Selbstgesteuertes Projekt
Energy and Renewable: Machine Learning for the Power Grid
Junior Machine Learning Engineer · KI / ML · August 2026
Eine ProoV-Fallstudie · Lernprojekt, kein Arbeitsverhältnis
Built an end-to-end gas-turbine TEY predictor using leakage-free sensor features, with CO and NOx excluded because they are downstream emissions. Trained and compared a LinearRegression baseline and a RandomForest on a time-based held-out split, then evaluated the winner honestly with MAE, R2, and a residual read. The final model achieved about 1.53 MWh MAE and 0.983 R2 on unseen later-period data, with a clear model card describing intended use, limits, and drift monitoring.
Bewertet nach
- Build and validate the model correctly35%
- Optimize and evaluate honestly25%
- Write the Model Card (clarity + honesty)25%
- Explain it to a non-expert15%
Bestanden · Bestehensgrenze 60/100
Was herausstach6
- Correctly dropped CO and NOx because they are downstream emissions and would leak future information into the model.
- Used an earlier-period train / later-period test split instead of a random shuffle, which is the right validation pattern for ordered operational data.
- Compared a LinearRegression baseline against a RandomForest and showed a clear held-out MAE improvement.
- Noted heteroscedasticity and slight positive bias at the top end in the residual read, showing calibrated evaluation rather than overclaiming.
- Leakage-Free Feature Selection
- Time-Based Holdout Validation
Meine eingereichte Arbeit18 Aufgaben
10 Aufgaben · 11 Zeilen · Python, JavaScript · 8 Textantworten · 422 Wörter
- Problem Frame238 Zeichen
- Leakage Flags113 Zeichen
- Train Validate BaselinePython · 1.4k Zeichen
- Train Validate Forest943 Zeichen
- Train Validate124 Zeichen
- Residual Read168 Zeichen
- Drift Monitor91 Zeichen
- Model Card1.5k Zeichen
- Teach BackJavaScript · 848 Zeichen
- Jupyterlite Code2 Zeilen
- Problem Frame18 Wörter
- Leakage Flags1 Wort
- Train Validate Baseline141 Wörter
- Train Validate Forest76 Wörter
- Train Validate1 Wort
- Residual Read18 Wörter
- Drift Monitor1 Wort
- Model Card166 Wörter
Bewusst zusammengefasst — der eingereichte Code und die Texte bleiben privat, damit diese Seite nicht als Lösungsvorlage dient. Die vollständige Einreichung steht hinter dem verifizierten Zertifikat.