Build with an Azure free account. Get USD200 credit for 30 days and 12 months of free services.

Start free today

Azure Time Series Insights – end-to-end solution for industrial IoT analytics

Play Azure Time Series Insights – end-to-end solution for industrial IoT analytics
Sign in to queue

Description

To help maximize the value of time series data and drive operational intelligence, Azure Time Series Insights introduces support for a broad range of industrial IoT analytics capabilities. Check out, Chandrika Shankarnarayan, Principal PM Manager for Azure Time Series Insights, showing the new capabilities in this space.
 
Learn more about Azure Time Series Insights: https://azure.microsoft.com/en-us/services/time-series-insights/
Create a Free Account (Azure): https://aka.ms/aft-iot

Embed

Download

Download this episode

The Discussion

  • User profile image
    Mark

    Please can you provide guidance on how you create/manage the hierarchy (on the left)?

  • User profile image
    Rahul K

    Hi Mark, Please refer to this document for guidance on authoring a time series model - https://docs.microsoft.com/en-us/azure/time-series-insights/time-series-insights-update-how-to-tsm

  • User profile image
    Neil MacMullen

    This is very interesting and we'd like to use it for our application (asset tracking of reusable packaging) but at first glance it looks like there are a few limitations that restrict its applicability. 1. The product (at least the demo) seems to be based around charts of measurements. We're generally more interested in location-names and typed-events. 2. A key concept for us is a 'visit' which is where a sensor stops at a location for a span of time. Since sensors report periodically there are always visits whose end-time are likely to be revised with new information. Is there any way for TSI to revise data that has already been ingested? 3. Almost all useful queries in our application involve associating a location-name with the query target. E.g. we might be interested in knowing that a high temperature was recorded at a certain warehouse. To do that we have to find the visit that spans the temperature timestamp. As in (2) because visit records can't be known to be complete at the time we ingest them, we can't just add a location column to the measurement. I'm pretty sure these are relatively common concerns in asset-tracking. Are they are any plans to extend the offering to better address this area?

Add Your 2 Cents