Unmanned aerial vehicle cluster network intelligent multi-hop routing method based on multi-agent cooperation
A multi-hop routing and cluster network technology, which is applied in the field of intelligent multi-hop routing of UAV cluster networks, can solve the problems of difficult to effectively reduce the time delay and immaturity of UAV cluster networks, and achieve the alleviation of non-stationary training problems, The effect of reducing computational complexity and improving scalability
Pending Publication Date: 2022-05-13
NANJING UNIV OF SCI & TECH
View PDF0 Cites 2 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
At present, the research on intelligent multi-hop routing of UAV cluster network has begun to take shape but is not yet mature. For example, it is difficult to effectively reduce the delay caused by high-speed node movement and frequent topology changes in UAV cluster network.
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment
[0064]One embodiment of the present invention is specifically described below, simulation programming based on Python under a computer operating system windows 10, the specific scenario is:
[0065] The communication topology state of a drone cluster is represented as a diagram thereinto Represents a collection of drone nodes, is a set of edges, edge e i,j ∈ε mean drones Can be directly with drones Communicate with each other. The UAV uses a random road point movement model, and the topology of Figure G is dynamically changing. Each drone node has its own send queue, expressed as where u m ＝(src m ,dst m ,L m ) is the mth packet to be sent in the queue, src m DST, the source node for the packet m For the destination node of the packet, L m is the size of the packet. The time is discretized into time slots t∈ {1,2,...,T}, in the drone cluster, each drone node can be either a sending node or a receiving node, the drone node will save the packet to be sent to the sending queue...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses an unmanned aerial vehicle cluster network intelligent multi-hop routing method based on multi-agent cooperation, and the method comprises the steps: employing an epsilon greedy strategy to select a relay node for an unmanned aerial vehicle node, and achieving the optimal routing selection in a scene in which a network environment part is observable; meanwhile, on the basis of observation of neighbor node queues and position information, a cooperative multi-agent value decomposition network method is applied, evaluation network parameters of a single unmanned aerial vehicle node are updated by calculating a time difference error of a joint value function, and finally an unmanned aerial vehicle node routing strategy is learned and a relay node is intelligently selected; and the transmission delay is reduced to the greatest extent. According to the invention, based on high dynamic topology characteristics in an unmanned aerial vehicle cluster network, high-load nodes are bypassed on the basis of a shortest path through cooperative cognitive ability between unmanned aerial vehicles, so that intelligent routing selection is realized; compared with traditional independent Q learning, a better routing strategy can be learned, and the communication transmission time delay of the unmanned aerial vehicle in a complex change environment is effectively reduced.
Description
Technical field [0001] The present invention relates to the field of wireless communication technology, in particular a UAV cluster network intelligent multi-hop routing method based on multi-agent collaboration. Background [0002] Unmanned aerial vehicle swarm (UAVs) network is composed of a certain number of unmanned aerial vehicles (UAV), because the unmanned aerial vehicle cluster network has the characteristics of rapid networking, high reliability, high scalability, strong anti-destruction ability and single-node replaceability, etc., it has been widely studied in academia and industry. At present, drone swarms are widely used in civilian fields such as border monitoring and environmental monitoring, as well as military fields such as reconnaissance, surveillance, search and rescue (N.Zhao W.Lu M. Sheng et al. UAV-Assisted EmergencyNetworks inDisasters[J]. IEEE Wireless Communication,2019 26(1):45-51)。 [0003] However, the unmanned aerial vehicle cluster network has the ...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): H04B7/185H04W40/02H04W40/22
CPCH04B7/18502H04W40/02H04W40/22Y02D30/70
Inventor 白金祥林艳张一晋范祥瑞李骏
Owner NANJING UNIV OF SCI & TECH