Ricerc@Sapienza

This proposal plans the activity for the SECOND year of the (two-year) "SoFT: Fog of Social IoT" project. The project aims at integrating the complementary features of the Social Internet of Things (SIoT) and Fog Computing (FC) pillar technological paradigms.
In fact, SIoT relies on the self-establishment and self-management of inter-thing social relationships to guarantee scalability to large IoT networks composed by both human and non-human agents. FC extends cloud capabilities to the access network, in order to allow resource-poor IoT devices to support delay-sensitive applications. FC natively supports three main services: thing virtualization, Thing-to-Fog task offloading and inter-Fog resource pooling. In principle, these services could be efficiently exploited to implement the SIoT social network as an overlay network of thing clones that entirely relies on the bandwidth/computing resources of the supporting Fog Nodes (FNs). So doing, the native resources of the physical things could be employed only for the synchronization with the corresponding Fog-hosted clones. This is, indeed, the main idea behind the proposed SoFT paradigm.
Overall, main goals of the SoFT-2 project are to complete the design and validate in SW the related algorithms already developed during the FIRST year, by focusing on the:
i)formalization of main building blocks and functionalities of the proposed SoFT technological platform. It should merge the physical things at the IoT layer and their virtual clones at the Fog layer into a cyber-physical overlay network of social clones;
ii) design and validation through software simulations of the performance of a small-scale SoFT prototype, so to compare its energy-vs.-delay performance with the corresponding ones of the state-of-the-art;
iii) design and validation through software simulations of novel distributed machine learning and deep learning algorithms for the analysis and forecasting of Big Data diffusion through the SoFT social network.