— There has been considerable work done in the study of Web reference streams: sequences of requests for Web objects. In particular, many studies have looked at the locality properties of such streams, because of the impact of locality on the design and performance of caching and prefetching systems. However, a general framework for understanding why reference streams exhibit given locality properties has not yet emerged. In this paper we take a first step in this direction. We propose a framework for describing how reference streams are transformed as they pass through the Internet, based on three operations: aggregation, disaggregation, and filtering. We also propose metrics to capture the temporal locality of reference streams in this framework. We argue that these metrics (marginal entropy and interreference coefficient of variation) are more natural and more useful than previously proposed metrics for temporal locality; and we show that these metrics provide insight into the ...
Rodrigo C. Fonseca, Virgilio Almeida, Mark Crovell