What is a Digital Twin?
A Digital Twin is a repository of facility structured and unstructured data. It also has descriptive operational and engineering models to capture the conditions of its facility and key indicators. A Digital Twin also enables the testing of futuristic models or scenarios in the virtual world before implementing them.
However, a Digital Twin is not just a repository of data. In addition to data, a Digital Twin includes two major elements: representation of workflows and simulation models of, for example, energy management and/or user comfort scenarios.
The Need for Digital Twins
The current status of data systems in the built environment has negative consequences on today's economy and climate. The problem spans four dimensions: data availability, data interoperability, normative research methods, and compatibility with socio-technical changes.
Based on a study by the Federal Reserve Bank of New York, over the last four decades all industries have achieved gains in their productivity, except the construction industry. At the core of the challenge is the lack of data. For example, less than 20% of commercial buildings have BMS. For those that do, the majority of these are outdated and lack the ability to verify data integrity. A key category of operational data, occupant data, is hardly collected.
The consequences go beyond economic inefficiencies. Buildings are among the top consumers of energy (52% of Toronto's GHG). If we are to meet our net-zero targets, a substantial proportion of our building stock will have to be rehabilitated. Material-wise, advanced green material is available. Economic-wise, the business case for sustainable buildings is long-established. The lack of data, especially operational data, is the Achilles heel. It hinders sound engineering/energy analyses.
The result: it is hard to find reliable and interconnected data. This makes any integrated analysis time consuming and inefficient. Occupants' engagement is another data-related challenge. The net-savvy and climate-active generation is not satisfied with the comfort levels of their buildings and their energy performance. They are also not satisfied with no-access to data or, in the few cases where it is available, the reactive nature of their role. In line with socio-technical trends, they want the ability to “act” on data.
The Opportunity with UofT's Digital Twins
Three main drivers made the Center feasible. First, the unprecedented dataset, which allows us to explore approaches that rely on machine learning (ML). This can lead to a breakthrough in informatics research in the domain, which has been dominated by normative thinking. The following features make our dataset unique:
- Data triangulation: longitudinal structured data (e.g. IoT data), unstructured data (e.g. complaints, and maintenance logs), and building contextual data (e.g. weather and community profile).
- Data reliability: The engagement of facility operators will provide researchers with a "ground truth” view of data, which can help overcome data reliability and completeness issues.
- Higher-value data: providing access to the data for other colleagues who work on topics such as energy, air quality will generate new sets of insightful data (simulations of possible scenarios).
- Occupants & their data: For long, informatics research in the domain has focused on professionals. The Center will have access to the (typically illusive) occupant data; and to occupants themselves (innovative stakeholders with unique knowledge profiles, who can create ideas/new apps).
Second, (the push of) industrial need. There is an increasing demand for advanced data analytics in buildings. For example, large buildings are required to report electricity, water, and gas use. There is an awareness that data-driven tools are needed to conduct such analysis and make the right decisions.
Third, the (pull of the) success of AI in other sectors. Key firms in the filed recognize that investments in data management are not just good engineering practices, it is an essential tool for market survival.