Skip to content

RUNNING.md

Latest commit

 

History

History
91 lines (63 loc) · 2.65 KB

RUNNING.md

File metadata and controls

91 lines (63 loc) · 2.65 KB
Raw

Running this project

Step-by-step setup and run instructions, including a VS Code walk-through.

Prerequisites

  • Python 3.10 or newer (developed on 3.13)
  • No API keys or accounts. All data is downloaded from the public SMARD.de endpoints on first run and cached locally.

1. Get the code and install dependencies

git clone https://github.com/CodingxFaisal/bess-dispatch-optimizer.git
cd bess-dispatch-optimizer

Create a virtual environment (recommended) and install:

python -m venv .venv

Activate it:

  • Windows (PowerShell): .\.venv\Scripts\Activate.ps1
  • Windows (cmd): .\.venv\Scripts\activate.bat
  • macOS / Linux: source .venv/bin/activate

Then:

pip install -r requirements.txt

2. Open in VS Code

  1. File -> Open Folder... and select this project folder.
  2. Install the Microsoft Python extension if prompted.
  3. Select the interpreter: Ctrl+Shift+P -> "Python: Select Interpreter" -> choose the .venv you just created.
  4. Open a terminal with Ctrl+`. It starts in the project root.

You can run any script with the ▶ button in the editor, or from the terminal as shown below.

3. Reproduce everything

This downloads the data once (a few minutes the first time, then cached) and runs all three stages, writing charts and CSVs to results/:

python scripts/run_all.py

4. Or run one stage at a time

python scripts/download_data.py         --start 2022-01-01 --end 2025-01-01
python scripts/run_perfect_foresight.py --start 2022-01-01 --end 2025-01-01
python scripts/run_backtest.py          --data-start 2022-01-01 --start 2023-01-01 --end 2025-01-01
python scripts/run_duration_sweep.py    --start 2023-01-01 --end 2025-01-01

The backtest is the slow step (it solves one small MILP per day and retrains the forecast model periodically), typically a few minutes.

5. Run the tests

pytest

Expected: 19 passed. The tests check energy balance, state-of-charge bounds, the charge/discharge binary, the cycle cap, and a hand-computed revenue case.

Outputs

Everything lands in results/:

  • capture_ratio.png, ml_dispatch_week.png, revenue_by_year.png, perfect_revenue_by_year.png, duration_sweep.png, tier1_dispatch_week.png
  • backtest_summary.csv and per-strategy daily_*.csv

Troubleshooting

  • Import errors running a script directly: run from the project root. The scripts add src/ to the path themselves, so python scripts/run_backtest.py works without installing the package.
  • First run is slow: it is downloading ~3 years of hourly data from SMARD. Subsequent runs read the local cache in data/.