Showing papers by "Alexandros Fragkiadakis published in 2021"

An IoT-based Platform for Supply Chain Monitoring

Abstract: Traditional supply chain traceability involves time-consuming operations where human involvement is required. With the help of IoT, supply chain traceability processes that are complex, time-consuming and error-prone, can be automated and become more reliable. In this paper, we present the work-in-progress of an IoT-based platform for supply chain monitoring that can make feasible the collection of IoT sensory data, jointly with supply chain data formatted, according to GS1standards.

Autonomous Maintenance in IoT Networks via AoI-driven Deep Reinforcement Learning

Abstract: Internet of Things (IoT) with its growing number of deployed devices and applications raises significant challenges for network maintenance procedures. In this work, we formulate a problem of autonomous maintenance in IoT networks as a Partially Observable Markov Decision Process. Subsequently, we utilize Deep Reinforcement Learning algorithms (DRL) to train agents that decide if a maintenance procedure is in order or not and, in the former case, the proper type of maintenance needed. To avoid wasting the scarce resources of IoT networks we utilize the Age of Information (AoI) metric as a reward signal for the training of the smart agents. AoI captures the freshness of the sensory data which are transmitted by the IoT sensors as part of their normal service provision. Numerical results indicate that AoI integrates enough information about the past and present states of the system to be successfully used in the training of smart agents for the autonomous maintenance of the network.

A Compilation-and Remote-Programming-as-a-Service Platform for IoT Devices

Abstract: The Internet-of-Things (IoT) presents itself as an emerging technology, which is able to interconnect a massive number of heterogeneous smart objects. These ubiquitous object-enabled networks, which may operate for several years in variable conditions, are used for supporting complex data-driven applications such as smart cities applications, home automation, health monitoring, etc. Throughout their extended lifetime, the devices forming the IoT networks need to be re-programmed, so that new features are added and software bugs or security vulnerabilities are resolved. In this work, we present work-in-progress on the design of a Compilation-and Remote-Programming-as-a-Service platform that enables cloud-based compilation and build of device firmware, as well as remote firmware updates for deployed IoT devices, in a reliable and secure way. We introduce the functional architecture of our platform and elaborate on the interaction of functional components. Our solution can easily support various embedded operating systems and heterogeneous hardware platforms, as well as different communication patterns for firmware transfer.

DTLS Connection Identifiers for Secure Session Resumption in Constrained IoT Devices

Abstract: This paper presents the design and implementation of DTLS v1.2 connection identifiers for secure session resumption in case of 5-tuple changes, in order to avoid a costly re-handshake process. Our implementation is based on the tinyDTLS and Contiki OS, and we show its feasibility on constrained IoT devices, while providing information on the incurred overhead in terms of the execution time, memory utilisation, and network traffic.