Interoperability in large-scale distributed information delivery systems

In this paper we address interoperability issues in large-scale distributed information delivery systems. Architecturally, we classify existing approaches and systems into two paradigms: Multidatabase management-based paradigm and Mediator-based information delivery paradigm, and analyze the techniques used in each. Technically, we describe a number of data delivery characteristics in terms of delivery protocols, delivery modes, and delivery frequencies. We further use these characteristics to discuss and compare several data delivery schemes. We argue that an advanced distributed information system must incorporate different types of information delivery so that the system can be optimized according to various criteria, such as network traffic and heterogeneity and constant evolution of online information sources. To illustrate the architectural and technical aspects of distributed information delivery systems, we review a number of research prototypes to demonstrate the various implementation approaches used in practice, and the different solutions to the interoperability issues addressed in the paper.