Toronto Metropolitan University (Ryerson) Smart Campus Urban Data Platform

TMU brought IoT systems data together to gain insights & create an urban data platform for its smart campus initiative


About Toronto Metropolitan University

Located in the Garden District of downtown Toronto, Ontario, Toronto Metropolitan University (TMU) has approximately 50,000 students and staff on campus.

The University has eight faculties: the Faculty of Arts, the Faculty of Community Services, the Faculty of Engineering and Architectural Science, the Faculty of Law, the Faculty of Science, the Ted Rogers School of Management, the Creative School, and the Yeates School of Graduate Studies.

Challenge: Creating a Smart Campus

Like most university campuses, Toronto Metropolitan University (previously Ryerson University) generates millions of data points per day from HVAC systems, sensors, energy and water meters, Wi-Fi nodes, and IoT devices. In fact, the university has outfitted a number of buildings on campus with IoT sensors, generating 500,000 data records per day—adding up to 150 million records per year.

Initially, a test system streamed data from SCADA systems to hard drives, which was slow and vulnerable to outages. The disparate IoT systems across buildings were also never designed to speak to a third-party integrator. Another challenge was the varied nature of building data, with different kinds of data from different kinds of systems and formats.

University researchers wanted to bring all the data together to gain new insights and therefore started investigating how analytics could be integrated. In addition, Toronto Metropolitan University wanted to use its campus as a smaller model for a smart city.

Solution: Developing an Urban Data Platform

Toronto Metropolitan University chose to partner with FuseForward in developing a smart data platform as well as its smart city project. FuseForward’s consulting skills, combined with its extensive AWS expertise, made the company a perfect smart city consulting partner for the university, which has since become a member of the FuseForward Intelligent Systems Alliance, a network of academic and industry partners exploring advanced analytics. FuseForward also helped Toronto Metropolitan University receive a grant from the Natural Sciences and Engineering Research Council of Canada (NSERC), a federal funding agency for university-based research.

Incorporating Amazon Web Services (AWS) Data Services, FuseForward created a smart urban data platform for collecting data from smart buildings, smart transportation, and smart infrastructure applications. Starting with structuring, normalizing, and streaming the university’s data into a secure cloud environment, FuseForward immediately helped improve scalability, streaming data retention, compute capacity, and time-to-access for researchers and, ultimately, building managers.

The platform relies on the Amazon OpenSearch Service and MySQL databases to run queries and analyze data from air quality monitors, energy meters, and temperature sensors. Live data is analyzed with Amazon Kinesis Data Streams and AWS Lambda, a serverless compute service. Amazon Kinesis Data Firehose processes the data and stores it in Amazon Simple Storage Service (Amazon S3) buckets. University researchers use AWS Glue to prepare and process data and visualization dashboards running on Amazon Elastic Compute Cloud (Amazon EC2).

Together, FuseForward and the university also designed a digital twin of the Daphne Cockwell Health Sciences Complex. The digital twin serves as a 3D visual representation of structured data from the building, providing a real-time picture of equipment and spaces in the building while simulating scenarios such as the impact of shutting down utilities.

Results: Real-Time Big Data Visibility

Since implementing the urban data platform, FuseForward and Toronto Metropolitan University have increased the data retention rate from around 10 percent to more than 100 percent. Instead of having the data sitting on a server in each building, it’s all on AWS, which means it can scale to take on larger amounts of data going forward. The platform currently ingests and stores up to 8.4 million records per day.

The data coming from the digital twin is allowing the university to stop being reactive, enabling proactive decisions through data visualizations that help predict building behavior and run the buildings more efficiently. Machine learning is helping to identify energy usage patterns and detect anomalies.

In addition, the university’s department of civil engineering is using the digital twin campus to focus on 3D modeling and geospatial data analytics. The team is looking at thermal data analytics to try to monitor the energy efficiency of different buildings on campus, using data modeling to assess the quality of insulation and see if there are any leaks, for example.

Toronto Metropolitan University has found that the smart data platform is providing visibility into things that couldn’t be seen before. The team wrote an algorithm that uncovered a mislabeled CO2 sensor, which was labeled as a temperature sensor. Building automation systems usually can’t tell when sensors aren’t working, so that was something that was only discovered through the data science in the data platform.

Eventually, the university will use the digital twin as a small-scale model of a smart city. The team anticipates integrating building data with infrastructure data like water, foot traffic, and electricity. FuseForward also aims to take the experience gained from this project and other consulting and data analytics projects, as well as from the AWS Partner Smart Cities pilot program, to work closely with city governments to develop smart city solutions for them.

About FuseForward

FuseForward accelerates digital transformation for critical infrastructure providers such as cities, utilities, and transportation providers through consulting and technology expertise. With expertise across cloud, intelligent systems, advanced analytics, cybersecurity, and much more, FuseForward serves customers around the world from offices in Canada, Europe, and South Africa.

Case Study: Toronto Metropolitan University (Ryerson University) - Smart Campus

FuseForward partnered with Toronto Metropolitan University (formerly Ryerson University) to support their smart campus initiative with advanced data services & analytics expertise.


Enabling the Toronto Metropolitan University Smart Campus

Smart building technology has the potential to optimize energy consumption, improve occupant comfort, lower costs and improve emergency response.

Toronto Metropolitan University’s Smart Building Analytics group, led by Associate Professor Jenn McArthur, explores how utilities, transportation, building use, and human behavior can be optimized through insights generated by streaming data.

