부산대학교 도서관

Minimizing data overheads in packet networks is an essential performance promotion issue. One of the past solutions was to select a single optimum packet size that minimizes the combined data overhead factor resulting from both operational and blank padding requirements. Such a packet size is associated with the characteristics of the random streams of messages applied to the network. This paper provides a different method that lead to improved minimization of the overheads. The method is based on selecting multiple packet sizes, with each being concerned with minimizing data overheads of messages falling within a certain range of length. The performance of the method was studied using computer simulation. The results obtained illustrate that in comparison with the old method, the new method can reduce the combined data overhead factor by approximately 25%. Future use of the method would provide more efficient data flow through packet networks.