Resource Discovery Workload (resourcediscovery-2009)

This dataset was used in the paper "Efficient Event-based Resource Discovery".

The dataset in the SimilarityForwarding_6.3.1 directory is mainly used in
Section 6.3.1 of the paper. There are two folders, named resourcedata and
subdata, representing resource information and discovery (subscription)

In the resourcedata directory, each file follows the format
"total_B/U_id.txt". "B" means balanced and "U" unbalanced. The "id" refers to
the broker to which the file's messages are deployed. The value range in this
data set is 1~20.

In the subdata directory, the numbers 0.1 ~ 1.0 in the filename represents the
similarity, "_Z" indicates a Zipf distribution and "_G" a Gaussian
distribution. As with the resourcedata directory, the id represents the
broker to which the current file's messages are deployed.

This dataset is also used in Section 6.3.2 ("Decentralized Architecture") of
the paper, with various deployment and update intervals.

If you have any questions, please email or
Download 326 times)
Related Projects