Building Automation System for Oems
We can predict the future; What if you could foresee what would happen during your day? For instance, you would know the outcomes of a meeting and be able to implement the findings immediately. In a nutshell, you can make accurate, well-informed decisions. Anticipating the future and taking action is the idea behind predictive control. And that’s what we do for buildings.
Why buildings need a sixth sense
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. To optimize a building’s energy consumption, integrating data and predicting the building’s future behavior is crucial.
Your company offers smart thermostats or building automation solutions.
Unfortunately, your smart thermostats cannot make the right decisions as the underlying control principles rely on heuristics or simple feedback principles. You are missing the know-how for technologies such as Self-learning predictive control and you want to be ready for future technological trends such as demand response, peak shaving, occupancy prediction and time-varying energy prices.
We empower your devices by connecting them to our cloud.
We provide Predictive control as a Service: Your devices integrate with our platform by sending measurements of room temperatures and actuator states to our cloud. Depending on the selected product, our platform makes recommendations for your future control inputs based on our algorithms, such as Self-Learning Predictive Control, occupancy prediction, energy price prediction, etc..
Efficient
By using predictive control, we find optimal control inputs while taking into account the future behaviour of the building, user preferences and the weather forecast. This leads to a reduced energy consumption while increasing comfort.
Fast-learning
Our algorithms learn the thermal behaviour of the connected building by themselves. They do this faster than other approaches, because we combine physics-based knowledge with Machine Learning methods. 1-2 weeks of training data is usually enough to learn the building’s behaviour.
Scalable
Our approaches are lightweight and thus scalable. In contrast to other Machine Learning based approaches, the resulting optimization problem is convex and can be solved fast and for large systems. Our technology is ready for variable energy pricing and demand response schemes.