Human-in-the-Loop Mobile Networks: A Survey of Recent Advancements

Recent developments of smart devices and mobile applications have significantly increased the level at which human users interact with mobile systems. As a result, human activities, usage behavior, and perceived experience of users weigh increasingly on the performance of mobile networks, which has created new challenges for system operation in various aspects, such as increasing uncertainty, selfishness in operations, and complicated performance evaluation. On the other hand, the strong engagement of a large population of human users makes it possible to take advantage of the unique features of human behavior and to leverage the computing powers owned by users. Due to these emerging features of mobile networks, their design and evaluation require a hybrid view of human factor and information technology, and a paradigm shift is required for designing a new human-in-the-loop architecture by actively learning, adapting, and steering user behavior, so as to exploit the human factor in future ubiquitous mobile systems, and to greatly enhance system efficiency and provide superior quality-of-experience to users. The goal of this survey is to summarize recent results that focus on understanding and exploiting the human factor in mobile networks. In the tutorial, we summarize and discuss novelties of these formulations, adopted methodologies, and interesting results. We also point out some future research directions.