MIRAI will be based on machine intelligence techniques, to enable smart and sustainable planning and operation of IoT and Edge computing applications that will supplement the traditional vertical scaling approach with horizontal scaling of IoT and edge computing applications amongst edge devices. The result will be the MIRAI Framework Building Blocks (MFBB).
The main components of the MFBB which the consortium’s research and industrial partners stand for are:
• AI algorithms and mechanisms for energy-efficient and resource-efficient deployment and run-time adaptation of IoT and edge computing applications.
• Distributed and composable AI models and techniques that scale vertically/horizontally to guarantee high-quality decision making.
• Advanced AI algorithms and techniques for continual and evolving learning under uncertainty and noise, that are critical factors for IoT applications in vital sectors like industry and transportation.
• Innovative methodologies for model development, training, and evaluation with no direct access to labelled data.
• New solutions to guarantee trust and quality assurance in a heterogenous ecosystem.