reference deployment

Utility Meter Data Analytics on AWS

Gain insights from meter data with AWS machine learning

View deployment guide

This solution deploys Utility Meter Data Analytics to the Amazon Web Services (AWS) Cloud. It's for utilty companies that want to generate insights from meter data using AWS managed machine learning (ML). The solution transforms and organizes data in a central AWS Glue Data Catalog and uses Amazon SageMaker to make inferences from them. Users access energy usage, meter outage, and forecasting insights with API queries managed by Amazon API Gateway.  

cisco logo

This solution was developed by AWS.

  •  What you'll build

  • The solution sets up the following: 

    • Amazon Simple Storage Service (Amazon S3) buckets to store the following:
      • Weather and topology data from external databases.
      • Raw meter data.
      • Partitioned data.
      • Processed data from the AWS Step Functions model training workflow.
    • AWS Lambda functions to do the following:
      • Load and transform topology data from an external database.
      • Process late-arriving meter data.
      • Obtain API query results of partitioned business data and SageMaker inferences.
    • An AWS Glue crawler to transform meter data from MDM and HES systems into partitioned data.
    • Amazon EventBridge to process and store late-arriving meter data in the correct partition.
    • An AWS Glue Data Catalog for a central catalog of weather, topology, and meter data.
    • Amazon Athena to provide query results of partitioned data.
    • Two AWS Step Functions workflows:
      • Model training to build an ML model using partitioned data.
      • Batch processing of partitioned business data from the Data Catalog and ML model data for use in forecasting.
    • Amazon SageMaker to generate energy usage inferences using the ML model. 
    • Amazon API Gateway to manage API queries.
  •  How to deploy

  • To deploy Utility Meter Data Analytics, follow the instructions in the deployment guide, which includes these steps.

    1. Sign in to your AWS account. If you don’t have an AWS account, sign up at https://aws.amazon.com.
    2. Launch the solution. The stack takes about 30 minutes to deploy. Before you create the stack, choose the AWS Region from the top toolbar.

    Amazon may share user-deployment information with the AWS Partner that collaborated with AWS on this solution.  

    View deployment guide for details
  •  Costs and licenses

  • You are responsible for the cost of the AWS services and any third-party licenses used while running this solution. There is no additional cost for using the solution.

    This solution includes configuration parameters that you can customize. Some of these settings, such as instance type, affect the cost of deployment. For cost estimates, refer to the pricing pages for each AWS service you use. Prices are subject to change.

    Tip: After you deploy a solution, create AWS Cost and Usage Reports to track associated costs. These reports deliver billing metrics to an Amazon Simple Storage Service (Amazon S3) bucket in your account. They provide cost estimates based on usage throughout each month and aggregate the data at the end of the month. For more information, refer to What are AWS Cost and Usage Reports?