Gabor Kecskemeti, PhD. dr. habil

Career

Gabor Kecskemeti
Official SZTAKI contact card
Official contact card from Miskolc

I am a research fellow at the MTA SZTAKI and an assistant lecturer at the University of Miskolc. Below you can find a detailed list of my career so far, starting from the most recent employers to the oldest ones.

MTA-SZTAKI

I am a research fellow at the Laboratory of Parallel and Distributed Systems at MTA SZTAKI Hungary. I started working in SZTAKI in 2006 as a Research Associate. I did participate in several projects. First, the Coregrid project allowed my short research visits to my past institute: the University of Westminster. These visits allowed the joint development and integration of a graphical user interface for the GEMLCA service (see below) into the Laboratory's flagship product: the P-Grade portal. Later on, I was working on the first parametric study enabled version of the portal (version 2.5). Then I have joined the S-Cube and the EDGeS projects in 2008 (see further details below). Finally between 2011 and 2012, I was coordinating the initial investigations and research on cloud computing within the Laboratory.

For the EDGeS project, I have extended the GEMLCA service with several repository functionalities that were required for the EDGeS scenarios the GEMLCA service would participate in. After the EDGeS project has completed, I was the administrator and the maintainer of the EDGeS application repositories within the EDGeS followup project called DEGISCO.

In the S-Cube project, I have started collaborative research in the domain of service oriented architectures. I was participating in the adaptation and monitoring related research by investigating the adaptation related aspects of my � PhD topic (see below). I was also leading two deliverables that dealt with the issues to set up cross layer adaptation and monitoring frameworks within the S-Cube project. In the project, virtualization based self-* service infrastructures was the other main area I was contributing to.

In 2012, I have postponed my job at SZTAKI so I could work as a postdoctoral researcher in Innsbruck, then I have returned on the 1st of April 2014. Since then, I have four main duties:

• Leading the ENTICE project's internal efforts.
• Conducting research in the field of VM orchestration techniques and background load prediction for clouds with multi tenancy.
• Contributing and coordinating the development and research about the DISSECT-CF open source cloud simulator (for details see: sources, archives).
• In the terms of my Janos Boyai Research scholarship from the Hungarian academy of sciences, I am conducting research in the topic of beyond exa-scale cloud computing simulations.

University of Miskolc

I have attended University of Miskolc from 1999-2004 for the degree of MSc in Software Engineering. During my studies, I was teaching Database Systems (including SQL basics, FoxPro, Oracle) for lower year students.

With the supervision of Laszlo Kovacs, I have received my masters degree from the Institute of Information Technology at the University of Miskolc, in 2004. My masters thesis topic revolves around document classification algorithms. In my MSc project, I have developed an algorithm to construct ID3 based decision trees and I have compared the constructed decision tree's performance with Bayesian classifiers using a Reuters article database available for the University of Miskolc.

After the two years I have spent at the University of Westminster, alongside with SZTAKI, I have also joined the University of Miskolc again. This time, I was teaching MSc students for Parallel and Distributed systems for two years between 2006 and 2008. During these two years, I have supervised Gabor Szmetanko's MSc project - an implementation of the Application Content Service standard proposal - who have published his results on SourceForge. After 2008, I have postponed my post at the University to allow more focus on my PhD studies.

During the summer of 2011, I have rejoined the University. Afterwards, my duties were focused on a BSc. level Web Technologies lecture for third year Electrical engineer students and I was also supporting the PhD level Parallel and Distributed systems lecture.

Universität Innsbruck

At the beginning of 2013, I have joined the university's Distributed and Parallel Systems group. My duties were to participate in the group's cloud computing related research and to collaborate in proposal writing tasks. While at DPS I have contributed to the research related to energy efficient management of cloud systems. My contributions were focused on three areas: (i) simulation of energy behavior of infrastructure cloud systems, (ii) evaluating the energy characteristics of virtual machine migration strategies and (iii) strategies and techniques to increase energy consciousness in academic clouds. I have left the university at the end of March 2014.

University of Westminster

Starting from 2004, I was working at the University of Westminster for two years. During those two years, I have started my PhD studies and participated in two projects - namely the ePerSpace and GEMLCA.

In the ePerSpace project, I have been working on the project's local service provisioning platform. I have got my first experiences with service oriented architectures and embedded systems while I was developing parts of the provisioning platform with the help of OSGi.

When I have joined the University in 2004, they have just started the work on the GEMLCA project that I have joined from its beginning. I was involved in the conceptual design, development and reengineering of the Globus Toolkit 3 and 4 based GEMLCA versions. Since 2007, I am the main maintainer of the GEMLCA code, during this period the GEMCLA was extended to support gLite and act as a repository for the EDGeS project. Nowadays GEMLCA is facing new demands as it is mostly used for its repository functionalities and its execution capabilities are neglected.

