| Autonomic Communications in Software-Driven Networks | ||
| Prof. Torsten Braun Institute of Computer Science, University of Bern, Bern, Switzerland |
||
 |
Autonomic communications aims to provide quality-of-service in networks using self-management mechanisms. Autonomic communications inherits many characteristics from autonomic computing, in particular, when communication systems are running as specialized applications in software-driven networks, i.e. networks based on software-defined networking and network function virtualization. We focus on network self-management as well as on-going research projects and standardization activities on different perspectives of self-management of networks. We further elaborate issues of automatic service testing, integration, and deployment in the context of virtualized network functions. Another important purpose of Autonomic Communications is to automate network performance optimization by analyzing real-time network data. Therefore, we discuss the importance of applying machine learning approaches to implement network self-management and optimization. Moreover, secure communication must be guaranteed for any autonomic operations. | |
| Creating Autonomous Vehicle Systems |
||
| Prof. Jean-Luc Gaudiot, Department of Electrical Engineering and Computer Science, University of California – Irvine, USA |
||
 |
In this technical overview of autonomous vehicles, weshare our practical experiences designing autonomous vehicle systems. Autonomous vehicle systems are complex, consisting of three major subsystems: algorithms for localization, perception, and planning and control; client systems, such as the robotics operating system and hardware platform; and the cloud platform, which includes data storage, simulation, high-definition (HD) mapping, and deep learning model training. The algorithm subsystem extracts meaningful information from sensor raw data to understand its environment and make decisions about its actions. The client subsystem integrates these algorithms to meet real-time and reliability requirements. The cloud platform provides offline computing and storage capabilities for autonomous vehicles. Using the cloud platform, we are able to test new algorithms and update the HD map – plus, train better recognition, tracking, and decision models. | |
| Cybersecurity in a Maritime Supply Chain Environment: Issues and Modelling | ||
| Prof. Christos Douligeris, University of Piraeus Greece |
||
 |
Due to the progressive reliance of the industrial sector on Information and Communucation Technologies (ICT) and the interconnection of heterogeneous ICT systems among ports to share and transfer data, the impact of a coordinated physical attack, a deliberate disruption of critical automation (cyber) systems or even a combined scenario including both kinds of attacks, could have tremendous consequences for the port and its vicinity.
To enhance the security awareness of maritime supply chains infrastructures, this lecture will present a process-oriented model of port supply chain security concepts. The model reflects the ports’ critical infrastructures security particularities and presents best practices to improve their cyber-physical systems’ sustainability and resilience. This is illustrated via a real-life attack scenario taken as a use case to show how security vulnerabilities and weaknesses can be exploited by adversaries to launch a coordinated cyber – physical attack. The attack scenario use case is part of the SAURON EU project, that introduces a multidimensional yet installation-specific Situational Awareness (SA) model that enables port operators and authorities to anticipate and withstand cyber, physical and combined security threats to their freight and cargo business and to enhance the safety of their employees, visitors and passengers. |
|