Title :
A New Measure for Charcterizing Data Traffic
Author_Institution :
Dept. of Comput. Sci., Texas Univ., Austin, TX, USA
fDate :
1/1/1978 12:00:00 AM
Abstract :
It is generally recognized that data traffic has more diverse characteristics and transmission requirements than voice traffic. In particular, data traffic associated with many interactive data processing applications is often characterized to be extremely bursty, which lends support to the choice of Packet (or message) switching over circuit switching in data network design. We introduce in this paper a new measure called bursty factor for characterizing the burstiness of a data traffic source. Unlike the usual measures of peak-to-average ratio and duty cycle, the new measure introduced is independent of a specific network design and dependent only upon the traffic source characteristics and performance requirements. It can therefore be used to guide the direction of an initial network design.
Keywords :
Data communications; Attenuators; Circuits; Equations; Low pass filters; Packet switching; Resource management; Sampling methods; Signal processing; Signal sampling; Telecommunication traffic;
Journal_Title :
Communications, IEEE Transactions on
DOI :
10.1109/TCOM.1978.1093956