As I listened to U.S. President Barack Obama’s second inaugural address in January, I was struck by the emphasis he placed on addressing global climate change and the need for clean energy. “The path toward sustainable energy sources will be long and sometimes difficult,” the president said, but he also noted that it will spawn technology that “will power new jobs and new industries.”
Data-intensive analysis plays a key role in the design of energy-efficient buildings. © Starp Estudi
Those statements had special resonance for me, as I had recently sat in on discussions of one such new technology: a set of next-generation architectural design tools that will use cloud computing to simulate a future building’s energy consumption. Researchers at Microsoft Research Connections and the Royal Danish Academy (opens in new tab) are collaborating with Green Prefab (opens in new tab), a small startup in northern Italy, to develop these eco-friendly civil engineering tools.
Spotlight: On-demand video
AI Explainer: Foundation models and the next era of AI
Explore how the transformer architecture, larger models and more data, and in-context learning have helped advance AI from perception to creation.
The technology to perform energy-use simulations—parametric building performance simulations, to use the precise terminology—has been around for a while. But despite its potential for optimizing building designs, these energy studies are rarely performed, because complex parametric analysis models require simulation on a scale that is nowadays only attainable in research laboratories that are equipped with enormous computing power. After all, architectural design firms, most of which are small or medium-sized companies, cannot afford the supercomputers that would reduce the simulation time to a manageable level. Happily, cloud computing has the potential to change this.
Green Prefab is developing a library of prefabricated green building components that can be used to design eco-friendly buildings. During the design phase, architects will be able to access civil engineering services in the cloud to produce energy efficiency reports, conduct in-depth structural analysis, and view photo-realistic images of the building—long before the actual groundbreaking. Green Prefab is collaborating with Microsoft Research Connections to develop some of the first tools in the Windows Azure cloud computing environment. And the Institute of Architectural Technology of the Royal Danish Academy has conducted an experiment that proves the potential of this approach.
The Academy’s experiment used Green Prefab’s prototype web-based tools and cloud computing to execute parametric energy simulations, enabling an experienced architect to use 220,184 variable combinations for creating an energy optimization of a hypothetical office building. The objective was to show how architects could use cloud computing to do what heretofore had required extremely large-scale computation clusters. In a parallel experiment, the same architect used the business-as-usual approach on the same building, conceiving and testing 50 design options with a standard dual-core PC.
In the end, the cloud-based approach achieved about twice the potential energy savings: 33 percent, compared to only 17 percent for the conventional method. And using the cloud reduced the computing time to a manageable level: running the 220,184 parametric simulations on a standard dual-core PC would have taken 122 days; running those same energy simulations in the cloud took only three days.
Microsoft Research’s collaboration with Green Prefab leaves little doubt that new cloud-based tools have the potential to aid in the design of buildings that consume substantially less energy than most buildings today. Scientific breakthroughs like these are helping researchers make great strides worldwide in achieving the overall goals of green building—and puts us one step further down that path toward sustainable energy that President Obama envisioned.
—Dennis Gannon, Director of Cloud Research Strategy, Microsoft Research Connections
Learn More