View a markdown version of this page

Connected Airports Using IoT and AI/ML - Connected Airports Using IoT and AI/ML
Connected airports diagramFurther readingDiagram history

Connected Airports Using IoT and AI/ML

Publication date: December 23, 2022 (Diagram history)

This reference architecture shows how to build a smart, connected airport using Internet of Things (IoT) and artificial intelligence/machine learning (AI/ML). Airport operators use this architecture to generate near real-time data for aircraft movement, gate turns, baggage tracking, queue depth, and passenger traffic.

Traditional airports rely on manual processes and disconnected systems. These approaches cannot provide the real-time visibility that operations teams need. This architecture connects IoT devices at the edge, processes data in near real time, and applies ML models for predictive insights. You can also implement compliance measures such as social distancing and security monitoring.

This architecture references the Aircraft Turn Tracking Passive Data Collection solution for gate turn event collection.

Connected airports diagram

Architecture for connected airports using AWS IoT Core, AWS IoT Greengrass, and Amazon SageMaker AI.

The following steps describe the architecture:

  1. Use AWS IoT Greengrass Core to connect, publish, and subscribe data. Use Message Queuing Telemetry Transport (MQTT) protocol with IoT devices.

  2. Use AWS IoT Core to maintain shadows of IoT devices. Connect to AWS Cloud, manage devices, update over the air (OTA), and secure devices.

  3. Use purpose-built databases such as DynamoDB and serverless architecture for events, microservices, and operational data.

  4. Build a real-time operational dashboard by using microservices and AWS AppSync. Deliver alerts through Amazon Pinpoint.

  5. Build the data lake in Amazon S3. Use AWS Glue and Amazon EMR for raw and curated processed data.

  6. Discover and govern data in Amazon S3 by using AWS Glue crawlers, Glue Data Catalog, and Lake Formation. Deploy Amazon Macie to detect sensitive data.

  7. Use AWS Glue jobs and Amazon EMR for data transformation and enrichment.

  8. Use Amazon Redshift, Athena, and Quick for analytics. Build data marts in Amazon Redshift for heavily used analytics.

  9. Use Amazon SageMaker AI to build, train, and deploy inference models. Deploy edge models on AWS IoT Greengrass Core.

  10. Use the Aircraft Turn Tracking solution to passively collect gate turn events.

  11. Use social distancing and queue depth management solutions for compliance.

Further reading

For additional information, see the following resources:

Diagram history

To receive updates about this reference architecture diagram, subscribe to the RSS feed.

ChangeDescriptionDate

Initial publication

Reference architecture diagram first published.

December 23, 2022

RSS subscription requirement

To subscribe to RSS updates, you must have an RSS plugin enabled for the browser you are using.