Low-orbit satellite routing strategy method based on deep reinforcement learning architecture

Abstract

The invention discloses a low-orbit satellite routing strategy method based on a deep reinforcement learning architecture, and belongs to the field of wireless communication. Firstly, an iridium constellation network is established, and a deep reinforcement learning framework is established in combination with a Markov decision process; and for a certain satellite node A, a HELLO packet is periodically sent to a neighbor node, and an adjacent node communicated with the link state of the current node A is searched, a next hop node of a current node is obtained by inputting a destination node coordinate, a link state of the current node and a link state of a neighbor node into a deep reinforcement learning architecture, and a next hop node is continuously obtained in the same way; and when aspecial routing condition (such as open circuit, loop and congestion) occurs, a link state is repeatedly input into the deep reinforcement learning architecture by adopting a corresponding solution strategy until a destination node is reached, and a path planning process is finished. According to the method, the system complexity and the storage overhead are reduced, the effect of detecting the satellite link state in real time is achieved, and satellite routing is more stable and reliable.

Description

technical field [0001] The invention belongs to the field of wireless communication, relates to the technical problem of inter-satellite routing in a low-orbit constellation system, and specifically relates to a low-orbit satellite routing strategy method based on a deep reinforcement learning framework. Background technique [0002] As the infrastructure for future space system information exchange, satellite network has become an important part of the global information network. Low Earth Orbit (LEO) satellites have the advantages of low loss, low delay, wide coverage, short development cycle and low cost, and are more suitable for carrying real-time services. [0003] The low-orbit satellite communication systems that have been launched and networked and are in operation so far include: "Iridium" (Iridium) satellites, "Globalstar" (Globalstar) and "Orbit Communication" (Orbcomm) systems. After years of operation and development, the above low-orbit satellite communicatio...

AI Technical Summary

Problems solved by technology

[0008] Aiming at the on-off switching of inter-satellite links, real-time changes in satellite load status, and satellite routing failures during the operation of low-orbit constellations, the present invention proposes a low-orbit satellite routing strategy method based on deep reinforcement learning architecture, which is a low-orbit constellation Propose an effective solution to the problem of path transmission selection in the network

Images