My PhD research topic was automatic service deployment. In my first years, I was focusing on general deployment techniques, then with the rise of cloud computing, I have started to focus on the support of highly dynamic service environments in Infrastructure as a Service systems. My director of studies was Dr. Gabor Terstyanszky, and my other two supervisors were Prof. Peter Kacsuk and Prof. Stephen Winter. I have submitted my dissertation at the end of March 2011. Afterwards, my PhD defense took place on 30th of September 2011, my examiners were Dr. Rizos Sakellariou (external, from University of Manchester) and Dr. Ljerka Beus-Dukic (internal). After the suggested revision, you can now download the final version of my dissertation (titled: "Foundations of Efficient Virtual Appliance Based Service Deployments") from here.

Research

Even after the completion of my dissertation, my main research topic is still focused on the support of virtualization based service deployment tasks by optimizing the size and delivery of virtual machine images (so called "virtual appliances"). I am currently working with several virtualization platforms (e.g. Xen, kvm) and Infrastructure as a Service Cloud systems (e.g. Amazon EC2, Eucalyptus, Nimbus and OpenNebula). I am also working on several interesting issues regarding cloud systems management. Just to mention a few: (i) increasing energy awareness within providers, (ii) constructing cloud federations or creating inter-cloud systems. Finally, I am the main maintainer of the DISSECT-CF cloud simulator.

Research interests: IaaS cloud computing, virtualization, virtual appliances, federations, interoperability, energy awareness, distributed systems, service oriented architectures, classification algorithms, software reengineering

Scientometrics

My academic performance according to Harzing's Publish or Perish (based on Google Scholar search results collected on June 2015.):

There are several automatically populating list of my publications, please have a look at them on the following locations:

• Web of Science
• Scopus
• DBLP of the University of Trier
• MTA-SZTAKI
• Google MyCitations Service
• Google Scholar
• Arnetminer
• Microsoft Academic Search
• Digital Library of the Association for Computer Machinery (ACM)
• iamResearcher
• ORCID
• ResearchGate
• MTMT - Hungarian Scientific Repository

Publications

My most referred paper has appeared in the Future Generation Computer Systems journal, it's title is the following: "An Approach for Virtual Appliance Distribution for Service Deployment." My other notable papers that show my progress through my research career are included in the following list with abstracts. Papers that I have had significantly contributed to are available from this site directly - and marked with a [PDF] sign before the author list.

2015.

• [PDF] G. Kecskmeti: "DISSECT-CF: a simulator to foster energy-aware scheduling in infrastructure clouds", in Simulation Modelling Practice and Theory, DOI: 10.1016/j.simpat.2015.05.009, to appear.
  • Abstract: Infrastructure as a Service (IaaS) systems offer on demand virtual infrastructures so reliably and flexibly that users expect a high service level. Therefore, even with regards to internal IaaS behaviour, production clouds only adopt novel ideas that are proven not to hinder established service levels. To analyse their expected behaviour, new ideas are often evaluated with simulators in production IaaS system-like scenarios. For instance, new research could enable collaboration amongst several layers of schedulers or could consider new optimisation objectives such as energy consumption. Unfortunately, current cloud simulators are hard to employ and they often have performance issues when several layers of schedulers interact in them. To target these issues, a new IaaS simulation framework (called DISSECT-CF) was designed. The new simulator's foundation has the following goals: easy extensibility, support energy evaluation of IaaSs and to enable fast evaluation of many scheduling and IaaS internal behaviour related scenarios. In response to the requirements of such scenarios, the new simulator introduces concepts such as: a unified model for resource sharing and a new energy metering framework with hierarchical and indirect metering options. Then, the comparison of several simulated situations to real-life IaaS behaviour is used to validate the simulator's functionality. Finally, a performance comparison is presented between DISSECT-CF and some currently available simulators.

2014.

