ENERGIA GROUP

Energy Trading Optimisation

Market-optimised electricity trading strategy using DAM, demand, wind, and pricing signals — profitability improved under a €50k daily loss cap.

Python
Optimisation
Time Series

Problem

Electricity trading means committing to positions against volatile market prices, where a bad day can be expensive. This project set out to build a market-optimised electricity trading strategy with an explicit risk constraint: a €50,000 daily loss cap.

TODO(Abraham): describe the trading scenario in more detail — the market and region, whether this was a live trading problem or a modelling exercise, and the time period covered.

Approach

The strategy was built in Python around multiple time-series market signals:

Day-ahead market (DAM) data
Electricity demand
Wind generation
Pricing signals

These signals were combined to optimise trading decisions while keeping downside exposure within the €50k daily loss cap.

TODO(Abraham): describe the optimisation method used (e.g. linear programming, heuristic search, backtested rules) and how the loss cap was enforced in practice.

TODO(Abraham): describe the data sources, granularity, and forecast horizon for each signal.

Tech stack

Python
Optimisation
Time-series analysis

TODO(Abraham): list the specific libraries used (e.g. for optimisation, data handling, or forecasting).

Outcome

The strategy improved profitability while staying within the €50k daily loss cap.

TODO(Abraham): quantify the profitability improvement and the baseline it was measured against.

TODO(Abraham): add any follow-on impact — e.g. how the strategy or its findings were used, or academic result if this was a study project.