Case article
From input to implication
01
Decision context
To schedule a battery for the next day, an operator must commit the plan before the 09:50 auction. The daily gap between the highest and the lowest price averages GBP 69/MWh. The forecast determines how much of this spread the battery earns.
The case covers one national price. A battery anywhere in Great Britain sees the same price and the same forecast.
02
Method
To compare forecasts on equal terms, the backtest schedules one 100 MW / 400 MWh battery on each forecast. The battery has 85% round-trip efficiency, one cycle per day, and a degradation cost of GBP 10/MWh.
The comparison includes a naive schedule that repeats the previous day and three rival foundation models that read price history only. The free public forecasts are the demand, wind, and solar forecasts published by NESO, which a gradient-boosting model converts into a price forecast.
eomer Expert adds three agents to the eomer forecasting model. Site Agent forecasts the output of the largest solar and wind plants, Grid Agent reads the published system forecasts, and Border Agent reads interconnector capacities and neighbouring markets.
03
Finding and implication
eomer Expert captures 91% of the perfect-foresight profit, compared with 88% for the free public forecasts and 85% for the most profitable rival model. eomer Expert is ahead of the most profitable rival model in 24 of 25 months and ahead of the free public forecasts in 23 of 25 months.
The 80% uncertainty interval of eomer Expert contains 79% of outcomes, compared with 57% for the public-forecast benchmark. Relative to the naive schedule, eomer Expert adds GBP 1.19M per battery-year.
The schedule settles at the day-ahead price without intraday updates, so the estimate excludes intraday trading and balancing markets. A deployment must add the constraints and the market access of the actual asset.
