Search

Federated learning is a branch of machine learning where a shared model is created in a decentralized and privacy-preserving fashion, but existing approaches using blockchain are limited by tailored models. We consider the possibility to extend a set of supported models by introducing the oracle service and exploring the usability of blockchain-based architecture. The investigated architecture combines an oracle service with a Hyperledger Fabric chaincode. We compared two logistic regression implementations in Go language&mdash, a pure chaincode and an oracle service&mdash, at various data (2&ndash, 32 k instances) and network (3&ndash, 13 peers) sizes. Experiments were run to assess the performance of blockchain-based model inference using 2D synthetic and EEG eye state datasets for a supervised machine learning detection task. The benchmarking results showed that the impact on performance is acceptable with the median overhead of oracle service reaching 2&ndash, 4%, depending on the dimensionality of the dataset. The overhead tends to diminish at large dataset sizes with the runtime depending on the network size linearly, where additional peers increased the runtime by 6.3 and 6.6 s for 2D and EEG datasets, respectively. Demonstrated negligible difference between implementations justifies the flexible choice of model in the blockchain-based federated learning and other machine learning applications.

International audience; Photovoltaic water pumping systems (PVWPS) are a promising solution to improve domestic water access in low-income rural areas. It is challenging, however, to make them more affordable for the local communities. We develop here a comparative methodology to assess relevant features of both widely employed PVWPS architecture with water tank storage, and hardly used PVWPS architecture with a battery bank instead of tank storage. The quantitative comparison is carried out through techno-economic optimization, with the goal of minimizing the life cycle cost of PVWPS with constraints on the satisfaction of the water demand of local inhabitants and on the groundwater resource sustainability. It is aimed to support decision-makers in selecting most appropriate storage for domestic water supply projects. We applied the methodology in the rural village of Gogma, Burkina Faso. Results indicate that the life-cycle cost of an optimized PVWPS with batteries is $24.1k while it is $31.1k if a tank is used instead. Moreover, reduced impact on groundwater resources and greater modularity to adapt to evolving water demand is noted if using batteries. However, as batteries must be replaced regularly and recycled adequately, PVWPS’ financial accessibility could increase only if sustainable and efficient operation, maintenance, and recycling facilities for batteries were present or developed locally. View Full-Text

Emerging 5G systems will need to seamlessly guarantee novel types of services in a multi-do-main ecosystem. New methodologies of network and infrastructure sharing facilitate the cooperation among the operators, exploiting the core and access sections of the system architecture. Network slicing (NS) is the operators' best technique for building and managing a network. Without NS, the 5G requirements in terms of flexibility, optimal resource utilization, and investment returns cannot materialize. Before slicing is commercially available, different sections of the 5G architecture should be modified to include NS. In this work, we present a novel dynamic radio access network slicing resource sharing method aimed to guarantee optimal service level agreements through the monitoring of each slice tenant's key performance indicators. The experiments are conducted following the 3GPP specifications, and the solution is validated using a testbed based on the main 5G functionalities. © 1979-2012 IEEE., Acknowledgments This work is supported by the research projects 5GROUTES (GA 951867), MSCA ITN 5G STEPF-WD (GA 722429), SPOT5G (TEC2017-87456-P), and AGAUR (2017-SGR-891). © 2021, IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other work.

Almost every research project that focuses on the cooperation of autonomous robots for underwater operations designs their own architectures. As a result, most of these architectures are tightly coupled with the available robots/vehicles for their respective developments, and therefore the mission plan and management is done using an ad-hoc solution. Typically, this solution is tightly coupled to just one underwater autonomous vehicle (AUV), or a restricted set of them selected for the specific project. However, as the use of AUVs for underwater operations increases, there is the need to identify some commonalities and weaknesses of these architectures, specifically in relation to mission planning and management. In this paper, we review a selected number of architectures and frameworks that in one way or another make use of different approaches to mission planning and management. Most of the selected works were developed for underwater operations. Still, we have included some other architectures and frameworks from other domains that can be of interest for the survey. The explored works have been assessed using selected features related to mission planning and management, considering that underwater operations are performed in an uncertain and unreliable environment, and where unexpected events are not strange. Furthermore, we have identified and highlighted some potential challenges for the design and implementation of mission managers. This provides a reference point for the development of a mission manager component to be integrated in architectures for cooperative robotics in underwater operations, and it can serve for the same purposes in other domains of application.

