IoT Platform:Intelligent baseline

Prerequisites

• A device is connected to IoT Platform. For more information, see Create a product.

• A device diagnostics feature is enabled. For more information, see Enable or disable device diagnostics features.

Background information

To effectively utilize the intelligent baseline feature, it is important to understand the following two concepts:

• Intelligent baseline training algorithm: This algorithm runs daily in the early morning to generate an intelligent baseline prediction model for each intelligent baseline.

• Intelligent baseline prediction algorithm: This algorithm operates every minute to produce a metric value based on the minute's metric data and the intelligent baseline prediction model.

  

Create intelligent baseline

1. Log on to the IoT Platform console.

2. In the upper-left corner of the console, select the region where your target Enterprise Edition instance is located. Then, on the Instance Overview page, find the corresponding Enterprise Edition instance and single click its name.

3. In the left-side navigation pane, select Monitoring & Operations >Device Diagnostics, and then single click Intelligent Baseline.

4. On the Intelligent Baseline page, single click Create Intelligent Baseline. In the dialog box that appears, configure the parameters and then single click OK.

   Parameter	Description
   Intelligent Baseline Name	Assign a name to the intelligent baseline for easy identification. It supports Chinese, English letters, numbers, and underscores (_), up to 32 characters in length. You can modify the name after creation. Once the intelligent baseline is established, it supports modifications.
   Chart	Choose the detection metric for the intelligent baseline. For available metrics, refer to Metric Description in this topic.
   Product	Select the product to be monitored by the intelligent baseline, either All Products or a specific product.
   Alert Sensitivity	The alert sensitivity level determines the frequency of alert generation. You can adjust this setting after creating the intelligent baseline. Once the intelligent baseline has been established, it supports modifications.

View intelligent baseline detection information

Once the intelligent baseline is successfully established, you can view its detailed information in the list.

The Status column in the list reflects the daily training status of the intelligent baseline training algorithm.

• Training: The intelligent baseline is less than 14 days old and has not completed its training.

• Training Abnormal: The intelligent baseline is at least 14 days old, but due to insufficient metric data or the average metric data not meeting the minimum training standards, the training has failed for the day.

  Note

  The intelligent baseline training algorithm updates the training status after executing each early morning. If the status is Training Abnormal, check the intelligent baseline status the next day to see if training has succeeded.

• Training Successful: The intelligent baseline is at least 14 days old, and the metric data volume and average value meet the training standards, resulting in successful training for the day.

  Note

  Following successful training, the intelligent baseline prediction model remains valid for 30 days. The intelligent baseline feature operates normally within this period, and intelligent baseline alerts can be generated. If training fails for 30 consecutive days, the prediction model will become invalid.

• Single click the icon next to the metric name to view the metric line chart.

  The metric line chart displays:

  Chart Data Item	Description
  Metric Value	Shows the real-time value of the metric.
  Intelligent Baseline	Represents the intelligent baseline value predicted by the machine learning algorithm based on historical data, as output by the intelligent baseline prediction algorithm.
  Anomaly	Indicates if the current metric value is abnormal, as determined by the intelligent baseline prediction algorithm.

  Important

  Common reasons for the absence of intelligent baseline values in the metric line chart include:

  • The intelligent baseline is less than 14 days old and has not begun training the model.

  • The intelligent baseline is at least 14 days old, but due to insufficient metric data or the average metric data not meeting the minimum training standards, training has not been successful.

  • The intelligent baseline is at least 14 days old and was successfully trained, but it has been over 30 days since the last successful training, rendering the model invalid.

Enable alert notification push

In the intelligent baseline list, single click the Alert Notification Push column's icon to activate alert notifications for the intelligent baseline and push alerts to CloudMonitor.

Before using intelligent baseline alerts for the first time, click Alert Notification Configuration at the top of the page. In the Alert Notification Configuration panel, select the alert notification recipient and alert level, and click OK.

After configuring alert notifications, click View Alert Records in the Operations column to review and manage alert content in batch.

Metric description

The intelligent baseline supports the detection of the following data metrics: