EGNN-based topology control in wireless mobile infrastructure on demand with shared access restrictions.

Abstract

Mobile Infrastructure on Demand (MIoD) involves deploying a mobile ad-hoc network through a team of network agents to provide communication infrastructure for another group of mobile agents serving a specific application. This study aims to determine the optimal locations for these network agents. Previous approaches have focused on maximizing graph connectivity or directly utilizing communication indicators. However, these methods often overlook the shared nature of the wireless communication medium, leading to suboptimal results. In this study, we incorporate shared access restrictions into our optimization model, addressing the inherent challenges in wireless communication. By leveraging the natural equivariance to translations and rotations of communication indicators, we employ E(n)-Equivariant Graph Neural Networks (EGNNs) to approximate the dependency of our indicator on node positions. We then use a gradient ascent algorithm to find optimal positions for the network agents. Our methodology demonstrates superior performance compared to traditional approaches, as evidenced by a higher figure of merit for the final configurations. These findings highlight the critical importance of considering the shared nature of the wireless medium for effective topology control in MIoD systems. The key contributions of this work include the incorporation of shared access restrictions into the optimization model, allowing for a more accurate representation of the problem, and the proposal of an EGNN-based Black Box Optimization approach to solve the resulting topology control problem.