Optimised Scenarios for Bergen Light Rail Expansion

Best‑practice description
The Bergen Light Rail (BLR) upgraded its 20 km single‑line network into a multi‑line system to boost efficiency, ridership, cost‑effectiveness, and sustainability. Using the Asistobe platform—a data‑integration and AI tool—the city combined internal transport data (vehicle telemetry, passenger counts, schedule adherence) with external datasets (trafic flows, land‑use, demographic trends).

Key steps:

1. Data collection & integration – Sensors, ticketing systems, and open‑data portals fed real‑time and historic information into Asistobe.
2. AI‑driven scenario modelling – Machine‑learning algorithms identified bottlenecks, forecasted demand, and simulated infrastructure upgrades (new branches, passing loops, station redesigns).
3. Operational optimisation – Recommendations reduced unnecessary kilometres travelled, refined timetables, and re‑allocated rolling stock to match peak‑hour demand.
4. Targeted infrastructure enhancements – Investments focused on high‑density corridors, adding passing tracks and platform extensions without purchasing additional vehicles.

The implementation demonstrated how a data‑centric, AI‑supported workflow can simultaneously improve service capacity, environmental performance, and financial outcomes for an existing light‑rail system.

Evidence of success / impact

• Operating expenditure (OPEX) fell 23 %, delivering multi‑year cost savings.
• CO₂ emissions dropped 30 %, contributing to Bergen’s climate targets.
• Annual passenger numbers rose 25 %, reflecting higher attractiveness and reliability.
• Economic value creation increased by €22 million per year through productivity gains and reduced congestion.
• Capacity grew without extra rolling stock, thanks to smarter scheduling and targeted track upgrades.

Key lessons learned

• Data integration & AI are decisive – Merging heterogeneous datasets and applying machine‑learning models yielded precise, actionable insights that traditional planning missed.
• Balancing expansion with efficiency – The main challenge was extending the network while keeping operating costs low; AI‑guided scenario selection allowed the city to prioritize upgrades that delivered the highest marginal benefit.
• Infrastructure tuned to real‑time demand – Adding passing loops and extending stations where demand peaked increased capacity without buying new trams.
• Stakeholder engagement matters – Early, continuous dialogue with operators, municipalities, and the public smoothed adoption of new schedules and helped secure funding.
• Future‑proofing through continuous analytics – Maintaining a live data pipeline enables ongoing optimisation as travel patterns evolve.