• A. Kertesz, G. Kecskemeti, I. Brandic: "An interoperable and self-adaptive approach for SLA-based service virtualization in heterogeneous Cloud environments", Future Generation Computer Systems - The International Journal of Grid Computing and eScience, DOI: 10.1016/j.future.2012.05.016, Volume 32, Pages 54-68.
• G. Kecskmeti, A. Kertesz, M. Attila, Zs. Nemeth: " Strategies for Increased Energy Awareness in Cloud Federations", a chapter of High-Performance Computing on Complex Environments, DOI: 10.1002/9781118711897.ch19, ISBN: 9781118712054, Pages 365-382.
• [PDF] G. Kecskmeti, G. Terstyanszky, P. Kacsuk, Zs. Nemeth: "Towards Efficient Virtual Appliance Delivery with Minimal Manageable Virtual Appliances", IEEE Transactions on Services Computing, DOI: 10.1109/TSC.2013.12, Volume 7, Issue 2, Pages 279-292.
  • Abstract: Infrastructure as a Service systems use virtual appliances to initiate virtual machines. As virtual appliances encapsulate applications and services with their support environment, their delivery is the most expensive task of the virtual machine creation. Virtual appliance delivery is a well-discussed topic in the field of cloud computing. However, for high efficiency, current techniques require the modification of the underlying IaaS systems. To target the wider adoptability of these delivery solutions, this article proposes the concept of minimal manageable virtual appliances (MMVA) that are capable of updating and configuring their virtual machines without the need to modify IaaS systems. To create MMVAs, we propose to reduce manageable virtual appliances until they become MMVAs. This research also reveals a methodology for appliance developers to incorporate MMVAs in their own appliances to enable their efficient delivery and wider adoptability. Finally, the article evaluates the positive effects of MMVAs on an already existing delivery solution: the Automated Virtual appliance creation Service (AVS). Through experimental evaluation, we present that the application of MMVAs not only increases the adoptability of a delivery solution but it also significantly improves its performance in highly-dynamic systems.
• [PDF] G. Kecskmeti, S. Ostermann, R. Prodan: "An Architecture to Stimulate Behavioral Development of Academic Cloud Users", Sustainable Computing: Informatics and Systems, DOI: 10.1016/j.suscom.2014.04.002, Volume 4, Issue 2, Pages 136-150.
  • Abstract: Academic cloud infrastructures are constructed and maintained so they minimally constrain their users. Since they are free and do not limit usage patterns, academics developed such behavior that jeopardizes fair and flexible resource provisioning. For efficiency, related work either explicitly limits user access to resources, or introduce automatic rationing techniques. Surprisingly, the root cause (i.e., the user behavior) is disregarded by these approaches. This article compares academic cloud user behavior to its commercial equivalent. We deduce, that academics should behave like commercial cloud users to relieve resource provisioning. To encourage commercial like behavior, we propose an architectural extension to existing academic infrastructure clouds. First, every user's energy consumption and efficiency is monitored. Then, energy efficiency based leader boards are used to ignite competition between academics and reveal their worst practices. Leader boards are not sufficient to completely change user behavior. Thus, we introduce engaging options that encourage academics to delay resource requests and prefer resources more suitable for the infrastructure's internal provisioning. Finally, we evaluate our extensions via a simulation using real life academic resource request traces. We show a potential resource utilization reduction (by the factor of at most 2.6) while maintaining the unlimited nature of academic clouds.

2013.

• A. Kertesz, G. Kecskemeti, M. Oriol, P. Kotcauer, S. Acs, M. Rodrigez, O. Merce, A. Cs. Marosi, J. Marco, X. Franch: "Enhancing Federated Cloud Management with an Integrated Service Monitoring Approach", Journal of Grid Computing, DOI: 10.1007/s10723-013-9269-0, Volume 11, Number 4, Pages 699-720.

2012.

• A. Kertesz, G. Kecskemeti, A. Marosi, M. Oriol, X. Franch and J. Marco: "Integrated Monitoring Approach for Seamless Service Provisioning in Federated Clouds", in Proceedings of the Cloud Computing for Compute and Data Intensive Applications special session of the 20th Euromicro conference on parallel, distributed and network-based processing. Leipniz Supercomputing Centre, Garching, February 15-17th 2012. pp. 567-574. ISBN:978-0-7695-4633-9, DOI: 10.1109/PDP.2012.25
• [PDF] G. Kecskemeti, M. Maurer, I. Brandic, A. Kertesz, Zs. Nemeth and S. Dustdar: "Facilitating self-adaptable Inter-Cloud management", in Proceedings of the Cloud Computing for Compute and Data Intensive Applications special session of the 20th Euromicro conference on parallel, distributed and network-based processing. Leipniz Supercomputing Centre, Garching, February 15-17th 2012. pp. 575-582. ISBN:978-0-7695-4633-9, DOI: 10.1109/PDP.2012.41
  • Abstract: Cloud Computing infrastructures have been developed as individual islands, and mostly proprietary solutions so far. However, as more and more infrastructure providers apply the technology, users face the inevitable question of using multiple infrastructures in parallel. Federated cloud management systems offer a simplified use of these infrastructures by hiding their proprietary solutions. As the infrastructure becomes more complex underneath these systems, the situations (like system failures, handling of load peaks and slopes) that users cannot easily handle, occur more and more frequently. Therefore, federations need to manage these situations autonomously without user interactions. This paper introduces a methodology to autonomously operate cloud federations by controlling their behavior with the help of knowledge management systems. Such systems do not only suggest reactive actions to comply with established Service Level Agreements (SLA) between provider and consumer, but they also find a balance between the fulfillment of established SLAs and resource consumption. The paper adopts rule-based techniques as its knowledge management solution and provides an extensible rule set for federated clouds built on top of multiple infrastructures.
• [PDF] G. Kecskemeti, G. Terstyanszky and P. Kacsuk. "Virtual Appliance Size Optimization with Active Fault Injection", in IEEE Transactions on Parallel and Distributed Systems, DOI: 10.1109/TPDS.2011.309, Volume 23, Number 10, Pages 1983-1995.
  • Abstract: Virtual appliances store the required information to instantiate a functional virtual machine on Infrastructure as a Service (IaaS) cloud systems. Large appliance size obstructs IaaS systems to deliver dynamic and scalable infrastructures according to their promise. To overcome this issue, this article offers a novel technique for virtual appliance developers to publish appliances for the dynamic environments of IaaS systems. Our solution achieves faster virtual machine instantiation by reducing the appliance size while maintaining its key functionality. The new virtual appliance optimization algorithm identifies the removable parts of the appliance. Then, it applies active fault injection to remove the identified parts. Afterwards, our solution assesses the functionality of the reduced virtual appliance by applying the - appliance developer provided - validation algorithms. We also introduce a technique to parallelize the fault injection and validation phases of the algorithm. Finally, the prototype implementation of the algorithm is discussed to demonstrate the efficiency of the proposed algorithm through the optimization of two well-known virtual appliances. Results show that the algorithm significantly decreased virtual machine instantiation time and increased dynamism in IaaS systems.
• G. Kecskemeti, A. Kertesz, A. Cs. Marosi and P. Kacsuk. "Interoperable Resource Management for establishing Federated Clouds", in Achieving Federated and Self-Manageable Cloud Infrastructures: Theory and Practice, ISBN: 9781466616318. pp. 18-35. DOI: 10.4018/978-1-4666-1631-8.ch002
  • Abstract: Cloud Computing builds on the latest achievements of diverse research areas, such as Grid Computing, Service-oriented computing, business process modeling and virtualization. As this new computing paradigm was mostly lead by companies, several proprietary systems arose. Recently, alongside these commercial systems, several smaller-scale privately owned systems are maintained and developed. This chapter focuses on issues faced by users with interests on Multi-Cloud use and by Cloud providers with highly dynamic workloads. We propose a Federated Cloud Management architecture that provides unified access to a federated Cloud that aggregates multiple heterogeneous IaaS Cloud providers in a transparent manner. The architecture incorporates the concepts of meta-brokering, Cloud brokering and on-demand service deployment. The meta-brokering component provides transparent service execution for the users by allowing the interconnection of various Cloud brokering solutions. Cloud-Brokers manage the number and the location of the Virtual Machines performing the user requests. In order to decrease Virtual Machine instantiation time and increase dynamism in the system, our service deployment component optimizes service delivery by encapsulating services as virtual appliances allowing their decomposition and replication among IaaS Cloud infrastructures. The architecture achieves service provider level transparency through automatic virtual appliance replication and Virtual Machine management of Cloud-Brokers.

