← All case studies

Fleet management · Logistics

Real-time ingestion and route deviation platform

TCP gateway authentication feeding Azure Event Hubs and Stream Analytics, correlated output in Cosmos DB, and an ML model computing net path deviation with alerts via Notification Hub.

Azure Event HubsStream AnalyticsCosmos DBNotification Hub

The problem

Vehicle sensor and dispatch data from millions of edge devices had no scalable path to ML use cases.

Our approach

  1. 1Built an authenticated TCP gateway for millions of vehicle edge devices.
  2. 2Streamed telemetry into Event Hubs and correlated it with dispatch data in Stream Analytics.
  3. 3Persisted correlated state in Cosmos DB for low-latency lookups.
  4. 4Scored a net path deviation model and pushed alerts through Notification Hub.

Measurable outcomes

Real time
Telemetry ingestion at fleet scale
Millions
Edge devices supported
Reusable
Framework for further AI use cases

Architecture and workflow

Architecture and workflow
  1. 01

    Edge

    Vehicle sensors · TCP gateway

  2. 02

    Stream

    Azure Event Hubs

  3. 03

    Process

    Stream Analytics correlation

  4. 04

    Store

    Cosmos DB state

  5. 05

    Act

    Deviation model · Notification Hub

Want a build like this?

We start with a two-week diagnostic and leave you with an architecture and migration plan you own.

Talk to an architect