MAESTRO-X: Distributed Orchestration of Rotary-Wing UAV-Relay Swarms

TL;DR

This paper introduces MAESTRO-X, a scalable framework for orchestrating UAV swarms as cellular relays, optimizing latency and energy use through hierarchical decision-making and decentralized control, significantly outperforming existing methods.

Contribution

It develops a novel hierarchical optimization framework for UAV relay swarms, extending single-UAV policies to scalable multi-UAV systems with decentralized coordination.

Findings

MAESTRO achieves 3.8x faster service than high-altitude platforms.

MAESTRO-X outperforms convex schemes by 4.7x in data delivery speed.

Single UAV optimized by MAESTRO outperforms 3 UAVs with deep-Q networks by 38%.

Abstract

This work details a scalable framework to orchestrate a swarm of rotary-wing UAVs serving as cellular relays to facilitate beyond line-of-sight connectivity and traffic offloading for ground users. First, a Multiscale Adaptive Energy-conscious Scheduling and TRajectory Optimization (MAESTRO) framework is developed for a single UAV. Aiming to minimize the time-averaged latency to serve user requests, subject to an average UAV power constraint, it is shown that the optimization problem can be cast as a semi-Markov decision process, and exhibits a multiscale structure: outer actions on radial wait velocities and terminal service positions minimize the long-term delay-power trade-off, optimized via value iteration; given these outer actions, inner actions on angular wait velocities and service trajectories minimize a short-term delay-energy cost. A novel hierarchical competitive swarm optimization scheme is developed in the inner optimization, to devise high-resolution trajectories via iterative pair-wise updates. Next, MAESTRO is eXtended to UAV swarms (MAESTRO-X) via scalable policy replication: enabled by a decentralized command-and-control network, the optimal single-agent policy is augmented with spread maximization, consensus-driven conflict resolution, adaptive frequency reuse, and piggybacking. Numerical evaluations show that, for user requests of 10 Mbits, generated according to a Poisson arrival process with rate 0.2 req/min/UAV, single-agent MAESTRO offers 3.8x faster service than a high-altitude platform and 29% faster than a static UAV deployment; moreover, for a swarm of 3 UAV-relays, MAESTRO-X delivers data payloads 4.7x faster than a successive convex approximation scheme; and remarkably, a single UAV optimized via MAESTRO outclasses 3 UAVs optimized via a deep-Q network by 38%.