The rapid growth of Artificial Intelligence and Machine Learning in scientific research has highlighted a gap between industry-standard machine learning operations (MLOps) tools and platforms and the unique requirements of modern and Open Science, particularly regarding the FAIR (Findable, Accessible, Interoperable, and Reusable) principles. This paper presents AI4EOSC, a federated, open-source platform designed to operationalize the full AI/ML life-cycle within the European Open Science Cloud (EOSC) ecosystem. Our methodology tackles the fragmentation of distributed research infrastructures by integrating a modular and distributed architecture comprising an AI development platform, a serverless AI-as-a-Service layer, and a federated orchestration model that is able to integrate heterogeneous computing and storage resources from distributed e-infrastructures. AI4EOSC also introduces a “FAIR-by-design” approach that enforces metadata standardization (via MLDCAT-AP) and W3C PROV-compliant provenance tracking through a platform-integrated CI/CD pipeline. The added value of AI4EOSC is demonstrated through the delivery of a diverse set of community installations, which show consistent and seamless deployment across heterogeneous cloud providers. These installations are validated by a set of scientific cases, showing how our work reduces the manual burden on researchers while ensuring high levels of reproducibility and interoperability and providing a unified environment for the development, training, and production of AI/ML models in the EOSC.

Data will be made available on request.

This paper proposes an automated framework for efficient application profiling and training of Machine Learning (ML) performance models, composed of two parts: OSCAR-P and aMLLibrary. OSCAR-P is an auto-profiling tool designed to automatically test serverless application workflows running on multiple hardware and node combinations in cloud and edge environments. OSCAR-P obtains relevant profiling information on the execution time of the individual application components. These data are later used by aMLLibrary to train ML-based performance models. This makes it possible to predict the performance of applications on unseen configurations. We test our framework on clusters with different architectures (x86 and arm64) and workloads, considering multi-component use-case applications. This extensive experimental campaign proves the efficiency of OSCAR-P and aMLLibrary, significantly reducing the time needed for the application profiling, data collection, and data processing. The preliminary results obtained on the ML performance models accuracy show a Mean Absolute Percentage Error lower than 30% in all the considered scenarios.

This paper introduces the Software Quality Assurance as a Service (SQAaaS) concept and it describes an open-source implementation of a comprehensive platform that supports the automated assessment of specific quality metrics for software and services, defined as a set of baseline requirements. The platform is openly accessible, focuses on research software and open science, and promotes best practices by awarding standards-based digital badges to software and services. It provides an easy-to-use web-based graphical user interface which facilitates the interaction with server-side components in charge of automatically creating CI/CD (Continuous Integration/Continuous Delivery) pipelines for automated testing of the baseline criteria. The service is in production and has performed over 2800 assessments, awarding more than 125 digital badges across several scientific disciplines.

Serverless computing was a breakthrough in Cloud computing due to its high elasticity capabilities and fine-grained pay-per-use model offered by the main public Cloud providers. Meanwhile, open-source serverless platforms supporting the FaaS (Function as a Service) model allow users to take advantage of many of their benefits while operating on the on-premises platforms of organizations. This opens the possibility to deploy and exploit them on the different layers of the cloud-to-edge continuum, either on IoT (Internet of Things) devices located at the Edge (i.e. next to data acquisition devices), in on-premises clusters closer to the data sources (i.e. Fog computing) or directly on the Cloud. This paper presents two strategies to mitigate the overload that disparate data ingestion rates may cause in low-powered devices at the Edge or Fog layers. To this end, it is proposed to delegate and reschedule serverless jobs between the different layers of the cloud-to-edge continuum using an open-source platform for event-driven file processing. To demonstrate the performance of these strategies, a use case for fire detection is proposed that includes processing in the Fog via minified Kubernetes clusters located near the Edge, in the private Cloud via on-premises elastic clusters and, finally, in the public Cloud by using the AWS (Amazon Web Services) Lambda FaaS service. The results indicate that these strategies can mitigate overloads in use cases involving processing across the cloud-to-edge continuum by coordinating several layers of computing resources.

