FL-CARE: Federated Learning-Based Contention-Aware and Energy-Balanced Routing for Dense FANETs

Abstract

In dense multi-drone FANET environments, routing efficiency is often reduced due to constant competition for a wireless channel, frequent changes in network topology, and uneven energy consumption between UAV nodes. These factors lead to a decrease in the packet delivery ratio, an increase in delays on the busiest or most unstable routes, and a reduction in the total network lifespan. Although many existing routing methods utilize mobility forecasting or reinforcement learning, most are based on independent decision-making by individual agents. As a result, such approaches may create a significant service load and insufficiently account for competition for the communication channel, as well as the fair distribution of energy consumption between network nodes. To overcome these integrated challenges, this paper proposes FL-CARE, a Federated Learning-based Contention-Aware and Energy-balanced Routing protocol. In FL-CARE, each UAV acts as a learning agent using a multidimensional state (predicted link stability, channel contention, queue occupancy, residual energy) and a tail-latency-sensitive reward function. A lightweight federated learning mechanism enables collaborative, swarm-level intelligence with bounded communication overhead. Extensive MATLAB simulations demonstrate that FL-CARE outperforms state-of-the-art protocols MP-QGRD and RL-MPEAOLSR, improving PDR by 12-18%, reducing average delay by 20–25% and tail latency (p99) by up to 30%. Additionally, FL-CARE yields a 15-22% energy consumption per bit delivered, and control overhead reduction of 35-45%, and advances network lifetime by approx. 25% in dense network deployments. The proposed framework maintains low computational and communication overhead through lightweight local learning and compact federated model updates, while adaptive aggregation intervals facilitate efficient collaborative learning and scalable operation under varying network conditions. These simulation results validate the holistic integration with federated multi-agent learning, with emphasis on contention awareness and energy balancing is essential for scalable and efficient routing in next-generation dense FANETs.