Development of a Simulation Platform for Wireless Network Topology Inference

The importance of networks, in their broad sense, is rapidly and massively growing in modern day society thanks to unprecedented communication capabilities offered by technology. A sensor network deployed to collect environmental data (i.e., humidity, temperature) or a tactical network aiming to exchange information between soldiers, are only few examples of the vastness of networks widely diffused today. In this scenario of ultra-densely connected objects, the knowledge of network topology is an essential aspect that can help to predict traffic flow, infer the potential receivers of a currently active transmitter, understand the degree of connectivity of users, help network maintenance and optimization. For this reason, the development of an ad-hoc simulator for wireless network topologies is necessary, if not mandatory, for the generation and the collection of big amounts of data as much as possible realistic and precise. In this work, a wireless network simulator based on ns-3 open source infrastructure is developed and tested. Furthermore, the high-quality data generated with the simulator are used to evaluate the accuracy of a machine learning based topology inference algorithm.