Rank the next wireless charging point for one EV decision event.

A deployment-valid Graph Transformer that compares candidate WCPs without candidate IDs, proxy-label criteria, or cross-event batch aggregation.

Event-specific graphListwise rankingBatch invariant

01 · Decision event

EV context

Consumer ruleValid consumer request · maximum 30 kWh battery headroom.
Consumer propensityValid consumer propensity · pₑ = 0.50 from SoC 50.0%.Paper definition: pₑ = 1 − SoC. Higher values indicate greater charging urgency as battery energy falls. It adjusts criterion importance and is not an observed user preference.

02 · Candidate generation

Journey context

Source and destination describe the journey. Candidate WCPs are selected by minimum additional detour from the remaining trip. Coordinates and detours never enter the model.

Recommended input methodSelect journey positions on the mapChoose a point, then click the corresponding street-map position.
Placing · Source
Loading position picker…
Click the map to place source

Select Journey origin, then click its position on the map.

Journey validationSource, current and destination codes

Manual coordinate entry

Source position

Current EV position

Destination

03 · Graph ranking

Recommendations

Awaiting event

No ranking yet

Enter one EV decision event to construct its candidate graph.

REVIEWER-FACING CONTROLS

What the model does—and does not use

✓

Independent event graph

The result for an EV is unchanged when unrelated events enter the batch.

✓

No identifier embeddings

Event and WCP identifiers map records and topology only; they are never learned inputs.

✓

No proxy criteria

Distance, speed, popularity, TOPSIS intermediates, EM outputs, and derived ranks are excluded.