The mission of this group is to bring together utility professionals in the power industry who are in the thick of the digital utility transformation. 

Post

Predictive Analytics Intelligence Is A Gold Mine For Business Bottom Line

image credit: © Ksenia Kolesnikova | Dreamstime.com
Michael Skurla's picture
Chief Product Officer Radix IoT

 Michael C. Skurla is the Chief Product Officer of Radix IoT–offering limitless monitoring and management rooted in intelligence–helping consolidate global Marketing and Product Viability,...

  • Member since 2020
  • 7 items added with 4,593 views
  • Dec 31, 2021
  • 695 views

With the exponential expansion of our automated world, IoT devices play an integral role in enabling real-time alarming, analytics, and even triage of potential problems. While data plays a major role in our daily business operations, the real value lies in providing access not just to the “now”, but information from the historical context of this data. Historical context access through analytics allows organizations to not only learn about current events but to predict and triage upcoming problems before they occur.

With the move to the industry 4.0, enterprises are regularly now integrating IoT infrastructure and legacy systems to help lower OpEx across various verticals. Addressing risks before they become disruptive, or costly to repair, empowers businesses to use the data they already have, but for a very different and forward-thinking purpose.

The Internet of Things (IoT) redefined our automated world’s relationship with data. It transformed data into the new oil. While the first generation of IoT platforms provided organizations with real-time alarming and event management to avert critical failures and problems without requiring on-site staff; they missed out on the historical context value of the same aggregated data. This is the refined data, now available via AI and ML engines and offering added real value to what was already there in the way of data.

This redefinition enables organizations to extrapolate additional actionable outcomes. Ideally known as the second generation of IoT solutions, these solutions re-delegated IoT’s role from a merely supplementary operation to a critical business operation. The digital ‘boots on the ground’ transformed already existing data into a valuable analytical solution within a system that organizations can tap into for additional and deeper data insight through the life cycle of an installation—and all remotely.

Thanks to the marriage of data infrastructure, IoT technology, edge computing, and telecommunications advancements, a wider range of previously unavailable capabilities and analytics now allow businesses to do much more in a very predictive sense. It is important to note that this analytics revolution is not confined to facility management. The full IoT ecosystems–from edge, through fog to cloud–offer greater possibilities to businesses to monitor processes and operations for stakeholders far outside of F+M. The once undervalued facility data now plays a major role within a range of other activities beyond–spilling over to logistics, staffing, marketing, safety, and others.

It’s important to note that all this new insight is gained by simply analyzing the same data, but with a different lens. IoT ecosystems are not about replacement, but reutilization of data for a more expanded set of use cases.

Fostering Predictive Analytics For Business Insight

Using real-time and historical data together helps determine patterns and predict future outcomes. An IoT platform has the capability for pattern adaptation based on operator’s contextual understanding. No single analytics platform knows all the trade secrets to operating a specific facility or portfolio of facilities–but an IoT platform enables an easy (non-programmatic) method to allow operators to set up these privately known factors to determine trends and enable predictive results.

While IoT platforms offer various customizable approaches to create predictive analytics on the fly, it is also common for businesses to use microservice analytics–software companies which rely on the core IoT platform for data but have special knowledge in specific verticals. Whether you choose to use an external microservice analytics service is completely optional and often depends on the specific use-case of the business. It is very common for an enterprise to enter an IoT platform model to focus on facility management, and use the platform for all of its analytics, but then realize there are uses for the same data when looked at differently through external service engines which offer advantages to other stakeholders far outside of F+M. (Examples of this include common facility technologies such as indoor positioning, space utilization, and people counting technologies)  

First generation IoT platforms consolidated data from legacy systems within a building and were the key to aggregating, organizing, and harnessing insightful data intelligence on scale. (Thousands of locations).  We are now really talking about taking a second step into using that data for a more holistic purpose.

While predictive analytics aren’t a recent phenomenon, integration and automation have been the real challenge. IoT platforms offer a native path to consolidated data that is aggregated across huge footprints, without significant programming, customization, or proprietary integration. This repository offers a single location to run analytics en mass.

