Buildings sector is responsible for about 40 to 70 percent of world energy consumption and greenhouse gas emissions. Providing a shelter as the fundamental axiom of our lives, plays a great role in inhabiting the earth in symbiosis with the environment. Both as a treat or as a help. Automatic controlling of the components of residential, commercial, and public spaces can potentially help bringing down this impact while providing dwellers peace of mind and comfort. In AiCtrl we aim to use state of the art machine learning algorithms to leverage the potential of automated systems in order to tackle current global environmental issues.
Using AI to train machines that can help us to make decisions about design and control in a smart, low-cost solution is the bridge. Decisions which were conventionally possible solely through expensive, non affordable, and advanced daylight, thermal and energy simulations/optimizations and/or knowledge of concessionaires.
AiCtrl addresses the shortcomings of building automation to save energy while providing thermal and visual comfort. The trained models considers the main driving environmental conditions and their contributions to each component to control the systems effectively.
Occasionally neglected factor of human comfort is what we care the most in AiCtrl. In our projects we always ready to go the extra mile to find the optimum solution based on multi objective criteria of visual and thermal comfort along with energy saving.
Decisions in AiCtrl are made based on their impact on our environment. Our cloud based infrastructure not only developed to lower the complexity of on premise control systems while utilizing the cutting edge algorithms to control building components without expensive sensors, but also to minimize consumption significance which technology has caused.
AiPlantCare is an advance tool for predicting the required natural and supplemental light for various plant species using state-of-the-art simulation models and cloud computing features.
Using AI to train machines that can help us to make decisions about design and control in a smart, low-cost solution is the bridge. Decisions which were conventionally possible solely through expensive, non affordable, and advanced daylight, thermal and energy simulations/optimizations and/or knowledge of concessionaires.