Cognitive Computing

Elevating working and living environments to a new level

Share this post:

How cognitive buildings are evolving to learn, adapt and react

The famous German-American architect Ludwig Mies van der Rohe said “Architecture starts when you carefully put two bricks together. There it begins.”

Joern Ploennigs, research staff member, IBM Research-Ireland

Joern Ploennigs, research staff member, IBM Research-Ireland

“I wonder what he would think when we add IoT to those bricks,” said Joern Ploennigs, a scientist at IBM Research – Ireland, who has always been fascinated with buildings.

Whether it was the influence of his father, who was an architect, or his own innate interest in how things work while growing up in Germany, Joern wanted to improve people’s lives through design.

Eventually this led him to pursue a research career where he could apply his interests in automated system design, semantic modelling, fault detection and diagnosis, as well as wireless sensor networks to inject cognitive computing into architecture. Joern’s vision is to create cognitive buildings by combining IoT technology, machine learning, reasoning and augmented reality, to help the humans who design, operate, maintain, and live and work in buildings.

The number of IoT devices in buildings is rapidly increasing alongside new requirements for flexible operation of climate, lighting, and other energy control systems. Cognitive buildings are able to autonomously integrate IoT devices and learn system and user behavior. And they have evolved to actively learn and adapt, making them aware of their own energy performance, and balance it with the comfort of its occupants.

Joern is the principal investigator for two EU-funded H2020 projects focused on cognitive building applications. The first of these two projects is called Tribute. Joern’s team is studying how occupants use their buildings to identify ways to reduce energy consumption. The project collects and mines a building’s energy data  and compares the performance against its intended efficiency from building energy performance simulations. This toolkit will evolve the building model from “as built” to “as is” and then to “as it will be” to predict the best way to minimize a building’s energy impact.

The second H2020 project is TOPAs (Tools for Continuous Building Performance Auditing). After the three-year study, TOPAs will provide decision support tools for building and facilities managers to more effectively manage their site, such as providing visibility on how decisions impact energy related occupant comfort and health. Joern’s team is particularly interested in the energy flow within a campus, and how machine learning can correctly predict energy consumption and detect and diagnose energy waste.

Joern doesn’t have to travel far to apply his technologies since the IBM Research – Ireland lab is currently being used as a demonstrator site in both projects. The research facility is a “living lab” that provides real-time data from thousands of sensors on heating, cooling, lighting, water, electricity, and presence. This data is used to create comprehensive energy usage models and real-time reports, providing deeper insight into how the space is being used, how the infrastructure is performing, and where resource usage can be optimized.

Recently, Joern has also begun scaling his cognitive building vision to a new level of cognitive operations for large groups of buildings or campuses. His latest demo builds on IBM’s Watson IoT platform to create eight cognitive IoT use cases with several buildings, including a datacenter at the IBM Technology Campus in Dublin, Ireland – a rich test environment with more than 3,000 sensors. These use cases (pictured below) show how cognitive operations solutions will drive predictive maintenance and integrate new immersive virtual and augmented reality interfaces.

Cognitive Operations Use Cases

Cognitive Operations Use Cases

Live Demo at Cognitive Buildings Forum

Joern’s work was recently presented by John Cohn and Claire Penny at the Cognitive Buildings Forum in London, organized by Watson IoT and Wired magazine. At the event, Joern himself investigated the social sentiment of iconic buildings around the world using Watson APIs from Twitter Insights and Alchemy.

Together with fellow IBM scientist Paulito Palmes, he analyzed 5 million tweets and extracted the sentiments of the world’s most tweeted buildings of 2015. Who would have guessed that the Space Needle in Seattle, Washington is the most positively perceived building, and that the Louvre is infamous for its air conditioning, while the Sidney Opera has the best facilities? What buildings would you tweet about?

More Cognitive Computing stories

Meet Ari, the Smart Bike that Helps you Catch Green Lights

As more bikes take to the city streets than ever, researchers at RMIT have designed Ari, a smart e-bike that could help riders cruise the ‘green wave’.

Continue reading

Making Sense of Neural Architecture Search

It is no surprise that following the massive success of deep learning technology in solving complicated tasks, there is a growing demand for automated deep learning. Even though deep learning is a highly effective technology, there is a tremendous amount of human effort that goes into designing a deep learning algorithm.

Continue reading

IBM Researchers Design Winning AI Algorithms for Drones

For the second year in a row, researchers at the IBM-Illinois Center for Cognitive Computing Systems Research(C3SR) won a competition challenging experts worldwide to design low-power embedded systems for Internet-of-Things (IoT) applications. The 2019 Design Automation Conference (DAC) System Design Contest’s objective: create algorithms that can accurately detect and locate objects from images taken by […]

Continue reading