Modeling 802.11 AP Usage through Daily Keep-Alive Event Counts

Wireless and in particular 802.11 is one of the major technologies for accessing the Internet at home, in coffee shops or other public places, and in enterprises and university campuses. While most recent work on modeling wireless sites focuses on user mobility, this paper presents and compares a number of models for characterizing access point (AP) usage; moreover, rather than looking at throughput we focus on daily counts of keep-alive events that mobile devices generate every 15 minutes they are connected to the wireless network. Our models are trained and evaluated on data collected from a Porto hotspot of Eduroam, the European academic wireless network. The models we present are generative, in the sense they can be used to generate synthetic daily event counts for a single AP or a collection of APs. We provide standard cross validation comparison of models using the log-likelihood of the models on training and test data.