@article{li:ijcnds,
    author = {Ming Li and David Kotz},
    title = {Towards Collaborative Data Reduction in Stream-Processing Systems},
    journal = {International Journal of Communication Networks and Distributed
Systems (IJCNDS)},
    year = {2009},
    volume = {2},
    number = {4},
    pages = {375--400},
    publisher = {Inderscience},
    copyright = {Inderscience Enterprises Ltd.},
    earlier = {li:quality},
    doi = {10.1504/IJCNDS.2009.026555},
    url = {http://www.cs.dartmouth.edu/~dfk/papers/internal/li-ijcnds.pdf},
    abstract = {We consider a distributed system that disseminates high-volume
event streams to many simultaneous monitoring applications over a
low-bandwidth network. For bandwidth efficiency, we propose a collaborative
data-reduction mechanism, ``group-aware stream filtering'', used together
with multicast, to select a small set of necessary data that satisfy the
needs of a group of subscribers simultaneously. We turn data-compressing
filters into group-aware filters by exploiting two overlooked, yet important,
properties of monitoring applications: 1)~many of them can tolerate some
degree of ``slack'' in their data quality requirements, and 2)~there may
exist multiple subsets of the source data satisfying the quality needs of an
application. We can thus choose the ``best alternative'' subset for each
application to maximize the data overlap within the group to best benefit
from multicasting. We provide a general framework that treats the group-aware
stream filtering problem completely; we prove the problem NP-hard and thus
provide a suite of heuristic algorithms that ensure data quality
(specifically, granularity and timeliness) while collaboratively reducing
data. The framework is extensible and supports a diverse range of filters.
Our prototype-based evaluation shows that group-aware stream filtering is
effective in trading CPU time for data reduction, compared with
self-interested filtering.}
}