Distributed Learning for Proportional-Fair Resource Allocation in Coexisting WiFi Networks.

In this paper, we revisit the widely known performance anomaly that results in severe network utility degradation in WiFi networks when nodes use diverse modulation and coding schemes. The proportional-fair allocation was shown to mitigate this anomaly and provide a good throughput to the stations. It can be achieved through the selection of contention window values based on the explicit solution of an optimization problem or, as proposed recently, by following a learning-based approach that uses a centralized gradient descent algorithm. In this paper, we leverage our recent theoretical work on asynchronous distributed optimization and propose a simple algorithm that allows WiFi nodes to independently tune their contention window to achieve proportional fairness. We compare the throughputs and air-time allocation that this algorithm achieves to those of the standard WiFi binary exponential back-off and show the improvements.