Zhu Yian

Gaining Flexibility and Performance of Computing Using Tailored Instruction Set and Reconfigurable Architecture

As data transfer rates become higher, general processor is not competent for works with high computing intensity in wireless communication area. The other hand, existing baseband processors lack adaptive ability to support new applications and newer versions of existing application. Thus the paper puts forward a novel architecture of reconfigurable stream processor along with application-specific instruction set for software radio. The main goal of the processor is to point out an effective way to designing hardware of software radio with high computational performance and adaptive ability. We achieve this by analyzing multi-stream modalities of advanced wireless communication standards, such as 3G and WLAN. Simulation results show that the processor with powerful calculational capability can adapt to applications of wireless communication area easily.As data transfer rates become higher, general processor is not competent for works with high computing intensity in wireless communication area. The other hand, existing baseband processors lack adaptive ability to support new applications and newer versions of existing application. Thus the paper puts forward a novel architecture of reconfigurable stream processor along with application-specific instruction set for software radio. The main goal of the processor is to point out an effective way to designing hardware of software radio with high computational performance and adaptive ability. We achieve this by analyzing multi-stream modalities of advanced wireless communication standards, such as 3G and WLAN. Simulation results show that the processor with powerful calculational capability can adapt to applications of wireless communication area easily.

Multilevel Trust Management Framework for Pervasive Computing

A multilevel trust management framework in pervasive environment is proposed in this paper. In the framework, the trust, the reputation, reciprocity and related concepts are defined newly. The multilevel discrete trust metric finds a good way to solve the problems, which the granularity of binary trust is coarse and the calculation of continuous trust is complex. The design of storage counter in the framework makes up the deficiency that storage capacity of pervasive devices is limited. The experimental result indicates preliminarily that the multilevel trust metric has good effect on trusted authentication in pervasive environment.

Object Service Provision in Internet of Things

In this paper, we take the interoperability and collaborative problems among various objects belong to different smart space into account and propose the features for object service provision in smart space. On the basis of the above features, we give a semantic and automatic framework for objects service in smart space. In the framework, techniques of object service provision, context-aware, semantic reasoning, and pervasive service management are smoothly synthesized. A conceptual architecture is introduced in the light of functional characteristics of framework. It enables objects in smart space to interact spontaneously, provides semantic-integration context awareness, and supports meta-service based adaptability and scalability. Several technical challenges to develop Internet of Things need to be addressed is introduced in the last section.

A Model Driven Approach for Self-Healing Computing System

Self-healing system attempt to enable computing systems to automatically discover, diagnose, and repair (or at least mitigate) faults without human intervention, thus it is a potential approach to improve the dependability and autonomy of computing system. A model-driven approach for modeling and analyzing the self-healing computing system is proposed in this paper. In our approach, the function part and the self-healing part of the system can be modeled respectively. Further, a consequence-oriented fault model is proposed as the ligaments to keep the associations between the function model and the self-healing model. Based on the fault model, we can construct the self-healing model and further analyze the self-heal ability of the computing system. The approach has the advantages of the two aspects: 1) The functional components of target system and the self-healing components for the target system can be modeled respectively and can be coupled through fault model later, 2) The self-heal ability of the target system can be analyzed at the model level.

The Services Composition Algorithm in Incomplete Visible and Dynamic Environment

As the increasing of the type and number for web services, how to effectively deal with composition service problem in transparent and dynamic environment has become a hot issue for researchers. Considering most of the current works for service composition are based on the static and known topology, this paper puts forward a new service composition algorithm—NVDSCM, which show great interest for service composition in dynamic and partially-known environment. By dynamically and automatically monitoring the connection state with neighbors, NVDSCM can effectively reduce the number of duplicated and unnecessary composition request. Furthermore, it applies local-repair strategy to maintain the connection relation with neighbors for each web services, which is very important to improve algorithm efficiency for large scope. Based on the analysis of the experiment, NVDSCM can effectively solve the problem of service composition in partially-known and dynamic environment, including better composition path quality and more stability as the change of scope size.

