Abstract:

Abstract:As an instance of Internet resource sharing based virtual computing environment, iVCE (Internet based virtual computing environment) for Memory try to solve the problem of memory resource sharing and utilization. Due to the special properties of memory resource, traditional resource management approaches can not be adapted easily. A clustering based resource aggregation scheme is proposed under the background of iVCE for Memory, which can reduce the problem scale efficiently. With analogy to the force field and potential energy theory in physics, the basic model, force field-potential energy model and corresponding distributed algorithms are proposed respectively. The models and algorithms are also evaluated by real network topology based simulation.

Abstract:Based on the fact that Web service dynamically changes and rapidly increases in the Internet, a user-oriented service workflow constructing model is proposed. The same or similar function services are accumulated into a kind of service set in this model, which is organized by the spanning tree, and the business spanning graph is formed according to workflow’s business logic relation. At the same time, on the basis of redefining the position, velocity, addition, subtraction and multiplication of particle swarm algorithm, combining with the cross and mutation operations in genetic algorithm, the QoS (quality of service)scheduling algorithm based on hybrid particle swarm optimization algorithm (HPSOA) is designed to satisfy different multi-QoS demands when Web service rapidly increases. Experimental results demonstrate that the constructing model could effectively shield the physical varieties and differences of Web service, and preferably combine the Web service resource in the Internet. It is suitable for the application demands in the virtual computing environment.

Abstract:The Virtual Computing Environment (VCE) should "on demand" collect and aggregate distributed resources, and provide efficient publication, discovery and subscription mechanisms. Since resources are usually virtualized as services, the goals of the VCE largely rely on service oriented computing technologies. However, Service Oriented Architecture (SOA) organizes services in a "provider-centric" manner, which brings a critical problem: More services come to being, more complex and difficult the service discovery and subscription become. A "consumer-centric" approach is proposed to addressing this problem. First, function similar services according to consumer’s functionality requirements are dynamically aggregated as a service pool. The pool will act as a virtual service so that consumers only discover and subscribe the service pool instead of a large number of candidate services. The qualities of the services in a service pool could form a spectrum of QoS so that consumer’s quality requirements can be satisfied by automated QoS negotiation. Based on the service pool, the VCE could provide an "on demand of consumers" way for resource sharing.

Abstract:An approach based on backward tree to compose services automatically is proposed. It composes services for a user through three steps: 1) Builds a complete backward trees on-line; 2) Searches for optimal valid generation sources (generation-paths); 3) Composes generation paths. Compared to traditional graph-based methods, it has a smaller search space and avoids the repetition search. Experimental results show that this method has a good performance even the repository has a large number of services.

Abstract:It is proposed to establish inverted indexing for ontology-annotated outputs when services are registered in order to find the target services in a quick, accurate and efficient way. For each ontology-annotated output, there is a service list which records all the services in the registry that deliver the output. Based on the indexing, a composition-oriented service discovery algorithm is proposed, which greatly accelerates the filtering of irrelevant atomic services by making use of the inverted indexing, and increases the likelihood of finding a possible candidate by exploring service composition. The results of the extensive experiments show that the proposed algorithm provides better performance on response time than the sequential matchmaking, and better recall rate than the algorithms without the exploration of composition.

Abstract:In open Internet environment, it is inevitable that multiple ontologies coexist. Centralized service discovery mechanism becomes the bottleneck of SOC (service oriented computing), which results in poor scalability of system. Aiming at solving these problems, a two layered P2P based model for semantic service discovery is proposed in this paper. The model is based on ontology community and integrates iVCE (Internet-based virtual computing environment) core concepts into a P2P model. Based on this model, a service discovery algorithm composed of two stages and three steps is proposed. It matches services across communities as well as within community. Within a community, algorithm locates registers holding service information with a high probability of satisfying a request firstly. Then it captures semantic matching between service advertisements and service requests by logical reasoning. Service discovery across communities occurs according to some policies. The model is suitable for opening environment with coexistent multiple ontologies. Experimental results show that given an appropriate setting, the model can make a tradeoff between recall and responding time. In addition, the model will release the mean load of registers efficiently while holding recall.

Abstract:Based on the characteristics of evolution, autonomy and diversity of Internet resources, researchers recently proposed to realize the publication and query of Internet resource information through common DHT (distributed Hash table) information services. However, current research on resource information services is insufficient in generality, usability and adaptability. Aiming at the needs of iVCE (Internet-based virtual computing environment) for resource aggregation, the SDIRIS (scalable distributed resource information service) is proposed to construct. First, the adaptive DHT (A-FissionE) infrastructure is presented, which supports to adapt to different system scale and stability transparently. Second, the MR-FissionE, which is an efficient multiple-attribute range query algorithm, is presented based on A-FissionE. Theoretical analysis and experimental results prove that SDIRIS can realize resource information publication and query efficiently.

Abstract:A unified framework based on Petri-net for the modeling of service behavior and QoS is proposed. Based on this framework a set of service consistency rules are derived to improve the accuracy of service discovery and to ensure the system consistency in service substitution. A middleware named SOBECA (service-oriented, behavior and capability support architecture) compatible with current Web services standards is developed to make a proof of concept of the framework. In SOBECA the service description is extended with behavior and quality attributes which can be automatically checked against current requirements.

