Abstract:
The main factor in measuring server performance is
the accuracy of detection mechanisms. Sever is needed
to detect server overload condition accurately.
Therefore, it can be satisfied customers by reducing
request drop rate. Server overload detection would be
an initial step of overload control system. In order to
provide such a detection mechanism, it is important to
choose the best classifier which is the most suitable for
our dataset. Selecting correct classifier maximize the
performance of detection mechanism.
In this paper, we present how server workload
classification task is performed by using different
machine learning classification methods and how the
best classifier improve overload detection mechanism.
We make a synthetic dataset by using window
performance monitor tool. Many classifiers are
evaluated over synthetic dataset.