2011.

• S. Guinea, G. Kecskemeti, A. Marconi and B. Wetzstein. "Multi-layered Monitoring and Adaptation", in Service-Oriented Computing: 9th International Conference, ICSOC 2011, Paphos, Cyprus, December 5-8, 2011 Proceedings. ISBN: 978-3-642-25535-9.
• A. Cs. Marosi, G. Kecskemeti, A. Kertesz and P. Kacsuk. "FCM: an Architecture for Integrating IaaS Cloud Systems", in Proceedings of the Second International Conference on Cloud Computing, GRIDs, and Virtualization (CLOUD COMPUTING 2011). ISBN: 978-1-61208-153-3.
• [PDF] G. Kecskemeti, G. Terstyanszky, P. Kacsuk and Zs. Nemeth. "An Approach for Virtual Appliance Distribution for Service Deployment", Future Generation Computer Systems - The International Journal of Grid Computing and eScience, DOI: 10.1016/j.future.2010.09.009, Volume 27, Number 3, Pages 280-289.
  • Abstract: Fulfilling a service request in highly dynamic service environments may require deploying a service. Therefore, the effectiveness of service deployment systems affects initial service response times. On Infrastructure as a Service (IaaS) cloud systems deployable services are encapsulated in virtual appliances. Services are deployed by instantiating virtual machines with their virtual appliances. The virtual machine instantiation process is highly dependent on the size and availability of the virtual appliance that is maintained by service developers. This article proposes an automated virtual appliance creation service that aids the service developers to create efficiently deployable virtual appliances œôòó in former systems this task was carried out manually by the developer. We present an algorithm that decomposes these appliances in order to replicate the common virtual appliance parts in IaaS systems. These parts are used to reduce the deployment time of the service by rebuilding the virtual appliance of the service on the deployment target site. With the prototype implementation of the proposed algorithms we demonstrate the decomposition and appliance rebuilding algorithms on a complex web service.
• A. Kertesz, G. Kecskemeti and I. Brandic. "Autonomic SLA-aware Service Virtualization for Distributed Systems", in Proceedings of the Virtualization in Distributed systems special session of the 19th Euromicro conference on parallel, distributed and network-based processing. Cyprus, February, 2011. DOI: 10.1109/PDP.2011.17
• [PDF] [buy] G. Kecskemeti. "Foundations of Efficient Virtual Appliance Based Service Deployments", PhD dissertation, University of Westminster, December 2011. Also available from: the University of Westminster and EThOS (the online service of the British Library).
  • Abstract: The use of virtual appliances could provide a flexible solution to services deployment. However, these solutions suffer from several disadvantages: (i) the slow deployment time of services in virtual machines, and (ii) virtual appliances crafted by developers tend to be inefficient for deployment purposes. Researchers target problem (i) by advancing virtualization technologies or by introducing virtual appliance caches on the virtual machine monitor hosts. Others aim at problem (ii) by providing solutions for virtual appliance construction, however these solutions require deep knowledge about the service dependencies and its deployment process.
    This dissertation aids problem (i) with a virtual appliance distribution technique that first identifies appliance parts and their internal dependencies. Then based on service demand it efficiently distributes the identified parts to virtual appliance repositories. Problem (ii) is targeted with the Automated Virtual appliance creation Service (AVS) that can extract and publish an already deployed service by the developer. This recently acquired virtual appliance is optimized for service deployment time with the proposed virtual appliance optimization facility that utilizes active fault injection to remove the non-functional parts of the appliance. Finally, the investigation of appliance distribution and optimization techniques resulted the definition of the minimal manageable virtual appliance that is capable of updating and configuring its executor virtual machine.
    The deployment time reduction capabilities of the proposed techniques were measured with several services provided in virtual appliances on three cloud infrastructures. The appliance creation capabilities of the AVS are compared to the already available virtual appliances offered by the various on-line appliance repositories. The results reveal that the introduced techniques significantly decrease the deployment time of virtual appliance based deployment systems. As a result these techniques alleviated one of the major obstacles before virtual appliance based deployment systems.