As machine learning models are increasingly deployed in production, robust monitoring and detection of concept and covariate drift become critical. This paper addresses the gap in the widespread adoption of drift detection techniques by proposing a serverless-based approach for batch covariate drift detection in ML systems. Leveraging the open-source OSCAR framework and the open-source Frouros drift detection library, we develop a set of services that enable parallel execution of two key components: the ML inference pipeline and the batch covariate drift detection pipeline. To this end, our proposal takes advantage of the elasticity and efficiency of serverless computing for ML pipelines, including scalability, cost-effectiveness, and seamless integration with existing infrastructure. We evaluate this approach through an edge ML use case, showcasing its operation on a simulated batch covariate drift scenario. Our research highlights the importance of integrating drift detection as a fundamental requirement in developing robust and trustworthy AI systems and encourages the adoption of these techniques in ML deployment pipelines. In this way, organizations can proactively identify and mitigate the adverse effects of covariate drift while capitalizing on the benefits offered by serverless computing.

Abstract The increasing use of multiple Workflow Management Systems (WMS) employing various workflow languages and shared workflow repositories enhances the open-source bioinformatics ecosystem. Efficient resource utilization in these systems is crucial for keeping costs low and improving processing times, especially for large-scale bioinformatics workflows running in cloud environments. Recognizing this, our study introduces a novel reference architecture, Cloud Monitoring Kit (CMK), for a multi-platform monitoring system. Our solution is designed to generate uniform, aggregated metrics from containerized workflow tasks scheduled by different WMS. Central to the proposed solution is the use of task labeling methods, which enable convenient grouping and aggregating of metrics independent of the WMS employed. This approach builds upon existing technology, providing additional benefits of modularity and capacity to seamlessly integrate with other data processing or collection systems. We have developed and released an open-source implementation of our system, which we evaluated on Amazon Web Services (AWS) using a transcriptomics data analysis workflow executed on two scientific WMS. The findings of this study indicate that CMK provides valuable insights into resource utilization. In doing so, it paves the way for more efficient management of resources in containerized scientific workflows running in public cloud environments, and it provides a foundation for optimizing task configurations, reducing costs, and enhancing scheduling decisions. Overall, our solution addresses the immediate needs of bioinformatics workflows and offers a scalable and adaptable framework for future advancements in cloud-based scientific computing.

Abstract Serverless computing and, in particular, the functions as a service model has become a convincing paradigm for the development and implementation of highly scalable applications in the cloud. This is due to the transparent management of three key functionalities: triggering of functions due to events, automatic provisioning and scalability of resources, and fine‐grained pay‐per‐use. This article presents a serverless web‐based scientific gateway to execute the inference phase of previously trained machine learning and artificial intelligence models. The execution of the models is performed both in Amazon Web Services and in on‐premises clouds with the OSCAR framework for serverless scientific computing. In both cases, the computing infrastructure grows elastically according to the demand adopting scale‐to‐zero approaches to minimize costs. The web interface provides an improved user experience by simplifying the use of the models. The usage of machine learning in a computing platform that can use both on‐premises clouds and public clouds constitutes a step forward in the adoption of serverless computing for scientific applications.

Abstract CERN (Centre Europeen pour la Recherce Nucleaire) is the largest research centre for high energy physics (HEP). It offers unique computational challenges as a result of the large amount of data generated by the large hadron collider. CERN has developed and supports a software called ROOT , which is the de facto standard for HEP data analysis. This framework offers a high-level and easy-to-use interface called RDataFrame , which allows managing and processing large data sets. In recent years, its functionality has been extended to take advantage of distributed computing capabilities. Thanks to its declarative programming model, the user-facing API can be decoupled from the actual execution backend . This decoupling allows physical analysis to scale automatically to thousands of computational cores over various types of distributed resources. In fact, the distributed RDataFrame module already supports the use of established general industry engines such as Apache Spark or Dask. Notwithstanding the foregoing, these current solutions will not be sufficient to meet future requirements in terms of the amount of data that the new projected accelerators will generate. It is of interest, for this reason, to investigate a different approach, the one offered by serverless computing. Based on a first prototype using AWS Lambda , this work presents the creation of a new backend for RDataFrame distributed over the OSCAR tool, an open source framework that supports serverless computing. The implementation introduces new ways, relative to the AWS Lambda -based prototype, to synchronize the work of functions.

