Teradata AppCenter’s Web-based interface. (Image courtesy of Teradata.)
"With this announcement, we are making it easier for our customers to move sensor data around, optimize data management systems to deal with the massive volumes of data and run real-time, advanced analytics against streams of IoT data,” said Oliver Ratzesberger, president of Teradata.
Using the Teradata Aster Analytics tool, engineers can use machine learning techniques to better understand their IoT devices.
For Industrial IoT users (IIoT), these analytical tools can be used to reduce downtime, mitigate risk and better schedule maintenance. For designers, these analytical insights can be used to measure how a product is actually being used, where it is breaking and how to better optimize the next round of the product’s design.
IoT analytics can also be applied to other applications like administration, development and operations. Some assessments engineers can perform using Teradata’s IoT data analytics include:
- Early warning of failure
- Reducing warranty and repair costs
- Discovery of new revenue and pricing strategy (pay-by-the-hour or pay-per-use)
- Security alerts
- Reducing energy usage
- Reducing idle time
- Reducing part faults
- Geopositioning
Teradata’s IoT unit will also be updating their Listener tool to simplify the process to acquire and distribute sensor data for future analysis. The software is designed to manage the continuous streams of data collected by the IoT devices. This new connection speeds up the data transfer to the Teradata Unified Data Architecture on an on-premises or off-premises cloud.
Many of the machine learning tools created by Aster Analytics can be used on machines that have Java installed. Additionally, the Aster Scoring SDK (software developer’s kit) can also deploy Aster IoT analytics to various IoT edge servers, public clouds and data centers.
For more benefits of the IoT as well as IoT analytics, see Benefits and Challenges of the IoT for Engineering Businesses.