| dc.description.abstract | Existing methods to utilize capacity-heterogeneity in a P2P system either rely
on constructing special overlays with capacity-proportional node degree or use topology adaptation to match a node's capacity with that of its neighbors. In existing
P2P networks, which are often characterized by diverse node capacities and high
churn, these methods may require large node degree or continuous topology adaptation, potentially making them infeasible due to their high overhead. In this thesis,
we propose an unstructured P2P system that attempts to address these issues. We
first prove that the overall throughput of search queries in a heterogeneous network
is maximized if and only if traffic load through each node is proportional to its capacity. Our proposed system achieves this traffic distribution by biasing search walks
using the Metropolis-Hastings algorithm, without requiring any special underlying
topology. We then define two saturation metrics for measuring the performance of
overlay networks: one for quantifying their ability to support random walks and the
second for measuring their potential to handle the overhead caused by churn. Using
simulations, we finally compare our proposed method with Gia, an existing system
which uses topology adaptation, and find that the former performs better under all
studied conditions, both saturation metrics, and such end-to-end parameters as query
success rate, latency, and query-hits for various file replication schemes. | en |
