Data Quality Of Service Research Articles

A dynamic server selection method using QoS statistics

AbstractIn this paper, we study server selection methods from the perspective of selecting the server having the shortest download time when a file is downloaded from a mirror Web site. Specifically, we focus on server selection methods on the client side and propose a dynamic server selection method based on Quality of Service (QoS) statistical data. This method features using past stored data in a more advanced manner than a conventional server selection method by collecting past QoS data according to the day of the week and the time period. We also study and evaluate the method based on experimental results using the Internet. First, we study the optimum values for the parameters of the proposed server selection method. Then we compare and evaluate this server selection method and an existing server selection method. As the evaluation metrics, in addition to objective evaluation indices such as the mean and maximum download time, we use the download give‐up rate and the stress level which reflect the user's feelings. Based on these results, we demonstrate the superiority of this server selection method. © 2004 Wiley Periodicals, Inc. Electron Comm Jpn Pt 1, 87(7): 43–54, 2004; Published online in Wiley InterScience (www.interscience.wiley.com). DOI 10.1002/ecja.10168

Personalised Grid service discovery

The authors take a broad view that ultimately Grid- or Web-services must be located via personalised, semantic-rich discovery processes. They argue that such processes must rely on the storage of arbitrary metadata about services that originates from both service providers and service users. Examples of such metadata are reliability metrics, quality of service data or semantic service description markup. The paper presents UDDI-MT, an extension to the standard UDDI service directory approach that supports the storage of such metadata via a tunnelling technique that ties the metadata store to the original UDDI directory. They also discuss the use of a rich, graph-based RDF query language for syntactic queries on this data. Finally, they analyse the performance of each of these contributions in their implementation.

A scalable monitoring approach based on aggregation and refinement

Network monitoring is an integral part of any network management system. In order to ensure end-to-end service quality stated in service level agreements (SLAs), managers of a service provider network need to gather quality-of-service (QoS) measurements from multiple nodes in the network. For a large network with over thousands of flows with end-to-end SLAs, the information exchanged between network nodes and a central network management system (NMS) could be substantial. We propose a mechanism called aggregation and refinement based monitoring (ARM) to reduce the amount of information exchange. ARM is a generic mechanism that can be configured to run with different objectives, including threshold-based, rank-based and percentile-based. The mechanism enables the NMS to collect data from network nodes using a dynamic QoS data aggregation/refinement technique, and to process these information differently depending on its measurement objective. Our simulation results show that for these various objectives, the selective refinement process is able to validate SLAs quickly, is an order of magnitude more efficient than a simple polling scheme, and performs well across a wide range of traffic loads.