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

Abstract

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.

Machine Learning for Wireless Link Quality Estimation: A Survey

“…More explicitly, an intelligent and autonomous mechanism for analyzing wireless links of any transceiver and technology can assist in better handling of current operational aspects of increasingly heterogeneous networks. This opens up a new avenue for wireless network design and optimization [58], [59] and calls for the ML techniques and algorithms to build robust, agile, resilient and flexible networks with minimum or no human intervention. A number of contributions for such mechanisms can be found in the literature, for instance radio spectrum observatory network is designed in [60] and [61].…”

Machine Learning for Wireless Link Quality Estimation: A Survey

“…More explicitly, an intelligent and autonomous mechanism for analyzing wireless links of any transceiver and technology can assist in better handling of current operational aspects of increasingly heterogeneous networks. This opens up a new avenue for wireless network design and optimization [54], [55] and calls for the ML techniques and algorithms to build robust, agile, resilient and flexible networks with minimum or no human intervention. A number of contributions for such mechanisms can be found in the literature, for instance radio spectrum observatory network is designed in [56] and [57].…”