28 October 2022 in IEEE Transactions on Vehicular Technology
Routing protocols do not respond quickly to environmental changes due to the high mobility of nodes in the Flying Ad Hoc Network (FANET), to obtain reliable transmission links. This paper proposes an adaptive link maintenance method based on deep reinforcement learning (DRL-MLsA), which can dynamically adjust the time interval of broadcasting Hello packets. This method can cope with the highly dynamic network environment, and adapt to both active routing and table-driven routing protocols. The method considers the channel model of the signal and investigates the impact of UAV communication range on link maintenance. We can get an agent by perceiving the degree of changes in the number of neighbors in a dynamic environment. The optimal broadcast cycle was obtained to maximize the energy of the node to send and receive task data. We substituted the single-output network model with a competitive network to overcome the reward overestimation problem, which also improves the convergence speed of the algorithm. Simulation results showed that DRL-MLsA can reduce the communication overhead for link maintenance, while at the same time increase the throughput of the network and decrease the packet loss of transmission.
26 June 2024 in IEEE Sensors Journal
Recent advancements in protocol design and optimization for Flying Ad-hoc Networks have shown significant progress. However, the existing centralized optimization control algorithms pose conflicts with the distributed nature of these systems. To address this challenge, this paper proposes a novel distributed routing optimization algorithm based on multi-agent reinforcement learning, integrated with an adaptive multi-mode routing framework incorporating multi-protocol cooperation mechanisms. The algorithm adopts the Decentralized Execution Multi-Agent Deep Deterministic Policy Gradient (DE-MADDPG) algorithm framework, enabling individual unmanned aerial vehicles to directly adjust the protocols and protocol parameters of the current node based solely on local network information. This optimization enhances network structure and overall performance without considering the transmission delay of control signals. The ns3-gym simulation platform is employed for performance evaluation, comparing the proposed algorithm with Deep Q-Network (DQN), Multi-Agent Deep Deterministic Policy Gradient (MADDPG), and other algorithms. The experimental results demonstrate that compared to the routing algorithm optimized based on DQN, the proposed algorithm exhibits the best overall performance, with a 26.31% reduction in energy consumption and a 19.69% decrease in end-to-end delay.
23 November 2020 in IEEE Communications Letters
Network coding based multipath transmission method has been shown to improve the reliability and throughput of end-to-end data delivery for ad hoc networks. However, when it is adapted to flying ad hoc networks (FANETs), multipath establishment and maintenance scheme should be elaborately designed due to frequently local topology changes during UAVs’ formation flying. This letter proposes a network-coding-aware multipath routing protocol NCAnt. It achieves reliable end-to-end transmission by maximizing recoding opportunities based on the ant colony optimization (ACO). Moreover, the positive feedback mechanism of ant colony pheromone is utilized to reduce the routing reconstruction cost under frequent local topology changes. Simulation results show NCAnt can provide up to 50% additional coding opportunities and achieves lower path recovery delay than baseline schemes.
8 November 2021 in IEEE Transactions on Communications
For space communications, the transmitted signal generally faces a long-distance transmission and a high-accelerating movement. The long-distance transmission causes a very low signal-to-noise ratio (SNR) and the high-accelerating movement causes a dynamic Doppler-shift. Under a very large acceleration, the long-time accumulation which aims to solve the very low SNR, brings about the serious energy dispersion problem, thus posing a great challenge for Doppler-shift acquisition. Introducing the clustering idea in machine learning, we propose one clustering-fast-Fourier-transform (CFFT) based Doppler-shift acquisition scheme with an affordable computational complexity, to address the energy dispersion problem for space communications. The proposed CFFT scheme includes two algorithms called the Generic CFFT algorithm and the High-order CFFT algorithm, respectively. First, the Generic CFFT algorithm clusters multiple density-reachable signal elements into one signal cluster, thus accumulating the dispersed energy again. Second, the High-order CFFT algorithm, which conducts several rounds of clustering, clusters more density-reachable signal elements into one larger signal cluster. Simulations results show that our proposed CFFT scheme achieves a higher acquisition probability than the existing FFT based schemes and consumes a lower computational complexity than the FRFT scheme.
11 September 2004 in Computer Communications