A5090306567- Distributed and Parallel Computing Systems
- Scientific Computing and Data Management
- Cloud Computing and Resource Management
- Advanced Data Storage Technologies
- Parallel Computing and Optimization Techniques
- IoT and Edge/Fog Computing
- Software System Performance and Reliability
- Research Data Management Practices
- Simulation Techniques and Applications
- Digital Transformation in Industry
- Distributed systems and fault tolerance
- Peer-to-Peer Network Technologies
- Service-Oriented Architecture and Web Services
- Semantic Web and Ontologies
- Bioinformatics and Genomic Networks
- Cloud Data Security Solutions
- Blockchain Technology Applications and Security
- Computational Drug Discovery Methods
- Business Process Modeling and Analysis
- Embedded Systems Design Techniques
- Cryptography and Data Security
- Data Quality and Management
- Reservoir Engineering and Simulation Methods
- Carbohydrate Chemistry and Synthesis
- Glycosylation and Glycoproteins Research
University of Westminster
2015-2024
Budapest University of Technology and Economics
2023
Institute for Computer Science and Control
2011-2015
STMicroelectronics (France)
2014
University of Exeter
2014
Brunel University of London
2014
Swansea University
2011
Cardiff University
2011
University of Pisa
2004
Abstract Automated deployment and run-time management of microservices-based applications in cloud computing environments is relatively well studied with several mature solutions. However, managing such tasks the cloud-to-edge continuum far from trivial, no robust, production-level solutions currently available. This paper presents our first attempt to extend an application-level orchestration framework called MiCADO utilise edge fog worker nodes. The illustrates how MiCADO-Edge can...
Digital Twins (DTs) are real-time digital models that allow for self-diagnosis, self-optimization and self-configuration without the need human input or intervention. While DTs a central aspect of ongoing fourth industrial revolution (I4.0), this leap forward may be reserved established, large-cap companies since adoption technologies among Small Medium-size Enterprises (SMEs) is still modest. The aim H2020 European Project "DIGITbrain" to support modular construction by reusing their...
Abstract IoT systems are becoming an essential part of our environment. Smart cities, smart manufacturing, augmented reality, and self-driving cars just some examples the wide range domains, where applicability such have been increasing rapidly. These use cases often require simultaneous access to geographically distributed arrays sensors, heterogeneous remote, local as well multi-cloud computational resources. This gives birth extended Cloud-to-Things computing paradigm. The emergence this...
Cloud technology has the potential for widening access to high-performance computational resources e-science research, but barriers engagement with remain high many scientists. Workflows help overcome by hiding details of underlying infrastructure and are portable between various platforms including cloud; they also increasingly accepted within research communities. Issues arising from range workflow systems available complexity development have been addressed focusing on interoperability,...
Simulation is used in industry to study a large variety of problems ranging from increasing the productivity manufacturing system optimising design wind turbine. However, some simulation models can be computationally demanding and projects require time consuming experimentation. High performance computing infrastructures such as clusters speed up execution or multiple experiments but at cost that often too much for Small Medium-sized Enterprises (SMEs). Cloud presents an attractive, lower...
There are many benefits of implementing simulation software on a Cloud. These include the use scalable, on-demand access to resources that can be used speed up and development composable Modeling & Simulation services (Modeling as Service (MSaaS)). However, developing Cloud computing solutions for in industry is difficult without appropriate expertise due complex technologies involved. This paper introduces CloudSME Platform based proven gUSE CloudBroker being create versions industrial...
Computational fluid dynamics (CFD) is widely used in manufacturing and engineering from product design to testing. CFD requires intensive computational power typically needs high-performance computing reduce potentially long experimentation times. Dedicated systems are often expensive for small-to-medium enterprises (SMEs). Cloud claims enable low-cost access without the need capital investment. The cloud-based simulation platform aims provide a flexible easy use platform-as-a-service (PaaS)...
So far BOINC based desktop grid systems have been applied at the global computing level. This paper describes an extended version of called SZTAKI (SZDG) that aims using grids (DGs) local (enterprise/institution) The novelty SZDG is it enables hierarchical organisation DGs, i.e., clients a DG can be DGs lower level take work units from their higher server. More than that, even clusters connected client and hence contain complete MPI programs to run on clusters. In order easily create...
One of the biggest obstacles in wide-spread industrial take-up grid technology is existence a large amount legacy code that not accessible as services. The paper describes new approach (GEMLCA: execution management for architecture) to deploy codes services without modifying original code. Moreover, we show workflow oriented portal (P-GRADE portal) by which such based can be applied complex business processes. GEMLCA has been implemented GT-3 but easily ported into WSRF standards.
Summary As cloud adoption increases, so do the number of available service providers. Moving complex applications between clouds can be beneficial—or other times necessary—but achieving this so‐called portability is rarely straightforward. This article presents OASIS TOSCA, a standard in declarative description applications, to encourage and facilitate MiCADO, an application‐level multi‐cloud orchestration auto‐scaling framework. The interface MiCADO Application Description Template, which...
The use of mature, reliable, and validated solutions can save significant time cost when introducing new technologies to companies. Reference Architectures represent such best-practice techniques have the potential increase speed reliability development process in many application domains. One area where are increasingly utilized is cloud-based systems. Exploiting high-performance computing capability offered by clouds, while keeping sovereignty governance proprietary information assets be...
Manual deployment of the application usually requires expertise both about underlying system and application. Automatic service can improve significantly by using on-demand self-healing services. To support these features this paper describes an extension globus workspace service. This includes creating virtual appliances for grid services, from a repository, influencing schedules altering execution planning candidate set generators or information systems.
Cloud computing offers massive scalability and elasticity required by many scientific commercial applications. Combining the computational data handling capabilities of clouds with parallel processing also has potential to tackle Big Data problems efficiently. Science gateway frameworks workflow systems enable application developers implement complex applications make these available for end-users via simple graphical user interfaces. The integration such tools on cloud opens new...
Summary Scholars worldwide leverage science gateways/virtual research environments (VREs) for a wide variety of and education endeavors spanning diverse scientific fields. Evaluating the value given gateway/VRE to its constituent community is critical in obtaining financial human resources necessary sustain operations increase adoption user community. In this article, we feature exemplar gateways/VREs detail how they define impact terms of, example, their purpose, operation principles, size...
Large reductions in completion times can result from transfer of Big Data tasks edge nodes to cloud resources, which reduce the by up 97 % and meet client deadlines for computational with responsive agile solutions. Using scientific programs varying complexity model resource-intensive tasks, we demonstrate that task jobs, Wide Area Network (WAN) speed potential overload servers (as reflected CPU workloads) are crucial achieving total time edge-cloud orchestrators situated nodes. With...
The grid execution management for legacy code architecture (GEMLCA) describes a solution exposing and executing applications through an OGSI service. This has been introduced in previous paper by the same authors where general concept was demonstrated creating OGSI/GT3 version of MadCity traffic simulator. class structure is described presenting each component describing relationships between them. Also, current implementation evaluated test results gained running simulator as C/PVM application.