← Back to portfolio

Renewable Energy: Battery Energy Storage (BESS) Health

Config-driven data science pipeline for high-fidelity industrial domains.

Renewable Energy: Battery Energy Storage (BESS) Health Public dataset

At a glance

Task: regression  |  Headline: r2 = 1.0

rmse
0.0039
mae
0.0033
median_ae
0.0032
mape
0.0034
r2
1.0
adj_r2
1.0
explained_variance
1.0
mean_residual
0.0032

Summary

Project

Config-driven data science pipeline for high-fidelity industrial domains.

What was investigated

The engagement modelled the target 'soh_percentage' as a regression problem in the Renewable Energy: Battery Energy Storage (BESS) Health domain, using 2000 records across 10 columns (data source: Synthetic sandbox). The pipeline audited data quality, engineered features, split the data honestly into train/test, and compared several models by cross-validation.

Outcome

The selected model was Ridge, with r2 = 1.0000 on the held-out test set. Supporting metrics: rmse=0.004, mae=0.003, median_ae=0.003, mape=0.003, adj_r2=1.000, explained_variance=1.000, mean_residual=0.003. Full results, the deployment gates and the audit trail are in the run's report.

Figures

02_distributions.png
02 distributions
03_correlation.png
03 correlation
04_vif.png
04 vif
05_target.png
05 target
10_pred_vs_actual.png
10 pred vs actual
11_residuals.png
11 residuals
12_leaderboard.png
12 leaderboard
13_feature_importance.png
13 feature importance
20_capacity_decay.png
20 capacity decay
21_thermal_runaway_gauge.png
21 thermal runaway gauge

Artifacts

Data source: Synthetic sandbox

Download report (.docx)

Audit SHA-256: cb1b8ca76598b3ebd154e5449da33c9ec701ab9e1da58e30b479b20dc18c949e