Our proprietary optimisation engine demonstrates how to maximise revenue for Battery Energy Storage Systems (BESS) by running powerful simulations against historical data from the Great Britain (GB) electricity markets. The strategy is built on a sophisticated two-stage mathematical model that backtests a robust and flexible approach to energy trading, showing the full potential revenue available on previous dates.
The first stage establishes an optimal 24-hour trading plan by analysing the historical Day-Ahead market data for a selected day. This process simulates the perfect foresight a BESS operator would have had at the start of the trading day.
This stage simulates how an operator could have capitalised on price movements closer to the time of delivery, using the optimal Day-Ahead schedule as a baseline.
By simulating a co-optimisation strategy, we demonstrate how a battery’s full potential can be utilised, stacking revenues in a way a single-market model cannot.
The two-stage simulation demonstrates a strategy that combines a day-ahead plan with intraday agility, providing a clear picture of balanced risk and reward.
The optimisation is governed by constraints that reflect the battery's physical characteristics, ensuring the simulated strategy is both profitable and sustainable.
Our model is built using Pyomo, a powerful Python-based optimisation modelling language, and leverages high-performance solvers to find the optimal schedule under complex conditions.