Data Driven Wireless Network Design: A Multi-level Modeling Approach

Wireless network technology keeps improving by solving problems detected in current systems and anticipating requirements for future systems. One of the possible approaches to help advancing wireless technology is to develop methods that help researchers understand the less desired behaviors that may occur in a real-world system. One such method is data driven multi-level analysis that uses the monitoring data collected from real-world networks to provide detailed insight, at several levels and/or scales, into the system behavior. This paper discusses data driven multi-level analysis, provides a proof of concept on how it can be applied and identifies challenges. The contributions of this paper are (1) the use of data driven multi-level analysis for understanding the behaviour of wireless networks and (2) the identification of open challenges and directions for future research.