This paper introduces an open-source platform to support serverless computing for scientific data-processing workflow-based applications across the Cloud continuum (i.e. simultaneously involving both on-premises and public Cloud platforms to process data captured at the edge). This is achieved via dynamic resource provisioning for FaaS platforms compatible with scale-to-zero approaches that minimise resource usage and cost for dynamic workloads with different elasticity requirements. The platform combines the usage of dynamically deployed auto-scaled Kubernetes clusters on on-premises Clouds and automated Cloud bursting into AWS Lambda to achieve higher levels of elasticity. A use case in public health for smart cities is used to assess the platform, in charge of detecting people not wearing face masks from captured videos. Faces are blurred for enhanced anonymity in the on-premises Cloud and detection via Deep Learning models is performed in AWS Lambda for this data-driven containerised workflow. The results indicate that hybrid workflows across the Cloud continuum can efficiently perform local data processing for enhanced regulations compliance and perform Cloud bursting for increased levels of elasticity.

State-of-the-art techniques for detecting, or predicting, neurological disorders (1) focus on predicting each disorder individually, and are (2) computationally expensive, leading to a delay that can potentially render the prediction useless, especially in critical events. Towards this, we present a real-time two-tiered framework called EMAP, which cross-correlates the input with all the EEG signals in our mega-database (a combination of multiple EEG datasets) at the cloud, while tracking the signal in real-time at the edge, to predict the occurrence of a neurological anomaly. Using the proposed framework, we have demonstrated a prediction accuracy of up to 94% for the three different anomalies that we have tested.

The advent of open-source serverless computing frameworks has introduced the ability to bring the Functions-as-a-Service (FaaS) paradigm for applications to be executed on-premises. In particular, data-driven scientific applications can benefit from these frameworks with the ability to trigger scalable computation in response to incoming workloads of files to be processed. This paper introduces an open-source framework to achieve on-premises serverless computing for event-driven data processing applications that features: i) the automated provisioning of an elastic Kubernetes cluster that can grow and shrink, in terms of the number of nodes, on multi-Clouds; ii) the automated deployment of a FaaS framework together with a data storage back-end that triggers events upon file uploads; iii) a service that provides a REST API to orchestrate the creation of such functions and iv) a graphical user interface that provides a unified entry point to interact with the aforementioned services. Together, this provides a framework to deploy a computing platform to create highly-parallel event-driven file-processing serverless applications that execute on customized runtime environments provided by Docker containers that run on an elastic Kubernetes cluster. The usefulness of this framework is exemplified by means of the execution of a data-driven workflow for optimised object detection on video. The workflow is tested under three different workloads which process ten, a hundred and a thousand functions. The results show that the presented architecture is able to process such workloads taking advantage of its elasticity to make a sensible usage of the resources.

This paper describes the achievements of the H2020 project INDIGO-DataCloud. The project has provided e-infrastructures with tools, applications and cloud framework enhancements to manage the demanding requirements of scientific communities, either locally or through enhanced interfaces. The middleware developed allows to federate hybrid resources, to easily write, port and run scientific applications to the cloud. In particular, we have extended existing PaaS (Platform as a Service) solutions, allowing public and private e-infrastructures, including those provided by EGI, EUDAT, and Helix Nebula, to integrate their existing services and make them available through AAI services compliant with GEANT interfederation policies, thus guaranteeing transparency and trust in the provisioning of such services. Our middleware facilitates the execution of applications using containers on Cloud and Grid based infrastructures, as well as on HPC clusters. Our developments are freely downloadable as open source components, and are already being integrated into many scientific applications.

