Showing papers in "International Journal of Web and Grid Services in 2012"

Meta-scheduling issues in interoperable HPCs, grids and clouds

Abstract: Over the last years, interoperability among resources has been emerged as one of the most challenging research topics. However, the commonality of the complexity of the architectures (e.g., heterogeneity) and the targets that each computational paradigm including HPC, grids and clouds aims to achieve (e.g., flexibility) remain the same. This is to efficiently orchestrate resources in a distributed computing fashion by bridging the gap among local and remote participants. Initially, this is closely related with the scheduling concept which is one of the most important issues for designing a cooperative resource management system, especially in large scale settings such as in grids and clouds. Within this context, meta-scheduling offers additional functionalities in the area of interoperable resource management, this is because of its great agility to handle sudden variations and dynamic situations in user demands. Accordingly, the case of inter-infrastructures, including InterCloud, entitle that the decentralised meta-scheduling scheme overcome issues like consolidated administration management, bottleneck and local information exposition. In this work, we detail the fundamental issues for developing an effective interoperable meta-scheduler for e-infrastructures in general and InterCloud in particular. Finally, we describe a simulation and experimental configuration based on real grid workload traces to demonstrate the interoperable setting as well as provide experimental results as part of a strategic plan for integrating future meta-schedulers.

The smart-travel system: utilising cloud services to aid traveller with personalised requirement

Abstract: Recent advancements in cloud computing allow smart phone provide a variety of movable services. This paper proposed a design of service, including human-centred recommendation service and travel-gaming service. The Smart-Travel System (STS) aids traveller with personal requirements to tour by smart phone. STS provides personalised travelling real-time information, and automatically tells traveller when they show up around the task, which providing by government or local store, to make the trip like a game mission for user. No matter if the traveller deviated from the planned route or not, the STS could provide the new trip itineraries and allows the share on social network in real-time from any computer. According to the cloud-based service, STS is a new way to look up the travel information. The STS provides a whole new experience in travelling for mobile phone users via smart phone, GPS, Google map and Augmented Realty.

Specifying and implementing an eventual leader service for dynamic systems

Abstract: The election of an eventual leader in an asynchronous system prone to process crashes is an important problem of fault-tolerant distributed computing. This problem is known as the implementation of the failure detector Ω. Nearly all papers that propose algorithms implementing such an eventual leader service consider a static system. In contrast this paper considers a dynamic system, i.e. a system in which processes can join and leave. The paper has three main contributions. It first proposes a specification of Ω suited to dynamic systems. Then, it presents and proves correct two algorithms implementing this specification. Finally, the paper discusses the notion of an eventual leader suited to dynamic systems. It introduces an additional property related to system stability. The design of an algorithm satisfying this last property remains an open challenging problem.

A spectral clustering-based optimal deployment method for scientific application in cloud computing

Abstract: Similar to Grid computing systems, scientific applications in cloud are large scale distributed systems that are deployed on distributed cloud nodes. Scientific applications usually have a lot of communications between the nodes for deployment. Therefore conventional ranking methods are not appropriate for deploying scientific applications. The reason is ranking methods do not consider the relations between nodes. We propose a novel spectral clustering based deployment method that takes not only the computing qualities of cloud nodes into account, but also the communication performance between different nodes. Experimental results show the effectiveness of our method for improving the performance of scientific applications.

Hybrid algorithms for independent batch scheduling in grids

Abstract: Grid computing has emerged as a wide area distributed paradigm for solving large-scale problems in science, engineering, etc. and is known as the family of eScience grid-enabled applications. Computing planning of incoming jobs efficiently with available machines in the grid system is the main requirement for optimised system performance. One version of the problem is that of independent batch scheduling, in which jobs are assumed to be independent and are scheduled in batches aimed at minimising the makespan and flowtime. Given the hardness of the problem, heuristics are used to find high quality solutions for practical purposes of designing efficient grid schedulers. Recently, considerable efforts were spent in implementing and evaluating not only stand-alone heuristics and meta-heuristics, but also their hybridisation into even higher level algorithms. In this paper, we present a study on the performance of two popular algorithms for the problem, namely Genetic Algorithms (GAs) and Tabu Search (TS) and two hybridisations involving them, namely, the GA (TS) and GA-TS, which differ in the way the main control and cooperation among GA and TS are implemented. The hierarchic and simultaneous optimisation modes are considered for the bi-objective scheduling problem. Evaluation is done using different grid scenarios generated by a grid simulator. The computational results showed that the hybrid algorithm outperforms both the GA and TS for the makespan parameter, but not for the flowtime parameter.

