Federated Multi-Agent Deep Reinforcement Learning for Dynamic and Flexible 3D Operation of 5G Multi-MAP Networks

This paper addresses the efficient management of Mobile Access Points (MAPs), which are Unmanned Aerial Vehicles (UAV), in 5G networks. We propose a two-level hierarchical architecture, which dynamically reconfigures the network while considering Integrated Access-Backhaul (IAB) constraints. The high-layer decision process determines the number of MAPs through consensus, and we develop a joint optimization process to account for co-dependence in network self-management. In the low-layer, MAPs manage their placement using a double-attention based Deep Reinforcement Learning (DRL) model that encourages cooperation without retraining. To improve generalization and reduce complexity, we propose a federated mechanism for training and sharing one placement model for every MAP in the low-layer. Additionally, we jointly optimize the placement and backhaul connectivity of MAPs using a multi-objective reward function, considering the impact of varying MAP placement on wireless backhaul connectivity.

Dual-Attention Deep Reinforcement Learning for Multi-MAP 3D Trajectory Optimization in Dynamic 5G Networks

5G and beyond networks need to provide dynamic and efficient infrastructure management to better adapt to time-varying user behaviors (e.g., user mobility, interference, user traffic and evolution of the network topology). In this paper, we propose to manage the trajectory of Mobile Access Points (MAPs) under all these dynamic constraints with reduced complexity. We first formulate the placement problem to manage MAPs over time. Our solution addresses time-varying user traffic and user mobility through a Multi-Agent Deep Reinforcement Learning (MADRL). To achieve real-time behavior, the proposed solution learns to perform distributed assignment of MAP-user positions and schedules the MAP path among all users without centralized user's clustering feedback. Our solution exploits a dual-attention MADRL model via proximal policy optimization to dynamically move MAPs in 3D. The dual-attention takes into account information from both users and MAPs. The cooperation mechanism of our solution allows to manage different scenarios, without a priory information and without re-training, which significantly reduces complexity.

Cost-Efficient and QoS-Aware User Association and 3D Placement of 6G Aerial Mobile Access Points

6G networks require a flexible infrastructure to dynamically provide ubiquitous network coverage. Mobile Access Points (MAP) deployment is a promising solution. In this paper, we formulate the joint 3D MAP deployment and user association problem over a dynamic network under interference and mobility constraints. First, we propose an iterative algorithm to optimize the deployment of MAPs. Our solution efficiently and quickly determines the number, position and configuration of MAPs for highly dynamic scenarios. MAPs provide appropriate Quality of Service (QoS) connectivity to mobile ground user in mmwave or sub-6GHz bands and find their optimal positions in a 3D grid. Each MAP also implies an energy cost (e.g. for travel) to be minimized. Once all MAPs deployed, a deep multiagent reinforcement learning algorithm is proposed to associate multiple users to multiple MAPs under interference constraint. Each user acts as an independent agent that operates in a fully distributed architecture and maximizes the network sum-rate.