Research On Routing Protocols For FANET In Highly Dynamic Topology Scenarios

With the increasing utilization of intelligent unmanned aerial vehicle(UAV)clusters in both military and civilian fields,the FANET routing protocol has become increasingly important in cluster communication.However,the high dynamic characteristics of network topology in FANET,which are highlighted by the rapid movement and changing direction of UAV nodes as well as frequent entry and exit from the network,result in an increase in link interruption rate.While traditional protocols can achieve basic network service quality(Qo S)requirements in MANET with relatively fixed topology changes,they may choose suboptimal routing and limit information propagation in FANET with larger topology changes,ultimately leading to increased packet loss and delay.Therefore,a new routing method that can adapt to FANET must be proposed,which is different from traditional protocols.Currently,using artificial intelligence to optimize routing is a promising direction.Based on reinforcement learning methods,This thesis conducted in-depth research on how to solve the problems faced by current routing protocols in high dynamic topology scenarios,such as delay and packet loss,and proposed innovative routing methods.The summary is as follows:(1)A Q-learning empowered highly dynamic and latency aware routing algorithm for ad-hoc network(QEHLR)is proposed,which combines Q-learning with end-to-end delay improvement to address the issue of ineffective packet routing in highly dynamic FANET using traditional routing algorithms.The method of Q-learning is used to learn the link status in the network,and effective routing is selected through Q-value to avoid connection loss.Based on this,the remaining time of the link or the path lifespan is included in the routing criteria to maintain the routing table.QEHLR can delete estimated failed links according to the network status,reducing packet loss caused by failed routing selection.The packet delivery rate of the improved routing algorithm is about 12% higher than AODV,about 22% higher than OLSR,about 20% higher than DSDV,about 8% higher than PARROT,and about 25% higher than B.A.T.Mobile,which has the highest packet delivery rate.(2)A routing method based on topology change degree improvement is proposed to address the problem that routing protocols cannot adapt to various mobility model in FANET with high dynamic topology due to the diversification of task scenarios and the variability of tasks.The calculation factor of network topology change degree is introduced on the basis of QEHLR protocol.The experimental results designed in this thesis show that the improved routing algorithm can achieve higher packet transmission rate and lower delay.(3)A FANET network routing experiment was conducted using six rotary-wing unmanned aerial vehicles.The Ad-hoc network configuration of the six-node FANET was first completed based on the RTL8192 chip network card.Subsequently,the improved routing protocol proposed in this thesis was transplanted to the Linux user space of the unmanned aerial vehicle onboard computing platform to enable the routing of data packets.Notably,the protocol proposed is relatively independent of application traffic and underlying link connections.Finally,the experiment of multi-hop forwarding of data packets demonstrated the stable routing function provided by the proposed routing protocol.