Imagine a giant brain that manages a network of computers, from massive data centers to small devices on the street. Instead of guessing where to run a task, this brain uses a digital mirror of the whole system to pick the perfect spot. It ensures your app runs as fast as possible while using the least amount of electricity.
Current cloud tools like Kubernetes struggle with 'messy' networks where hardware varies and energy use is ignored. This leads to slow response times and wasted electricity in smart city and industrial setups.
An AI-powered scheduler and a digital twin of the computing system. These tools automatically place data and tasks on the best available hardware within a Kubernetes environment.
If you are a traffic management provider dealing with ultra-low latency needs for autonomous signals — this project developed an AI-scheduler that maps jobs to the closest available hardware. This ensures real-time response and reduces data travel time.
If you are a factory operator dealing with high-availability requirements for robot control — this project developed a portable management tool integrated with Kubernetes. It automatically moves tasks to avoid downtime and optimizes energy use.
If you are a service provider dealing with inconsistent network capacity across different sites — this project developed a digital twin system to simulate what-if scenarios. This allows you to optimize job placement before deploying to real hardware.
Based on available project data, no specific pricing or cost structures are provided as this is a research project.
Yes, the project is designed for heterogeneous systems and is being validated across 2 sites in its second phase.
The project aims to develop an open and portable management tool, though specific licensing agreements are not detailed in the provided text.
The tool is integrated directly into the Kubernetes ecosystem, making it compatible with the most common industry standard for cluster orchestration.
The project period runs from 2022-12-01 to 2025-11-30, indicating it is currently in the development and validation phase.
The consortium is well-balanced for technology transfer, consisting of 13 partners across 6 countries. With a 31% industry ratio (4 companies) and a strong presence of 6 SMEs, the project is grounded in commercial needs rather than just academic theory, supported by 5 universities and one research entity.
Contact Georg-August-Universität Göttingen for technical inquiries.
Contact us to connect with the DECICE consortium for early adoption pilots.
