With the wide adoption of smart phones and other mobile devices, cellular mobile data traffic has grown tremendously in the past few years. This rapid growth in cellular data traffic, coupled with the increasing demands for mobile data services, has exerted enormous competitive pressure on cellular network service providers. How to effectively manage a large-scale cellular data network is therefore a daunting challenge that is not only important to cellular network service providers, but also to mobile data users and emerging mobile applications and services. In this project, the PI sets out to develop a data-driven, statistical machine learning-based framework to identify, analyze and understand various challenging issues in cellular data networks, and develop mechanisms and tools for effectively managing and trouble-shooting constantly evolving cellular data networks. The PI leverages vast amounts of heterogeneous sources of data obtained from operational cellular data networks, and designs statistical inference techniques to analyze, mine and correlate various sources of real-world data to uncover and identify various key factors that contribute to network performance issues and affect user experiences.
This research project brings benefits not only to cellular service providers, but also to millions of users who are increasingly dependent on mobile voice and data services. It also provides valuable insights to inform further development of emerging mobile and cloud computing. Research outcomes will be disseminated through publications and outreach activities, as well as technology transfer.