After a sequence of creation and destruction of virtual machines (VMs) in an on-premises Cloud computing platform, the scheduling decisions to host the VMs are far from being optimal and the fragmentation of the physical resources may impede the platform to host some VMs despite the free available virtualization resources. This paper describes a Virtual Machine Consolidation Agent that addresses this problem by analyzing the distribution of the VMs in the virtualization platform to migrate some of them among hosts, in order to defragment the physical resources and to enhance the efficiency on their usage. The agent has been validated in a production platform, where it is capable of minimizing the number of servers needed to host the VMs. The algorithms achieve near-optimal values at a very reduced computational cost, thus making it suitable for production platforms.

There is an opportunity for Distributed Computing Infrastructures (DCIs) to embrace container-based virtualisation to support efficient execution of scientific applications without the performance penalty commonly introduced by Virtual Machines (VMs). However, containers (e.g. Docker) and VMs feature different image formats and disparate procedures for deployment and management, thus hindering the adoption of hybrid DCIs (HDCIs) comprised of those kind of resources. This paper describes a workflow based on open-source tools and standards to introduce coherent application delivery on HDCIs in which applications require to be deployed on both VMs and Docker containers. Leveraging and extending the TOSCA standard to describe application requirements, and adopting DevOps practices, resulted in the coherent creation of the artifacts required for the execution of the applications on different platforms. The paper features the adoption of this approach in the INDIGO-DataCloud project.

A case study on climate models intercomparison data analysis addressing several classes of multi-model experiments is being implemented in the context of the EU H2020 INDIGO-DataCloud project. Such experiments require the availability of large amount of data (multi-terabyte order) related to the output of several climate models simulations as well as the exploitation of scientific data management tools for large-scale data analytics. More specifically, the paper discusses in detail a use case on precipitation trend analysis in terms of requirements, architectural design solution, and infrastructural implementation. The experiment has been tested and validated on CMIP5 datasets, in the context of a large scale distributed testbed across EU and US involving three ESGF sites (LLNL, ORNL, and CMCC) and one central orchestrator site (PSNC).

Education in Engineering requires bringing the students to scenarios as close to reality as possible. Indeed, the new technologies have fostered the development of a wide spectrum of Computational Environments (CE), such as simulators, virtual laboratories or specific software tools. These environments typically share the same Physical Hardware Resources (PHRs) (e.g. laboratories of PCs) for different subjects on which the CEs are deployed. It is especially important to properly and efficiently manage the rationalization of these PHRs so that the level of service, scalability and versatility is maintained without requiring additional investments in new hardware. The innovation in this work consists on introducing Virtualized CEs (VCEs) based on Cloud Computing by means of the open-source ODISEA platform. The benefits have been assesed and evaluated through 12 educational activities carried out in 8 subjects across 4 degrees at the Universitat Politècnica de València (UPV), in Spain. The results assessed in the paper demonstrate that ODISEA provides economical benefits for the educational institutions. Also, the platform provides the students with ubiquitous and highly available access to VCEs. In addition, this approach fosters BYOD (Bring Your Own Device) where students use their own computers to access the remote labs provided by the VCEs.

The massive amount of multimedia information currently available through the Internet demands efficient techniques to extract knowledge from Big Data. In this work, we propose an architecture to capture, process, analyse and visualize data coming from multiple streaming multimedia TV stations and radio stations. For that, we rely on the Hadoop framework available within the IBM InfoSphere BigInsights platform. We create a workflow to automate the different stages that range from Automatic Speech Recognition using open-source tools to visualization by means of the R framework. We emphasize techniques such as diarization and the optimization of the number of Hadoop nodes, provisioned from Cloud infrastructures, to deliver enhanced performance. The results show that it is possible to automate knowledge extraction from multimedia data running on virtualized infrastructures by means of Big Data techniques.

