“Using Analytics is like Information Alchemy. You Can Turn Data into Money,”  said John Petze, Partner at SkyFoundry, developer of the SkySpark analytics platform. The statement set the tone of the Cor Advisors’ panel discussion November 12th entitled “Using Data and Analytics to Reduce Operational Costs.” The panel put to rest some of the biggest misconceptions about data analytics in the service of improving the energy performance and comfort of commercial properties. The speakers made a great case for getting started today. The following captures the panel discussion with some editing to improve readability:

Misconception #1. It’s All or Do Nothing

John Petze of SkyFoundry:

 “Some teams add an investment in analytics to their capital schedule—scheduling it a few years out when they think they will be more ready. It doesn’t work like that. Analytics is a journey. Unlike the installation of major capital equipment, you can start right away and in a limited way, expanding the activity as you learn and gain confidence. Many projects start with just metered energy data. With just that time-series interval data, you can identify when your building is starting operations too early or running too late, or operating continuously. You can save significant energy by just realizing that scheduling is wrong. With data from the Building Automation System, you can move to fault detection on equipment systems and down to individual devices and sensors. But, it doesn’t have to be real-time data, you can get tremendous value out of historical data.

It makes sense to drive the greatest value with the lowest investment. The incremental approach makes money and minimizes risk. With analytics you can prove value rapidly.  Then you can go further because you get the financial buy-in.

Matt Schwartz of Altura Associates:

There is usually a lot of low-hanging fruit. Most of the energy efficiency measures we implement are low- or no-cost operational changes. As a result, the investment required is low, and returns are high. Energy savings are measurable, and other long-term benefits like longer equipment life and lower total maintenance costs are directly attributable to running a more efficient facility. One of our clients, Pacific Medical Buildings (PMB) makes the analogy that it’s like healthcare delivery today: Diagnostics are now used to look at the whole patient to understand root causes, whereas once medical teams had just enough information to treat symptoms. In the same way, our Connected Building Commissioning process leverages analytics to help building operators be proactive rather than reactive to tenant complaints. Applying rules against BAS data enables an iterative, top-down approach when you are trying to identify and prioritize energy conservation measures across a whole portfolio of buildings.

Misconception #2. It’s more dumb dashboards

John Petze of Sky Foundry:

“Data analytics is taking knowledge of your best operators and translating it into machine-learning rules. Rules are software that identifies patterns in data—equipment faults, deviations from expected performance, actual results versus goals or benchmarks. The result is like an ever-present expert watching all systems 24X7 for sensors that have failed, systems that have been overridden—all the things that degrade performance. Buildings are too complex to be run by humans. Data analytics is the solution.”

Matt Schwartz of Altura Associates:

“A data analytics platform that connects right into the Building Automation System can serve as an automated whole-building diagnostics tool. The point is to write analytics that are actionable. You don’t want to add more nuisance alarms. If the building operator’s eyes glaze over when you suggest a rule, that’s a cue that his team won’t act on the results. You may be able to add that rule later when you’ve had some early wins and the team understands the process. We keep the focus on implementation and fixing the problems: action versus monitoring dashboards. With today’s remote connection capabilities, even our first visit to a building is not to investigate the issues. We’ve already imported data into the analytics platform and understand deficiencies and operational issues — space temperatures too high or too low, insufficient cooling capacity, equipment operating after hours, cycling and maintenance. By correcting these as soon as we get onsite, we save energy dollars immediately. Then, with connection to BAS data, we move to fault detection on bigger equipment systems and down to individual devices and sensors, like variable frequency drives not modulating as expected.”

Misconception #3.  Building operators don’t want it

Schwartz of Altura Associates:

“Building operators just need to interpret the reports, not become IT experts. It’s been our experience that they welcome the data support. The fact is that many have been making their buildings run, shooting from the hip without the engineering background and without data. The classic situation is that a new automation system is designed and installed to operate without intervention from the facilities staff. It runs for a few days or a few weeks until complaints start coming in. The needed adjustability is not there, so the operators just defeat the automation. That’s when you get the overrides that lead to waste, inefficiencies and malfunction. The analytics tools give them deeper insight into building data and provide support for their operations and maintenance decisions, as well as the documentation they need to better manage relations with their automation vendors. 

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 critical factor for long-term success.

So we engage building operators throughout the process. We give them ongoing training in the analytics. We create O&M-specific training documentation that references the analytics. We’ve rewritten the procedures for responding to hot and cold maintenance calls to include analytics steps. This is technology to make people better, not to replace them.

David Borchardt, Current Instructor at Georgetown University School of Continuing Studies Real Estate Program and Former Chief Sustainability Officer at The Towers Companies:

“Getting started with analytics is an investment in making your engineers smarter, helping them learn from each other.”

Misconception #4. IT won’t allow it

John Petze:

“IT people come in when the data is going to be communicated over their networks. There are security challenges with a live connection over the internet.  However, again, you could load historical BAS data as a .csv file and get a lot of value. For this, IT doesn’t need to be involved. So, prove value with just utility data, and then with just historical BAS data. With proof of results, your request for live connection to the Internet to get realtime data will get the necessary support. You may want to connect to the enterprise database to get realtime production data, such as square footage that is leased in an office, hours that kitchen equipment is in use for a restaurant,  the number of beds filled in a hospital. If you are going to access enterprise data and use a cloud-based service, IT will want to know what the security regime is.”

David Borchardt:

“It is important that the IT folks be engaged. In our case, IT hired the analytics company. We made the decision to allow these data analytics experts to drive the project. IT was experienced at defining such cloud service contracts. For example, in our contract, we said analytics supplier needed to give us the data back if we ended the contract.”

John Petze:

“Yes, owners need to know they can get their data. Here’s another point: Even with open protocols like BACnet and oBix, vendors can claim support but make slight formatting changes that make live connections brittle and incompatible with other systems that want the data. With movements like Project Haystack, the industry is moving toward self-describing or semantically-defined language that will make translation – the data cleansing step – more straightforward.

Misconception #5. ROI isn’t there

David Borchardt:

Our experience with the three Towers buildings was that analytics projects can be profitable. Savings from reduced electricity use in the first year alone exceeded total project expenses by more than $74,000. These results were achieved by non-disruptive operational improvements and no substantial capital investment. We could do some peak shaving and demand response once we got our buildings under control. This shortened our payback down to ‘as quickly as we could file and the money came in.’

Matt Schwartz:

ROI comes in many forms. Data is especially empowering in vendor relations. It’s hard to define the dollar value on data that helps to keep everyone honest in these relationships.  When there is a question about who is responsible for the automation framework not working, analytics lets building owners verify vendor implementation.  In one case, a vendor refused to make a change for an Altura client.  When the building operator sent over the visualized SkySpark data, the vendor was very quick to come out and fix the problem.  We then went through a few iterations, with the vendor making fixes and additional SkySpark analysis to verify the solution was correct. 

The panel event that was the source of the above conversation, is available as a webcast from CoR Advisors. It also included Darlene Pope, President and Founder of CoR Advisors, a consulting firm who advises building owners on energy efficient solutions for buildings; David Borchardt, who as Chief Sustainability Officer of Tower Companies, initiated and oversaw an energy management initiative in three large, multi-tenant office buildings in downtown Washington, D.C.;  and Matt Schwartz of Altura Associates, an innovator in the area of data-driven building commissioning.