Guidance for Queue Depth Management on AWS
Overview
This Guidance for queue depth management shows how you can improve customer experience by monitoring queues using cameras, use computer vision to measure queue depth, and provide alerts about bottlenecks and unreasonable queue depths to customer service managers. Travel & Hospitality organizations can apply this solution to improve employee productivity, streamline lobby management, gain customer insights, reduce walkaways and negative perceptions of wait times.
How it works
Monitor the passenger and guest queues using cameras, use computer vision to measure queue depth, and provide alerts about bottlenecks and unreasonable queue depths to customer service managers, improving the traveler experience.
Well-Architected Pillars
The architecture diagram above is an example of a Solution created with Well-Architected best practices in mind. To be fully Well-Architected, you should follow as many Well-Architected best practices as possible.
Operational Excellence
This Guidance has been written using the AWS Cloud Development Kit (AWS CDK) for infrastructure as code wherever possible. It can be easily redeployed into new environments with minimal setup. It has also been created with examples of how to route data for analysis purposes, in addition to having IoT rules established for the publishing of metrics and notifications.
Security
By default, all AWS IoT data in transit and at rest is encrypted. Data in transit is encrypted using TLS, and data at rest is encrypted using AWS owned keys. In addition, the frontend uses authentication through Amazon Cognito, which helps you control which users are able to access the system.
Reliability
All communications within the system are handled through AWS IoT Core MQTT messaging protocol, which allows for “At Least Once” delivery of messages. The edge device (simulated by an Amazon Elastic Compute Cloud (Amazon EC2) instance) is managed through the AWS Lambda runtime. Updates to those components are continuously version controlled and managed through deployments within AWS IoT Greengrass.
Performance Efficiency
The computer vision model is developed to capitalize the resources available on the host system. Where GPU processing is available, it will use that to speed up processing. Images are automatically downscaled to decrease processing time.
Cost Optimization
To ensure that costs are kept low, the Guidance only uses a single EC2 instance to simulate an edge device and illustrate the function of the computer vision model. In addition, only the minimal usage of other AWS services is present within the system. These include a single Amazon S3 bucket for uploading pictures, a single DynamoDB table for storing queue vertices, and a minimal set of examples of using IoT rules to route data to CloudWatch. To further reduce costs, users can remove all of the IoT rules that route incoming data and run the model on their edge device.
Sustainability
This Guidance focuses on reducing environmental impact by only ever using the minimal set of resources required to make the system operate. There is very little resource usage throughout the system because it does not need to operate frequently or interact with many other services. For most of the time, the system will be inert until it is manually initiated by the user.
Disclaimer
Did you find what you were looking for today?
Let us know so we can improve the quality of the content on our pages