As discussed in my last blog, Autonomation vs. Autonomous Analytics, transforming a facility to a fully autonomous smart building provides predictive actions based on the data from Internet of Things (IOT) devices, a Building Management System (BMS), and external data sources. To truly optimize occupant experience and building performance, the implementation of a data analytics tool to analyze large sets of data and provide actionable recommendations from the data is an industry imperative. Depending on the sophistication level of the data analytics tool, the value of the results will vary. Let’s review the four classic types of data analytics:
Now let’s assume a smart refrigeration system is failing. Here is the information organizations would expect to receive from each of these analytic types:
There is a fifth type of analytics you may be hearing about call Semantic. Semantic analytics incorporates artificial intelligence (AI) and enables the building to be self-aware. A smart building with semantic analytics figures out not only what is wrong and how to fix it, but semantics also provides the necessary “smart” information for an autonomous transaction to launch to correct the problem. Using the same smart refrigeration system scenario, here’s a potential semantic response:
I believe that the continued advancement of AI in analytics will find its way into the built environment. With other industries, such as healthcare or retail, access to data, and the analysis and effective use of the data evolves, leading to groundbreaking innovation. AI can be controversial and will need to be carefully and ethically implemented over time in the built environment This is sounding like science fiction, but like most science fiction from years past, it eventually becomes a reality.