International Journal of Grid and Utility Computing http://www.inderscience.com/browse/index.php?journalID=108&year=2011&vol=2&issue=4 Inderscience Publishers Ltd en-uk International Journal of Grid and Utility Computing 1741-847X 1741-8488 © 2011 Inderscience Publishers Ltd editor@inderscience.com https://www.inderscience.com/images/files/coverImgs/ijguc_scoverijguc.jpg http://www.inderscience.com/browse/index.php?journalID=108&year=2011&vol=2&issue=4 http://www.inderscience.com/link.php?id=42942 Constructing application marketplace to supply application services is a new trend of service industry. However, traditional techniques used to build a marketplace may not be easy to cooperate and integrate. The construction process also wastes huge cost and time. Therefore, the valuable reference architecture for easy building the application marketplace becomes more important. This research proposed the reference architecture for a new marketplace service construction and integration. The proposed system is named AMaaS (Application Marketplace as a Service), which redesigned the original architecture of online application marketplace according to the concept of Software as a Service (SaaS). Besides, this work preserves the feasible features to conjunct with other optional functionalities, like payment service and certification service, etc. Our proposed system is the state-of-the-art towards to develop the internet integrated service for mobile devices and applications. A reference architecture for application marketplace service based on SaaS
Shih-Fang Chang
International Journal of Grid and Utility Computing, Vol. 2, No. 4 (2011) pp. 243 - 252
Constructing application marketplace to supply application services is a new trend of service industry. However, traditional techniques used to build a marketplace may not be easy to cooperate and integrate. The construction process also wastes huge cost and time. Therefore, the valuable reference architecture for easy building the application marketplace becomes more important. This research proposed the reference architecture for a new marketplace service construction and integration. The proposed system is named AMaaS (Application Marketplace as a Service), which redesigned the original architecture of online application marketplace according to the concept of Software as a Service (SaaS). Besides, this work preserves the feasible features to conjunct with other optional functionalities, like payment service and certification service, etc. Our proposed system is the state-of-the-art towards to develop the internet integrated service for mobile devices and applications.

]]> 10.1504/IJGUC.2011.042942 International Journal of Grid and Utility Computing, Vol. 2, No. 4 (2011) pp. 243 - 252 Shih-Fang Chang Industrial Technology Research Institute (ITRI), 195, Sec. 4, Chung Hsing Rd., Chutung, Hsinchu 31040, Taiwan application marketplace App Store SaaS software as a service PaaS platform as a service Web 2.0 SOA service-oriented architecture internet services mobile devices. 2011-10-08T23:20:50-05:00 2 4 243 252 2011-10-08T23:20:50-05:00 http://www.inderscience.com/link.php?id=42943 In recent years, organisations have been seeking technological solutions for enacting their business process models using ad-hoc and heuristic approaches. However, limited results have been obtained due to the expansion of business processes across geographical boundaries and the absence of structured methods, frameworks and/or Information Technology (IT) infrastructures to enact these processes. In an attempt to enact business process models using distributed technologies, we introduce a novel architectural framework to bridge the gap between business process models and Grid-aware Service-Oriented Architectures (GSOA). BPMSOA framework is aligned with the Model-Driven Engineering (MDE) approach and is instantiated for role-based business process models [in particular Role Activity Diagramming (RAD)], using mobile process languages such as pi-ADL. The evaluation of the BPMSOA framework using the Submission process from the digital libraries domain has revealed that role-based business process models can be successfully enacted in GSOA environments with certain limitations. Bridging the gap between business process models and service-oriented architectures with reference to the grid environment
Zaheer Khan, Mohammed Odeh, Richard McClatchey
International Journal of Grid and Utility Computing, Vol. 2, No. 4 (2011) pp. 253 - 283
In recent years, organisations have been seeking technological solutions for enacting their business process models using ad-hoc and heuristic approaches. However, limited results have been obtained due to the expansion of business processes across geographical boundaries and the absence of structured methods, frameworks and/or Information Technology (IT) infrastructures to enact these processes. In an attempt to enact business process models using distributed technologies, we introduce a novel architectural framework to bridge the gap between business process models and Grid-aware Service-Oriented Architectures (GSOA). BPMSOA framework is aligned with the Model-Driven Engineering (MDE) approach and is instantiated for role-based business process models [in particular Role Activity Diagramming (RAD)], using mobile process languages such as pi-ADL. The evaluation of the BPMSOA framework using the Submission process from the digital libraries domain has revealed that role-based business process models can be successfully enacted in GSOA environments with certain limitations.