This paper describes the research work in the context of the CLUVIEM project towards achieving migratable, self-managed virtual elastic clusters on hybrid Cloud infrastructures. These virtual clusters can span across on-premises and public Cloud infrastructures thus leveraging hybrid Cloud platforms. They are elastic since working nodes are automatically provisioned and relinquished to dynamically adapt the capacity of the virtual cluster (in terms of number of nodes) according to the current workload. They are self-managed since the elasticity rules are managed via the head node without requiring any external software entity for monitoring and deciding when to scale in and out. Finally, they are migratable since they consider both application migration, via application check pointing, and infrastructure migration, by cloning infrastructures across multi-Clouds. These features introduce unprecedented flexibility for cost-effective cluster-based computing with minimal impact for cluster users. The paper summarises the current state of developments and future roads to achieve this vision.

Summary This paper presents a software platform to dynamically deploy complex scientific virtual computing infrastructures, on top of Infrastructure as a Service Clouds. The platform orchestrates different services to provision the virtual computing resources. It dynamically installs the appropriate software to satisfy the requirements of a researcher, both on public and on‐premise Clouds. The platform provides a web interface to enable the users to easily manage the life cycle of virtual infrastructures. It enables users to define infrastructures, share them with other users, deploy and relinquish them, add or remove resources dynamically, create and share application recipes, and so on. The paper also describes three case studies to deploy complex infrastructures, namely, a Hadoop cluster, a single‐node to perform Next Generation Sequencing and a gateway for users to access the European Grid Infrastructure. This platform promotes a better use of on‐premise hardware resources of a research center by allocating the computing resources just‐in‐time to the specific life time of the virtual infrastructures as well as the deployment of the very same infrastructures on a public Cloud. Copyright © 2015 John Wiley & Sons, Ltd.

The increasing interest of online learning is unquestionable nowadays, with MOOCs being taken by thousands of students. However, for online learning to go mainstream it is necessary that professors perceive that the effort required to prepare and manage an online course is manageable. Today, a myriad of inexpensive tools and services can be used to produce and manage online courses with unprecedented ease and without distressing the professor. For that, this paper proposes an architecture based on Cloud services that simplifies the process of managing an online course, from delivering on-demand fully customized remote laboratories to communication automation for student engagement and feedback gathering. This approach has been applied to produce, distribute and manage an Online Course on Cloud Computing with Amazon Web Services. The paper describes the methodology, tools and results of this experience to point out that it is possible to deliver online courses with automatically provisioned labs, with minimal management overhead, while still providing a high quality learning experience to a worldwide audience.

SUMMARY The main advantage of Grid computing over other distributed computing paradigms is its capability to coordinate the access to data and resources in a virtual multi‐institutional environment. To this end, the information system plays a decisive role in selecting the services that meet the applications' needs. This paper presents an information system for the Grid that provides transparent and scalable group communication services to standard Grid applications, with the objective of supporting dynamic collaborations that could help address problems that involve only some participants of a virtual organization. In particular, it enables more flexible delivery mechanisms, which allows applications to select the appropriate services before sending their data to the information system. This significantly enhances the protection of data from unauthorized access, and avoids the transmission of unnecessary messages over the network. The proposed information system is based on the use of XML technologies and replication. It introduces several new advanced features that are not currently supported as a whole by any Grid middleware, such as: several entry points to the information, persistent capabilities, support for advanced queries based on XQuery, and support for the industrial standard WS‐Policy. The information system has been stress tested under realistic workloads in a Grid infrastructure with 50 sites. Scalability has been evaluated in up to 1000 messages that can be up to 10KB in size each, updated with a frequency of 5min. Copyright © 2012 John Wiley & Sons, Ltd.

With the advent of cloud technologies the scientists have access to different cloud infrastructures in order to deploy all the virtual machines they need to perform the computations required in their research works. This paper describes a software architecture and a description language to simplify the creation of all the needed resources, and the elastic evolution of the computing infrastructure depending on the application requirements and some QoS features.

