SIR approach in modeling data packets forwarding at a leaky bucket

Abstract

When network users are intensively interacting during rush hour, avoiding data loss and latency is a concern in guaranteeing segment reliability. Implementing a leaky bucket could be needed to achieve flows effective monitoring by generating network of queues at given output link. Packets associated with different sessions and originated from different hosts may be mixed up and queuing delay may become longer, depending on network segment state, buffering strategy, users’ behavior among other factors. It is interesting to assimilate these stages of packets traveling through network segment to the concept of epidemic control. This paper proposes a SIR (Susceptible–Infected–Recovered) approach in modeling data packets transmission at a leaky bucket at peak hour. We focused our analysis on packets buffering and recovery strategy impact on segment forwarding performance in heavy load situation. Numerical results suggested adapting buffering strategy and packets recovery to enhance transmission and network overall performance.