Delay Modelling for Single Cell IEEE 802.11 WLANs Using a Random Polling System

In this paper, we consider the problem of modelling the average delay experienced by a packet in a single cell IEEE 802.11 DCF wireless local area network. The packet arrival process at each node i is assumed to be Poisson with rate parameter \lambda_i. Since the nodes are sharing a single channel, they have to contend with one another for a successful transmission. The mean delay for a packet has been approximated by modelling the system as a 1-limited Random Polling system with zero switchover time. We show that even for non-homogeneous packet arrival processes, the mean delay of packets across the queues are same and depends on the system utilization factor and the aggregate throughput of the MAC. Extensive simulations are conducted to verify the analytical results.

💡 Research Summary

This paper tackles the long‑standing problem of analytically estimating the average packet delay in a single‑cell IEEE 802.11 Distributed Coordination Function (DCF) wireless LAN. The authors model the network as a 1‑limited random polling system (RPS) with zero switchover time, thereby converting the complex contention‑based medium access into a mathematically tractable queueing framework. Each node i generates packets according to an independent Poisson process with rate λ_i. Because all nodes share a single wireless channel, they must contend for transmission opportunities; the authors capture this contention through the aggregate throughput of the MAC layer rather than modeling each back‑off and collision event explicitly.

In the RPS abstraction, a single server (the wireless channel) visits the N queues (the nodes) in a random order. Upon each visit the server serves at most one packet (the 1‑limited discipline) and then immediately moves to the next queue. The switchover time between queues is assumed to be zero, which eliminates the DIFS, SIFS, and ACK overhead from the analytical model but is compensated by using the measured MAC throughput C as a proxy for the average service time. The total system utilization is defined as ρ = Σ_i λ_i · E