The formidable processing power and analytical tools available in public clouds could make industrial IoT more effective and less expensive. But bringing IoT data into the cloud takes more than a network connection.
On Tuesday, two companies moved to help enterprises adapt their IoT data for popular cloud services. OSIsoft introduced its PI Integrator for Microsoft Azure, and Particle announced a custom integration with Google Cloud Platform.
While some large enterprises with sensitive IoT data do all their analytics in-house, public clouds offer greater scale and better security than many organizations can achieve on their own, MachNation analyst Dima Tokar said. And more advanced analytics, including better error correction, in some cases can give enterprises the same insights with fewer sensors, he said. Trading hardware for software -- especially the cloud-based kind -- typically means savings.
OSIsoft’s PI Integrator software cleans up the data captured by its PI System IoT platform, such as a chronological record of everything that happens in an industrial plant, and makes it ready for machine learning by the Cortana Intelligence Suite in Azure. With the new software, the data can retain its original order after it's been analyzed in Azure, OSIsoft says.
Some PI System users today write custom code to prepare their data for analysis. This tool can replace that effort, according to the company.
OSIsoft says one of its customers, Deschutes Brewery, used the PI Integrator to take advantage of Cortana’s machine learning and avoided installing US$750,000 worth of meters on its fermentation tanks. Instead, Cortana uses historical and contextual information to predict when the next phase of fermentation will begin.
OSIsoft is collaborating with Microsoft on an incubation program for selected early users of the PI Integrator. The company introduced a similar tool for the SAP Hana analytics platform last year.
Particle, which sells hardware and software to develop and produce IoT devices, has integrated its platform with Google Cloud Platform so customers can apply the full suite of Google Cloud services to their products. Those services include Prediction API for machine learning, the Cloud Datastore NoSQL database, and the BigQuery data warehouse.
The integration is built into Particle’s console so it can be easily activated, the first time the company has integrated a cloud platform to that degree, Particle said.