1,720,999 research outputs found
Tiny keys hold big secrets: On efficiency of Pairing-Based Cryptography in IoT
No full textPairing-Based Cryptography (PBC) is a sub-field of elliptic curve cryptography that has been used to design ingenious security protocols including Short Signatures (SS), Identity-Based Encryption (IBE), and Attribute-Based Encryption (ABE). These protocols have extremely promising applications in diverse scenarios, including Internet of Things (IoT), which usually involves computing devices with limited processing, memory, and energy capabilities. Many studies in the literature evaluated the performance of PBC on typical IoT devices, giving promising results, and showing that a large class of constrained devices can run PBC schemes. However, in the last years, new advancements in Number Field Sieve algorithms threatened the security of PBC, so that all protocols must be re-parametrized with larger keys to maintain the same security level as before. Therefore, past literature reporting PBC performance on IoT devices must be redone because optimistic, and it is not clear whether present IoT devices will bear PBC. In this paper we evaluate the performance of some prominent PBC schemes on a very constrained device, namely the Zolertia RE-Mote platform, which is equipped with an ARM Cortex-M3 processor. From our experiments, the usage of IBE and SS schemes is still possible on IoT devices, but the security level is limited to 80 or 100 bits. Reaching greater security levels leads to higher execution times, which might not be compatible with many IoT applications. The usage of ABE is efficient only with IoT-oriented schemes, which offer good performance at the cost of a limited policy expressiveness
Rapid Prototyping of IoT Solutions: A Developer's Perspective
No full textMany new Internet-of-things (IoT) devices and solutions appear in the market every day. Although commercial IoT products are the majority, Do-It-Yourself (DIY) solutions implemented by independent developers still represent a significant driving force. In this scenario, the availability of development tools for both less experienced developers and professionals to reduce the time to create prototypes is crucial. In this paper, we first review the tools available to implement all the components of a typical IoT architecture in different programming languages, then, we analyze how Python can be used to implement all the components of a typical IoT architecture. As a practical example, we illustrate the implementation of a smart home system built exploiting low-cost off-the-shelf hardware and programmed only through Python
Latency-Energy Tradeoffs in Federated Learning on Resource Constrained Edge Computing Systems
No full textArtificial intelligence and machine learning have become of crucial importance in many scientific and industrial fields, thanks to the ability to extract information, make predictions and identify patterns on data. For the creation of increasingly accurate predictive models, these technologies are based on the collection and control of large amounts of data within controlled systems. Federated learning is a new framework that exploits the computational capabilities and local data of a set of multiple resource-constrained devices coordinated by a central server for the creation of a shared global predictive model, without any centralised data collection. In this work, we focus on assessing the performance of federated learning executed on resource constrained Edge computing system. A set of experiments to assess the energy consumption and processing times on a set of heterogeneous GPU-enabled embedded systems were executed. Our analysis shows that, by varying the amount of data that each system is in charge of processing, it is possible to identify a trade-off between the overall energy consumption of the devices and the processing time required to train an effective predictive model
Performance Evaluation of Federated Learning for Residential Energy Forecasting
No full textShort-term energy-consumption forecasting plays an important role in the planning of energy production, transportation and distribution. With the widespread adoption of decentralised self-generating energy systems in residential communities, short-term load forecasting is expected to be performed in a distributed manner to preserve privacy and ensure timely feedback to perform reconfiguration of the distribution network. In this context, edge computing is expected to be an enabling technology to ensure decentralized data collection, management, processing and delivery. At the same time, federated learning is an emerging paradigm that fits naturally in such an edge-computing environment, providing an AI-powered and privacy-preserving solution for time-series forecasting. In this paper, we present a performance evaluation of different federated-learning configurations resulting in different privacy levels to the forecast residential energy consumption with data collected by real smart meters. To this aim, different experiments are run using Flower (a popular federated learning framework) and real energy consumption data. Our results allow us to demonstrate the feasibility of such an approach and to study the trade-off between data privacy and the accuracy of the prediction, which characterizes the quality of service of the system for the final users
Performance Evaluation of Adaptive Autonomous Scheduling Functions for 6TiSCH Networks
No full textThe Internet Engineering Task Force (IETF) has recently defined the 6TiSCH architecture to enable the Industrial Internet of Things (IIoT), i.e., the adoption of the IoT paradigm for industrial applications with stringent requirements, in terms of reliability and timeliness. In 6TiSCH networks, the scheduling of communication resources is of paramount importance to meet the application requirements, and many different Scheduling Functions have been proposed to cope with the needs of various applications. Recently, autonomous scheduling has emerged as an efficient and robust approach, as it allows nodes to allocate communication resources autonomously, i.e., without any negotiation with their neighbors, thus avoiding the related overhead. Typically, this is obtained through static resource-allocation algorithms that are not able to adapt to variations in traffic conditions. In this paper, we consider adaptive autonomous scheduling, and compare the performance of three different algorithms in various IIoT scenarios. We investigate their ability to adapt to traffic changes, and evaluate them in terms of performance, resource consumption, and complexity. Based on the results obtained, we also provide a set of guidelines to select the most appropriate Scheduling Function, and its configuration parameters, depending on the specific use case
Performance evaluation of Attribute-Based Encryption on constrained IoT devices
