by

DOI: 10.1023/A:1023727201236
Print publication date: 6/1/2003
View article on SpringerLink

by Boutaba, Raouf; Goldszmidt, Germán; Schönwälder, Jürgen; Zuckerman, Douglas

DOI: 10.1023/A:1023775117166
Print publication date: 6/1/2003
View article on SpringerLink

by Garg, Pankaj K.; Griss, Martin; Machiraju, Vijay

Determining service configurations is essential for effective service management. In this paper we describe a model-driven approach for service configuration auto-discovery. We develop metrics for performance and scalability analysis of such auto-discovery mechanisms. Our approach addresses several problems in auto-discovery: specification of what services to discover, how to efficiently distribute service discovery, and how to match instances of services into related groups. We use object-oriented models for discovery specifications, a flexible bus-based architecture for distribution and communication, and a novel multi-phased, instance matching approach. We have applied our approach to typical e-commerce services, Enterprise Resource Planning applications, like SAP, and Microsoft Exchange services running on a mixture of Windows and Unix platforms. The main contribution of this work is the flexibility of our models, architecture and algorithms to address discovery of a multitude of services.

DOI: 10.1023/A:1023723100328
Print publication date: 6/1/2003
View article on SpringerLink

by Hellerstein, Joseph L.

Quantitative performance diagnosis (QPD) provides explanations that quantify the impact of problem causes. An example of such an explanation is it Increased web server traffic accounts for 90% of the increase in LAN utilization, which in turn accounts for 20% of the increase in web response times. This paper describes GAP, a general approach to quantitative performance diagnosis. GAP has two parts: (1) an algorithm for computing quantitative performance diagnoses; and (2) a framework for constructing diagnostic techniques that provides the basis for quantifications produced by the algorithm. The GAP algorithm makes use of a measurement navigation graph, a directed acyclic graph whose nodes are measurement variables and whose arcs have weights that quantify the effect of child variables (e.g., LAN utilization) on parent variables (e.g., response time). The framework for developing diagnostic techniques consists of (a) the choice of statistic (e.g., mean, variance) to aggregate problem values, and (b) the estimator of the statistic.

DOI: 10.1023/A:1023771016257
Print publication date: 6/1/2003
View article on SpringerLink

by Quittek, Jürgen; Brunner, Marcus

The idea of Distributed Management has been around for quite some time. In recent years, several different technologies have been developed to implement this paradigm. However, until today a practical comparison of these technologies with the implementation of various management applications has—to the authors knowledge—not been made. Therefore, this paper discusses and compares the application of different active technologies to distributed Internet management. Three management application areas that profit from the Distributed Management paradigm are investigated: scalable monitoring, explicit placement of management tasks, and remote systems management of network nodes. The specific requirements of these application areas are analyzed and compared to the capabilities of three different active Distributed Management technologies: the Internet Engineering Task Force (IETF) Script MIB, the active network backbone (ABone), and the mobile agent platform Voyager. For all combinations of technologies and application areas, prototype implementations have been made, that demonstrate strengths and weaknesses of current Distributed Management technologies. The paper evaluates the tested technologies and concludes with suggestions for improvements.

DOI: 10.1023/A:1023719032187
Print publication date: 6/1/2003
View article on SpringerLink

by Beard, Cory C.; Frost, Victor S.

For broadband packet networks to be widely useful to society, they must dynamically recognize some network flows, like those that deal with disaster response, military operations, or emergencies as having greater importance than others. This paper proposes an architecture of geographically distributed ticket servers that issue importance tickets that indicate the priority that a flow should be given in the current dynamic network context. Any type of user or flow can be given priority, depending on the user needs and the context. User agents contact ticket servers using an agent communication language; then a ticket server intelligent agent determines how valuable of a ticket to issue. Use of ticket servers and agent communication enables quick adaptation to dynamic context changes and provides user feedback so that high priority communication activities can be conducted effectively.

DOI: 10.1023/A:1023766915349
Print publication date: 6/1/2003
View article on SpringerLink

by Bohoris, C.; Pavlou, G.; Liotta, A.

Virtual Home Environment (VHE) encompasses the deployment and management of adaptable services that retain any personalized service aspects, irrespective of terminal, network’ and geographic location. We assert that the dynamic nature of the VHE requires management capabilities that can be suitably provided through the use of mobile agent technology. We examine four different engineering solutions for the realization of a VHE performance management component that allows service adaptation in relation to the available network Quality-of-Service (QoS). The mobile agent approach is compared with competing technologies in order to identify the benefits of this novel application of mobile agents, discuss its drawbacks’ and finally focus on the lessons learned from our prototype system. Although mobile agents are typically associated with increased performance costs, it is through agent migration that we were able to address the VHE requirements of universality, dynamic programmability, and network technology independence.

DOI: 10.1023/A:1023714931278
Print publication date: 6/1/2003
View article on SpringerLink

by Weidong, Wu; Bingxin, Shi

DOI: 10.1023/A:1023765814440
Print publication date: 6/1/2003
View article on SpringerLink