The CSEM innovation enables devices to run independently for over a year, reducing installation and maintenance costs. The system's two-tiered data processing approach drastically reduces power requirement, with most applications using only the first accelerator.
Swiss Center for Electronics and Microtechnology engineers developed an approach to overcome the initial trial-and-error phase of reinforcement learning. This allows computers to quickly find the right path without extreme fluctuations, slashing energy use by over 20% in complex systems.
Maestro, a predictive software developed by CSEM, analyzes weather forecasts and data from local infrastructure to determine the best time to consume energy. The system can reduce heating costs by approximately 20% and is designed to keep costs down, making it suitable for individual homes and entire neighborhoods.