2010.

• I. Brandic, V. C. Emeakaroha, M. Maurer, S. Acs, A. Kertesz, G. Kecskemeti and Schahram Dustdar. "LAYSI: A Layered Approach for SLA-Violation Propagation in Self-manageable Cloud Infrastructures", in Proceedings of the First IEEE International Workshop on Emerging Applications for Cloud Computing (CloudApp 2010), In conjunction with the 34th Annual IEEE International Computer Software and Applications Conference Seoul, pp. 365-370, Korea, July 19-23 2010.
• F. Andre, I. Brandic, E. Daubert, G. Gauvrit, M. Giordano, G. Kecskemeti, A. Kertesz, C. Di Napoli, Zs. Nemeth, J-L. Pazat, H. Psaier, W. Renz and J. Sudeikat. "Architectures & Infrastructure", in Service Research Challenges and Solutions for the Future Internet. Editors: Papazoglou, M., Pohl, K., Parkin, M., Metzger, A.. ISBN: 978-3-642-17598-5, Springer, pp. 85-117.
• A. Metzger, S. Benbernou, M. Carro, M. Driss, G. Kecskemeti, R. Kazhamiakin, K. Krytikos, A. Mocci, E. Di Nitto, B. Wetzstein and F. Silvestri. "Analytical Quality Assurance", in Service Research Challenges and Solutions for the Future Internet. Editors: Papazoglou, M., Pohl, K., Parkin, M., Metzger, A.. ISBN: 978-3-642-17598-5, Springer, pp. 209-271.

2009.

• A. Kertesz, G. Kecskemeti and I. Brandic. "Autonomic Resource Virtualization in Cloud-like Environments", Technical Report, TUV-1841-2009-04, Distributed Systems Group, Institute for Information Systems, Vienna University of Technology
• [PDF] A. Kertesz, G. Kecskemeti and I. Brandic. "An SLA-based Resource Virtualization Approach For On-demand Service Provision", in Proceedings of International Conference on Autonomic Computing, 3rd International Workshop on Virtualization Technologies in Distributed Computing (pp.: 27-34)

  • Abstract: Cloud computing is a newly emerged research infrastructure that builds on the latest achievements of diverse research areas, such as Grid computing, Service-oriented computing, business processes and virtualization. In this paper we present an architecture for SLA-based resource virtualization that provides an extensive solution for executing user applications in Clouds. This work represents the first attempt to combine SLA-based resource negotiations with virtualized resources in terms of on-demand service provision resulting in a holistic virtualization approach. The architecture description focuses on three topics: agreement negotiation, service brokering and deployment using virtualization. The contribution is also demonstrated with a real-world case study.
• E. Urbach, P. Kacsuk, Z. Farkas, G. Fedak, G. Kecskemeti, O. Lodygensky, A. Cs. Marosi, Z. Balaton, G. Caillat, G. Gomb�ás, A. Kornafeld, J. Kov�ács, H. He and R. Lovas. "EDGeS: Bridging EGEE to BOINC and Xtrem Web", in Journal of Grid Computing, Special Issue: Grid Interoperability (Volume: 7, No. 3, pp.: 335 -354)
• CD-JRA-1.2.4: Integrated adaptation and monitoring principles, techniques and methodologies across functional SBA layers. A research deliverable of the S-Cube project. Editor: G. Kecskemeti.

2008.

