grid information service influences quality of service for grid platforms directly. In this paper, based on network latency, network coordinate is introduced into grid information service to locate each grid node. By ...
详细信息
To provide live streaming services based on peer-to-peer overlays is popular now. Previous researches put their emphasis on how to improve overlays efficiency with single overlay optimizations. These optimizations hav...
详细信息
Deploying all kinds of scheduling schemes to extend the service capacity of cluster systems has been a popular method due to their potential scalability. However, most of them pay little attention to the diversity of ...
详细信息
Deploying all kinds of scheduling schemes to extend the service capacity of cluster systems has been a popular method due to their potential scalability. However, most of them pay little attention to the diversity of requests and real servers, therefore they can not be efficiently applied to heterogeneous cluster systems. In this paper, we propose a novel adaptive scheduling scheme, called ADLB, to handle this problem. Different from the existing solutions, it offers a scheduling method based on least delay, which implements adaptive scheduling for incoming requests without any additional communication among real servers. Experimental results show that our scheme achieves better load balancing among real servers than the existing ones for heterogeneous cluster systems.
Relevance feedback (RF) has been extensively studied in the content-based image retrieval community. However, no commercial Web image search engines support RF because of scalability, efficiency and effectiveness issu...
详细信息
ISBN:
(纸本)1595934472
Relevance feedback (RF) has been extensively studied in the content-based image retrieval community. However, no commercial Web image search engines support RF because of scalability, efficiency and effectiveness issues. In this paper we proposed a scalable relevance feedback mechanism using click-through data for web image retrieval. The proposed mechanism regards users' click-through data as implicit feedback which could be collected at lower cost, in larger quantities and without extra burden on the user. During RF process, both textual feature and visual feature are used in a sequential way. To seamlessly combine textual feature-based RF and visual feature-based RF, a query concept-dependent fusion strategy is automatically learned. Experimental results on a database consisting of nearly three million Web images show that the proposed mechanism is wieldy, scalable and effective.
The ability of worms to spread at high rate has made them an incredible security threat to modern networked computer systems. In addition, the rate of worms spreading has risen dramatically with the increasing in conn...
详细信息
The ability of worms to spread at high rate has made them an incredible security threat to modern networked computer systems. In addition, the rate of worms spreading has risen dramatically with the increasing in connectivity. Most prior works on defending against infection are focus on slowing down the infection rate after worms being detected during worms' propagation. A novel vaccine propagation architecture is proposed in this paper, named PropaV, that seeks to expedite the spreading of vaccines and depress the spreading rate of worms in distributed environment. PropaV demonstrates that distributing vaccine to most nodes as fast as possible after the vaccine has been published is also an effective way to restrain the worms spreading. This paper describes our system architecture, discusses challenges of various components, gives some simulation results and directions for future research
Due to the highly distributed and dynamic features, service discovery is a key requirement in gridcomputing. The paper first introduces the existing service discovery mechanisms in distributed computing, and then poi...
详细信息
ISBN:
(纸本)9780769526645;0769526640
Due to the highly distributed and dynamic features, service discovery is a key requirement in gridcomputing. The paper first introduces the existing service discovery mechanisms in distributed computing, and then points out the problems in MDS which is widely used in grid systems. In order to address these issues, GNSD, a novel service discovery mechanism is proposed, which is based on the OSPF (Open Shortest Path First) flooding mechanism and combines the advantages of tree architecture and flat architecture. The time and space complexity of both GNSD and MDS are also analyzed. Experimental results show that GNSD not only accelerates the service discovery but also relieves the burden of servers at the cost of little extra storage and communication traffic. Furthermore, it is more robust. As a conclusion, GNSD is an efficient service discovery mechanism
In a grid workflow, data transfer scheme plays a key role on its performance. In most grid projects, data is transferred between source and destination directly in the traditional way, without considering the status o...
详细信息
In server-based computing (SBC), one key step is to send the server screen to the clients timely. To reduce the bandwidth taken by this transfer, many encoding techniques such as Hextile, Zlib, Tight, FCE have been pr...
详细信息
In server-based computing (SBC), one key step is to send the server screen to the clients timely. To reduce the bandwidth taken by this transfer, many encoding techniques such as Hextile, Zlib, Tight, FCE have been presented. Since they only take the spatial redundancy into account, the reduction of bandwidth is limited and the bottleneck of transfer is still prominent, especially in ubiquitous environments. This paper presents a novel mechanism for remote screen synchronization based on the association of spatio-temporal redundancy reductions (ASTR), which can reduce the screen data transfer further. The temporal redundancy between the current changed screen area and the previous frame is taken into account. An improved SSC-APDS (subsampling search candidates in adjustable partial distortion search) algorithm is presented, which can increase the speed of the block motion estimation (BME) prominently. Experimental results show that this novel approach can reduce more bandwidth consumption of transferring the screen data than others, which quite caters for the requirements of the ubiquitous environments
gridcomputing is emerging as a new format of wide area distributed computing. Because the distribution of services and resources in wide-area networks are heterogeneous, dynamic, and multi-domain, security is a criti...
详细信息
Quality of Service (QoS) is necessary for service-oriented computing. Web Services Agreement (WSA) aims at defining a language and a protocol for advertising the capabilities of providers, creating agreements based on...
详细信息
暂无评论