Optical packet-switched networks (OPNs), which consist of edge nodes and core nodes, are regarded as one of the most promising solutions to meet the increasing service requirements of the global Internet and to utilize efficiently the huge bandwidth of dense wavelength division multiplexing (DWDM) technology. In particular, the edge nodes perform adaptation function which interfaces between the legacy packet networks (i.e. IP networks) and OPNs. Namely, the edge nodes assembly IP packets from electronic layer into a larger optical packet. The function of packet assembly has become an important issue to be addressed in OPNs, since it not only increases the bandwidth utilization, but also reduces the self-similarity of the traffic.
Studied in this paper are three kinds of typical packet assembly schemes in unslotted OPNs, i.e. the timer-based one, the length-threshold one and the hybrid algorithm. Based on a generic architecture of the edge nodes, these assembly mechanisms are examined by simulations under various self-similar traffic loads. The impacts of these algorithms on the traffic, including statistics of generated optical packets and self-similarity of optical packet traffic, are compared. The simulation results indicate that optical packet assembly can fulfill traffic shaping by improving key traffic characteristics of interest in network performance evaluation, such as the long-term correlation and so on. Moreover, the hybrid algorithm proves to be a better solution when both the assembly time and the packetisation efficiency have been also considered at the same time.