• [PDF] G. Kecskemeti, P. Kacsuk, T. Delaitre and G. Terstyanszky. "VIRTUAL APPLIANCES: A WAY TO PROVIDE AUTOMATIC SERVICE DEPLOYMENT" in proceedings of� 3rd International Workshop on Distributed Cooperative Laboratories (INGRID2008)
• [PDF] G. Kecskemeti, P. Kacsuk, G. Terstyanszky, T. Kiss and T. Delaitre. "Automatic service deployment using virtualisation." in proceedings of� 16th Euromicro conference on parallel, distributed and network-based processing pp.: 628-635., Toulouse� 
  • Abstract: Manual deployment of the application usually requires expertise both about the underlying system and the application. Automatic service deployment can improve deployment significantly by using on-demand deployment and self-healing services. To support these features this paper describes an extension the Globus Workspace Service. This extension includes creating virtual appliances for Grid services, service deployment from a repository, and influencing the service schedules by altering execution planning services, candidate set generators or information systems.

2007.

• [PDF] G. Kecskemeti, G. Terstyanszky, T. Kiss, T. Delaitre and P. Kacsuk. "Automatic service deployment using virtualisation." in proceedings of the UK e-Science all hands meeting 2007 (pp.: 718-725.),� Nottingham� 

2006.

• P. Kacsuk, G. Sipos, A. Toth, Z. Farkas, G. Kecskemeti, and G. Herman. "Defining and running parametric study workflow applications by the P-GRADE portal." in proceedings of�  Cracow grid Workshop'06. Cracow (pp.: 75-83.)
• [PDF] G. Kecskemeti, G. Terstyanszky, T. Kiss, and P. Kacsuk. "Legacy Code Repository with Broker-based Job Execution"� in CoreGRID Workshop on Grid Systems, Tools and Environments
  • Abstract: As Grid technology matures more and more production Grids become available to run computationally intensive scientific applications. However, as these Grids are based on different middleware solutions interoperation between these platforms is one of the major challenges the Grid community is facing today. The P-GRADE/GEMLCA portal is a workflow oriented Grid portal that supports the execution of workflow components simultaneously on multiple Grids based on different underlying technology. Jobs can be submitted to Globus or LCG/gLite based Grids, or can be selected from the GEMLCA legacy code repository. However, as GEMLCA is implemented on top of GT4, it was capable to interact only with GT2 and GT4 based Grids until recently. Moreover, legacy codes selected from the GEMLCA repository were statically mapped to resources. This paper describes how GEMLCA has been ported to the LCG/g-Lite based EGEE infrastructure. Besides simply porting GEMLCA to another middleware it had to be made capable to interact with the EGEE broker solution. A legacy code can not only be selected from the repository, but using its legacy code interface description it is also defined which resources are capable to execute the given code. Based on this information the broker can find the most suitable resource at workflow execution. As a result of this integration the P-GRADE/GEMLCA portal is capable to interact with both Globus and LCG/g-Lite based Grids by the means of either direct or broker-based job submission, or by browsing and selecting the executable from the legacy code repository. The described work illustrates how two important components of production Grids, a legacy code solution and a Grid broker can be successfully integrated.
• R. Stancheva, G. Terstyanszky, T. Kiss, T. Delaitre, S. Winter, P. Kacsuk and G. Kecskemeti. "Hidden access mechanism for demonstrating and teaching Grid"� in proceedings of MIPRO 2006. 29th international convention� (Pages: 212-217), Opatija.
• G. Terstyanszky, T. Kiss, T. Delaitre, S. Winter, P. Kacsuk and G. Kecskemeti. "Legacy code support for commercial production grids"� in proceedings of the UK e-Science All Hands Meeting 2006 (Pages: 21-28), Nottingham.
• T. Kiss, P. Kacsuk, G. Terstyanszky, T. Delaitre, G. Kecskemeti and S. Winter. "Solving Grid interoperability between 2nd and 3rd generation Grids by the integrated P-GRADE/GEMLCA portal" in proceedings of the UK e-Science All Hands Meeting 2006 (Pages: 389-392), Nottingham.
• G. Terstyanszky, T. Kiss, T. Delaitre, S. Winter, P. Kacsuk and G. Kecskemeti. "User support for next generation production Grids" in proceedings of Grid-enabling legacy applications and supporting end users workshop (GELA) in conjunction with HPDC 2006 (Pages: 35-43), Paris.
• G. Terstyanszky, T. Kiss, T. Delaitre, S. Winter, P. Kacsuk and G. Kecskemeti. "Service-oriented production grids and user support." In proceedings of� the 7th IEEE/ACM International Conference on Grid Computing, Barcelona, Spain, September 28-29, 2006. IEEE, Los Alamitos, USA, pp. 323-324. ISBN 1424403448

2005.

