Prerequisites - Amazon IoT SiteWise
Setup Amazon CLI for Computation Model APIsProperty requirementsLabeling prerequisitesModel evaluation prerequisites
Services or capabilities described in Amazon Web Services documentation might vary by Region. To see the differences applicable to the China Regions, see Getting Started with Amazon Web Services in China (PDF).

Prerequisites

To complete these steps, you must have an asset model and at least one asset created. For more information, see Create an asset model (Amazon CLI), and Create an asset (Amazon CLI). We do not support external IDs at this time.

If you are new to Amazon IoT SiteWise (and do not have historical data), you must call the CreateBulkImportJob API to import asset property values into Amazon IoT SiteWise. This is used to train the model. For more information, see Create an Amazon IoT SiteWise bulk import job (Amazon CLI).

Setup Amazon CLI for Computation Model APIs

Follow these steps to update your Amazon CLI configuration, and access the computation model APIs:

  • Install the latest awscli version aws-cli.

  • Verify the installation by checking for the new APIs:

    aws iotsitewise help

The command output displays the complete list of Amazon IoT SiteWise APIs, including the newly added computation model operations.

Property requirements

To set up anomaly detection, you must have the following requirements and the UpdateAssetModel (Amazon CLI):

  • At least one input property that is of either DOUBLE or INTEGER data type. It is either a measurement or transform property, and is used to train the model.

  • A result property of STRING data type. It must be a measurement property, and stores the anomaly detection results.

Labeling prerequisites

  • Upload your data labels to an Amazon S3 bucket.

  • Update the bucket policy of this bucket to allow Amazon IoT SiteWise to read your labels.

    On console, go to Permissions -> Bucket policy. Paste the following policy and replace bucket-arn with ARN of your bucket.

    {
     "Version": "2012-10-17",
     "Statement": [
         {
             "Sid": "SiteWiseReadAccess",
             "Effect": "Allow",
             "Principal": {
                 "Service": "iotsitewise.amazonaws.com"
             },
             "Action": [
                 "s3:GetObject",
                 "s3:ListBucket"
             ],
             "Resource": [
                 "bucket-arn",
                 "bucket-arn/*"
             ]
         }
     ]
 }

Model evaluation prerequisites

  • Model evaluation generates pointwise model diagnostics in the Amazon S3 bucket location provided by you.

  • In order for the pointwise diagnostic results to be written to your Amazon S3 bucket, update the bucket policy of this bucket to allow Amazon IoT SiteWise to write the results.

    On console, go to Permissions -> Bucket policy. Paste the following policy and replace: bucket-arn with ARN of your bucket

    {
      "Version": "2012-10-17",
      "Statement": [
          {
              "Sid": "SiteWiseWriteAccess",
              "Effect": "Allow",
              "Principal": {
                  "Service": "iotsitewise.amazonaws.com"
              },
              "Action": [
                  "s3:GetObject",
                  "s3:ListBucket",
                  "s3:PutObject"
              ],
              "Resource": [
                  "bucket-arn",
                  "bucket-arn/*"
              ]
          }
      ]
  }