Comparative parallel execution of SWAT hydrological model on multicore and grid architectures

Abstract: The paper presents a comparative analysis made on the calibration of a large-scale model, executed both on grid and multicore architectures. The goal is to highlight the advantages brought by the grid infrastructure over the multicore architecture, especially for large-scale applications, which require large amounts of data and a large number of executions. The large-scale application used as a case study for this research work is the calibration of a large-scale SWAT hydrological model, covering the Danube River Basin.

Experiences of sampling-based approaches for estimating QoS parameters in the Web Service composition problem

Abstract: QoS parameters can be used to characterise services or their compositions according to non-functional criteria. We propose sampling-based techniques to accurately estimate QoS values that will be used in a hybrid composer named PT-SAM, to identify the compositions that best meet a user request. PT-SAM adapts a Petri-Net unfolding and uses a utility function defined on the QoS estimates, to guide the composer. We report on the quality of the estimates and the performance of the composer. Our experiments show that solutions generated by PT-SAM are close to the optimal solutions while the composer can scale to large search spaces.

MIRSOFT: mediator for integrating and reconciling sources using ontological functional dependencies

Abstract: Providing automatic integration solutions is the key to the success of applications managing massive amounts of data. Two main problems stand out in the major studies: (i) the management of the source heterogeneity; (ii) the reconciliation of query results. To tackle the first problem, formal ontologies are used to explicit the semantic of data. The reconciliation problem consists in deciding whether different identifiers refer to the same instance. Two main trends emerge in the reconciliation process: (i) the assumption that different source entities representing the same concept have the same key – a strong hypothesis that violates the autonomy of sources; (ii) The use of statistical methods that identify affinities between concepts – not suitable for sensitive applications. In this paper, we propose a methodology integrating sources referencing shared domain ontology enriched with functional dependencies (FD). The presence of FD gives more autonomy to sources when choosing their primary keys and allows deriving a reconciliation key for a given query. The methodology is then validated using LUBM.

A novel aspect-oriented BPEL framework for the dynamic enforcement of web services security

Abstract: In this paper, we propose a new framework for the dynamic enforcement of composite Web services security, which is based on a synergy between Aspect-Oriented Programming (AOP) and BPEL (Business Process Execution Language). This synergy is achieved through the elaboration of a new language called AspectBPEL, which is used to specify security policies as separate components, referred to as aspects, to be weaved systematically in a BPEL process. The injected aspects activate the security policies at runtime on specific join points. Our approach enjoys several additional features such as (1) separating the business and security concerns of composite Web services (2) allowing the update of security mechanisms of composite Web services at run time, (3) providing modularity for modelling cross-cutting concerns between Web services, (4) centralising some security measurements at the BPEL side and (5) providing a framework fully compatible with any BPEL engine regardless of the adopted development environment.

Semantic web services discovery based on I/O parameter relations

Abstract: For the precise selection of services, this paper proposes an efficient method for discovering services based on relations among input and output parameters. The proposed method consists of two steps. First, like the conventional methods, the proposed method computes candidate services, which are executable with the inputs of a user request and capable of satisfying all the outputs of the request. Relations among input and output parameters in a user request and candidate services are compared to select services that meet a user's intention. For service providers' convenience, the proposed method automatically extracts parameter relations from the documentations or comments of WSDL or OWL-S descriptions. Experimental results show that the proposed scheme for specifying relations among parameters facilitates the precise selection of services. The proposed method of automatically extracting relations reduces the overhead of manually describing relations while not decreasing the accuracy of service discovery too much.

Pragmatic granularity decision for right-grained services in service-oriented modelling

Abstract: The identification of right-grained services is important in leading a successful service orientation because it has a direct impact on two major goals: the composability of loosely-coupled services and the reusability of individual services in different contexts. Although the concept of service orientation has been intensely debated in recent years, a unified methodic approach for identifying services has not yet been identified. In this paper, we suggest a formal approach to identify services at the right level of granularity from the business process model abstraction. Our approach adopts the concept of activity allocation based on the locality principle for defining loosely-coupled services. The method utilising the concept of graph partitioning can minimise the network roundtrip costs incurred during the service execution. If we can define activities into a service as cohesively as possible, we can identify the reusable and self-contained services so as to reduce the coupling of remote tasks and increase the local task cohesion.

