YassY-The-AlchemYst/YassYBS26Sol46

YassYBS26 Solution 46

My submission for the NORA BatterySwapAI 2026 challenge. It holds the fitted models and the inference code that writes the submission file. No training code is included.

What changed

Solution 46 jointly calibrates candidate ranking, hazard strength, late-risk pricing, and weekly-aware schedule construction. It retains the fourteen-day candidate window and exact cost-based local search, while spreading feasible work more effectively across weeks. The serialized submission path scores 1381.48 under held-out-building validation on all 48 scenarios.

Method

1. Build features for every device, including the forward temperature block.
2. Score each device with the thermal survival model.
3. Mix 23.5 percent of the hazard rank with 76.5 percent of a learned ranker.
4. Keep the top 17 as swap candidates.
5. Plan dates and routes under a 16-swap cap, pricing travel, overtime, the daily and weekly hour caps, and the emergency visit the evaluator forces for any battery that was due and left unplanned.
6. Relieve any week that has gone over its hour cap, choosing dates from a window at least fourteen days wide so another week is always reachable.

Validation

Validation holds out whole buildings, so a battery and its neighbours never appear in both training and validation. Devices in one building share an install date and a thermal environment, which makes any weaker split optimistic. Every battery below is scored by a model that never saw its own building, through the same code path the submission runs, with features rebuilt from the raw readings rather than read from a cache.

Version	Total time	Late swap	Early swap	Weekly cap	Daily cap
Solution 30	1430.14	704.17	533.13	33.33	31.25
plus the wider window	1425.69	702.92	532.53	31.25	31.25
Solution 41	1425.09	702.92	532.24	29.17	33.33
Solution 46	1381.48	690.21	512.39	18.75	33.33

Split into the four chronological quarters of the scenario set, against solution 30: 1303.8 to 1303.6, 2322.4 to 2316.2, 1189.5 unchanged, and 904.9 to 891.1. No quarter is worse, which is the reason for preferring this configuration over the larger but lopsided one the search preferred.

These are local results on the 48 public training scenarios, measured with the competition's own simulator. They are not competition scores.

A note on measurement. Configuration choices here were made only on numbers produced by the planner's own feature builder. An earlier version of this work was tuned against a cached feature table and picked a setting that turned out to be worse once measured properly, so cached results are not used for decisions.

Files

script.py                                       submission entry point
batteryswap_example/features.py                 feature extraction
batteryswap_example/thermal.py                  forward temperature features
batteryswap_example/survival.py                 end-of-life model
batteryswap_example/tsbp.py                     trajectory matching
batteryswap_example/costmodel.py                schedule cost calculation
batteryswap_example/planner.py                  scheduling search
batteryswap_example/ensemble.py                 shortlist and serving wrapper
batteryswap_example/planners/best.pickle        fitted model and ranker

Running

The competition image runs script.py, which reads the dataset, plans every scenario and writes submission.csv. Locally:

BATTERYSWAP_DATASET_PATH=/path/to/data BATTERYSWAP_SPLITS=train python script.py

Planning all 48 training scenarios takes about three minutes, most of it rebuilding each device's temperature history.