Modelling Large-Scale CSMA Wireless Networks

Increasingly more wireless devices adopt CSMA at the MAC layer, primarily due to the ubiquitous utilization of Wi-Fi, but also due to the development of new standards that implement CSMA variants, like LAA-LTE. It is thus critical to use reliable modelling tools that accurately evaluate the performance of large-scale CSMA deployments, as expected in practice. This paper compares the accuracy and computational efficiency of stochastic geometry modelling (SGM) and our proposed hybrid model, for estimating the MAC-layer throughput and signal-to-interference-and-noise ratio (SINR) of large-scale CSMA wireless deployments. Using ns-3 simulations as the baseline reference, we show that our hybrid model is significantly more accurate and at least one order of magnitude faster to compute than SGM. SGM underestimates the SINR, yet as it neglects the sensing overhead, it usually overestimates the MAC-layer throughput substantially. We thus argue that our hybrid model is preferable to SGM for modelling large-scale CSMA deployments.