Self-learning predictive control through physics-informed Machine Learning

20-40% less energy and improved thermal comfort

compared to state of industry controllers.

1-2 weeks of training time

compared to multiple months with pure Machine Learning methods.

Ready for demand response

due to computationally efficient predictive control algorithms.

Award-winning technology

Every two years Empa gives the Innovation Award in recognition of outstanding innovation and technology transfer projects. The prize honors excellent innovations or a successful technology transfer to industry. In 2022, the award was given to viboo co-founders Felix and Benjamin.

Outstanding doctoral theses are honoured with the Silver Medal of ETH Zurich. The medal is awarded to less than 8% of all theses submitted. It was awarded to our co-founder Felix, whose research is the foundation of viboo’s technology.

During the Swiss Digital Days 2022, 60 sustainable project ideas from driven entrepreneurs that preserve and protect natural resources competed at the “GreenTech Startup Battle”. viboo won the final and took home the award.

Self-learning predictive control...

We use a combination of Machine Learning methods and building physics to generate thermal building models purely from measurement data. Compared to conventional Model Predictive Control, no manual modelling is necessary. Compared to pure Machine Learning based methods, the inclusion of building physics ensures that the model has physical behaviour and reduces the training time to 1-2 weeks.

The generated models are used in a predictive control framework, which predicts the thermal behaviour of the building for the next couple of hours, considering the weather forecast. Taking into account user preferences, occupancy schedules and operational constraints, the optimal energy input for the building is calculated every few minutes and send to the building.

...as a cloud service...

Buildings account for 40% of Europe’s energy consumption. Existing buildings offer significant untapped potential for energy savings as they are the majority and often have a high heating demand. Heating and cooling systems in almost all of these buildings are controlled via room thermostats or thermostatic valves. Unfortunately, even smart thermostats often cannot make the right decisions as underlying control principles rely on heuristics or simple feedback principles.

We’ve developed a Predictive Control as a Service platform (PCaaS), empowering smart thermostats to actually be intelligent. By connecting to our cloud, you can bring viboo’s Self-Learning Predictive Control to your thermostat or BMS.

But we don’t stop here. We’re aiming to fully integrate buildings into the energy sector to reduce demand peaks or maximize the consumption of renewables. Buildings will provide demand-side response services, help to shave energy peaks and be connected to various smart devices. We’re providing the energy efficiency platform for all buildings.

...for various building types.

We have validated the method in residential and light commercial buildings, schools, and public buildings for heating and cooling operation, where it saves between 20% and 40% of energy compared to state-of-industry controllers. As the controller anticipates changes in weather, it also improves comfort, because it can act proactively.

Besides advantages in energy consumption and comfort, the method can exploit time-varying energy prices efficiently and is already ready for demand response schemes, which will become more and more relevant with more renewables entering the electricity grid.