Page 55 - index

John Petze of Sky Foundry explains the process of working include analytics steps. This is technology to make people better,
through the machine-learning: “Data analytics is taking knowledge not to replace them.”
of your best operators and translating it into machine-learning
rules. Rules are software that identifies patterns in data—equip- So what will a whole-building collaboration hub for such on-
ment faults, deviations from expected performance, actual results going O&M content soon look like? Team chat platforms like the
versus goals or benchmarks. The result is like an ever-present Slack app that integrate popular general-business services (Google
expert watching all systems 24/7 for sensors that have failed, Drive, Dropbox, etc.) with messaging and notifications are a start.
systems that have been overridden—all the things that degrade
performance.” Other integrations might be separate apps for HVAC, lighting,
and access security. Even dynamic glass windows are controlled
The CMU team is using their research as a launch point for a via intelligent algorithms designed to ‘learn’ user preferences, so
mobile app they are developing that will interact with building there will be an app for training those machine-learning rules
automation systems, enabling users to adjust lighting and tem- too. Then the hub will need to gather the notification streams
perature from their smartphones. This app builds upon OSIsoft’s of building operational analytics software like Sky Foundry’s
PI database system to capture streams of data and compile them SkySpark® and OSIsoft’s PI. Likewise, maintenance-call and
into a single source, and Microsoft’s Azure ML for writing ma- job-tracking services within enterprise workplace management
chine-learning rules to run against the gathered data. suites will need to be integrated. Slack boasts that all content
integrated into the platform becomes “instantly searchable, and
Building Robotics’ Comfy app is based on a similar premise— available wherever you go.” That’s what you want, even extend-
using people and their mobile devices as the sensors for the ing to archival content. Self-learning would be enhanced if there
building. VP Lindsay Baker explains how she sees mobility tech were apps for sites like automatedbuildings.com and realcomm.
permeating the world of building operations and facilities man- com where seekers could find the wealth of information they’ve
agement in the future: “Mobile devices will also become the inter- published on building operations and facilities management
face for the building. If you don’t like the light, you’ll pull out your over the years.
phone and change it. If you see something broken, you’ll snap
a photo and send it to the facility manager. In this way, mobile Writer/analyst Therese Sullivan reports about technologies and
devices will allow us to do what we’ve always wanted to do, which trends in data-driven commercial buildings via her blog, www.
is to have a better way to interact with occupants in buildings, in a BuildingContext.me. She also runs a content marketing agency
way that’s positive and manageable for the facilities team and the that serves a mix of clients including top energy management
workers in the building. Engaging occupants in helping to make and commissioning firms, brand-name data infrastructure
the building run smoothly, save energy, participate in Demand companies, and exciting new start-ups in building energy
Response events, hold competitions—these will all be significantly efficiency.
easier to do.”

When it comes to the ‘train-the-trainers’ task of engaging
building operators and occupants in inventing and refining ma-
chine-learning rules, Matt Schwartz, commissioning expert with
Altura Associates had this to say: “By introducing data analytics,
Altura has been able to shift our clients to proactive building
management. They don’t have to learn programming, but the
entire team does need to reprogram their thinking—the facility
engineers, property managers, asset managers and ownership.
It does take changing human processes to make this shift. Altura
places great emphasis on the people aspect because it’s the criti-
cal factor for long-term success. So we engage building operators
throughout the process. We give them ongoing training in the
analytics. We create Operations & Maintenance-specific training
documentation that references the analytics. We’ve rewritten the
procedures for responding to hot and cold maintenance calls to

Realcomm 53