Electricity Demand Forecast Accuracy, 30 Day Window to 28 October 2026
How far off was the day-ahead demand forecast? Over each grid's latest 30 day hourly window, measured against reported demand: US grids (EIA): 53 grids, average error from 1.3% (PGE) to 54.3% (SPA), data to 28 October 2026; European bidding zones (ENTSO-E): 47 grids, average error from 1.1% (Denmark West (DK1)) to 43.2% (Bosnia and Herzegovina), data to 28 October 2026. The two groups are ranked separately. Each grid is measured over its own latest 30 day window of hourly readings, shown in the last column of the tables.
Key Facts
- How far off was the day-ahead demand forecast? Over each grid's latest 30 day hourly window, measured against reported demand: US grids (EIA): 53 grids, average error from 1.3% (PGE) to 54.3% (SPA), data to 28 October 2026; European bidding zones (ENTSO-E): 47 grids, average error from 1.1% (Denmark West (DK1)) to 43.2% (Bosnia and Herzegovina), data to 28 October 2026. The two groups are ranked separately.
- United States (EIA): the most accurate forecast was PGE, off by 1.3% on average, with 99% of hours within 5% (28 September 2026 to 28 October 2026).
- United States, among grids averaging 5,000 MW or more, FPC had the largest average error, 24.4%.
- United States: 20 of 53 grids ran high on average by half a percent or more, 21 ran low by half a percent or more, and the rest were close to balanced.
- Europe (ENTSO-E): the most accurate forecast was Denmark West (DK1), off by 1.1% on average, with 98% of hours within 5% (30 September 2026 to 28 October 2026).
- Europe, among grids averaging 5,000 MW or more, Netherlands had the largest average error, 18.8%.
- Europe: 16 of 47 grids ran high on average by half a percent or more, 16 ran low by half a percent or more, and the rest were close to balanced.
What Is a Day-Ahead Demand Forecast and Why Do Errors Matter?
Grid operators publish a forecast of how much electricity their area will use, hour by hour, the day before. Power plants are scheduled, fuel is bought, and wholesale electricity is traded against that forecast. Real demand then arrives, driven by weather, holidays and the many small choices of millions of people.
When the forecast runs too low, operators must find extra generation or imports at short notice, which is usually dearer and can strain the grid. When it runs too high, plants are committed that were not needed. Errors are largest when the weather departs from what was expected, and grids with a lot of rooftop solar are harder to forecast because part of the demand is hidden behind the meter.
Average error, in the tables below, is the mean of the absolute percentage gap between forecast and reported demand across all compared hours, so a high miss and a low miss both count. Bias is the signed average: above zero means the forecast was too high on average, below zero too low. The worst miss is the largest single-hour gap in megawatts.
United States: Forecast Accuracy by Grid
Operator data to 2026-10-28, 53 grids| Grid | Average error | Bias | Hours within 5% | Worst miss | Hours compared | Data to |
|---|---|---|---|---|---|---|
| PGE | 1.3% | +0.5% | 99% | 332 MW(13%, high) | 719 | 2026-10-28 |
| BPA | 1.3% | +0.1% | 98% | 469 MW(6%, high) | 719 | 2026-10-28 |
| AVA | 1.4% | +0.0% | 98% | 179 MW(12%, low) | 695 | 2026-10-28 |
| ERCOT | 1.5% | +0.3% | 97% | 6,529 MW(10%, high) | 695 | 2026-10-28 |
| MISO | 1.8% | +1.3% | 96% | 5,043 MW(6%, high) | 719 | 2026-10-28 |
| BANC | 1.8% | -0.3% | 96% | 1,014 MW(37%, low) | 693 | 2026-10-28 |
