In this era of rapid technological evolution, businesses are constantly seeking innovative ways to gain a competitive edge and stay ahead of the curve. Edge Computing and Artificial Intelligence have emerged as two pivotal technologies that can revolutionize how industries operate in an increasingly challenging global market. The combination of these two new paradigms is expected to help organizations unlock new opportunities, enhance operational efficiency, and ultimately drive business success.

Based on IKERLAN’s first-hand experience as members of the Mondragon Corporation—the largest industrial group in the Basque Country (Spain)—this Keynote will focus on examining the practical implementation of edge-cloud solutions in EU strategic sectors such as Industry, Manufacturing, Transport, and Energy. This talk will include real-world examples that demonstrate how open source solutions can contribute significantly to fostering innovation within Europe and to maintaining the competitiveness of European businesses.

This presentation will also describe a concrete example of successful R&D collaboration revolving around open source edge cloud technologies: the COGNIT Project. Funded by the Horizon Europe program, this project will establish a novel distributed Function-as-a-Service model for managing edge applications. This new AI-enabled platform is poised to revolutionize the processing of data by allowing edge and IoT devices to easily offload heavy processing tasks to the emerging multi-provider Cognitive Cloud Continuum.

In resent years monolith architecture gains once again a lot of popularity, in order to reduce costs and time compared to more complicated architectures. Taking into account the advantages of micro-service, and trying to embed some of them to monolith architectures, we come to the creation of modular monoliths. This type of design can be consider quite new, and so there isn’t yet a specific architecture design that someone could follow if they wish to use it.

In this paper we present an architectural design and an implementation strategy for modular monoliths. To evaluate the usefulness of this architecture, we have conducted a study, validating the design and its implementation. In this study 12 architects from different companies took part, expressing some concerns regarding the feasibility in bigger project but also giving an overall positive feedback for the design.

Architectural patterns are high level design guidelines and principles for software systems. They play a crucial role laying the foundations to the organization and structure of software systems and have high impact on their quality and success both in terms of business and engineering aspects. Deciding for a specific software architecture requires careful analysis of several factors regarding the software system including system characteristics, constraints and required quality attributes, and is often not trivial.

This paper presents a framework for architectural pattern selection and application that supports the decision-making process of choosing an appropriate architectural pattern, and the organization of the software structure based on the chosen pattern in an automated fashion when integrated in IDEs. In particular, the paper presents how this framework is implemented and integrated within an innovative open source cloud-native integrated development environment.

This article presents a model-driven engineering (MDE) integrated development environment (IDE) to assist the DevSecOps (Development Security and Operations) process. This tool has been developed within the PIACERE H2020 project, which proposes a framework composed of a set of tools developed to support all phases of the DevSecOps life cycle including modeling, test/validation, build/generate, deployment, operate and modeling.

PIACERE IDE is an Eclipse based tool, that acts as the front-end for this framework, and plays a key role in integrating other PIACERE tools. The IDE allows developers to access the different tools in a simple and unified way.

MLOps, or Machine Learning Operations, play a significant role in streamlining production deployment, monitoring, and management of machine learning models. Integrating MLOps with edge devices poses unique challenges that require customised deployment strategies and efficient model optimisation techniques. This paper introduces LinkEdge, a set of tools that enable the integration of MLOps practices with edge devices. LinkEdge consists of two sets of tools: one for setting up infrastructure within edge devices to be able to receive, monitor, and run inference on ML models and another for MLOps pipelines to package models to be compatible with the inference and monitoring components of the respective edge devices.

The LinkEdge platform is evaluated by obtaining a public dataset for predicting the breakdown of Air Pressure Systems in trucks. Additionally, the platform is compared against a set of commercial and open-source tools and services that serve similar purposes. The overall performance of LinkEdge matches that of already existing tools and services while allowing end users setting up Edge-MLOps infrastructure the complete freedom to set up their system without entirely relying on third-party licensed software.

Data is a critical asset in today’s world, and its value cannot be overstated. However, ensuring that data is accessible only to authorized parties and protecting it against theft present significant challenges. A potential solution to these issues is creating data spaces that interconnect clusters managed by different actors. The latter can securely exchange data under specific constraints and terminate connections when needed.

This paper aims to show how to create infrastructure-level data spaces to facilitate secure data exchange and prevent data theft. Furthermore, we investigate how data sovereignty can be maintained through cluster data exchange, which is crucial in an era where data is increasingly regulated and controlled. Additionally, we explore how offloading applications from the data consumer into the data producer cluster can match data gravity patterns, improving overall system efficiency. Finally, this paper presents the potential integration of the proposed solution within the framework of IDSA and Gaia-X, serving as promising option for implementing their proposed functionalities.

As a fast and inexpensive machining method applicable for creating a wide range of shapes and producing large batches, sheet metal punching is widely used e.g., in automotive, aerospace, electronics, and construction industries. A significant downside of sheet metal punching is the punching tool wear in use. A worn punch tool may impact the quality of the end product by causing imperfections and reduce the efficiency of the manufacturing process through increased scrap and by slowing down the production.

Effective monitoring of punching tool wear is therefore essential for an efficient and cost-effective production of high-quality parts. The monitoring can be based on acceleration measurement which produces large amounts of raw data, making edge processing ideal as only the indication of the tool condition needs to be sent forward for decision support. Classification models for tool wear identification were built and compared in this study. The models are based on measured acceleration data. Two different open-source methods for time series feature extraction, namely TSFEL and MiniRocket, were tested and the classification results based on them compared.

All methods used for building the models are computationally light and therefore applicable for real-time data processing at the edge. According to the results the MiniRocket algorithm is suitable for the task and superior compared to the TSFEL method. The classification accuracies based on the MiniRocket features are at best over 96.5 % and at worst around 84 %, whereas the corresponding accuracies are between 35 and 56 % for TSFEL feature based models. The use of the MiniRocket algorithm in building a model for punch tool monitoring shows very promising results. However, the dataset used was very limited. Therefore, further investigation is required based on an ampler dataset.

The convergence megatrend of Cloud Computing and IoT towards a computing continuum has been clearly recognised at European level and is having significant innovation, economic, and policy impact. This transition is creating a tremendous opportunity for Europe to demonstrate its ability to facilitate the implementation of sustainable, resource-efficient, fair, and inclusive digital infrastructure.

These first three years of the Horizon Europe programme have seen several research and innovation initiatives start and gather momentum, while the originally separated R&I communities around Cloud and IoT have increasingly come together in a new, seamless ecosystem: EUCloudEdgeIoT provides coordination and support across this thriving landscape of projects and communities, covering key horizontal enablers such as Open Source and Open Standards as well as verticalised stakeholder engagement and market sectors. Further development is expected for 2024 and 2025, with new complementary initiatives rolled out and updated vision and roadmap for Computing Continuum research.