Insights · Reference Architectures

Reference Architectures

Illustrative deployment models designed to show how the Navigato AI platform can be applied to real infrastructure challenges. These are reference configurations, not deployed customer implementations.

Illustrative Deployment Models — these architectures are designed to demonstrate platform capability. They are not deployed customer implementations or proven production systems.

EV Infrastructure Intelligence

National eMobility Platform

Illustrative Deployment Model

A reference architecture for a national fuel-station or retail network transforming its physical estate into a scalable eMobility platform. Designed for organisations with 50–500+ existing sites seeking to deploy EV charging at scale across road corridors and urban locations.

Business Context

  • Organisation type: national fuel retailer or large CPO
  • Sites: 100–500 locations
  • Timeline: 18–36 month phased rollout
  • Starting point: GIS audit and Digital Twin model

Illustrative KPIs

Model-based assumptions only

  • Target utilisation: 15–35% (model assumption)
  • Revenue per charger: depends on location, pricing and demand
  • System uptime: design target >98%

Financial projections are model-based and depend on site selection, grid access, charging demand and pricing strategy.

Key Integrations

OCPP 2.0.1OCPIISO 15118Payment processorsFleet management APIsGrid operators

Architecture Layers

01Site Network200 locations — illustrative
02AC/DC/HPC Charging Infrastructure
03OCPP 2.0.1 Charging Management Platform
04Payments and Loyalty Layer
05GIS and Digital Twin
06AI Optimisation Engine
07NOC and Field Operations
08Management and Investor Dashboard

Phased Deployment Model

Phase 0Discovery and GIS audit
Months 1–3
Phase 1Digital Twin and financial model
Months 3–6
Phase 23–5 pilot sites
Months 6–12
Phase 3Phase 1 rollout — 30–50 sites
Months 12–24
Phase 4National scale
Months 24–36+

Proposed architecture — subject to site assessment, grid access and regulatory compliance.

Discuss an eMobility Pilot

Smart Transformers & Substations

Smart Transformer Vendor Platform

Illustrative Deployment Model

A reference architecture for a mid-to-large transformer manufacturer launching a digital lifecycle platform across its installed base. Designed to create a white-label Digital Passport and connected asset service that generates recurring revenue without requiring hardware replacement.

Business Context

  • Organisation type: transformer or substation manufacturer
  • Installed base: 1,000–50,000+ assets (illustrative range)
  • Starting point: Digital Passport pilot on new production units
  • Growth path: retrofit existing installed base progressively

Illustrative Value Metrics

Model-based assumptions only

  • Target digital attachment rate: 40–80% of new units in year 1 (illustrative)
  • Recurring revenue per asset: depends on service tier and pricing

Revenue projections depend on market pricing, adoption rate and service tier uptake.

Deployment Note

Manufacturer brand, domain and customer relationships remain primary throughout. Data ownership is contractually defined.

Architecture Components

01Physical transformer fleetexisting + new
02QR Digital Passport layer
03Optional IoT sensor integration
04Digital Twin per asset
05AI Health Score engine
06Customer and service portal
07Manufacturer management dashboard

Four-Level Product Rollout

Level 1Digital Passport for all new units shipped
Year 1
Level 2Optional telemetry for high-value assets
Year 2
Level 3AI Health Score for connected fleet
Year 2–3
Level 4Customer portal and full SaaS launch
Year 3+

Illustrative model — commercial terms, data ownership and integration scope defined in pilot agreement.

Discuss a Smart Asset Pilot

Adaptive Traffic & Urban Mobility

Adaptive Traffic Management Platform

Reference Architecture

A reference architecture for a European city deploying AI-based adaptive traffic management across a priority corridor or district. Based on European urban-pilot principles and applicable to cities with different infrastructure maturity, transport systems and regulatory environments.

Business Context

  • Organisation type: municipality or metropolitan transport authority
  • Pilot scope: 5–50 intersections
  • Starting point: Digital Twin and baseline simulation
  • Growth path: corridor → district → citywide

Governance Requirements

Every live change requires human approval in initial phases
Manual override available at all times
Full audit log of all signal changes
Rollback to static signal plan within seconds
Performance validated against baseline before expansion
Privacy-by-design data processing throughout

Modules in Use

TrafficSense™SignalAI™MobilityTwin™TransitPriority™SafeFlow™CleanTraffic™

Deployment Phases

01City data audit and intersection survey
02Digital Twin baseline model (no live changes)
03Simulation-only — test AI recommendations
04Shadow mode — AI recommends, human decides
05Human-approved pilot — limited live adaptive control
06Corridor deployment — validated intersections
07District scale-up
08Citywide orchestration

Illustrative KPI Targets

Model-based — validated during pilot phase

  • Average journey time reduction: depends on baseline and corridor characteristics
  • Public transport punctuality: improvement target defined in pilot scope

Performance projections are established during the Digital Twin baseline phase and validated with field data during the human-approved pilot. No production claims are made prior to field validation.

Representative architecture — applicable to cities with different infrastructure maturity and regulatory environments.

Discuss a City Pilot

Shared Foundation

All three architectures share one platform core

Whether the asset is an EV charger, transformer or traffic signal, the same six-layer platform stack provides connectivity, intelligence and governance.

01

Physical Assets

EV chargers, transformers, traffic signals and sensors — the physical estate the platform connects.

02

Data & Connectivity

OCPP, IoT sensors, edge gateways and APIs ingesting real-time signals from every asset.

03

Digital Twin

High-fidelity virtual models representing each asset, site and network — updated continuously.

04

AI Intelligence

Predictive analytics, anomaly detection, demand forecasting and adaptive optimisation engines.

05

Operations

NOC dashboards, field operations tooling, customer portals and management reporting.

06

Governance & Evidence

Full audit logs, human-approval workflows, rollback controls and regulatory evidence packs.

About These Reference Architectures

These reference architectures are illustrative deployment models created to demonstrate how the Navigato AI platform can be applied to infrastructure challenges in each sector. They are not case studies of deployed customers, signed contracts or live operational systems. Physical deployment depends on site assessment, regulatory compliance and applicable permits. Financial projections are model-based and subject to real-world conditions. Navigato AI acts as a technology integrator and platform provider.

Next Steps

Discuss which reference architecture fits your organisation

We work with organisations in each sector to scope, validate and pilot deployments based on real site data and operational context.