 80% target. It is empirically adjusted from prior errors. Coverage is not uniform across conditions and price spikes remain difficult.

What makes a forecast eligible for the live record?

Sources must arrive by 09:10 London on the preceding day. The forecast must be completed, durably archived and publicly published by 09:15. London summer time is UTC+1. Late previews, historical reconstructions and missing days must be kept separate.

Which limitations remain?

The historical price-availability rule is an explicit compatibility assumption. The research seed is time-limited. Controlled learning, durable storage, scheduling and publishing still require integration and acceptance testing. No guarantee of improvement, trading suitability or bankability is made.

Recorded limitations

Every figure above is regenerated by the scripts in research/audit_scripts/ and written to research/evidence/.

Source: Low Carbon Contracts Company, IMRP actuals. Contains public sector information licensed under the Open Government Licence v3.0. Forecast inputs: Elexon Insights WINDFOR and NDF. The research archive supplies the reconstructed model results shown here.