Network coordinates provide a scalable way to estimate latencies among
large numbers of hosts.  While there are several algorithms for
producing coordinates, none account for the fact that nodes observe a
stream of distinct observations that may vary by as much as three
orders-of-magnitude.  With such variable data, coordinate systems are
prone to high error and instability in live deployments.  In addition,
dynamics such as triangle violations can lead to coordinate
oscillations, producing further instability and making it difficult
for applications to know when their coordinates have truly changed.
Because simulation results demonstrate that network coordinates are
capable of providing low cost and sufficiently accurate answers to
common queries, it is vital that we develop the ability to obtain
similar results in practice.

We introduce latency filters, which turn streams of latency
observations into a single approximation, and update filters, which
summarize underlying coordinate change and squelch false application
updates.  We show how a compact, non-linear, low-pass filter can
extract a clear underlying signal from each link: these latency
filters improve accuracy.  We evaluate a set of change-detection
heuristics that allow coordinates to evolve at the system-level and
initiate an application-level update only after a coordinate has
undergone a significant change: these update filters boost coordinate
stability without diminishing accuracy.  These two filters combined to
improve network coordinate accuracy by 54 percent and coordinate
stability by 96 percent when run on a real, large-scale network.