ChargeScape London
A spatial decision system for EV charging networks under uncertain demand.
Where should London's next rapid-charging hubs go, how large should they be, and how sure can we be? Built end to end from open data, with every assumption visible.
Public charging demand, 2026
285 GWh
P10 to P90: 216 to 361
Rapid sites that queue at the peak
348 / 632
P(wait) above 0.5 in the peak hour
Recommended plan at £20M
51 hubs
serve 63% of unmet rapid demand
Usage model in an unseen city
R² −0.25
against 0.70 with random cross-validation
- Who has chargers, who has EVs13,174 charging sites by power over EV ownership and housing
- Public charging demandP10, P50, P90 and 2030 as 3D hexes
- Rapid network loadDrive time, modelled load and peak-hour queues per site
- Where the next hubs goBudgets from £5M to £40M, one plan per demand scenario, robust core
Notebooks
- Supply auditChargers against EVs, Moran's I and Gi* hot spots, drive-time gaps
- Demand surfaceMonte Carlo demand with P10, P50, P90, calibration, 2030
- Choice and queuesLogit station choice, Erlang C queues, new against captured demand
- SitingCapacitated MILP per scenario, regret, budget sweep, sensitivity
- Transfer testDoes a context model explain usage in an unseen city?
Documentation
- MethodologyEvery model step, with formulas and assumptions
- Architecture and stackWhat each tool does and why it was chosen
- Model cardIntended use, limits and how the result could be proven wrong
- Data catalog32 datasets with source, licence and status
- RoadmapWhat changes with operator data