Energy-Efficient UAV Swarm Assisted MEC with Dynamic Clustering and Scheduling
Jialiuyuan Li, Jiayuan Chen, Changyan Yi, Tong Zhang, Kun Zhu, Jun Cai
TL;DR
The paper tackles the problem of energy-efficient UAV swarm assisted MEC under dynamic clustering and scheduling. It treats the system as a series of coupled multi-agent stochastic games and proposes RLDC, a reinforcement-learning-based coordination framework with six specialized learners and Q-learning, to reach equilibrium across energy replenishment, application placement, trajectory planning, clustering, and delegation decisions. Empirical results show that RLDC outperforms fixed-swarm and no-swarm baselines, with energy efficiency improving as IoT demand grows and demonstrating robustness to velocity, storage, and grid parameters. The approach offers a scalable, decentralized mechanism to adapt UAV swarm formations and task handling in response to dynamic service needs, advancing practical deployments of MEC with UAV swarms.
Abstract
In this paper, the energy-efficient unmanned aerial vehicle (UAV) swarm assisted mobile edge computing (MEC) with dynamic clustering and scheduling is studied. In the considered system model, UAVs are divided into multiple swarms, with each swarm consisting of a leader UAV and several follower UAVs to provide computing services to end-users. Unlike existing work, we allow UAVs to dynamically cluster into different swarms, i.e., each follower UAV can change its leader based on the time-varying spatial positions, updated application placement, etc. in a dynamic manner. Meanwhile, UAVs are required to dynamically schedule their energy replenishment, application placement, trajectory planning and task delegation. With the aim of maximizing the long-term energy efficiency of the UAV swarm assisted MEC system, a joint optimization problem of dynamic clustering and scheduling is formulated. Taking into account the underlying cooperation and competition among intelligent UAVs, we further reformulate this optimization problem as a combination of a series of strongly coupled multi-agent stochastic games, and then propose a novel reinforcement learning-based UAV swarm dynamic coordination (RLDC) algorithm for obtaining the equilibrium. Simulations are conducted to evaluate the performance of the RLDC algorithm and demonstrate its superiority over counterparts.