The growing need of technological assistance to provide support to people with special needs demands for systems more and more efficient and with better performances. With this aim, this work tries to advance in a multirobot platform that allows the coordinated control of different agents and other elements in the environment to achieve an autonomous behavior based on the user’s needs or will. Therefore, this environment is structured according to the potentiality of each agent and elements of this environment and of the dynamic context, to generate the adequate actuation plans and the coordination of their execution.

Modern robots often use more than one processing unit to solve the requirements in robotics. Robots are frequently designed in a modular manner to fulfill the possibility to be extended for future tasks. The use of multiple processing units leads to a distributed system within one single robot. Therefore, the system architecture is even more important than in single-computer robots. The presented concept of a modular and distributed system architecture was designed for robotic systems. The architecture is based on the Operator&ndash, Controller Module (OCM). This article describes the adaption of the distributed OCM for mobile robots considering the requirements on such robots, including, for example, real-time and safety constraints. The presented architecture splits the system hierarchically into a three-layer structure of controllers and operators. The controllers interact directly with all sensors and actuators within the system. For that reason, hard real-time constraints need to comply. The reflective operator, however, processes the information of the controllers, which can be done by model-based principles using state machines. The cognitive operator is used to optimize the system. The article also shows the exemplary design of the DAEbot, a self-developed robot, and discusses the experience of applying these concepts on this robot.

Dynamic directional modulation (DDM) has already proven to be an efficient technique to achieve physical layer security in wireless communications. System architectures based on vector modulators provide a flexible framework to implement synthesis methods that allow us to obtain increased security and/or independent multichannel transmissions. However, the implementation of DDM with vector modulators requires an accurate calibration (amplitude and phase) of every component in the RF path. In this contribution, we study the sensitivity of the response of a DDM system based on commercial vector modulators showing how to correct the nonideal behavior of all the components thanks to the flexibility provided by the vector modulator.

Truck platooning for which multiple trucks follow at a short distance is considered a near-Term truck automation opportunity, with the potential to reduce fuel consumption. Short following distances and increasing automation make it hard for a driver to be the backup if the system fails. The EcoTwin consortium successfully demonstrated a two truck platooning system with trucks following at 20 meters distance at the public road, in which the driver is the backup. The ambition of the consortium is to increase the truck automation and to reduce the following distance, which requires a new fail-operational truck platooning architecture. This paper presents a level 2+ platooning system architecture, which is fail-operational for a single failure, and the corresponding process to obtain it. First insights in the existing two truck platooning system are obtained by analyzing its key aspects, being utilization, latency, reliability, and safety. Using these insights, candidate level 2+ platooning system architectures are defined from which the most suitable truck platooning architecture is selected. Future work is the design and implementation of a prototype, based on the presented level 2+ platooning system architecture.

Cyber-Physical-Systems (CPS) enable flexible and reconfigurable realization of automation system architectures, utilizing distributed control architectures with non-hierarchical modules linked together through different communication systems. Several control system architectures have been developed and validated in the past years by research groups. However, there is still a lack of implementation in industry. The intention of this work is to provide a summary of current alternative control system architectures that could be applied in industrial automation domain as well as a review of their commonalities. The aim is to point out the differences between the traditional centralized and hierarchical architectures to discussed ones, which rely on decentralized decision-making and control. Challenges and impacts that industries and engineers face in the process of adopting decentralized control architectures are discussed, analysing the obstacles for industrial acceptance and the new necessary interdisciplinary engineering skills. Finally, an outlook of possible mitigation and migration actions required to implement the decentralized control architectures is addressed. The authors would like to thank the European Commission for the support, and the partners of the EU Horizon 2020 project PERFoRM (2016b) for the fruitful discussions. The PERFoRM project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 680435. info:eu-repo/semantics/publishedVersion