| TPWR | 1.9% | +1.3% | 96% | 37 MW(8%, high) | 719 | 2026-10-28 |
| NWMT | 1.9% | -0.6% | 93% | 255 MW(24%, high) | 719 | 2026-10-28 |
| DUK | 1.9% | +0.6% | 92% | 1,485 MW(12%, high) | 719 | 2026-10-28 |
| TVA | 2.3% | +1.3% | 89% | 26,747 MW(60%, low) | 719 | 2026-10-28 |
| PACW | 2.4% | +0.8% | 90% | 269 MW(11%, low) | 719 | 2026-10-28 |
| CHPD | 2.6% | +0.2% | 88% | 26 MW(10%, low) | 719 | 2026-10-28 |
| CPLW | 2.6% | +0.4% | 86% | 69 MW(14%, high) | 719 | 2026-10-28 |
| TIDC | 2.8% | +0.3% | 86% | 54 MW(15%, high) | 716 | 2026-10-28 |
| GCPD | 2.9% | -2.7% | 89% | 75 MW(10%, low) | 719 | 2026-10-28 |
| NYISO | 2.9% | -2.8% | 85% | 1,450 MW(7%, low) | 719 | 2026-10-28 |
| PJM | 3.0% | -1.1% | 84% | 7,621 MW(9%, high) | 719 | 2026-10-28 |
| FPL | 3.0% | +0.3% | 80% | 2,303 MW(12%, high) | 719 | 2026-10-28 |
| TEPC | 3.1% | -0.3% | 82% | 392 MW(27%, high) | 719 | 2026-10-28 |
| TEC | 3.2% | -0.1% | 82% | 661 MW(25%, low) | 719 | 2026-10-28 |
| DOPD | 3.3% | +2.5% | 76% | 27 MW(11%, high) | 719 | 2026-10-28 |
| ISO-NE | 3.3% | -2.8% | 74% | 1,662 MW(18%, low) | 719 | 2026-10-28 |
| EPE | 3.3% | -1.2% | 77% | 275 MW(21%, high) | 719 | 2026-10-28 |
| SCL | 3.4% | -2.9% | 79% | 154 MW(14%, low) | 719 | 2026-10-28 |
| TAL | 3.5% | -1.8% | 76% | 111 MW(22%, low) | 719 | 2026-10-28 |
| AECI | 3.6% | -0.3% | 72% | 441 MW(21%, high) | 719 | 2026-10-28 |
| FMPP | 3.8% | +0.4% | 71% | 501 MW(19%, high) | 719 | 2026-10-28 |
| CPLE | 3.9% | +2.2% | 76% | 2,036 MW(36%, high) | 719 | 2026-10-28 |
| IPCO | 4.2% | +1.3% | 65% | 280 MW(15%, high) | 695 | 2026-10-28 |
| SC | 4.8% | +4.3% | 59% | 1,530 MW(130%, high) | 719 | 2026-10-28 |
| JEA | 4.9% | +3.7% | 56% | 381 MW(16%, low) | 719 | 2026-10-28 |
| SPP | 4.9% | +4.1% | 62% | 5,019 MW(17%, high) | 703 | 2026-10-28 |
| SCEG | 5.0% | -3.9% | 61% | 635 MW(20%, low) | 719 | 2026-10-28 |
| IID | 5.3% | +2.9% | 71% | 275 MW(74%, high) | 695 | 2026-10-28 |
| SOCO | 5.3% | +5.0% | 66% | 19,751 MW(44%, low) | 712 | 2026-10-28 |
| HST | 5.4% | +0.8% | 62% | 71 MW(47%, low) | 695 | 2026-10-28 |
| PNM | 5.5% | -5.5% | 45% | 253 MW(15%, low) | 719 | 2026-10-28 |
| LGEE | 7.4% | -7.3% | 25% | 736 MW(18%, low) | 719 | 2026-10-28 |
| CAISO | 7.7% | -6.5% | 63% | 9,702 MW(33%, low) | 719 | 2026-10-28 |
| PACE | 8.6% | +6.3% | 37% | 2,098 MW(37%, high) | 719 | 2026-10-28 |
| NEVP | 8.8% | -8.3% | 37% | 1,762 MW(30%, low) | 719 | 2026-10-28 |
| LDWP | 9.1% | -8.9% | 28% | 1,190 MW(23%, low) | 667 | 2026-10-25 |
| BHBA | 10.0% | -10.0% | 7% | 198 MW(21%, low) | 719 | 2026-10-28 |
| SWPW | 10.8% | +10.1% | 63% | 1,043 MW(39%, high) | 689 | 2026-10-28 |
| GVL | 11.5% | -10.7% | 23% | 159 MW(44%, low) | 719 | 2026-10-28 |
| AZPS | 13.2% | -8.7% | 15% | 3,894 MW(165%, high) | 715 | 2026-10-28 |
| WALC | 16.4% | +8.5% | 18% | 494 MW(70%, high) | 719 | 2026-10-28 |
| PSCO | 23.6% | -23.5% | 1% | 2,687 MW(45%, low) | 719 | 2026-10-28 |
| FPC | 24.4% | -24.4% | 0% | 3,080 MW(31%, low) | 719 | 2026-10-28 |
| SEC | 25.4% | -21.2% | 12% | 179 MW(37%, low) | 695 | 2026-10-28 |
| SRP | 26.8% | +25.9% | 24% | 2,700 MW(130%, high) | 719 | 2026-10-28 |
| PSEI | 49.5% | -49.5% | 0% | 2,246 MW(71%, low) | 719 | 2026-10-28 |
| SPA | 54.3% | +42.2% | 8% | 29 MW(414%, high) | 591 | 2026-10-27 |
Ranked from the smallest average error. Bias is signed: plus means the forecast ran above reported demand. Worst miss shows its size, its percentage of the reading and its direction. Each grid uses only the hours in which both a forecast and a positive demand reading exist; the latest hours, for which the forecast exists but demand is not yet reported, are left out.
