Price forecasting
Wholesale price forecasting for the National Electricity Market
For every five-minute interval in all five regions, the model publishes the expected price, the chance of a spike and an 80% range. The results below come from 18 months of forecasts, each one scored against the price that actually settled.
What the forecast provides
Every interval carries three outputs. The nowcast anchors the horizon, and the same control logic reads them whether the saving comes from spot, time-of-use or demand charges.
Most likely price
The expected price for each interval, from conditions the model has learned to associate with it.
Spike probability
The chance the interval settles at a spike price. Of the alerts issued, 93–99% were verified real spikes.
Realistic range
The 80% interval the price is expected to fall within. The nowcast is built from live market data and anchors the rest of the horizon.
What the 18 months showed
Every forecast in the window was scored against the settled price at the same five-minute interval.
The window included genuine price-cap events up to about $20,000/MWh. Region-by-region results are below.
Results by region, 18 months (wMAPE): click to expand
| Region | Nowcast: our tool | Nowcast: AEMO look-ahead | Day ahead: our tool | Day ahead: AEMO (2025) |
|---|---|---|---|---|
| QLD | 16.7% | 35.1% | 61.0% | 160.2% |
| NSW | 20.4% | 54.5% | 69.0% | 188.3% |
| VIC | 22.4% | 82.1% | 79.5% | 87.6% |
| SA | 24.7% | 58.1% | 89.9% | 119.4% |
| TAS | 14.8% | 47.3% | 43.4% | 65.2% |
| Average | 19.8% | 55.4% | 68.6% | 124.1% |
wMAPE = average miss as % of actual price. 18-month window: 1 Jan 2025 – 30 Jun 2026, all 5-min intervals, tool scored 5-min vs 5-min. AEMO look-ahead scored from published pre-dispatch (~28 min look-ahead at 30-min resolution). AEMO day-ahead figures are the 2025 published pre-dispatch 12–36h series from the project’s earlier backtest.
The test window
A single quiet year would not show much. This window covered two summers, price caps, interconnector outages and calm periods, and the accuracy held.
- Scarcity events. The window included genuine scarcity up to about $20,000/MWh. In normal trading the median miss is about $5, and of the spike alerts issued, 93–99% were real.
- Range calibration. The published 80% range contained the actual price 84–91% of the time.
- Comparison with AEMO. AEMO’s published look-ahead, for the same task, shows two to five times the error at the nowcast.
- Runs daily. It downloads fresh data and publishes the next day’s forecast with its ranges.
Why a forecast matters on a fixed tariff
Backtesting against settled prices shows what a decision would have saved. A forecast is what lets the same logic run forward: whether to pump now or wait, hold gas or generate, charge the battery or discharge. A plant on a fixed tariff still has time-of-use windows, demand-peak risk, solar output and inflow to look ahead for.
Sources: AEMO NEM dashboard, AEMO pre-dispatch, BOM weather.
Talk to us about your plant
The forecast is the price data behind the simulation. Modelled against your plant’s real load, market and tariff data, it shows whether there is a case worth building.