Glueing grids and clouds together: a service-oriented approach

Abstract: Scientific communities are actively developing services to exploit the capabilities of service-oriented distributed systems. This exploitation requires services to be specified and developed for a range of activities such as management and scheduling of workflows and provenance capture and management. Most of these services are designed and developed for a particular community of scientific users. The constraints imposed by architectures, interfaces or platforms can restrict or even prohibit the free interchange of services between disparate scientific communities. Using the notion of 'Platform as a Service' (PaaS), we propose an architectural approach that addresses these limitations so that users can make use of a wider range of services without being concerned about the development of cross-platform middleware, wrappers or any need for bespoke applications. The proposed architecture shields the details of heterogeneous Grid/Cloud infrastructure within a brokering environment, thus enabling users to concentrate on the specification of higher level services.

The design, implementation and usage analysis of an event-based consumer mashup system

Abstract: Mashups are web applications that combine data, content and application functionality from multiple sources to produce a single value-added application and they have been gaining wide popularity over the past few years. Due to the inherent programming difficulties required to integrate data and services from multiple sources, mashups have largely been a programmer's affair. Based on the research question "How to bring end-users closer to creating and using mashups", this paper presents the design and implementation of a user-centred mashup system which provides greater motivation for mashup usage by relating every-day calendar events to useful gadgets. The system is evaluated by 131 end-users to test for usability. Also, the system is used as a representative example in proposing a user-acceptance model for consumer mashups.

On cyberwarfare

Abstract: Today the computer networks of numerous organisations in critical digital infrastructure industries, as well as those of the militaries and governments around the world, are under constant cyberattacks. Many nation states are now preparing for cyberwarfare. However, it is not even clear what cyberwarfare is, as the term is used in the news media. In this paper, we first try to define the term. Then we examine the status of cyberwarfare; in particular, the weapons, the US preparations, the fog and the law of cyberwarfare.

Self-adaptive approximate queries for large-scale information aggregation

Abstract: Self-adaptation enables distributed software to modify its behaviour based on changes in the operating environment. In large-scale information systems for cloud computing that use hierarchical data aggregation, self-adaption may be used to respond to an approximate query, thereby reducing use of network bandwidth and retrieval time. We present a novel algorithm that uses an Analytic Hierarchical Process (AHP) in order to apply self-adaption to approximate queries based on network-awareness. The AHP-based algorithm provides a trade-off among network usage, retrieval time and the accuracy of the retrieved results. Simulations show that the number of needed messages reduces with AHP to a constant upper bound. The retrieval time reduces to a constant factor under an increasing number of nodes. Our results demonstrate that the algorithm is able to provide responses with the required accuracy, primarily by adapting the depth of the query based on the number of messages and the network conditions.

Mobility management for multimedia services in heterogeneous environments

Abstract: Nowadays, the wireless access network infrastructure is growing at an accelerated pace. In the current environment which consists of a multitude of wireless networks, live migration of multimedia streaming between different types of connectivity offers important advantages for mobile users. In this paper we provide the description of efficient mobility service architecture for multimedia environments. The proposed architecture handles multimedia streaming adaptation, session management, and takes into consideration user profiles and a set of quality of service criteria. Session management in a mobile environment also implies that a handover mechanism must be used in order to ensure session continuity when a user moves from one network to another. Our architecture supports handover at the application layer, which offers a better quality control than the majority of mobility solutions. In order to demonstrate the performance of our mobility solution, we analyse results from different test scenarios.

A paragraph-inserted word salad filtering algorithm

Abstract: Social spam is one type of spam which includes spamming the members of social websites by sending or posting unwanted ads or baiting them to visit particular websites. Word salad in turn is one type of social spam which aims at baiting people to visit particular websites, such as blogs, personal profiles, third-party applications built on social networking websites, etc. A word salad is created by inserting either words or paragraphs within a normal document, where the inserted words or paragraphs have no relevance to the document. The purpose of a word salad is to fool the search engines into assigning high ranks to the document. In this paper, we discuss an algorithm that filters (detects) paragraph-inserted word salads. The algorithm is based on the Singular Value Decomposition (SVD) method and, based on experiments, shows up to 81.3% accuracy.

An aspect-oriented framework for specification and enforcement of non-functional concerns in WS-BPEL

Abstract: Web Service processes in WS-BPEL have several non-functional requirements such as security and reliable messaging. Although there are many WS-* specifications that address these concerns, their integration with WS-BPEL is still open. In this paper, we discuss these non-functional requirements and present a survey on the current support for their specification and enforcement in WS-BPEL engines. Moreover, we introduce an aspect-oriented container framework that uses a declarative deployment descriptor to specify the non-functional requirements. For the enforcement, aspects in AO4BPEL 2.0 are generated, which intercept the process execution and call dedicated middleware Web Services.