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.
4) INNOVATIVE EXPECTED OUTPUTS OF SoFT-2 AND EXPECTED POTENTIAL TECHNO-SOCIAL IMPACT
The SoFT technological platform is expected to quickly foster the development of Fog-supported Future Internet Applications [8], that are considered a world-wide huge business opportunity (Fig.2). In particular, it is foreseen that the Fog related outputs could move from the research cycle to prototype cycle in the next years (Fig.2). In the following, we detail the main technological and social impact of the proposed SoFT-2 project.
Expected Technological Impact: The activities involved in the SECOND year of the proposed SoFT-2 project is expected to have a significant positive impact on the development of future low-latency and energy-aware application inspired by the FC and SIoT paradigms. This is expected to have a relevant technological impact on many novel families of technologies, such as Smart Wireless Sensor Networks (SWSNs), Smart Objects of IoT and Intelligent Embedded Systems. Overall, it is expected that proposed SoFT research permit to enter a new phase where real-world problems emerging from complex IoT applications are addressed.
Expected Social Impact: It is expected that intelligent and green FC platforms are able to provide more robust, energy-efficient and higher QoS and, for this reason, are expected to increase the trust people have in machine-related and real-time critical applications. Furthermore, the novel SoFT-2 platform would enable to quickly acquire a full awareness about hazards and situations that cannot be foreseen and promptly activate appropriate countermeasures. Overall, the proposed SoFT-2 platform will be of paramount to enable and efficiently support a wide class of IoT-involving application scenarios, all having a high significant social impact, e.g. smart grid where energy load balancing applications may run on end-devices at the edge of network to autonomously switch to alternative energies, i.e., solar, wind-based, on energy demand, availability, environment conditions and economic convenience.
5) SoFT-2 PLAN AND SoFT-2 TARGETS
The two-year research activity of the overall SoFT workprogramme is organized into two Workpackages (e.g., WP.1 and WP.2), coordinated by Prof. E. Baccarelli (DIET Dpt.) and Prof. M. Scarpiniti (DIET Dpt.), respectively. As detailed in Table III, each WP comprises two tasks.
The SoFT-2 project will be coordinated by Dr. Michele Scarpiniti. The team of 4 researchers (3 promoters supported by 1 PhD researcher) is organized into two Research Units located at the DIET Dpt. The multiple scientific sectors involved by the SoFT-2 project (ING-INF/03 and ING-IND/31) confirm, indeed, the inter-disciplinary nature of the project itself. Table IV sketches the tasks completed during the FIRST year and the planned tasks scheduled for the SECOND year.
From these tables, we argue that main project target during the SECOND year is to complete the scheduled tasks, in order to:
(a) design, develop and validate scalable energy-saving and resource-scalable opportunistic Fog access strategies for Big Data gathering under fairness and real-time constraints;
(b) design, develop and validate a distributed and virtualized networked Fog technological platform for the support of the anomaly detection functionalities over social networks, while jointly minimizing the resulting energy consumption;
(c) design, develop and validate adaptive distributed and cognitive Machine Learning-based algorithms that exploit deep learning techniques for social network analysis and social media forecasting.