PePa Ping Dataset: Comprehensive Contextualization of Periodic Passive Ping in Wireless Networks

Abstract

Among all Internet Quality of Service (QoS) indicators, Round-trip time (RTT), jitter and packet loss have been thoroughly studied due to their great impact on the overall network's performance and the Quality of Experience (QoE) perceived by the users. Considering that, we managed to generate a real-world dataset with a comprehensive contextualization of these important quality indicators by passively monitoring the network in user-space. To generate this dataset, we first developed a novel Periodic Passive Ping (PePa Ping) methodology for Android devices. Contrary to other works, PePa Ping periodically obtains RTT, jitter, and number of lost packets of all TCP connections. This passive approach relies on the implementation of a local VPN server residing inside the client device to manage all Internet traffic and obtain QoS information of the connections established. The collected QoS indicators are provided directly by the Linux kernel, and therefore, they are exceptionally close to real QoS values experienced by users' devices. Additionally, the PePa Ping application continuously measured other indicators related to each individual network flow, the state of the device, and the state of the Internet connection (either WiFi or Mobile). With all the collected information, each network flow can be precisely linked to a set of environmental data that provides a comprehensive contextualization of each individual connection.