Models

A machine learning model contains algorithms that analyze what happened in the past to help us do better in the future.

In Arundo Edge, you can stream tag data into models, execute the model logic, and then view visualizations of the model output.


Deploying Models to Arundo Edge

To use a machine learning model in Arundo Edge, you must first deploy the model from Arundo Edge Manager or Arundo Fabric.

Deploying a Model from Arundo Edge Manager

Complete the following to deploy a machine learning model from Arundo Edge Manager to Arundo Edge.

Prerequisites

Verify your device meets the system requirements​

Install the latest version of Docker Desktop/CE (Windows / macOS / Linux)

Start Docker and keep it running

Build the model into a Docker image and add it to your Docker registry

Instructions

  1. Access Arundo Edge Manager.
  2. Select Docker Images on the sidebar.
  3. Click Deploy next to the image containing the model.
  4. Select Model (Deploy image to an edge as a model).
  5. Enter the name of the model.
  6. Complete the following for every model endpoint you want to define:
  7. Click Add endpoint.
  8. Enter a name for the endpoint.
  9. Select Update Criteria for the endpoint.
  10. Add input tags for the endpoint.
  11. Add output tags for the endpoint.
  12. Click Start.
Deploying a Model from Arundo Fabric

Complete the following to deploy a machine learning model from Arundo Fabric to Arundo Edge.

Warning

You need an Arundo Fabric subscription to use this feature.

Prerequisites

Verify your device meets the system requirements​

Install the latest version of Docker Desktop/CE (Windows / macOS / Linux)

Start Docker and keep it running

Publish the model into Arundo Fabric

Set up a Cloud interface between Arundo Edge and Arundo Fabric

Instructions

  1. Access Arundo Edge.
  2. Open the System menu and select Upload Configuration to Fabric.

    Upload Configuration

  3. Access Arundo Fabric.

  4. Select Models on the Navigation bar.
  5. Locate the model in the Models list.
  6. Click Deploy to Edge next to the model.
  7. In the Edge Agents list, select the edge device where you want to deploy the model.
  8. Under Endpoint Configuration, select the tags to use for the model's inputs and outputs.
  9. Click Deploy.

Viewing Model Output in Edge

Complete the following to view the calculated outputs for deployed models.

Prerequisites

Install the latest version of Docker Desktop/CE (Windows / macOS / Linux)

Start Docker and keep it running

Instructions

  1. Select Viewer on the sidebar.
  2. Open the Graphs tab.
  3. Move down to the Models section. Graphs showing the output for deployed models now display.

    Model output


Managing Models

Complete the following to manage deployed models.

Editing a Model
  1. Select Compute Chain on the sidebar.
  2. Locate the model in the list.
  3. Click Edit next to the model.
  4. Make changes as necessary.
  5. Click Update.
Deleting a Model
  1. Select Compute Chain on the sidebar.
  2. Locate the model in the list.
  3. Click Remove next to the model.
  4. Click Yes to confirm.