Abstract:A trustworthiness-based ad-hoc secure interoperation method is proposed, in which the concept of trustworthiness is introduced to describe the probability of proper collaboration. The trustworthiness of an autonomic domain on a user is decided jointly by direct experiences of interactions and other domains’ assessments on the user. Only the users who satisfy the requirements of target domains’ trust policies have the privileges to access entry roles. Records of a user’s malicious actions will decrease his trustworthiness and then accordingly reduce his privileges. Target domain uses weighted majority algorithm to update recommender’s trustworthiness, which is reduced by unfair ratings. Experimental results show that this method can effectively resist cheating and malicious actions.

Abstract:By borrowing the construction and evolution mechanisms of the social groups, a reputation system based on groups of autonomic elements (AE) is proposed, which is called clique-based reputation system (CRS). With the combination of the clique-based reputation evaluation and reputation inspired clique evolution, CRS makes the reputation model more realistic on evaluation of the characteristic of AE behaviors and better convergent properties. Meanwhile, the node cluster results from the clique evolution make a foundation for the differential service for AE based on reputation, incentivize them to take corporative behaviors, and provide reliable services.

Abstract:RNMS (R-Net monitoring system), the monitoring infrastructure of R-Net virtual computing environment, takes intrusiveness control as an important research objective. RNMS tries to control the intrusiveness in many aspects. Of them, RNMS focuses on intrusiveness control in the procedure of monitoring data acquisition. Based on the concept of autonomic element, autonomic host sensors intrusiveness control mechanism and main control thought are introduced, and adaptive sensor control algorithm and policies are implemented. By practical testing, the usage background of adaptive algorithm and policies are described. Then, the monitoring accuracy and overhead are compared in different policies and configuration parameters by simulating. Comparing with the non-control policy, on the precondition of ensuring the monitoring accuracy, the monitoring with the adaptive policies can effectively reduce intrusiveness.

Abstract:A fine-grained controllable delegation authorization model (FCDAM) suitable for open environments is presented. It integrates the merits of both RBAC (role based access control) and role-based trust management and can effectively control the propagation of permissions of different sensitivity levels in roles. An approach for assigning trustworthiness thresholds to permissions in local access control policy is discussed. The RT₀ framework is extended to support trustworthiness and the algorithm of calculating the values of trustworthiness of entities in the extended framework is proposed. The usage of the FCDAM model is illustrated through a typical example.

Abstract:Based on the analysis of hypervisor technologies and typical projects on the hypervisor based virtual computing environment, the design of CIVIC (CROWN-based infrastructure for virtual computing) is provided, which has three characteristics. Firstly, it can offer separated and isolated computing environment for users. Secondly, it can also realize hardware and software consolidation and centralized management for computer administrators. Thirdly, it can be transparent to upper layer applications, hiding the dynamicity, distribution and heterogeneousness of underlying resources from applications. The experimental results show that CIVIC can provide a customized computing environment for user easily and efficiently.

Abstract:Based on the core mechanisms of Internet-based virtual computing environment (iVCE), a novel architectural framework for the multi-cluster task co-allocation is proposed by introducing the autonomic scheduling elements, domain scheduling commonwealth and meta-scheduling executor. A new multi-cluster task scheduling schema based on the multi-cluster task execution performance model is presented. Four multi-cluster heuristic scheduling algorithms are provided. Experiments indicate the scheduler schema and the algorithms are effective in the objective function of makespan and average utilization.

Abstract:In virtualized computing environments, users’ mobility in physical space poses a challenge in the research on the applications’ mobility in cyber space. The characteristics of network-intensiveness and resource-intensiveness in pervasive environments provide an opportunity for application mobility. To support it, the paper exploits software Agents to realize the resource virtualization in cyber space. It investigates the application mobility from the perspectives of underlying application model, mobility management, and context-awareness, etc. By exploiting software Agents’ inherent autonomy and mobility, an Agent-based mechanism for adaptive component binding and migration is proposed. A framework called MDAgent is proposed and the corresponding prototype is implemented. It can provide the support of mobility management, context-awareness, resource matching and logic reasoning for the application mobility. On top of the framework, several applications are implemented and the performances are evaluated.

Abstract:A semantic-based information integration scheme for MedImGrid (medical image grid) is presented, which creates parent-ontology (HL7-RIM ontology) based on HL7-RIM (health level 7 referenced information model), and adopts hybrid means to construct the hierarchical structure of MedImGrid global and local ontologies. The HL7 (health level 7) gird middleware is developed based on Agent and middleware technology, which gives the semantic parsing capability to HL7 intelligent Agent to support grid service encapsulation and uniform access of heterogeneous data sources. The interrelations of data modes at ontology layer are denoted with ontology tag and used to support the semantic parsing and mapping between different medical data sources referring to MedImGrid ontologies. MedImGrid prototype is based on CGSP2 (China grid support platform v2.0) and adopts global and local semantic mapping loosely coupled means, and its special layered structure makes resource sharing and matching across systems and hospitals more efficient.