Spatial Mean-Field Limits for CSMA Networks

Random-access algorithms such as the CSMA protocol provide a popular mechanism for distributed medium access control in large-scale wireless networks. Mean-field analysis has emerged as a convenient approach to obtain tractable performance estimates in such networks, but a critical limitation of the classical set-up is that all nodes are assumed to belong to a finite number of classes. We consider spatial mean-field limits which do not involve such a requirement, characterized in terms of a set of partial-differential equations, and in particular examine the fixed points of these equations for some specific network configurations. We discuss how the fixed points can be used to obtain estimates for key performance metrics, and present simulation experiments to demonstrate the accuracy of these estimates.