]]> 10.1504/IJGUC.2011.042943 International Journal of Grid and Utility Computing, Vol. 2, No. 4 (2011) pp. 253 - 283 Zaheer Khan Mohammed Odeh Richard McClatchey Centre for Complex Cooperative Systems, Department of Computer Science and Creative Technology, Faculty of Environment and Technology, University of the West of England, BS16 1QY, Bristol, UK. ' Centre for Complex Cooperative Systems, Department of Computer Science and Creative Technology, Faculty of Environment and Technology, University of the West of England, BS16 1QY, Bristol, UK. ' Centre for Complex Cooperative Systems, Department of Computer Science and Creative Technology, Faculty of Environment and Technology, University of the West of England, BS16 1QY, Bristol, UK grid aware utility services RAD business process models metamodelling pi-ADL process enactment model-driven engineering model transformation grid computing service-oriented architecture SOA role activity diagramming. 2011-10-08T23:20:50-05:00 2 4 253 283 2011-10-08T23:20:50-05:00 http://www.inderscience.com/link.php?id=42944 Shibboleth provides a federated single sign-on and an attribute exchange framework through its use of the security assertion markup language (SAML). One of major challenges for Shibboleth is the release of the user's information from an identity provider (IdP) to the service provider (SP) without prior consent of the user, and this may not comply with the privacy laws in some countries. This paper presents the requirements of a user consent acquisition system (UCAS) and a discussion on the existing UCASs for utilising GakuNin (Japanese academic federation) and the UCAS that we developed and call uApprove.jp. uApprove.jp is an extension of uApprove to enable users to control the release of optional attributes (user-attribute-filter) and to re-request the user consent if his/her information has changed (attribute-value check). User consent acquisition system for Japanese Shibboleth-based academic federation (GakuNin)
Tananun Orawiwattanakul, Kazutsuna Yamaji, Motonori Nakamura, Toshiyuki Kataoka, Noboru Sonehara
International Journal of Grid and Utility Computing, Vol. 2, No. 4 (2011) pp. 284 - 294
Shibboleth provides a federated single sign-on and an attribute exchange framework through its use of the security assertion markup language (SAML). One of major challenges for Shibboleth is the release of the user's information from an identity provider (IdP) to the service provider (SP) without prior consent of the user, and this may not comply with the privacy laws in some countries. This paper presents the requirements of a user consent acquisition system (UCAS) and a discussion on the existing UCASs for utilising GakuNin (Japanese academic federation) and the UCAS that we developed and call uApprove.jp. uApprove.jp is an extension of uApprove to enable users to control the release of optional attributes (user-attribute-filter) and to re-request the user consent if his/her information has changed (attribute-value check).

]]> 10.1504/IJGUC.2011.042944 International Journal of Grid and Utility Computing, Vol. 2, No. 4 (2011) pp. 284 - 294 Tananun Orawiwattanakul Kazutsuna Yamaji Motonori Nakamura Toshiyuki Kataoka Noboru Sonehara National Institute of Informatics, 2-1-2 Hitotsubashi, Chiyoda-ku, Tokyo 101-8430, Japan. ' National Institute of Informatics, 2-1-2 Hitotsubashi, Chiyoda-ku, Tokyo 101-8430, Japan. ' National Institute of Informatics, 2-1-2 Hitotsubashi, Chiyoda-ku, Tokyo 101-8430, Japan. ' National Institute of Informatics, 2-1-2 Hitotsubashi, Chiyoda-ku, Tokyo 101-8430, Japan. ' National Institute of Informatics, 2-1-2 Hitotsubashi, Chiyoda-ku, Tokyo 101-8430, Japan GakuNin Japanese Academic Federation user consent Shibboleth uApprove SAML security assertion markup language privacy laws. 2011-10-08T23:20:50-05:00 2 4 284 294 2011-10-08T23:20:50-05:00 http://www.inderscience.com/link.php?id=42945 Due to the recent popularisation of digital webcast systems, delivering continuous media data, i.e. audio and video, has been attracted great attention. In node relay-based webcast, the server has better load balance by receiving data concurrently from other several nodes. Conventional methods reduce waiting time by sharing channels and receiving data from them. However, since the number of nodes by which the user can receive the data is one, occupation time of available bandwidth of the node increases. In this paper, we propose a scheduling method to reduce the waiting time for node relay-based webcast. In our proposed method, by considering available bandwidth of each node and producing an effective schedule, the waiting time is reduced. A scheduling method for waiting time reduction in node relay-based webcast considering available bandwidth
Yusuke Gotoh, Tomoki Yoshihisa, Hideo Taniguchi, Masanori Kanazawa
International Journal of Grid and Utility Computing, Vol. 2, No. 4 (2011) pp. 295 - 302
Due to the recent popularisation of digital webcast systems, delivering continuous media data, i.e. audio and video, has been attracted great attention. In node relay-based webcast, the server has better load balance by receiving data concurrently from other several nodes. Conventional methods reduce waiting time by sharing channels and receiving data from them. However, since the number of nodes by which the user can receive the data is one, occupation time of available bandwidth of the node increases. In this paper, we propose a scheduling method to reduce the waiting time for node relay-based webcast. In our proposed method, by considering available bandwidth of each node and producing an effective schedule, the waiting time is reduced.

