Just keeping the lights on in manufacturing plants with thousands of sensors and counters monitoring the production. Just data collection is useless if you don't put it on good use and that requires some aggregation and correlation to tell what is going on on the floor.
My only infrastructure/data analytics experience outside of standard RDMS is with AWS so anytime I mention an AWS service feel free to substitute a non AWS/open source alternative...
For aggregation and reporting my usual go to would be Redshift - a custom AWS version of Postgres that uses columnar storage instead of rows and/or something like Kinesis (aka similar to Kafka) for streaming data and real-time aggregation while the data is being captured.