International audience; Socio-technical systems are increasingly becoming software-intensive. The challenge now is to design the architecture of such software-intensive systems for guaranteeing not only its correctness, but also the correctness of its implementation. In social-technical systems, the architecture (including software and physical elements) is described in terms of Piping and Instrumentation Diagrams (P&ID). The design of these P&ID is still considered an art for which no rigorous design support exists. In order to detect and eliminate architectural design flaws, this paper proposes a formal-based automated approach for the verification of the essential architecture “total correctness” properties, i.e. compatibility, completeness, consistency, and correctness. This approach is based on the definition of an architectural style for P&ID design in Alloy. We use MDE to automatically generate Alloy models from a P&ID and check their compatibility with the style and its completeness, consistency, and correctness properties. Our approach is presented through an industrial case study: the system of storage and production of freshwater for a ship.

Conference of 21st IEEE International Conference on Emerging Technologies and Factory Automation, ETFA 2016 ; Conference Date: 6 September 2016 Through 9 September 2016; Conference Code:124646; International audience; Automated manufacturing systems are becoming increasingly flexible in order to support a growing number of different products and product variations, as well as shortening lot sizes and product life cycles. Many manufacturing resource are already multi-purpose. But they are integrated in an automation infrastructure that may require significant effort to adapt. In this contribution, we present a system architecture for the deployment of software functionality to manufacturing resources safely at runtime. The architecture integrates software model verification to ensure the integrity of new functionality, software-defined networking (SDN) to establish new communication pathways for collaboration, and the close interaction between a flexible runtime execution environment and its safety-critical counterpart.

The Finnish 5G test network (5GTN) is built to support development and analysis of 5G technologies and new services on top of them. 5GTN includes a holistic monitoring and test generation architecture, enabling generation and collection of diverse test and datasets, analyzing the results and using these as basis for developing new technologies, algorithms, services, and optimizations. Both the combined network and service parameters space, as well as data volume, provide us with several big data problems. In this paper, we describe the overall system architecture, the types of data we collect, the initial analysis we have performed on the data, and what we have learned so far. The network is constantly evolving with new services integrated and tested, and new big data analytics being applied as we learn from our tests. As such, these are preliminary results for ongoing work.

Recent developments in robotics and the associated fields of computer vision and sensors pave the floor for automated robotic solutions, exploitable in the wider field of inspection of civil infrastructures and particularly transportation tunnels, the latter ageing urgently requiring inspection and assessment. Currently, tunnel inspections are performed via visually by human operators. This can result into slow, labour expensive and subjective process often requiring lane shutdown during the inspection, parameters that need to be lowered while having safety requirements and tunnel uptimes increasing. ROBINSPECT is an EC research project (FP7 - ICT - 611145) driven by the tunnel inspection industry, that adapts and integrates recent research results in intelligent control in robotics, computer vision and active continuous learning and sensing, in an innovative, integrated, robotic system that automatically scans the intrados of tunnels for potential defects on the surface while at the same time inspects and measures radial deformation in the cross-section, distance between parallel cracks, cracks and open joints that impact tunnel stability, with mm accuracies. Intelligent control systems and robotics are integrated to set an automatic robotic arm manipulation and autonomous vehicle navigation so as to minimize humans' interaction during tunnel inspection. This way, the structural condition and safety of a tunnel is assessed automatically, reliably and speedily. The robotic system will be evaluated at the research infrastructure of tunnels of VSH, at three road tunnels of the Egnatia Motorway and the rail tunnel of London Underground. This paper will focus on the ROBISPECT EC project first year activities starting from the requirements, specifications and system architecture as well as the technologies that will be integrated and overall technological solution. Also it will provide the current status of implementations and following steps as well as its expected European and International impact.

Conference of 2013 8th International Conference on P2P, Parallel, Grid, Cloud and Internet Computing, 3PGCIC 2013 ; Conference Date: 28 October 2013 Through 30 October 2013; Conference Code:102403; International audience; This paper presents a full system architecture allowing the authentication and secured execution of binary files using hardware-assisted on-the-fly memory encryption/decryption. In a context of general blurring of the physical relationship between a user and the computer which which it eventually interacts, this architecture has been thought so as to achieve a certain degree of robustness against corruptions in a cloud computing IaaS software stack, including when the corruptions may come from the lowest hypervision layer.