PSI: Pervasive Self-Optimizing Computing Infrastructures

The amount of data that we produce on a daily bases is increasing exponentially, thanks to the emergence of technologies like Internet of Things (IoT) and Industrial IoT (IIoT).

With such a growth, requirements on the computational platforms are significantly increasing, calling for novel and more efficient solutions for the management of the IoT infrastructure.

This calls for solutions to enable (i) exploiting the whole computation infrastructure, (ii) scaling to larger datasets that cannot be moved to data centers for processing, and (iii) meeting predictability and timing requirements of IIoT.PSI (Pervasive Self-Optimizing Computing Infrastructures) aims to provide a fabric of software components able to dynamically optimize the behaviour of the IIoT infrastructure.

PSI targets an improved usage of resources at the systems’ edge via continuous and distributed system-wide optimizations.

This project covers both theoretical and practical aspects, and it combines different research areas including self-adaptive software, control theory, optimization, distributed and real-time systems.

The main goal of the project is to develop new methodologies for the efficient usage of computational resources while providing guarantees on different key performance indicators, like, for example, response time and throughput of the system.

The project will provide potentially significant advances both in the research community, as well as in industrial applications.