Q-Learning Based Aerial Base Station Placement for Fairness Enhancement in Mobile Networks

Abstract

In this paper, we use an aerial base station (aerial-BS) to enhance fairness in a dynamic environment with user mobility. The problem of optimally placing the aerial-BS is a non-deterministic polynomial-time hard (NP-hard) problem. Moreover, the network topology is subject to continuous changes due to the user mobility. These issues intensify the quest to develop an adaptive and fast algorithm for 3D placement of the aerial-BS. To this end, we propose a method based on reinforcement learning to achieve these goals. Simulation results show that our method increases fairness among users in a reasonable computing time, while the solution is comparatively close to the optimal solution obtained by exhaustive search.

Fairness-Aware Link Optimization for Space-Terrestrial Integrated Networks: A Reinforcement Learning Framework

“…Specifically, there are different fairness criteria such as max-min fairness [27], proportional fairness [28], and Jain's index [29]. However, the aforementioned work has not taken into account the issue of the fairness in SAGINs, and there are a few works in UAV networks that have considered this issue such as in [30]- [33]. In [30], the optimal altitude of a UAV was optimized to maximize the fairness between users.…”

“…The 2D trajectory design of the UAV was optimized based on the throughput fairness between vehicles and among different time slots. The fairness issue is considered in [33], where a proportional fairness metric is used to maintain fairness among users through optimizing the location of a single UAV. However, the previous studies on fairness [30]- [33] have not explicitly considered fairness in conjunction with load balancing, 3D trajectory of UAVs, BS-satellite/user-BS association and resource management in SAGINs.…”