How to make smart building data smarter

0


Too much data is as useless as no data. Here’s how to convert smart building data into reliable, useful and actionable information.





At some point in your career, you’ve probably sat down at your computer and looked at a spreadsheet with rows and rows of numbers, and you’ve been like, “This is completely useless to me. I have no earthly idea what this is trying to tell me.

It’s a universally accepted truth: too much data is just as bad as no data.

“Data by itself has no intrinsic value,” says Isaac Chen, vice president of technology systems creation for WSP. “Turning data into information is the goal. ”

So how, in this environment of increasing sophistication of building systems, do you do this? The challenge is really twofold: First, how do you create a smart, robust, interoperable, and integrated building automation system that can deliver the data you want in the format you need? And second, how to extract and present this data from this system so that it is usable, and without suffering from paralysis by analysis?

These are difficult questions, made more difficult by the fact that most buildings already have a system in place.

“Most commercial buildings were built before 2000, and most control systems are even older than that,” says Paul Ehrlich, Founder and Chairman of Building Intelligence Group. “You have a mix of old and obsolete systems with brand new ones. ”

Interoperable integrated intelligence

So let’s say your existing system – however you control your various building systems, measure results, analyze that data, and present it – needs a little work. Where to start ? Do you take everything apart and start over? Do you buy new analysis and control packages and hire an expensive system integrator to tie it all together? Are you just adding layers on top of what you already have?

Each building will be different in how it should approach interoperable building systems. It will depend on your existing systems, your existing contracts with suppliers, your budget, your own expertise and the expertise of your facilities management department.

“As an industry, we tend to layer more and more tools on top of each other,” says Saagar Patel, operations manager, Energy + Eco, for Environmental Systems Design. “This is where the problem comes in, because then you have redundant data streams. You have too many different technologies overlapping.

This is an issue you are probably familiar with: mission creep of building systems. Things have been added over the years to the point that the original system – and more importantly, how it’s supposed to work – is virtually unrecognizable.

And it doesn’t get any easier. For example, Internet of Things (IoT) technology and devices are often touted as a silver bullet to building automation problems. After all, these devices are meant to be plug and play.

“The IoT has opened the door to more device and sensor options because it’s easier to modernize sensors on everything and dramatically expand the functionality and capabilities of those sensors and devices,” says David. Quirk, Senior Director, DLB Associates.

So the IoT has improved functionality, but has it improved interoperability, especially when it comes to the way data is extracted or presented? The answer at this point is a bit hazy, say experts, who suggest that some IoT devices sometimes create more problems than they solve.

“In some ways, the IoT is making it harder right now,” Quirk says. “They are only interoperable on their individual cloud platforms. The only common point today is that everything converges to an IP protocol.

Patel agrees: “The IoT is in a state of entropy, just complete chaos, but in a good way,” he says. “We’re all trying to figure out the best way to move forward with IoT. ”

According to Chen, a new term is being used in the industry that describes a way of thinking about integrating old and new systems: Cyber-Physical Systems (CPS). While not specific to buildings, cyber-physical systems integrate sensing, computing, control, and networking into physical objects and infrastructure, connecting them to the Internet and to each other, according to the National Science Foundation. From a buildings perspective, CPS is essentially a way of thinking about integrating devices and systems into a holistic smart building. So while experts agree that we are still in the era of building automation system, holistic smart building is the future. And that’s how you should think about your building systems.

Incoming data, outgoing data

So what about the data that all of these systems produce?

“Facility managers have always been responsible for all building systems, HVAC, controls, power distribution, elevators, plumbing, and so on,” says Ehrlich. “The challenge is that they’ve never had a lot of data with these systems. Or the data wouldn’t be actionable because it was just raw data – there was no trend, no analysis, no way to see what the data meant in the real world.

Nowadays, the problem is almost the opposite: too much data, or data that is unsorted, not analyzed, and then largely ignored.

“The data doesn’t tell you what’s wrong,” explains Quirk. “It only gives you points.”

One of the first steps in data management is to identify who needs to see what.

“One of the biggest problems is not identifying the right stakeholders,” explains Quirk. “You need to know what kind of information each stakeholder needs and how they need it to be presented. ”

Patel agrees: “Data requirements are stakeholder based,” he says. “How the data is presented depends on who wants to see which data. It is really important to understand the needs and wants of everyone who might have access to the data.

Patel recommends setting up systems to manage data with web-based dashboards so that, for example, an energy manager logs in, that person only sees data related to energy efficiency or emissions. carbon, and not, for example, the preventive maintenance schedule for elevators.

Categorizing or categorizing this data for proper dissemination is a huge undertaking. Chen says the data fits into three levels. First there is the raw data, otherwise known as aggregate data, or if you want to be really whimsical, the “data lake”. The Data Lake is the “place” where all data from sensors, external systems (such as climate and weather data), air quality readings, etc. are collected. The second level is the database, where the aggregated data begins to be sorted into a format that can then be analyzed. The third is the data analysis engine. This is where the rubber meets the road, Chen says. Analytics provide the information the facility manager needs to make decisions. Instead of those notorious rows and columns in a spreadsheet, this is what you hope to see when you sit at a computer or watch a mobile device. “It’s what makes your life easier,” he says.

One solution to help you get the correct data collection, aggregation, dissemination, and analysis is monitor-based provisioning, Patel explains. It is essentially a continuous, real-time commissioning process in which a building is constantly being tuned in. The integration of artificial intelligence or machine learning into analytics engines, a niche practice still today but whose adoption is increasing daily, means that the building can actually adjust.

Ultimately, data management is all about measuring what needs to be measured, analyzing those metrics, and putting that information in the hands of the right experts to make the right decisions.

“If and when we use the data correctly, plant managers will reap huge benefits,” says Ehrlich.

Failure detection or alarm fatigue?

A key component of any successful monitor-based commissioning program is a fault detection and diagnosis (FDD) system. FDD can tell you both when something is not working, like a stuck-open shock absorber, but also if a particular measurement, like indoor humidity, is outside an expected range.

One of the biggest challenges in setting up a useful FDD system is what is known as “alarm fatigue”. become too bulky.

“We tend to abandon these systems because of these issues,” Patel explains. “These tools are not set and forget it.”

So, to be effective, FDD must be properly tuned.

“You have to develop a robust filtering system,” explains Quirk. “You have to order the devil from FDD or it’s going to be garbage. And that means tuning the system over several seasons. If you shorten this process, it will never work properly and you will never get any use out of it.

FDD is supposed to be a system that makes your life easier, not harder. Ideally, it takes data from all of your sophisticated sensors and building systems, and boils it down to what you need to know in the sense of telling you if something is wrong. But again, it takes a bit of front-end work to make it useful. This involves prioritizing the sensitivity of the system and identifying which events are critical enough to be alarm events, and which events could be included in an end-of-day or weekly summary email.

To do this, “machine learning and AI are your friends,” Chen explains. “They can help build the model on what should be the most important. They can help identify the true cost of any incident and stop false alarms. Chen mentions a project at a hospital he worked on that reduced critical alarms to just 10%, so facility managers could essentially ignore the remaining 90% and therefore be much more productive. “It’s so much more manageable that way,” he says.

And that’s the catch: creating a system to make data manageable and pragmatic with a combination of smart systems and analytics. Not only can you not manage what you don’t measure, but you can’t actually use what you measured if you don’t analyze it and make it actionable.

Greg Zimmerman is Associate Editor in the Facilities Market. He has 18 years of facility writing experience, with a particular focus on sustainability, health and wellness, and the evolution of smart buildings.




Related topics:

comments


Source link

Leave A Reply

Your email address will not be published.