This thesis explores the utility of interest management in peer-to-peer environments. Specifically, it proposes: a model for formulaic specification of interest criteria that is implementation neutral in terms of underlying interest operators (the functions that determine the satisfaction of interest); and, an interest management propagation model that ensures the specifications (termed formula interest expressions) are only sent to those DVE components that are likely to be able to satisfy the interest criteria. This selective propagation model uses a distributed index of supported interest operators to determine candidate remote filterers. Remote filtering ensures that a state change message is only sent if it meets the interest criteria previously expressed by the intended recipient. The selective remote filtering model requires no central infrastructure and is entirely supported by peer DVE components, which may join and leave the DVE dynamically. The performance of the proposed propagation model, in terms of the number of logical messages required, is compared to the only existing propagation model where interest expressions are simply sent to all participating DVE components. Analysis reveals that for stable long-lived DVEs the proposed model can significantly messaging overhead and thereby increase the potential scale-up of the DVE. The viability of the proposed model is examined by means of proof-of-concept system, which exercises the specification and propagation models over a range of values for key variables. / Doctor of Philosophy (PhD)
Identifer | oai:union.ndltd.org:ADTP/181800 |
Date | January 2006 |
Creators | Bartlett, Robert Graham, University of Western Sydney, College of Health and Science, School of Computing and Mathematics |
Source Sets | Australiasian Digital Theses Program |
Language | English |
Detected Language | English |
Page generated in 0.0022 seconds