]]> 10.1504/IJGUC.2011.042945 International Journal of Grid and Utility Computing, Vol. 2, No. 4 (2011) pp. 295 - 302 Yusuke Gotoh Tomoki Yoshihisa Hideo Taniguchi Masanori Kanazawa Graduate School of Natural Science and Technology, Okayama University, Okayama 7008530, Japan. ' Cybermedia Center, Osaka University, Osaka 5650871, Japan. ' Graduate School of Natural Science and Technology, Okayama University, Okayama 7008530, Japan. ' The Kyoto College of Graduate Studies for Informatics, 7 Monzen-cho Tanaka Sakyo-ku, Kyoto 6068225, Japan continuous media data node relay-based webcast scheduling waiting time available bandwidth. 2011-10-08T23:20:50-05:00 2 4 295 302 2011-10-08T23:20:50-05:00 http://www.inderscience.com/link.php?id=42946 This paper considers an InfiniBand connection between two bwGRiD clusters over a distance of 28 km in day-to-day production use. We discuss the hardware set-up of InfiniBand messages converted and transported over a fibre optic connection. The two clusters can be operated as single system image, the batch system will enforce that all nodes for a job are allocated on one side of the cluster. This is to optimise MPI performance, which would not be sufficient for communication between nodes on opposite sides of the 28 km connection. We report on the successful solution of all technical and organisational integration hurdles. By a simple performance model we discuss the anticipated costs for a doubling in communication performance. Operating two InfiniBand grid clusters over 28 km distance
Sabine Richling, Steffen Hau, Heinz Kredel, Hans-Günther Kruse
International Journal of Grid and Utility Computing, Vol. 2, No. 4 (2011) pp. 303 - 312
This paper considers an InfiniBand connection between two bwGRiD clusters over a distance of 28 km in day-to-day production use. We discuss the hardware set-up of InfiniBand messages converted and transported over a fibre optic connection. The two clusters can be operated as single system image, the batch system will enforce that all nodes for a job are allocated on one side of the cluster. This is to optimise MPI performance, which would not be sufficient for communication between nodes on opposite sides of the 28 km connection. We report on the successful solution of all technical and organisational integration hurdles. By a simple performance model we discuss the anticipated costs for a doubling in communication performance.

]]> 10.1504/IJGUC.2011.042946 International Journal of Grid and Utility Computing, Vol. 2, No. 4 (2011) pp. 303 - 312 Sabine Richling Steffen Hau Heinz Kredel Hans-Günther Kruse IT Center, University of Heidelberg, 69120 Heidelberg, Germany. ' IT Center, University of Mannheim, 68131 Mannheim, Germany. ' IT Center, University of Mannheim, 68131 Mannheim, Germany. ' IT Center, University of Mannheim, 68131 Mannheim, Germany operating clusters long-distance InfiniBand performance modelling grid utility grid computing grid clusters fibre optics communication performance. 2011-10-08T23:20:50-05:00 2 4 303 312 2011-10-08T23:20:50-05:00 http://www.inderscience.com/link.php?id=42947 Security-aware scheduling for real-time grid applications is an important task and a little work has been done to accomplish this. In this paper, we propose two scheduling algorithms for real-time grid applications with stringent security requirements, and the proposed algorithms are compared with a few existing scheduling algorithms, i.e. MinMin, MaxMin, EDF/ECT, SPMinMin and SPMaxMin. Security overhead computation for existing and proposed models is done on the basis of security level demand of the tasks. Performance of WB-EDFMin on success rate performance metric is considered to be the best among all the contemporary scheduling algorithms. SFWB-EDFMin compromises on the overall success rate of the grid application but its task scheduling is uniformly spread over the tasks of all security levels. Weight-balanced security-aware scheduling for real-time computational grid
Rekha Kashyap, Deo Prakash Vidyarthi
International Journal of Grid and Utility Computing, Vol. 2, No. 4 (2011) pp. 313 - 325
Security-aware scheduling for real-time grid applications is an important task and a little work has been done to accomplish this. In this paper, we propose two scheduling algorithms for real-time grid applications with stringent security requirements, and the proposed algorithms are compared with a few existing scheduling algorithms, i.e. MinMin, MaxMin, EDF/ECT, SPMinMin and SPMaxMin. Security overhead computation for existing and proposed models is done on the basis of security level demand of the tasks. Performance of WB-EDFMin on success rate performance metric is considered to be the best among all the contemporary scheduling algorithms. SFWB-EDFMin compromises on the overall success rate of the grid application but its task scheduling is uniformly spread over the tasks of all security levels.

]]> 10.1504/IJGUC.2011.042947 International Journal of Grid and Utility Computing, Vol. 2, No. 4 (2011) pp. 313 - 325 Rekha Kashyap Deo Prakash Vidyarthi School of Computer and Systems Sciences, Jawaharlal Nehru University, New Delhi 110067, India. ' School of Computer and Systems Sciences, Jawaharlal Nehru University, New Delhi 110067, India grid computing real-time secured scheduling security-aware scheduling grid scheduling CipherSuite success rate average response time security. 2011-10-08T23:20:50-05:00 2 4 313 325 2011-10-08T23:20:50-05:00