Source: U.S. Energy Information Administration (EIA). (US Government work, public domain) Data as of 2026-10-28. Accuracy is computed by World Power Monitor from the operator's hourly forecast and reported demand.
Europe: Forecast Accuracy by Grid
Operator data to 2026-10-28, 47 grids| Grid | Average error | Bias | Hours within 5% | Worst miss | Hours compared | Data to |
|---|---|---|---|---|---|---|
| Denmark West (DK1) | 1.1% | -0.4% | 98% | 375 MW(15%, low) | 643 | 2026-10-28 |
| Czechia | 1.2% | +0.1% | 99% | 435 MW(6%, low) | 686 | 2026-10-28 |
| Spain | 1.2% | +0.2% | 99% | 2,088 MW(8%, high) | 684 | 2026-10-28 |
| Denmark East (DK2) | 1.2% | -0.2% | 97% | 290 MW(14%, low) | 643 | 2026-10-28 |
| France | 1.4% | -0.2% | 99% | 3,120 MW(5%, low) | 686 | 2026-10-28 |
| Poland | 1.6% | +0.8% | 96% | 2,479 MW(13%, high) | 685 | 2026-10-28 |
| Portugal | 2.0% | -0.1% | 94% | 702 MW(9%, low) | 685 | 2026-10-28 |
| Norway Central (NO3) | 2.0% | -0.6% | 97% | 229 MW(8%, high) | 684 | 2026-10-28 |
| Norway South-West (NO2) | 2.0% | -1.5% | 98% | 289 MW(7%, high) | 683 | 2026-10-28 |
| Slovakia | 2.1% | -0.1% | 94% | 272 MW(10%, high) | 686 | 2026-10-28 |
| Sweden South-Central (SE3) | 2.3% | -0.3% | 93% | 2,468 MW(21%, low) | 685 | 2026-10-28 |
| Romania | 2.3% | +0.3% | 89% | 688 MW(10%, low) | 681 | 2026-10-28 |
| Italy North | 2.4% | -0.1% | 89% | 2,522 MW(13%, high) | 685 | 2026-10-28 |
| Switzerland | 2.5% | +0.2% | 84% | 1,609 MW(25%, high) | 685 | 2026-10-28 |
| Norway North (NO4) | 2.5% | -1.8% | 92% | 194 MW(8%, low) | 684 | 2026-10-28 |
| Austria | 2.5% | -1.4% | 85% | 920 MW(14%, low) | 685 | 2026-10-28 |
| Norway South-East (NO1) | 2.5% | -1.4% | 89% | 367 MW(10%, low) | 683 | 2026-10-28 |
| Belgium | 2.5% | -1.4% | 90% | 1,367 MW(11%, low) | 685 | 2026-10-28 |
| Georgia | 2.5% | -0.2% | 88% | 440 MW(26%, low) | 563 | 2026-10-28 |
| Italy Centre-North | 2.7% | -0.3% | 85% | 388 MW(17%, high) | 685 | 2026-10-28 |
| Norway West (NO5) | 2.8% | -1.3% | 85% | 202 MW(10%, low) | 684 | 2026-10-28 |
| Albania | 2.9% | -1.0% | 84% | 167 MW(19%, high) | 685 | 2026-10-28 |
| Slovenia | 3.3% | +0.1% | 82% | 918 MW(100%, high) | 686 | 2026-10-28 |
| Italy Sicily | 3.3% | +0.7% | 77% | 277 MW(18%, low) | 685 | 2026-10-28 |
| Germany and Luxembourg | 3.4% | -2.1% | 79% | 7,176 MW(16%, low) | 684 | 2026-10-28 |
| Croatia | 3.4% | +1.2% | 74% | 263 MW(16%, low) | 686 | 2026-10-28 |
| Greece | 3.4% | -1.1% | 77% | 1,656 MW(21%, low) | 661 | 2026-10-28 |
| Serbia | 3.5% | -0.7% | 75% | 500 MW(12%, low) | 685 | 2026-10-28 |
| Hungary | 3.6% | -2.3% | 77% | 715 MW(20%, high) | 685 | 2026-10-28 |
| Bulgaria | 3.8% | +0.8% | 74% | 845 MW(15%, low) | 677 | 2026-10-28 |
| Finland | 3.8% | -0.8% | 70% | 1,598 MW(14%, low) | 687 | 2026-10-28 |
| Italy Sardinia | 4.0% | +1.8% | 74% | 213 MW(40%, high) | 685 | 2026-10-28 |
| Kosovo | 4.1% | +2.9% | 70% | 109 MW(15%, high) | 628 | 2026-10-26 |
| Italy Centre-South | 4.9% | +0.8% | 62% | 1,088 MW(19%, low) | 685 | 2026-10-28 |
| Cyprus | 5.4% | -2.9% | 49% | 246 MW(52%, high) | 652 | 2026-10-28 |
| Latvia | 5.8% | +2.5% | 51% | 1,049 MW(50%, low) | 686 | 2026-10-28 |
| Montenegro | 6.2% | +2.6% | 63% | 202 MW(39%, low) | 670 | 2026-10-28 |
| North Macedonia | 8.7% | -2.7% | 46% | 374 MW(54%, low) | 626 | 2026-10-27 |
| Sweden South (SE4) | 8.8% | +8.3% | 31% | 715 MW(38%, high) | 683 | 2026-10-28 |
| Lithuania | 10.9% | -10.2% | 20% | 589 MW(30%, low) | 686 | 2026-10-28 |
| Italy South | 11.9% | -0.2% | 27% | 943 MW(37%, low) | 685 | 2026-10-28 |