The Cybersecurity and the Advancement of Purpose in Data

With Cybersecurity a major concern, IoT platforms address this problem from an I.T. perspective by nature, which is far ahead of that of the building management industry. Pattern detection and behavioral analytics allow organizational network administrators to locate and detect advanced persistent threats (APT) and abnormalities with predictive analytics capabilities. Security is a staple of these systems as they are born from the I.T. industry instead of their mechanical brethren.

With this data, organizations can expand upon resource management and operations by forecasting preventive maintenance and inventory requirements. Predictive analytics capabilities heighten business operations efficiency, transforming simple data into actionable insights, offering a competitive advantage for increased profitability. It can be as simple as “Why send a truck to investigate, and another with the solution, when you can do that in one truck roll before the problem even occurs?”  

We are in a shift from system integration to insights-as-a-service. Gartner estimates that by 2022, machines, not humans, will perform over half of the data and analytics services. They additionally predict that data, analytics and supporting technologies will increasingly live in the edge computing environment. Meaning ‘at the edge autonomy’ will be the decision maker in operations.

IoT platforms are the answer to getting actionable results from geographically distributed and disjointed sites and equipment. Simply put, there is no way to manage it any other way. They offer a gold mine of capabilities that previously were unrecognized but are now essential to our growing digital environment. Like oil, unrefined it is only a muddy mess, but when processed, it offers a wealth of differing practical applications that are truly life and business changing.

Michael Skurla's picture
Thank Michael for the Post!
Energy Central contributors share their experience and insights for the benefit of other Members (like you). Please show them your appreciation by leaving a comment, 'liking' this post, or following this Member.
More posts from this member
Discussions
Spell checking: Press the CTRL or COMMAND key then click on the underlined misspelled word.
Matt Chester's picture
Matt Chester on Dec 31, 2021

We are in a shift from system integration to insights-as-a-service

This is such an interesting trend, seeing everything move to 'as a service." But I suppose it helps specialize and get the maximum impact in all different business aspects

David Pope's picture
David Pope on Jan 5, 2022

Matt - while there are many opportunities to add value through an "insights-as-a-service" I believe this type of service will only replace a certain amount of "basic" type of analysis/tasks.  One reason for this belief is as soon as you provide useful insight based on a certain about of data, then further questions which usually requires other data sources from other systems start to come into play.  While some will say that's why all your data/systems should be in one cloud environment I don't think that solves all the issues, what do you think?

Matt Chester's picture
Matt Chester on Jan 5, 2022

Thanks for the insights David-- what you say sounds reasonable. There's obviously a limit and there is inherent value to keeping things in house and developing the expertise in your own employees. 

David Pope's picture
David Pope on Jan 5, 2022

Michael - I agree that predictive/preventive maintenance can be very valuable as long as the IoT platform is able to process the data and derive insights fast enough to take action will the value be realized.  Another challenge is earning the trust of the decision makers that the new information is valid and/or automating the process to the point that actions take place in real-time (if needed).  It's interesting to see that when people make mistakes in judgement we all try to learn from it in order to not repeat the same mistake twice, but when ML or AI cause a similar mistake it can cast doubt on continuing to use "data scientist". 

Michael Skurla's picture
Michael Skurla on Jan 18, 2022

So personally I think predictive analytics is a bit of a long game in most building automation. (Though I'll admit I'm really impressed with what some companies are doing with data). Prescriptive analytics, however (a phrase that is often lost), really has a place now, and I've seen them used highly effectively. The idea behind prescriptive analytics is that the system is designed in such a way that the user can easily insert their own logic for success based on their personal knowledge of problems and conditions, and these can change over time without 'technical expertise. For example, a facility engineer may know that if a fridge of model XYZ is consuming 2X the power in a week that most likely the compressor is going to go in the next month... This logic could be applied to the system to avoid a critical outage and addressed before the failure. This is where IoT platforms have really excelled. Instead of fixed alarming conditions, they offer a level of flexibility to adapt to their needs over time. Of course, you need a user that cares and wants to engage at this level, but that is becoming more frequent. 

Get Published - Build a Following

The Energy Central Power Industry Network is based on one core idea - power industry professionals helping each other and advancing the industry by sharing and learning from each other.

If you have an experience or insight to share or have learned something from a conference or seminar, your peers and colleagues on Energy Central want to hear about it. It's also easy to share a link to an article you've liked or an industry resource that you think would be helpful.

                 Learn more about posting on Energy Central »