Traffic Conscious Distribution of Service Components

Abstract

Abstract.A service is commonly realized by a set of components distributed over different nodes. For example, Internet based applications are orchestrated across a large scale distributed computing infrastructures and underlying resource elements; Similarly, in TINAlike approaches intelligence for control and management of services and resource, in particular, is distributed among network nodes and user/terminal nodes. In fact a service can be seen as a set of interacting components with a common purpose, being it application-oriented or of a support nature . The placement of components in different machines is more or less empirically determined at the design phase, by loosely (and occasionally subconsciously) taking into account "reasonable" predictions of the component usage. Code mobility has added complexity to the distribution problem: The aim of this paper is to present a methodology of dealing with component distribution, to explore its limitations, and to present its effect on service and network design. Introd uctionThe service-oriented computing paradigm considers services as the fundamental elements for constructing applications. Composite services as resulting by basic service components aggregation are utilized by service providers as commercial solutions to be affered to a diverse customer base. Thus, services may be viewed as open, self-contained software components that support effi.cient configuration as well quality of service composition of distributed applications. Services may be supplied by different business stakeholders and comprise a distributed computing infrastructure in support of intra-and cross-enterprise application integration and collaboration [1].Quality of service (QoS) considerations, are seen as an integral part of the service design lifecycle, taking into account important functional and nonfunctional service properties, such as performance, security, reliability, transactional integrity and services overall cost. Today's dominant manifestat ion of service-oriented computing implementation is realized in terms of ernerging web technologies [2] Current service design frameworks merely focus on service capabilities, interface and behavior models and notations, which are expressed in a N.