| Sweden North (SE1) | 12.4% | +2.0% | 30% | 625 MW(33%, low) | 685 | 2026-10-28 |
| Italy Calabria | 12.7% | +1.3% | 34% | 398 MW(63%, high) | 685 | 2026-10-28 |
| Estonia | 13.2% | +9.4% | 31% | 576 MW(99%, high) | 685 | 2026-10-28 |
| Sweden North-Central (SE2) | 16.6% | +14.8% | 24% | 1,066 MW(107%, high) | 685 | 2026-10-28 |
| Netherlands | 18.8% | +17.6% | 15% | 7,237 MW(195%, high) | 685 | 2026-10-28 |
| Bosnia and Herzegovina | 43.2% | +42.4% | 15% | 1,146 MW(383%, high) | 667 | 2026-10-28 |
Ranked from the smallest average error. Bias is signed: plus means the forecast ran above reported demand. Worst miss shows its size, its percentage of the reading and its direction. Each grid uses only the hours in which both a forecast and a positive demand reading exist; the latest hours, for which the forecast exists but demand is not yet reported, are left out.
Source: ENTSO-E Transparency Platform (transparency.entsoe.eu), CC BY 4.0. Aggregated and converted by World Power Monitor; ENTSO-E does not endorse this site. (ENTSO-E Terms of Use plus CC BY 4.0 for listed data items) Data as of 2026-10-28. Accuracy is computed by World Power Monitor from the operator's hourly forecast and reported demand.
How These Figures Are Built
- Source: the last 30 days of hourly demand and the operator's own day-ahead demand forecast. US grids come from EIA and European bidding zones from ENTSO-E; they are ranked separately and are not combined with each other or with Ember statistics.
- Error for an hour is (forecast minus reported demand) divided by reported demand. Hours with a missing or zero demand or forecast value, or a value under 30% or over 3 times the grid's own median for the window (a partial or garbled report), are ignored. A grid needs at least 168 compared hours (seven days) to appear.
- Some grids show a steady gap in one direction (for example a forecast that runs well above reported demand every day); that can come from a difference in what the two series cover rather than poor forecasting, and this page does not tell the two apart. The forecast is whatever the operator last published for the hour, so it may be refreshed during the day for some operators and stay fixed at the day-ahead value for others. This page does not check which.
- Reported demand is preliminary and can be revised. A short window is a small sample: one heat wave or holiday can move a grid's average error a lot, and the figures are not a long run measure of forecast skill.
- Grids with a forecast series but fewer than 168 usable hours, and grids that publish no forecast, are left out. A page notes when a grid's window has fewer than 600 of 720 hours compared.
- See methodology and data quality for known gaps in the operator series.
Related
Cite this page
World Power Monitor. (2026). Electricity Demand Forecast Accuracy by Grid. https://worldpowermonitor.com/forecast-accuracy/
World Power Monitor. Electricity Demand Forecast Accuracy by Grid. Data as of 2026-10-28. Data from U.S. Energy Information Administration and ENTSO-E Transparency Platform. https://worldpowermonitor.com/forecast-accuracy/
@misc{wpm_forecast_accuracy_2026,
title = {{Electricity Demand Forecast Accuracy by Grid}},
author = {{World Power Monitor}},
year = {2026},
note = {Data as of 2026-10-28. Data from U.S. Energy Information Administration and ENTSO-E Transparency Platform.},
url = {https://worldpowermonitor.com/forecast-accuracy/}
} Permalink: https://worldpowermonitor.com/forecast-accuracy/
The Copy buttons add today's date as the access date.