Open AccessService delays in strongly linked network communities
Author(s) -
Mikhail I. Bogachev,
Nikita S. Pyko,
Svetlana A. Pyko,
A. N. Vasenev
Publication year - 2019
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1352/1/012006
Subject(s) - queueing theory , computer science , relation (database) , service (business) , computer network , network dynamics , distributed computing , data mining , mathematics , economy , discrete mathematics , economics
We analyze aggregated traffic dynamics obtained from strongly linked network communities. Our results based on two empirical data traces from university campus networks indicate that neglecting the statistical links between traffic patterns generated by individual network nodes leads to the drastic underestimation of both waiting and sojourn times. We also show that similar effects can be observed in simulated traffic patterns obtained by agent based modeling. Moreover, we suggest several indices that could be used to quantify the links between nodes and show their relation with the queuing system performance indicators.