• T. Kiss, G. Terstyanszky, G. Kecskemeti, Sz. Illes, T. Delaitre, S. Winter, P. Kacsuk and G. Sipos. "Legacy code support for production Grids.", CoreGrid technical report TR 0011.
• Y. Zetuny, G. Kecskemeti, T. Kiss, G. Sipos, P. Kacsuk, G. Terstyanszky and S. Winter. "Deployment and interoperability of legacy code services" in Proceedings of the CoreGrid integration workshop. Integrated research in Grid computing. Pisa, (pp: 377-386)
• A. Goyeneche, T. Kiss, G. Terstyanszky, G. Kecskemeti, T. Delaitre, P. Kacsuk, and S. Winter. "Experiences with deploying legacy code applications as grid services using GEMLCA". In proceedings Advances in grid computing (EGC 2005): European Grid Conference, Amsterdam, The Netherlands, February 14-16, 2005: revised selected papers. Lecture notes in computer science (3470). Springer, Berlin, Germany, pp. 851-860. ISBN 3540269185
• [PDF] G. Kecskemeti, Y. Zetuny, G. Terstyanszky, S. Winter, T. Kiss and P. Kacsuk: "Automatic deployment and interoperability of grid services." in proceedings of the UK e-Science All Hands Meeting 2005, Steering via the Image in Local, Distributed and Collaborative Settings. EPSRC, Swindon, UK, pp. 729-736. ISBN 1904425534
  • Abstract: The Grid Execution Management for Legacy Code Architecture (GEMLCA) enables exposing legacy applications as Grid services without re-engineering the code, or even requiring access to the source files. The integration of current GT3 and GT4 based GEMLCA implementations with the P- GRADE Grid portal allows the creation, execution and visualisation of complex Grid workflows composed of legacy and non-legacy components. However, the deployment of legacy codes and mapping their execution to Grid resources is currently done manually. This paper outlines how GEMLCA can be extended with automatic service deployment, brokering, and information system support. A conceptual architecture for an Automatic Deployment Service (ADS) and for an x- Service Interoperability Layer (XSILA) are introduced explaining how these mechanisms support desired features in future releases of GEMLCA.
• T. Kiss, G. Terstyanszky, G. Kecskemeti, Sz. Illes, T. Delaitre, S. Winter, P. Kacsuk and G. Sipos. "Legacy code support for production grids." in proceedings of the 6th IEEE/ACM International Workshop on Grid Computing: November 13-14 2005. Seattle, Washington, USA. IEEE Computer Society, USA, pp. 278-283. ISBN 0780397933
• K. Madani, M. Lohi, G. Terstyanszky, Y. Zetuny and G. Kecskemeti. "A semi-autonomous generic network for seamless personalised services at home and elsewhere" In proceedings of IEE Forum on Autonomous Systems, 2005. IEEE Computer Society. ISBN 0863415865
• G. Terstyanszky, Y. Zetuny, G. Kecskemeti, K. Madani and M. Lohi: "Service management architecture in ePerSpace" in proceedings of EUROSCOM Summit 2005: Ubiquitous Services and Applications: Exploiting the Potential, 27-29 April 2005, Heidelberg, Germany. VDE Verlag, Berlin, Germany. ISBN 3800728915
• [PDF] G. Kecskemeti and G. Terstyanszky: "Automatic grid service deployment." in proceedings of� microCAD 2005 International Scientific Conference. microCAD, Miskolc, Hungary, pp. 201-206. ISBN 9636616566

2004.

• [PDF] G. Kecskemeti. "Comparison of Adaptive Classification Methods" - MSc. Thesis defended at the University of Miskolc
• [PDF] G. Kecskemeti and L. Kovacs. "Comparison of Classification Methods by Using the Reuters Database" in proceedings of XVIII. MicroCAD Internaltional Scientific Conference (MicroCAD 2004), Miskolc, Hungary
• T. Repasi, G. Kecskemeti and L. Kovacs: "Document classification in scope of spam filtering" in proceedings of 2nd Slovakian - Hungarian Joint Symposium on Applied Machine Intelligence (SAMI 2004), Herl'any, Slovakia, January 16-17.