“In my work, I look at how to use data to improve the performance of the built environment,” explains Jenn MacArthur, Associate Professor at Toronto Metropolitan University (formerly Ryerson University)


Optimal work environments have social, medical and environmental benefits. How can we make spaces healthier for people? How can we make an office into a great work environment?

Jenn MacArthur, Associate Professor


A major Toronto Metropolitan University project is looking to create a single platform integration between building, infrastructure, location, and transportation data, with the aim of creating a “digital twin” replica of the campus, which will ultimately serve as a small-scale model of a smart city.

Toronto Metropolitan University (formerly Ryeron University) is a member of FuseForward’s Intelligent Systems Alliance, a network of academic and industry partners that explores the application of advanced analytics to concrete, real-world needs. Based on this common aim and to support their needs with regard to data services and modeling, TMU chose to collaborate with FuseForward as a strategic partner.

Supporting smart building research with secure data services

Large complexes such as university campuses can generate millions of data points per day from HVAC systems, sensors, energy and water meters, Wi-Fi nodes, and IoT devices.

An initial Toronto Metropolitan University test system streamed data from SCADA systems to hard drives, which was slow and vulnerable to outages. The first step was therefore to improve scalability, streaming data retention, compute capacity, and time-to-access for researchers and, ultimately, building managers.

To achieve this, FuseForward worked with Toronto Metropolitan University to structure, normalize and stream that data into a secure cloud environment managed by FuseForward, that incorporates Amazon Web Services (AWS) Data Services.

One of our challenges is that building data is really varied. There’s different kinds of data from different kinds of systems and formats, and we’ve got to bring them all into one place.

Jenn MacArthur, Associate Professor


As a result, machine learning tasks that previously took up to eight days are now completed in a matter of hours. The system is able to ingest 8.4 million records per day, while data retention has increased tenfold.

To structure and categorize data produced by buildings in the university environment, FuseForward drew on 30 years of experience in data modeling for complex systems to create a smart campus-specific ontology model. The ontology provides clear identification of data points and enables researchers to run queries regarding specific pieces of equipment or spaces.

Informing real-world action with digital twins

Two years into the project, datasets are being leveraged into practical applications. Toronto Metropolitan University is currently working on an interactive data visualization platform that will enable staff to view data trends for equipment or faculty rooms.

“You can look at any given space and see any complaints alongside your current data stream,” Jenn says, “For example, temperature sensors in a room where people are complaining about feeling too cold. By bringing everything into one common environment, you can both troubleshoot and make knowledge-based decisions.”

A digital twin, or digital replica, acts as a visual representation of structured data from a building or a physical asset. Data modeling for the 19-storey Daphne Cockwell Complex, which hosts student residences on top of the university’s Health Sciences faculty, has enabled TMU to complete a full digital twin of the building.

The recently-built complex hosts over 10,000 building automation system (BAS) points which, via its digital twin, provide an in-depth look into the building’s energy consumption, environmental performance, airflow, and potential congestion in a single interface.


digital twin

Embedded with IoT devices during construction, the Daphne Cockwell Complex was the first candidate for virtual simulation.

Using streaming data, the digital twin of the Daphne Cockwell Complex provides facility managers with a real-time view of building operations.

Digital twins provide building managers with a real-time overview of equipment and spaces, but also enable them to simulate events and scenarios, such as fire drills or the potential impact of shutting down certain utilities during vacations, before taking real-world action.

FuseForward provided the necessary cloud analytics expertise and tools to manage and analyze the massive amount of data coming in from the real buildings and simulations in the digital twin.

At this point, digital twins for the other campus buildings are restricted to space management information as TMU works towards creating a full digital replica of the entire campus.

“We’re in the process of populating those replicas with data. All data will be tagged consistently with the ontology developed with FuseForward, which is going to make it so much easier for us to bring it inbound and online,” Jenn says. “A digital twin is the data behind it. If you don’t actually have that, it’s just pictures, rather than something that’s truly ‘smart’.”



Results of our work

Ingestion and storage of up to 8.4 million records per day


calculation engine

Tenfold increase in streaming data retention, from 10 to 100%


Highly secure data storage and analytics environment based in Canada


Smart campus-specific ontology model that structures data


Optimizing building systems through predictive analytics

The next steps of the project will involve using machine learning to identify usage patterns, detect anomalies and optimize the campus environment. “We’re starting to look at building event detection algorithms to detect system points that aren’t behaving as they should be,” Jenn explains, “We should get to the point where we’re able to predict when a boiler will need maintenance, and if it’s worth doing it straight away or waiting until a vacation shutdown. Being able to predict faults before they’re visible can help prevent serious damage costing thousands of dollars.”


Next steps: replicating our success across other industries

Toronto Metropolitan University and FuseForward will expand this research through the Smart Campus Integration & Testing (SCIT) Hub. This new facility will provide researchers with a realistic environment in which to experiment with smart building technology and look at how IoT devices can work as part of integrated systems without impacting residents. The lab will comprise a fully equipped remote operations centre connected to building systems throughout the campus.

Data-generated insights have the ability to optimize not only campus environments, but also asset-intensive organizations, such as hospitals, industrial plants, cities, and transportation agencies among many others. FuseForward and Toronto Metropolitan University look forward to continuing to collaborate over the years to come.


I hope this will become a 20-year partnership. I’m looking forward to seeing how far we can push up.

Jenn MacArthur, Associate Professor