Allocating Partially Overlapping Channels Using Robust Fuzzy Learning in UAV Communication Networks PROJECT TITLE : Robust Fuzzy Learning for Partially Overlapping Channels Allocation in UAV Communication Networks ABSTRACT: The emerging cellular-enabled unmanned aerial vehicle (UAV) Communication paradigm poses significant challenges to the ongoing research on UAV applications. These challenges are caused by the significantly dynamic characteristics of the new aerial users. When it comes to the robust channel allocation, the high mobility of UAV nodes and the unexpected disturbance of the external environment would render the majority of the existing methods, which rely on definite information and are susceptible to a dynamic environment, less appealing or even invalid. This is because these methods are vulnerable to the environment. In this paper, we specifically investigate a cellular-enabled mesh UAV network that takes advantage of partially overlapping channels (POCs). Additionally, we propose a distributed fuzzy space based learning scheme for POCs allocation in order to combat the dynamic environment. Instead of making the assumption of perfect channel state information (CSI), unmanned aerial vehicles have dynamic and uncertain CSI, which is characterized by fuzzy numbers. On the basis of this, the process of allocation can be carried out in a fuzzy space that has been mapped. By combining fuzzy logic and game-based learning, we model the problem of POCs assignment as a fuzzy payoffs game (FPG) and show that there is a fuzzy Nash equilibrium for the FPG that we designed. This was accomplished by integrating the two approaches. After that, using the derived priority vector in the fuzzy space, the proposed algorithm will be able to arrive at the equilibrium solution. The benefits of our new approach are illustrated through the use of numerical simulations. Did you like this research project? To get this research project Guidelines, Training and Code... Click Here facebook twitter google+ linkedin stumble pinterest Strong Sensitive Textual Content Protection for Mobile Applications with SchrodinText A Deep Learning Approach To Revenue-Optimal Auction For Resource Allocation In Wireless Virtualization