Conference and journal organization

• PC Member of the "5th International Conference on Cloud Computing and Services Science", May 20-22nd, 2015 in Lisbon, Portugal.
• Chair of the "Cloud Computing on Infrastructure as a Service and its Applications" special session of the 23rd Euromicro International Conference on Parallel, Distributed and network-based Processing (PDP 2015) (4 March - 6 March 2014 in Turku, Finland)
• PC Member of the Architectrue track of "The 6th IEEE International Conference on Cloud Computing Technology and Science", December 15-18th, 2014 in Singapore.
• PC Member� of the WCCS14 - The second World Conference on Complex Systems November 10-13 2014 in Agadir, Morocco
• Chair of the "FedICI14: the second international workshop on Federative and interoperable cloud infrastructures"in conjunction with EuroPar, 25-26th August, 2014 in Porto, Portugal.
• PC Member of the "4th International Conference on Cloud Computing and Services Science", April 3-5th, 2014 in Barcelona, Spain.
• Chair of the "Cloud Computing on Infrastructure as a Service and its Applications" special session of the 22nd Euromicro International Conference on Parallel, Distributed and network-based Processing (PDP 2014) (12 February - 14 February 2014 in Turin, Italy)
• Chair of the "FedICI13: the first international workshop on Federative and interoperable cloud infrastructures"in conjunction with EuroPar, 26th August, 2013 in Aachen, Germany.
• PC Member of the "First International Workshop on Cloud Storage Optimization (CLOUSO)", in conjunction with the European Conference on Service Oriented and Cloud Computing, Sep 11th, 2013 in Malaga, Spain.
• Guest Editor of the Journal of Grid Computing for its "Special Issue on Interoperability, Federation Frameworks and Application Programming Interfaces for IaaS Clouds" published in March 2014 (volume 12, issue 1).
• PC Member of the "3rd International Conference on Cloud Computing and Services Science", May 8-10th, 2013 in Aachen, Germany.
• Co-Chair of the "Cloud Computing on Infrastructure as a Service and its Applications" special session of the 21st Euromicro International Conference on Parallel, Distributed and Network-Based Computing, 27th February - 1st March, 2013 in Belfast, Northern Ireland.
• PC Member of the "2nd International Conference on Cloud Computing and Services Science", April 18-21th, 2012 in Porto, Portugal.
• PC Member of the "Cloud Computing for Compute and Data Intensive Applications" special session of the 20th Euromicro International Conference on Parallel, Distributed and Network-Based Computing, February 15-17th, 2012 in Garching, Germany.
• PC Member� of the ECCS'11 - European Conference on Complex Systems September 12-16 2011 in Vienna, Austria
• PC Member� of the 19th� Euromicro International Conference on Parallel, Distributed and network-based Processing (PDP 2011) February 9-11 2011 in Ayia Napa, Cyprus
• PC Member of the "Virtualization in Distributed Systems" special session of the 19th� Euromicro International Conference on Parallel, Distributed and network-based Processing (PDP 2011) February 9-11 2011 in Ayia Napa, Cyprus
• PC Member of the "Virtualization in Distributed Systems" special session of the 18th� Euromicro International Conference on Parallel, Distributed and network-based Processing (PDP 2010) February 17-19 2010 in Pisa, Italy
• PC Member of the "Virtualization in Distributed Systems" special session of the 17th Euromicro International Conference on Parallel, Distributed and network-based Processing (PDP 2009) February 18-20 2009 in Weimar, Germany
• PC Member of the "Virtualization in Distributed Systems" special session of the 16th Euromicro International Conference on Parallel, Distributed and network-based Processing (PDP 2008) February 13-15 2008 in Tolouse, France

Talks, Presentations and Lectures

illustration by Mushon Zer-Aviv

• About the computer science journal article writing process, University of Miskolc, Hungary, Nov 29 2012. Download the talk's slides here: Hungarian version, English version.
• WS-PGrade and Clouds day of the SCI-BUS, SHIWA, EDGI joint Summer School on Workflows and Gateways for Grids and Clouds, Budapest, Hungary, July 5 2012
  Contents:
  • Introduction to clouds
  • Clouds using OpenNebula
• MSc course on Text Mining at the University of Miskolc, Hungary, 2012. 1 semester with around 10 students.
• BSc course on Web Technologies at the University of Miskolc, Hungary, 2011. 1 semester with around 10 students.
• SZTAKI's cloud solutions for Academic use, e-Science Caf�é, University of Obuda, Hungary, Nov 14 2011. - Lecture.
• MSc courses on Parallel and distributed systems I-II at the University of Miskolc, Hungary, 2006-2008. 4 semesters with over 100 students per semester.
• "P-Grade portal training for grid tool developers", MIMOS Berhad, Kuala Lumpur, Malaysia, June 30 - July 4 2008
  Contents (I,II,III):
  • Introduction to grids, EGEE and the P-Grade portal
  • Hands-on with the P-Grade portal
  • Architecture and development environment of the P-Grade portal
  • Gridsphere portlet development
  • Development with the different P-Grade portal APIs
• "Grid Computing Course", Porto, Portugal, January 22-24 2007
  Contents:
  • Web services resource framework concepts and the WSRF core component of Globus Toolkit 4 (GT4)
  • GT4, P-Grade portal and GEMLCA installation and configuration hands-on day
• "Porting applications using the P-GRADE portal and GEMLCA", BalticGrid Summer School, Tartu, Estonia, July 4-8 2006
  Contents:
  • Grid enabling applications using the P-Grade portal and GEMLCA
  • GEMLCA traffic simulation handson

Reviews for scientific journals

• Journal of Grid Computing - ISSN: 1570-7873 - reviewed 21 papers as of June 2015.
• Future Generation Computer Systems - ISSN: 0167-739X - reviewed 16 papers as of June 2015.
• Cluster Computing - ISSN: 1386-7857 - reviewed 5 papers as of June 2014.
• Journal of Systems and Software - ISSN: 0164-1212 - reviewed 1 paper as of June 2014
• IEEE Transactions on Dependable and Secure Computing - ISSN: 1545-5971 - reviewed 1 paper as of June 2014
• Journal of Parallel and Distributed Computing - ISSN: 0743-7315 - reviewed 1 paper as of June 2014.
• Computers and Electrical Engineering - ISSN: 0045-7906 - reviewed 1 paper as of June 2014.