Full text linkThe Internet of Things (IoT) is enabling a new generation of innovative services based on the seamless integration of smart objects into information systems. This raises new security and privacy challenges that require novel cryptographic methods. Attribute-Based Encryption (ABE) is a type of public-key encryption that enforces a fine-grained access control on encrypted data based on flexible access policies. The feasibility of ABE adoption in fully-fledged computing systems, i.e., smartphones or embedded systems, has been demonstrated in recent works. In this paper, we consider IoT devices characterized by strong limitations in terms of computing, storage, and power. Specifically, we assess the performance of ABE in typical IoT constrained devices. We evaluate the performance of three representative ABE schemes configured considering the worst-case scenario on two popular IoT platforms, namely ESP32 and RE-Mote. Our results show that, if we assume to employ up to 10 attributes in ciphertexts and to leverage hardware cryptographic acceleration, then ABE can indeed be adopted on devices with very limited memory and computing power, while obtaining a satisfactory battery lifetime. In our experiments, as also performed in other works in the literature, we consider only the worst-case configuration, which, however, might not be completely representative of the real working conditions of sensors employing ABE. For this reason, we complete our evaluation by proposing a novel benchmark method that we used to complement the experiments by evaluating the average performance. We show that by always considering the worst case, the current literature significantly overestimates the processing time and the energy consumption
Design and evaluation of a fog platform supporting device mobility through container migration
Full text linkThe integration between the Internet of Things (IoT) and fog computing can pave the way to a plethora of applications. Fog computing indeed allows IoT devices to offload complex tasks to computing resources, known as fog nodes, that are in their proximity (e.g., at the network edge). Fog proximity enables important advantages, first and foremost low latency. However, IoT device mobility endangers those advantages, as the IoT device gets farther away from the serving fog node. Migrating the fog service among fog nodes, following the device route, permits to maintain proximity and preserve low latency. In this work, we propose an OpenStack-based platform that implements a fog service as a container and migrates the latter to support device mobility. We performed experiments over a real testbed to: (i) evaluate the impact of hardware resources of fog nodes on migration performance; (ii) validate our platform. Results are encouraging, as the average round-trip latency between the mobile device and the fog layer was as low as 10ms and exceeded the maximum value allowed by the considered application (i.e., 20ms) in 1.5% of the experiment duration
A methodology for the design and deployment of distributed cyber–physical systems for smart environments
Full text linkThe pervasiveness and the growing processing capabilities of mobile and embedded computing systems are leading to a shift from the Internet of Things (IoT) paradigm to the Fog computing scenario where the environment is instrumented with high-performance computing in the proximity to cyber–physical systems. The design of such systems requires an accurate planning, on the one hand, to ensure that specific application requirements will be properly met at run-time, and, on the other hand, to minimize the system's monetary costs. In this paper we present a methodology for an automated design and deployment of distributed cyber–physical systems into smart environments. We propose an engine based on a Mixed Integer Linear Programming (MILP) formulation which takes in input a planimetry of the environment and a description of the applications and, based on a repository of available processing boards, identifies the cost-optimized instantiation of the processing architecture and the corresponding distribution of the application functionalities. By comparing our proposal with the existing methodologies that address similar problems we can highlight the following novelties: (i) we address a system architecture composed of heterogeneous devices, (ii) we adopt a realistic model of the environment, and (iii) we perform a joint co-exploration of architecture instantiation and applications mapping. An experimental evaluation, considering a smart office case study, demonstrates the potential of the proposed approach in minimizing the overall system monetary cost around 42% w.r.t. a baseline approach not exploiting planimetry information. Such results have been also confirmed by an extensive experimental campaign using synthetic problems, which also highlighted how the execution times of the optimization process are affordable for the design-time process
Evaluation of Feasibility and Impact of Attacks against the 6top Protocol in 6TiSCH Networks
Full text linkThe 6TiSCH architecture has been gaining attraction as a promising solution to ensure reliability and security for communication in applications for the Industrial Internet of Things (IIoT). While many different aspects of the architecture have been investigated in literature, an in-depth analysis of the security features included in its design is still missing. In this paper, we assess the security vulnerabilities of the 6top protocol, a core component of the 6TiSCH architecture for enabling network nodes to negotiate communication resources. Our analysis highlights two possible attacks against the 6top protocol that can impair network performance and reliability in a significant manner. To prove the feasibility of the attacks in practice, we implemented both of them on the Contiki-NG Operating System and tested their effectiveness on a simple deployment with three Zolertia RE-Mote sensor nodes. Also, we carried out a set of simulations using Cooja in order to assess their impact on larger networks. Our results show that both attacks reduce reliability in the overall network and increase energy consumption of the network nodes
Analysis of the interplay between RPL and the congestion control strategies for CoAP
No full textThe Constrained Application Protocol (CoAP) is gaining attention as a standardised RESTful interface for the Internet of Things (IoT). Recent studies have focused on different congestion control strategies for CoAP, in order to ensure proper operation of large-scale IoT deployments. In this paper, we carry out a performance evaluation of different congestion control policies for CoAP in a realistic environment by exploiting WiSHFUL, a platform for large-scale experimentation of network architectures. Our goal is to analyse different congestion control policies and their interplay with the routing protocol in a real environment, where unstable links and route fluctuations are frequent, due to channel variability. The results of our experiments highlight that the dynamics of the routing protocol have a noticeable impact and can impair significantly the performance of the congestion control algorithm. Specifically, the influence of the routing protocol depends on the specific congestion control policy adopted: an aggressive policy that re-transmits messages more frequently, e.g. CoCoA, is more penalised than others, in terms of throughput
- …