The advent of Cloud computing has paved the way to envision hybrid computational infrastructures based on powerful Grid resources combined with dynamic and elastic on-demand virtual infrastructures on top of Cloud deployments. However, the combination of Grid and Cloud resources for executing computationally intensive scientific applications introduces new challenges and opportunities in areas such as resource provisioning and management, meta-scheduling and elasticity. This paper describes different approaches to integrate the usage of Grid and Cloud-based resources for the execution of High Throughput Computing scientific applications. A reference architecture is proposed and the the opportunities and challenges of such hybrid computational scenarios are addressed. Finally, a prototype implementation is described and a case study that involves a protein design application is employed to outsource job executions to the Cloud when Grid resources become exhausted.

This paper combines high-performance computing and grid computing technologies to accelerate multiple executions of a biomedical application that simulates the action potential propagation on cardiac tissues. First, a parallelization strategy was employed to accelerate the execution of simulations on a cluster of personal computers (PCs). Then, grid computing was employed to concurrently perform the multiple simulations that compose the cardiac case studies on the resources of a grid deployment, by means of a service-oriented approach. This way, biomedical experts are provided with a gateway to easily access a grid infrastructure for the execution of these research studies. Emphasis is stressed on the methodology employed. In order to assess the benefits of the grid, a cardiac case study, which analyzes the effects of premature stimulation on reentry generation during myocardial ischemia, has been carried out. The collaborative usage of a distributed computing infrastructure has reduced the time required for the execution of cardiac case studies, which allows, for example, to take more accurate decisions when evaluating the effects of new antiarrhythmic drugs on the electrical activity of the heart.

Grid computing technologies are mature enough to be successfully applied to computationally intensive scientific applications. However, the current process of applying grid computing to them is still hard and difficult for the least experienced users. In this paper we describe the adaptations made to the GMarte metascheduling framework in order to provide an ubiquitous access to its functionality as an efficient resource broker for the execution of tasks on computational grids. A metascheduling component accessible by only means of a Java-enabled Web browser has been developed, requiring almost zero configuration by the client. This approach has enabled to produce a generic multi-platform metascheduler which can be automatically deployed in the clients interested in resource brokering on computational grids based on the Globus Toolkit

Diesel engines are fuel efficient which benefits the reduction of CO2released to the atmosphere compared with gasoline engines, but still result in negative environmental impact related to their emissions. As new degrees of freedom are created, due to advances in technology, the complicated processes of emission formation are difficult to assess. This paper studies the feasibility of using artificial neural networks (ANNs) in combination with genetic algorithms (GAs) to optimize the diesel engine settings. The objective of the optimization was to find settings that complied with the increasingly stringent emission regulations while also maintaining, or even reducing the fuel consumption. A large database of stationary engine tests, covering a wide range of experimental conditions was used for this analysis. The ANNs were used as a simulation tool, receiving as inputs the engine operating parameters, and producing as outputs the resulting emission levels and fuel consumption. The ANN outputs were then used to evaluate the objective function of the optimization process, which was performed with a GA approach. The combination of ANN and GA for the optimization of two different engine operating conditions was analyzed and important reductions in emissions and fuel consumption were reached, while also keeping the computational times low

Grid computing technologies are now being largely deployed with the widespread adoption of the Globus Toolkit as the industrial standard Grid middleware. However, its inherent steep learning curve discourages the use of these technologies for non-experts. Therefore, to increase the use of Grid computing, it is important to have high-level tools that simplify the process of remote task execution. In this paper we introduce a middleware, developed on top of the Java Commodity Grid, which offers an object-oriented, user-friendly application programming interface, from the Java language, which eases remote task execution for computationally intensive applications. Copyright © 2006 John Wiley & Sons, Ltd.

With the recent advent of Grid Computing technologies, resource-starved applications can greatly benefit from the power that the Grid aims to deliver. In this paper, we focus on the application of Grid Computing to a biomedical computationally intensive application that simulates the electrical activity on cardiac tissues. A user level tool, called GMarte, was developed to simplify the usage of Grid facilities for the execution of scientific applications on distributed deployments. A cardiac case study has been executed, via GMarte, on the largest distributed Grid deployment available in Europe (the EGEE testbed) in order to assess the benefits of Grid Computing. The usage of a Grid infrastructure has dramatically reduced the time required to execute the case study, thus increasing research productivity.