An Autonomic Capacity Management Approach with Cloud Insight towards Cost-Efficient Throughput Optimization for High Performance Computing

High Performance Computing (HPC) leverages cluster combined with a set of computing nodes exploiting computational capacities to handle varying job submission for scientific computing work. Inappropriate capacity planning and related management mechanism applied, will lead HPC cluster into a rather large number of pending jobs which is considered as a critical factor to affect Systems throughput against the goal of HPC cluster. Moreover it will result in inefficiency and wasted capacities cost. Thus an autonomic capacity management approach is therefore proposed in this paper, in order to overcome such issues as regards. Firstly we survey recent researches related in deep, and find that they all lack of consideration on computing nodes personality which is crucial to solve job submission and is probable to lead submitted jobs into pending in case of there are insufficient computing nodes associated to this personality. Afterward we present our measures focused on autonomic capacity management by taking advantage of Cloud insight to provision capacities dynamically on demand. Such measures are capable of selfadaptively adjusting cluster capacities to form different personalities for varying job submission, by the repurposeability to coordinate capacities from the idle personality with lower running jobs to the other with higher demand on pending jobs. Finally we verify that, proposals in this paper are significantly in achieving optimized throughput by reducing the number of pending jobs in cost-efficiency, with a couple of simulations.

Improving Performance of Partial Reconfiguration Using Strategy of Virtual Deletion

In a partially reconfigurable system with online placement algorithm, we try to avoid mapping some redundant tasks by caching modules on the reconfigurable area. This paper proposes an elaborate strategy named virtual deletion and a low cost board- level hardware named recycle cache to accomplish the goal. In our strategy, the record of corresponding module is deleted from placer and indexed in the recycle cache. If the module might be used by following tasks, it can be restored from reconfigurable area by recycle cache immediately, without mapping the module again. Recycle cache can shorten average configuring time of partial reconfiguration without increasing arithmetic complex and placing time of the placer. Compared with large size of local register file which cache context of modules, the recycle cycle is much smaller and cheaper. Simulation results on large random tasks sets have shown that the recycle cache can improve performance of partially reconfigurable system effectively.In a partially reconfigurable system with online placement algorithm, we try to avoid mapping some redundant tasks by caching modules on the reconfigurable area. This paper proposes an elaborate strategy named virtual deletion and a low cost board- level hardware named recycle cache to accomplish the goal. In our strategy, the record of corresponding module is deleted from placer and indexed in the recycle cache. If the module might be used by following tasks, it can be restored from reconfigurable area by recycle cache immediately, without mapping the module again. Recycle cache can shorten average configuring time of partial reconfiguration without increasing arithmetic complex and placing time of the placer. Compared with large size of local register file which cache context of modules, the recycle cycle is much smaller and cheaper. Simulation results on large random tasks sets have shown that the recycle cache can improve performance of partially reconfigurable system effectively.

A new data transmission mechanism in aeronautical ad hoc network

In this paper, a new network topology control mechanism is proposed to improve routing path duration in Aeronautical ad hoc network, which can effectively decrease the probability of routing path breaks in the process of nodes high-speed moving, and be integrated with existing routing protocols used in Ad hoc network smoothly. The main principle of topology control mechanism is according to the different node densities with different topology construction method. For network regions having a high density of aircraft, the packets are preferentially routed over the long available links created by the aircraft moving in same direction. For low density of aircraft, the routing preferentially uses the short available links created by the aircraft moving in both directions. This mechanism can increase the routing path duration effectively. We combine the topology control mechanism with OLSR, and give the Path Link Availability Routing Protocol (PLAR). We compare the performance of PLAR protocol with other routing protocols in different scenes. Experimental results show that, PLAR protocol exhibits a significant improvement over most routing protocols base on topology and position.

Automatic Service Provision in Network Smart Space

A semantic and automatic framework for network smart space is proposed in this paper. In the framework, techniques of spontaneous service provision, context-aware, semantic reasoning, and pervasive service management are smoothly synthesized. A six-layer conceptual architecture is introduced on the basis of functional characteristics of framework. It enables objects in network smart space to interact spontaneously, provides semantic-integration context awareness, and supports meta-service based adaptability and scalability. We illustrate our ideas through a scenario of conference travel service in network smart space, which demonstrates the feasibility of our framework.