LogPal: A Generic Anomaly Detection Scheme of Heterogeneous Logs for Network Systems

Table 2

A brief summary of datasets.

Dataset	Time span	Size	No. of messages	Anomalies
BGL	214.7 days	708 MB	4,747,963	348,460
HDFS	38.7 hours	1.47 GB	11,175,629	288,250
Thunderbird	244 days	29.60 GB	211,212,192	43,087,287